IOT IN MANUFACTURING

Forces behind Industry 4.0

Dr. Suhas Deshmukh

1
 Outline

Todays Session

• Forces behind Industry 4.0 (IoT, big data, cloud computing,

robotics, additive manufacturing and artificial intelligence)
• Connected Factories (What is connected factory and criteria
for connected factory)
• How the current industry is different from Industry 4.0

2 BITS Pilani, Pilani Campus

 Forces behind Industry 4.0

Internet of Cloud Additive

Things (IoT) Computing Manufacturing
(3D Printing)

Big Data Robotics Artificial

Intelligence
(AI)

3 BITS Pilani, Pilani Campus

 Internet of Things (IoT)
IoT involves the interconnection of physical devices,
vehicles, buildings, and other items embedded with
sensors, software, and network connectivity.

Real-Time Data Collection: IoT devices collect and transmit real-time data from production
processes, enabling continuous monitoring and analysis.
Predictive Maintenance: Data from IoT sensors can predict equipment failures, allowing for proactive
Impact

maintenance and reducing downtime.

Enhanced Efficiency: IoT enables better resource management, process optimization, and energy
efficiency.
Smart Manufacturing: Integration of IoT in manufacturing systems leads to smarter factories with
improved decision-making capabilities.
4 BITS Pilani, Pilani Campus
 Forces behind Industry 4.0

Industry 4.0 is driven by a confluence of advanced technologies that are transforming

manufacturing and industrial processes.

Internet of Things (IoT)

• IoT involves the interconnection of
physical devices, vehicles, buildings,
and other items embedded with sensors,
software, and network connectivity.

Impact:
• Real-Time Data Collection: IoT devices
collect and transmit real-time data from
production processes, enabling
continuous monitoring and analysis.
• Predictive Maintenance: Data from IoT
sensors can predict equipment failures,
allowing for proactive maintenance and
reducing downtime.
• Enhanced Efficiency: IoT enables better
resource management, process
optimization, and energy efficiency.
• Smart Manufacturing: Integration of IoT
in manufacturing systems leads to
smarter factories with improved
decision-making capabilities.

5 BITS Pilani, Pilani Campus

 Internet of Things (IoT)
Data Collection:
• IoT devices equipped with sensors collect data from their
environment. This can include temperature, humidity,
motion, light, and other variables.

Data Transmission:
• The collected data is transmitted to a central server or
cloud platform via connectivity technologies such as Wi-
Fi, Bluetooth, or cellular networks.

Data Processing and Analysis:

• The transmitted data is processed and analyzed to extract
meaningful insights. This can involve real-time analytics,
machine learning algorithms, and big data processing.

Action and Automation:

• Based on the insights derived from data analysis, actions
can be automated, or recommendations can be provided
to users. For instance, a smart thermostat might adjust
the temperature based on occupancy patterns, or a
predictive maintenance system might alert technicians to
potential equipment failures.

User Interaction:
• Users can interact with IoT systems through various
interfaces, such as mobile apps, web dashboards, or
voice assistants, to monitor status, receive alerts, and
control devices.

6 BITS Pilani, Pilani Campus

 Applications: Internet of Things (IoT)

Smart Homes: Industrial IoT (IIoT): Healthcare:

• Connected devices such as • Use of IoT in manufacturing • Wearable devices, remote

smart thermostats, lighting and industrial processes. patient monitoring, and
systems, security cameras, • Benefits: Improved smart medical equipment.
and smart appliances. operational efficiency, • Benefits: Enhanced patient
• Benefits: Increased predictive maintenance, care, real-time health
convenience, energy real-time monitoring, and monitoring, and early
savings, and enhanced automation. detection of medical
security. conditions..

7 BITS Pilani, Pilani Campus

 Applications: Internet of Things (IoT)

Smart Cities: Agriculture: Transportation and Logistics:

• IoT applications in urban • IoT solutions for precision • Connected vehicles, fleet
infrastructure, such as smart farming, such as soil moisture management systems, and
lighting, traffic management, sensors, weather stations, smart logistics.
waste management, and and automated irrigation • Benefits: Enhanced route
environmental monitoring. systems. optimization, real-time
• Benefits: Improved urban • Benefits: Increased crop yield, tracking, and improved fuel
living, reduced energy optimized resource use, and efficiency.
consumption, and better reduced environmental
resource management impact.

8 BITS Pilani, Pilani Campus

 Case Studies

Smart Manufacturing: Siemens' Digital Factory

Overview: Siemens has implemented IoT technologies in its

Digital Factory initiative to create smart manufacturing
environments.

Objective: To optimize production processes, enhance

flexibility, and improve product quality.

Approach: Results:
•IoT Integration: Connected machinery, sensors, and •Increased Efficiency: Improved production
systems throughout the manufacturing process. efficiency through real-time monitoring and adaptive
•Data Collection: Collected real-time data on machine control.
performance, production rates, and product quality. •Reduced Downtime: Decreased unplanned
•Analytics and Automation: Used advanced analytics downtime with predictive maintenance strategies.
and automation to optimize production schedules, •Enhanced Product Quality: Achieved higher product
predict maintenance needs, and enhance quality quality with continuous monitoring and automated
control. quality control processes.

9 BITS Pilani, Pilani Campus

 Case Studies

Smart Agriculture: John Deere's Precision

Farming
Overview: John Deere uses IoT technologies to enable
precision farming, enhancing agricultural productivity and
sustainability.

Objective: To optimize crop yields, reduce resource

consumption, and increase farm efficiency.

• Approach: • Results:
• IoT Devices: Deployed IoT sensors on agricultural • Optimized Resource Use: Reduced water, fertilizer,
equipment and fields to monitor soil conditions, and pesticide usage by applying them precisely where
weather, crop health, and equipment status. needed.
• Data Analytics: Used data analytics to provide • Increased Yields: Improved crop yields through better
actionable insights to farmers. decision-making and optimized farming practices.
• Automated Equipment: Implemented automated • Cost Savings: Lowered operational costs through
machinery for tasks like planting, fertilizing, and efficient resource management and automated
harvesting based on IoT data. processes.

10 BITS Pilani, Pilani Campus

 Case Studies

Healthcare: Philips' Remote Patient

Monitoring
Overview: Philips has developed IoT-enabled remote
patient monitoring solutions to improve healthcare
delivery and patient outcomes.

Objective: To provide continuous monitoring and early

intervention for patients with chronic conditions.

• Approach: • Results:
• IoT Devices: Deployed IoT devices such as wearable • Improved Patient Outcomes: Enhanced patient
sensors and connected medical devices to monitor outcomes through continuous monitoring and early
patients' vital signs. detection of health issues.
• Data Integration: Integrated data from IoT devices • Reduced Hospitalizations: Lowered hospitalization
into healthcare providers' systems for real-time rates by enabling proactive management of chronic
monitoring and analysis. conditions.
• Alerts and Insights: Provided healthcare providers • Patient Engagement: Increased patient engagement
with alerts and insights to enable timely and adherence to treatment plans through remote
interventions. monitoring and feedback.
11 BITS Pilani, Pilani Campus
 What is Data Analysis ?

Why did it How we make

Descriptive it happened?
Analytics happen? Predictive Analysis Cognitive Analytics

Diagnostic Prescriptive How we Improve

What Analytics What will Analytics
Happen? the process or
Happened ?
product ?
Regression analysis,
Optimization
data mining, algorithms, Data visualization,
time series forecasting,
statistics (mean, correlations, and and machine learning simulation, and clustering, and principal
median, mode) root cause analysis models. decision trees component analysis.

Hindsight Oversight Foresight Insight Right Sight

12 BITS Pilani, Pilani Campus
 Benefits of Data Analysis

Innovation: Uncovers
Identifying Trends and
Informed Decision- Improving Efficiency: Risk Management: new opportunities and
Patterns: Helps in
Making: Enables Identifies inefficiencies Assists in identifying areas for innovation by
recognizing trends and
businesses and and areas for potential risks and analyzing customer
patterns that can be
organizations to make improvement in developing strategies behavior, market
leveraged for strategic
data-driven decisions. processes. to mitigate them. trends, and
planning.
operational data.

13 BITS Pilani, Pilani Campus

 Big Data Analysis
• Big Data Analysis refers to
the process of
• examining large and
varied data sets—
known as big data
• to uncover hidden
patterns,
• unknown correlations,
• market trends,
• customer preferences,
and
• other useful business
information.

The process involves using

advanced analytic
techniques on data sets that
are too large or complex to
be dealt with by traditional
data-processing software.

14 BITS Pilani, Pilani Campus

 Data to Big Data Analysis

15 BITS Pilani, Pilani Campus

 Steps in Big Data Analysis
Gathering data from
Storing data in distributed Applying statistical and Using the insights derived
various sources
systems that can handle machine learning from data analysis to
such as sensors,
large volumes of data techniques to extract inform business decisions
social media,
efficiently. insights from the data. and strategies.
transaction logs, etc.
Data Storage
Data and Data Decision
Collection Management Analysis Making:

1 2 3 4 5 6 7

Data Data Data

Cleaning Processing Visualization
and
Preparation
Removing duplicates, Using batch or real- Creating visual
handling missing values, and time processing representations of the
transforming data into a techniques to data to communicate
suitable format for analysis. analyze the data. findings effectively.

16 BITS Pilani, Pilani Campus

 Example : Predictive Maintenance in Manufacturing

• Scenario: Predictive Maintenance in Manufacturing

• Background: A large manufacturing company operates multiple factories equipped with
various machinery and equipment. The company aims to reduce maintenance costs and
machine downtime by implementing a predictive maintenance system using big data analytics.

Data Collection Data Cleaning and Data Exploration and

Preparation: Transformation:
• Sensor Data: Real-time data from
sensors embedded in machines • Removing Duplicates: • Feature Engineering: Creating
(e.g., temperature, vibration,
Eliminating duplicate records new features from raw data,
pressure). such as moving averages of
• Maintenance Records: Historical
from multiple sensors.
sensor readings or cumulative
maintenance logs, including details • Handling Missing Values: operating hours.
of repairs and parts replaced. Imputing or interpolating • Dimensionality Reduction:
• Operational Data: Machine usage missing sensor readings. Reducing the number of
data, including operating hours, load
conditions, and production rates.
• Standardizing Formats: features using techniques like
• Environmental Data: External Ensuring uniform data Principal Component Analysis
conditions such as ambient formats across different (PCA) to handle high-
temperature, humidity, and factory sources. dimensional data.

17 BITS Pilani, Pilani Campus

 Example : Predictive Maintenance in Manufacturing

Data Analysis and Modeling: Data Interpretation:

Model Training and
• Descriptive Analytics: Visualizing
Validation: • The insights derived from the
historical maintenance data to
• The predictive models are models are interpreted to
understand common failure inform maintenance
patterns and frequencies. trained on historical data and
validated using cross- decisions:
• Predictive Analytics: Building
machine learning models to predict validation techniques to • Failure Predictions:
machine failures before they occur. ensure accuracy and Identifying machines at high
Common models include: reliability: risk of failure based on current
• Regression Models: Predicting
• Training Set: Using historical sensor readings and historical
the remaining useful life (RUL) of patterns.
machinery. sensor and maintenance
• Classification Models: data to train the models. • Maintenance Scheduling:
Classifying whether a machine is • Validation Set: Testing the Optimizing maintenance
likely to fail within a certain models on a separate schedules to address
timeframe (e.g., within the next
dataset to evaluate potential failures proactively,
week). minimizing unplanned
performance
downtime.

18 BITS Pilani, Pilani Campus

 Example : Predictive Maintenance in Manufacturing

Data Presentation: Actionable Insights: Outcome:

• The results are presented to • Proactive Maintenance: • Reduced Downtime:

the maintenance team and Implementing predictive Machine downtime is
management using maintenance schedules reduced by 30% due to
dashboards and reports: based on model predictions, timely maintenance
• Predictive Maintenance reducing unexpected machine interventions.
failures.
Dashboard: Real-time • Cost Savings: Maintenance
visualization of machine • Resource Allocation: costs decrease by 20%
health, failure predictions, and Allocating maintenance through efficient resource
resources more efficiently by
recommended maintenance allocation and parts
focusing on high-risk
actions. machinery. management.
• Maintenance Reports: • Cost Savings: Reducing • Improved Equipment
Detailed reports on predicted maintenance costs by Lifespan: Machines
failures, maintenance history, preventing catastrophic experience fewer
and model performance failures and optimizing parts breakdowns, extending their
metrics. inventory. operational lifespan.

19 BITS Pilani, Pilani Campus

 Applications of Big Data Analysis
Healthcare: Retail: Finance: Manufacturing:
• Examples: Predictive analytics for • Examples: Customer behavior • Examples: Fraud detection, risk • Examples: Predictive maintenance,
patient outcomes, personalized analysis, inventory management, and management, and algorithmic trading. quality control, and supply chain
treatment plans, and outbreak personalized marketing. optimization.
detection.

20 BITS Pilani, Pilani Campus

 Applications of Big Data Analysis
Telecommunications: Transportation and Logistics: Energy and Utilities: Government and Public
• Examples: Network optimization, • Examples: Route optimization, • Examples: Smart grid management, Sector:
customer churn analysis, and targeted demand forecasting, and fleet energy consumption forecasting, and • Examples: Crime prediction and
advertising. management. predictive maintenance. prevention, traffic management, and
public health monitoring.

21 BITS Pilani, Pilani Campus

 Benefits & Challenges of Big Data Analysis

Benefits of Big Data Analysis Challenges of Big Data Analysis

Improved Decision Making: Data Quality:

• Data-driven insights enable more informed and • Ensuring the accuracy, completeness, and reliability of
effective decision-making. data.
Increased Efficiency: Data Integration:
• Optimizing processes based on data analysis can lead • Integrating data from various sources and formats.
to significant efficiency gains.

Cost Reduction: Scalability:

• Identifying inefficiencies and optimizing resource use • Managing and processing data at scale.
can lead to cost savings.
Security and Privacy:
Enhanced Customer Experience:
• Protecting sensitive data from breaches and ensuring
• Personalizing products and services based on compliance with regulations.
customer data can improve satisfaction and loyalty.
Skill Gaps:
Innovation:
• The need for skilled professionals who can work with big
• Discovering new trends and opportunities can drive data technologies and techniques.
innovation and competitive advantage.

22 BITS Pilani, Pilani Campus

 Case Studies : General Electric (GE): Predictive Maintenance

General Electric (GE): Predictive Maintenance

• Overview: General Electric (GE) has utilized big data

analytics to implement predictive maintenance across
its various industrial sectors, including aviation, power
generation, and manufacturing.
• Objective: To predict equipment failures and optimize
maintenance schedules, thereby reducing downtime
and maintenance costs.

Results:
Approach:
• Reduced Downtime: Predictive maintenance has led to
• Data Collection: Deployed sensors on equipment to
a significant reduction in unplanned equipment
collect real-time data on temperature, pressure,
downtime.
vibration, and other performance metrics.
• Cost Savings: Optimized maintenance schedules have
• Data Processing: Used big data platforms to process
resulted in substantial cost savings by avoiding
and analyze large volumes of sensor data.
unnecessary maintenance and reducing failure rates.
• Predictive Modeling: Developed machine learning
• Improved Efficiency: Enhanced overall operational
models to identify patterns indicative of potential
efficiency and productivity.
failures.
23 BITS Pilani, Pilani Campus
 Case Studies : Siemens: Smart Manufacturing

Siemens: Smart Manufacturing

• Overview: Siemens has integrated big data

analytics into its manufacturing processes to
create smart factories that are more efficient,
flexible, and responsive.
• Objective: To optimize production processes,
improve product quality, and reduce operational
costs.

Approach: Results:

• Data Collection: Collected data from various stages of the • Enhanced Productivity: Improved production
production process, including machinery performance, efficiency through optimized process parameters
production rates, and quality control metrics. and reduced cycle times.
• Data Integration: Implemented a digital twin of the • Higher Quality: Enhanced product quality by
production environment to integrate and visualize data. identifying and addressing quality issues in real-time.
• Advanced Analytics: Applied advanced analytics and • Cost Reduction: Achieved cost savings through
machine learning to optimize production parameters and more efficient use of resources and reduction of
identify areas for improvement. waste.

24 BITS Pilani, Pilani Campus

 Case Studies: Rolls-Royce: Engine Health Monitoring
Rolls-Royce: Engine Health Monitoring

• Overview: Rolls-Royce leverages big data

analytics for its TotalCare® service, which
involves monitoring the health of aircraft
engines to improve performance and
maintenance efficiency.
• Objective: To enhance engine
performance, reduce maintenance costs,
and improve reliability.

Approach: Results:
• Data Collection: Collected real-time data from • Enhanced Reliability: Improved engine reliability
sensors embedded in aircraft engines. through early detection of potential issues.
• Data Analysis: Used advanced analytics and • Reduced Costs: Lowered maintenance costs by
machine learning to monitor engine performance minimizing unplanned downtime and optimizing
and predict maintenance needs. maintenance schedules.
• Proactive Maintenance: Provided proactive • Customer Satisfaction: Increased customer
maintenance recommendations based on satisfaction through improved engine performance
predictive analytics. and reliability.

25 BITS Pilani, Pilani Campus

 Cloud Computing

• Cloud computing refers to the

delivery of computing services—
including
• servers,
• storage,
• databases,
• networking,
• software, and more—over the internet
("the cloud").

• Instead of owning and maintaining

physical data centers and servers,
cloud computing enables users to
access resources on-demand from
cloud service providers.

26 BITS Pilani, Pilani Campus

 Cloud Computing

Key Characteristics of Cloud Computing: Types of Cloud Computing Services:

On-Demand Self-Service: Infrastructure as a Service (IaaS):

• Users can provision and manage computing resources, such as server
time and storage, without requiring human interaction with the service • Provides virtualized computing resources over the internet. Users rent
provider. virtual machines, storage, and networking resources.
• Example providers: Amazon Web Services (AWS), Microsoft Azure, Google
Broad Network Access: Cloud Platform (GCP).
• Cloud services are accessible over the internet from various devices,
such as laptops, smartphones, and tablets. Platform as a Service (PaaS):
Resource Pooling: • Provides a platform allowing customers to develop, run, and manage
applications without the complexity of building and maintaining the
• Providers pool resources to serve multiple customers, with different
physical and virtual resources dynamically assigned and reassigned infrastructure.
based on demand. • Example providers: Heroku, Google App Engine, Microsoft Azure App
Service.
Rapid Elasticity:
• Cloud resources can scale up or down quickly and automatically to Software as a Service (SaaS):
accommodate changing workload demands. Users pay only for the
resources they use. • Delivers software applications over the internet on a subscription basis.
Users access software through a web browser without needing to install or
Measured Service: maintain it locally.
• Cloud systems automatically control and optimize resource use by • Example providers: Salesforce, Google Workspace (formerly G Suite),
leveraging a metering capability at some level of abstraction appropriate Microsoft Office 365.
to the type of service.

27 BITS Pilani, Pilani Campus

 Cloud Computing

Benefits of Cloud Computing: Use Cases of Cloud Computing:

• Cost Savings: Reduced capital • Data Backup and Storage: Storing data
expenditure on hardware and securely in the cloud with easy access and
maintenance costs. redundancy.
• Big Data Analytics: Processing and analyzing
• Scalability: Ability to scale resources large datasets using cloud-based tools and
up or down based on demand. resources.
• Flexibility: Access resources and • Software Development and Testing:
applications from anywhere with an Developing, testing, and deploying applications
internet connection. without investing in on-premises infrastructure.
• Collaboration and Productivity Tools: Using
• Reliability: Service providers often offer cloud-based platforms for email, document
high availability and uptime guarantees. collaboration, and project management.
• Security: Cloud providers invest heavily • IoT and Edge Computing: Leveraging cloud
in security measures and compliance services to manage and process data from IoT
certifications. devices and edge locations.

28 BITS Pilani, Pilani Campus

 Case Studies: General Electric (GE): Predix Platform

General Electric (GE): Predix Platform

• Overview: General Electric (GE) developed the Predix platform,

a cloud-based Industrial Internet of Things (IIoT) platform, to
improve operational efficiency and predictive maintenance in
its manufacturing processes.
• Objective: To harness the power of cloud computing for
industrial analytics and to enable predictive maintenance and
operational optimization.

Approach: Results:

• Cloud Platform: Predix is built on cloud infrastructure • Reduced Downtime: Achieved significant reductions in
to handle large volumes of data from GE’s industrial unplanned downtime by predicting equipment failures
machines. before they occur.
• Data Integration: Collected data from sensors and • Cost Savings: Lowered maintenance costs through
machines across GE's manufacturing facilities. predictive maintenance and optimized operational
• Analytics and Insights: Used advanced analytics and efficiencies.
machine learning to generate insights and predict • Enhanced Productivity: Improved productivity through
equipment failures. real-time monitoring and data-driven decision-making

29 BITS Pilani, Pilani Campus

 Case Studies: Siemens: MindSphere

Siemens: MindSphere

• Overview: Siemens launched MindSphere, an

open IoT operating system based on cloud
technology, to connect products, plants,
systems, and machines.
• Objective: To enable manufacturers to harness
data from their operations to improve efficiency,
productivity, and innovation.

Results:
Approach:
• Operational Efficiency: Improved operational efficiency
• Cloud Connectivity: Connected various manufacturing by analyzing data from various sources and optimizing
assets to the cloud for data collection and analysis. processes.
• Data Analytics: Leveraged cloud-based analytics tools • Innovation: Enabled the development of new
to process and analyze data from connected devices. applications and services by providing an open, scalable
• Application Development: Provided an open platform platform.
for developers to create industrial applications. • Cost Reduction: Reduced costs through improved asset
utilization and maintenance strategies.

30 BITS Pilani, Pilani Campus

 Case Studies: BMW: Cloud-Based Supply Chain Management

BMW: Cloud-Based Supply Chain Management

• Overview: BMW uses cloud computing to optimize its

supply chain management, ensuring that its manufacturing
processes are efficient and responsive to market demands.
• Objective: To enhance supply chain visibility, agility, and
efficiency using cloud technologies.

Approach: Results:
• Cloud Integration: Integrated cloud-based supply chain • Improved Visibility: Enhanced visibility across
management systems to connect suppliers, the supply chain, enabling better decision-
manufacturing plants, and logistics. making and risk management.
• Real-Time Data: Used real-time data analytics to • Agility: Increased agility in responding to market
monitor supply chain performance and predict potential
changes and demand fluctuations.
disruptions.
• Collaboration: Facilitated better collaboration between • Efficiency: Improved supply chain efficiency by
supply chain partners through shared data and cloud- optimizing inventory levels and reducing lead
based platforms. times.

31 BITS Pilani, Pilani Campus

 Robotics

32 BITS Pilani, Pilani Campus

 Robotics

33 BITS Pilani, Pilani Campus

 Robotics
Key Components of Robotics Types of Robots
Mechanical Structure: Industrial Robots:
•The physical form or shape of a robot, which can vary widely depending on its • Used in manufacturing and production environments. Examples include
intended function. This includes the frame, joints, and actuators (motors) that enable
movement. robotic arms for assembly, welding, painting, and material handling.
Sensors: Service Robots:
•Devices that allow a robot to perceive its environment. Sensors can detect light,
sound, temperature, distance, touch, and other environmental factors. Common • Designed to assist humans with tasks in various sectors such as
sensors include cameras, microphones, gyroscopes, and accelerometers. healthcare, logistics, and customer service. Examples include medical
robots, delivery robots, and cleaning robots.
Actuators:
•Components that enable the robot to move and interact with its environment. Mobile Robots:
Actuators include motors, servos, hydraulic and pneumatic systems that control the
robot's limbs, wheels, or other moving parts. • Robots that can move around in their environment. Examples include
Control System: autonomous vehicles, drones, and robotic vacuum cleaners.
•The "brain" of the robot, which processes sensor data and makes decisions based on Humanoid Robots:
that data. This system can be a simple microcontroller for basic tasks or a complex
computer running sophisticated AI algorithms for advanced functions. • Robots designed to resemble and mimic human behavior and
Power Supply: interactions. Examples include robots for research, entertainment, and
personal assistance.
•The energy source that powers the robot, which can be batteries, solar power, or
other forms of energy.
Exploratory Robots:
Software:
• Used for exploration in hazardous or inaccessible environments.
•The programming and algorithms that dictate how the robot performs tasks. This Examples include space exploration rovers and underwater robots.
includes everything from basic movement instructions to complex AI-driven decision-
making processes.

34 BITS Pilani, Pilani Campus

 • Advantages of Robotics
• Increased Efficiency: Robots can perform tasks
faster and more accurately than humans. Challenges in Robotics
•Complexity and Cost: Developing and
• Consistency and Precision: Robots can maintaining advanced robots can be expensive
maintain high levels of precision and and complex.
repeatability. •Flexibility: Robots are often designed for
• Safety: Robots can operate in hazardous specific tasks and may lack the flexibility of
environments, reducing the risk to human human workers.
workers. •Ethical and Social Implications: The rise of
robotics raises questions about job
• Cost Savings: Automation can reduce labor displacement, privacy, and ethical use.
costs and increase productivity.
• Innovation: Robotics can enable new
applications and technologies that were not
previously possible.

35 BITS Pilani, Pilani Campus

 Applications of Robotics

Manufacturing: Healthcare: Logistics: Agriculture:

• Automation of repetitive • Surgical robots, • Automated warehousing, • Automated planting,

tasks, improving rehabilitation devices, sorting, and delivery harvesting, and
precision and efficiency. and robotic assistants for systems. monitoring systems.
patient care.

36 BITS Pilani, Pilani Campus

 Applications of Robotics

Military: Entertainment: Research and Education:

• Unmanned vehicles, bomb • Robotic toys, animatronics, and • Tools for scientific research,
disposal robots, and interactive installations. teaching, and learning about
surveillance systems. technology and engineering.

37 BITS Pilani, Pilani Campus

 Case Studies: BMW: Flexible Manufacturing with Robotics

BMW: Flexible Manufacturing with Robotics

• Overview: BMW has integrated robotics extensively in

its manufacturing processes to enhance flexibility,
precision, and efficiency in its automotive production
lines.
• Objective: To improve manufacturing efficiency and
adapt quickly to changes in product design and
demand.

Approach: Results:
• Robotic Assembly: Utilized robotic arms for precise • Increased Production Flexibility: Enhanced the ability to
assembly of car parts, including welding, painting, and switch between different car models and configurations with
installation of components. minimal downtime.
• Human-Robot Collaboration: Implemented collaborative • Higher Efficiency: Improved production speed and consistency,
robots (cobots) that work alongside human workers to leading to increased output.
perform tasks that require precision and dexterity. • Enhanced Quality: Achieved higher product quality and
• Quality Control: Used robotic vision systems for quality reduced error rates through precise robotic operations and
inspections to ensure high standards and reduce defects. automated inspections.

38 BITS Pilani, Pilani Campus

 Case Studies: FANUC: Robotic Automation in Electronics Manufacturing
FANUC: Robotic Automation in Electronics
Manufacturing
• Overview: FANUC, a leading manufacturer of
industrial robots, implemented robotics
solutions in electronics manufacturing to
automate repetitive and precise tasks.
• Objective: To increase productivity, improve
product quality, and reduce labor costs in
electronics manufacturing.

Approach:
Results:
• Robotic Soldering: Deployed robots for soldering electronic
components onto circuit boards, ensuring precision and • Higher Productivity: Significantly increased production
consistency. throughput by automating time-consuming tasks.
• Material Handling: Used robots for material handling tasks, such
as loading and unloading components from machines and
• Improved Quality: Enhanced product quality through
conveyors. precise and consistent robotic operations.
• Automated Testing: Implemented robotic systems for automated • Cost Reduction: Reduced labor costs and minimized
testing of electronic devices to ensure functionality and quality. human error by automating repetitive tasks.

39 BITS Pilani, Pilani Campus

 Case Studies: Tesla: Robotic Assembly Line for Electric Vehicles

Tesla: Robotic Assembly Line for Electric

Vehicles
• Overview: Tesla has heavily invested in
robotic automation for the production of its
electric vehicles, particularly in its
Gigafactories.
• Objective: To scale up production capacity
while maintaining high quality and efficiency.

Approach: Results:
• Robotic Welding and Assembly: Utilized robotic arms for
welding and assembling car bodies with high precision. • Scalable Production: Increased production capacity
• Battery Production: Automated the production of battery to meet high demand for electric vehicles.
packs using robotics to ensure consistency and safety. • High Quality: Maintained stringent quality standards
• Painting and Finishing: Implemented robotic systems for with precise robotic operations.
painting and finishing processes to achieve a flawless
exterior. • Efficiency Gains: Achieved significant efficiency
improvements in manufacturing processes.

40 BITS Pilani, Pilani Campus

 Additive Manufacturing

41 BITS Pilani, Pilani Campus

 Additive manufacturing (AM),
Stereolithography (SLA)
Key Concepts in Additive Manufacturing

• Digital Design
• Layer-by-Layer Fabrication:
• Material Options:
• Printing Techniques:
• Fused Deposition Modeling (FDM): Uses a
thermoplastic filament that is melted and extruded Fused Deposition
to build up layers. Modeling (FDM)
• Stereolithography (SLA): Uses a laser to cure
liquid resin into solid layers. Electron Beam
Melting (EBM):
• Selective Laser Sintering (SLS): Uses a laser to
sinter powdered material into solid layers.
• Direct Metal Laser Sintering (DMLS): Similar to
SLS but specifically for metal powders.
• Electron Beam Melting (EBM): Uses an electron
beam to melt metal powders.
• Post-Processing:
• After printing, objects may require post-processing
to achieve the desired finish, such as sanding,
painting, or heat treatment.
Direct Metal Laser
Sintering (DMLS)
42 BITS Pilani, Pilani Campus
 Additive Manufacturing Processes

43 BITS Pilani, Pilani Campus

 Why Additive Manufacturing ?

Advantages of Additive Manufacturing

Challenges in Additive Manufacturing
• Complex Geometries: Enables the production of complex and
intricate designs that are difficult to achieve with traditional • Material Limitations: The range of materials available for
manufacturing methods. additive manufacturing is still limited compared to
• Customization: Allows for easy customization and personalization of traditional manufacturing methods.
products without significant changes to the manufacturing process. • Speed: While additive manufacturing is excellent for
• Reduced Waste: Generates less material waste compared to prototyping and small production runs, it may not be as fast
subtractive methods, as material is added only where needed. as traditional methods for large-scale production.
• Rapid Prototyping: Speeds up the development of prototypes by • Surface Finish: Objects may require post-processing to
allowing for quick iterations and adjustments to designs. achieve a smooth surface finish, as the layer-by-layer build
• Low-Cost Production: Reduces the need for expensive tooling and can result in visible lines.
molds, making it cost-effective for small production runs and custom • Cost: While additive manufacturing can be cost-effective
parts. for certain applications, the initial investment in equipment
• On-Demand Production: Enables the production of parts as needed, and materials can be high.
reducing inventory costs and lead times.

44 BITS Pilani, Pilani Campus

 Applications of Additive Manufacturing
Education and
Aerospace: Automotive: Healthcare: Consumer Goods: Construction:
Research:

• Used for creating • Employed for rapid • Utilized for • Enables the • Applied in the • Facilitates
lightweight and prototyping, producing production of construction of research and
complex parts, custom parts, and customized customized building educational
such as turbine lightweight medical implants, products, such as components and projects by
blades and components. prosthetics, and eyewear, jewelry, even entire providing a
structural surgical tools. and home decor structures using versatile tool for
components. items. large-scale 3D experimentation
printers. and prototyping.

45 BITS Pilani, Pilani Campus

 Materials for Additive Manufacturing

46 BITS Pilani, Pilani Campus

 Case Studies: GE Aviation: Fuel Nozzle for Jet Engines

GE Aviation: Fuel Nozzle for Jet Engines

• Overview: General Electric (GE) used

additive manufacturing to produce a complex
fuel nozzle for its LEAP jet engines.
• Objective: To improve performance and
reduce the manufacturing cost of the fuel
nozzle, which traditionally required multiple
components and assembly.

Approach: Results:

• Performance Improvement: Achieved a 5%

• Additive Manufacturing Technology: GE used Direct Metal increase in fuel efficiency and a 10% reduction in
Laser Sintering (DMLS) to create the nozzle from metal powder. engine emissions.
• Design Optimization: Redesigned the nozzle to be a single • Cost Reduction: Reduced production costs by
piece rather than several, optimizing its shape for performance eliminating the need for multiple components
and assembly steps.
and heat resistance.
• Enhanced Durability: Improved the durability
• Material: Utilized advanced nickel-based superalloys to and performance of the nozzle due to the
withstand high temperatures and stresses. optimized design and material properties.

47 BITS Pilani, Pilani Campus

 Case Studies: Adidas: Future craft 4D Sneakers

Adidas: Futurecraft 4D Sneakers

• Overview: Adidas leveraged additive

manufacturing to produce its Futurecraft 4D
sneakers, focusing on custom and high-
performance footwear.
• Objective: To create a midsole with unique
cushioning properties and a customized fit for
individual users.

Approach: Results:
• Additive Manufacturing Technology: Used Digital • Performance: Improved comfort and performance
Light Synthesis (DLS) technology to print midsoles with a highly customized midsole design.
using a resin-based process.
• Production Efficiency: Streamlined production
• Design: Employed generative design algorithms to
processes and reduced time-to-market.
optimize the midsole structure for comfort and
performance. • Innovation: Demonstrated advanced capabilities
• Customization: Allowed for customization based on in producing complex, performance-enhancing
individual foot shapes and preferences. footwear components.

48 BITS Pilani, Pilani Campus

 Case Studies: NASA: Mars Rover Components

NASA: Mars Rover Components

• Overview: NASA used additive manufacturing to

create parts for its Mars rovers, including the
Curiosity and Perseverance rovers.
• Objective: To produce lightweight and complex
parts that can withstand the harsh conditions of
space exploration.

Approach: Results:
• Additive Manufacturing Technology: Employed • Performance: Enabled the production of lightweight and
various additive techniques, including Fused durable parts that are critical for the rover’s performance on
Deposition Modeling (FDM) and Selective Laser Mars.
Sintering (SLS), for different components.
• Innovation: Pushed the boundaries of what is possible in
• Material: Used high-performance materials designed space exploration by using advanced manufacturing
to endure extreme temperatures and radiation.
technologies.
• Design: Created intricate parts that reduce weight and
increase functionality, such as custom brackets and • Cost and Efficiency: Reduced the need for complex and
supports. costly traditional manufacturing methods.

49 BITS Pilani, Pilani Campus

 Case Studies: Stratasys: Medical Models for Surgical Planning

Stratasys: Medical Models for Surgical Planning

• Overview: Stratasys, a leading provider of 3D

printing solutions, used additive manufacturing to
create accurate medical models for surgical
planning and education.
• Objective: To provide surgeons with precise, patient-
specific models for better planning and outcomes in
complex surgeries.

Approach: Results:
• Additive Manufacturing Technology: Utilized PolyJet • Improved Planning: Enhanced surgical planning and
and FDM technologies to create detailed anatomical accuracy by providing detailed and realistic models of
models from medical imaging data. patient anatomy.
• Material: Used biocompatible and high-resolution • Reduced Risk: Helped reduce surgical risks and improve
materials to replicate the texture and properties of outcomes by allowing surgeons to rehearse procedures
human tissue. beforehand.
• Application: Created models for various procedures, • Education: Supported medical education and training by
including orthopedic, cardiac, and neurosurgical providing realistic models for practice and demonstration.
planning.

50 BITS Pilani, Pilani Campus

 Artificial Intelligence (AI)

• Artificial Intelligence (AI)

refers to
• the simulation of human
intelligence in machines
• that are designed to think
and act like humans.
• These machines can
perform tasks that
typically require
• human intelligence, such
as
• learning,
• reasoning,
• problem-solving,
• understanding natural
language, and
perception.

51 BITS Pilani, Pilani Campus

 Artificial Intelligence (AI)

52 BITS Pilani, Pilani Campus

 Artificial Intelligence (AI)

53 BITS Pilani, Pilani Campus

 Artificial Intelligence (AI) : Key Concepts in Artificial Intelligence

Natural Language Processing

Machine Learning (ML): Deep Learning: Computer Vision:
(NLP):
• A subset of AI, where systems • A specialized area of machine • The ability of a machine to • The field of AI that enables
learn from data and improve learning that uses neural understand, interpret, and machines to interpret and
their performance over time networks with many layers generate human language. NLP make decisions based on
without being explicitly (deep neural networks) to enables applications such as visual data from the world,
programmed. Machine learning analyze complex patterns in language translation, such as images and videos.
algorithms identify patterns large amounts of data. Deep sentiment analysis, and Applications include facial
and make predictions based learning is often used for image chatbots. recognition, object detection,
on past data. Common types and speech recognition, and autonomous vehicles.
of ML include supervised natural language processing,
learning, unsupervised and other advanced
learning, and reinforcement applications.
learning.

54 BITS Pilani, Pilani Campus

 Robotic Process Artificial General Artificial Superintelligence
Expert Systems:
Automation (RPA): Intelligence (AGI): (ASI):
• Uses AI to automate • AI programs that mimic the • Refers to a theoretical AI • A hypothetical AI that
repetitive and routine tasks decision-making abilities of that possesses the ability to surpasses human
that are usually performed human experts. They use a understand, learn, and apply intelligence in all aspects,
by human workers. RPA can set of rules and knowledge intelligence across a wide including creativity,
streamline business to make decisions or solve range of tasks at a level problem-solving, and
processes and improve problems in specific comparable to human emotional intelligence. ASI is
efficiency. domains, such as medical beings. AGI is still a concept a subject of philosophical
diagnosis or financial and has not yet been and ethical discussions, as
forecasting. achieved. it could have profound
impacts on society.

55 BITS Pilani, Pilani Campus

 Applications of Artificial Intelligence

56 BITS Pilani, Pilani Campus

 Applications of Artificial Intelligence

Healthcare: Finance: Transportation:

• AI is used for diagnostics, • AI is employed for fraud • AI powers autonomous vehicles,

personalized treatment plans, detection, algorithmic trading, traffic management systems,
drug discovery, and medical risk assessment, and customer and route optimization. Self-
imaging analysis. For example, service. AI systems can analyze driving cars use AI to navigate
AI algorithms can detect large volumes of financial data roads, recognize obstacles, and
diseases from medical images to identify trends and make make driving decisions.
with high accuracy. investment decisions.

57 BITS Pilani, Pilani Campus

 Applications of Artificial Intelligence

Entertainment: Education:

• AI is used in content recommendation, • AI supports personalized learning, tutoring

gaming, and media production. Streaming systems, and administrative tasks.
services use AI to suggest movies and music Educational platforms use AI to tailor learning
based on user preferences. experiences and track student progress.

58 BITS Pilani, Pilani Campus

 Applications of Artificial Intelligence

Retail: Manufacturing:

• AI enhances customer experience • AI improves production processes,

through personalized recommendations, predictive maintenance, quality control,
inventory management, and chatbots. and supply chain management. AI-driven
Retailers use AI to analyze consumer robots and sensors enhance automation
behavior and optimize supply chains. and efficiency in manufacturing.

59 BITS Pilani, Pilani Campus

 Advantages and Challenges of Artificial Intelligence

Advantages of Artificial Intelligence Challenges in Artificial Intelligence

• Efficiency and Automation: AI can • Ethical and Privacy Concerns: AI raises

automate repetitive tasks, increasing questions about data privacy, security, and the
efficiency and reducing human error. potential for misuse. Ensuring that AI systems
• Data Analysis: AI can analyze large are used ethically is a significant challenge.
volumes of data quickly and accurately, • Bias and Fairness: AI systems can inherit
uncovering insights and patterns that biases from the data they are trained on, leading
might be missed by humans. to unfair or discriminatory outcomes.
• 24/7 Operation: AI systems can operate • Job Displacement: The automation of tasks
continuously without fatigue, providing may lead to job losses and require workers to
consistent performance and availability. adapt to new roles and skills.
• Personalization: AI enables personalized • Complexity and Transparency: Some AI
experiences and recommendations systems, especially deep learning models, can
based on individual preferences and be complex and opaque, making it difficult to
behaviors. understand how they make decisions.

60 BITS Pilani, Pilani Campus

 Case Studies : Siemens: Predictive Maintenance with AI
OEE : Overall
Siemens: Predictive Maintenance with AI Equipment Efficiency

• Overview: Siemens has leveraged AI to

enhance its predictive maintenance
capabilities in manufacturing.
• Objective: To improve equipment reliability
and reduce downtime by predicting failures
before they occur.

Approach: Results:
• Data Collection: Utilized sensors and IoT devices to collect data • Reduced Downtime: Achieved significant reductions in
from machinery, including temperature, vibration, and
operational parameters.
unplanned downtime by addressing maintenance needs
• Machine Learning: Applied machine learning algorithms to
before failures occurred.
analyze historical data and identify patterns indicative of • Cost Savings: Lowered maintenance costs by avoiding
potential equipment failures. unnecessary servicing and extending equipment lifespan.
• Predictive Models: Developed predictive models that forecast • Operational Efficiency: Improved overall efficiency and
maintenance needs and suggest optimal times for servicing productivity in manufacturing operations.
equipment.

61 BITS Pilani, Pilani Campus

 Case Studies: Bosch: AI-Powered Quality Control

Bosch: AI-Powered Quality Control

• Overview: Bosch implemented AI-driven

quality control systems in its manufacturing
processes to enhance product quality.
• Objective: To detect defects and ensure
high-quality standards in production.

Approach: Results:
• Computer Vision: Used AI-powered computer vision • Enhanced Accuracy: Increased the accuracy of defect
systems to inspect products on the assembly line. detection compared to manual inspection methods.
• Image Analysis: Trained AI models to recognize defects and • Reduced Rework: Minimized the need for rework and
anomalies in real-time by analyzing images captured by high- scrap by catching defects early in the production
resolution cameras. process.
• Integration: Integrated AI systems with existing
manufacturing equipment to provide automated quality
• Consistency: Ensured consistent product quality
inspection. across production runs.

62 BITS Pilani, Pilani Campus

 Case Studies: General Electric (GE): Digital Twin Technology
General Electric (GE): Digital Twin
Technology
• Overview: GE has employed digital
twin technology, which uses AI to
create virtual replicas of physical
assets.
• Objective: To optimize asset
performance and maintenance by
simulating and analyzing real-world
conditions.

Results:
Approach:
• Improved Performance: Enhanced asset performance
• Digital Twin Creation: Developed digital twins of industrial
and efficiency by identifying optimization opportunities.
equipment, such as turbines and generators, using data from
sensors and IoT devices. • Predictive Maintenance: Enabled proactive
maintenance strategies by forecasting potential issues
• Simulation and Analysis: Used AI to simulate various scenarios
based on digital twin data.
and analyze the performance of the physical assets in real-time.
• Operational Insights: Gained valuable insights into
• Predictive Insights: Provided insights into potential issues and
asset behavior and performance.
performance optimizations based on digital twin analysis.

63 BITS Pilani, Pilani Campus

 Case Studies: Fanuc: AI-Driven Robotics for Automation

Fanuc: AI-Driven Robotics for Automation

• Overview: Fanuc, a leading robotics

company, has integrated AI into its robotic
systems to enhance automation
capabilities.
• Objective: To improve the flexibility and
adaptability of robotic systems in
manufacturing environments.

Approach:
Results:
• AI Algorithms: Implemented AI algorithms to enable
robots to learn from their environment and adapt to • Increased Flexibility: Improved the ability of robots to
new tasks. handle diverse tasks and adapt to changes in production
• Machine Vision: Equipped robots with advanced requirements.
machine vision systems to recognize and handle • Enhanced Efficiency: Boosted efficiency and productivity
different parts and objects. by automating complex and repetitive tasks.
• Autonomous Operation: Enabled robots to perform
complex and variable tasks autonomously, without the
• Reduced Downtime: Minimized downtime and
need for extensive reprogramming. reprogramming efforts by utilizing AI-driven adaptability.

64 BITS Pilani, Pilani Campus

 Connected Factories

• Connected Factories refer to

manufacturing environments where
• various components,
• systems, and
• machines are interconnected
• through digital technologies,
• allowing for seamless
communication,
• data exchange, and
• coordination across the production
process.

• This connectivity enhances

operational efficiency, improves
decision-making, and drives
innovation by leveraging real-time
data and advanced analytics.

65 BITS Pilani, Pilani Campus

 Key Concepts of Connected Factories

Internet of Things (IoT): Data Integration:

• IoT devices and sensors are used to collect and • Centralized platforms aggregate data from
transmit data from machines, equipment, and various sources, providing a comprehensive view
environmental conditions within the factory. of operations and enabling more informed
decision-making.

66 BITS Pilani, Pilani Campus

 Key Concepts of Connected Factories

Automation: Advanced Analytics:

• Automated systems and robotics are • Data collected from connected devices is
integrated with IoT and data analytics to analyzed using advanced analytics and
optimize production processes and reduce machine learning to gain insights, predict
manual intervention. trends, and identify areas for improvement.

67 BITS Pilani, Pilani Campus

 Key Concepts of Connected Factories

Real-Time Monitoring: Interoperability:

• Continuous monitoring of production processes, • Systems and devices within the factory are
equipment performance, and environmental designed to work together, ensuring seamless
conditions allows for immediate response to integration and communication between
issues and optimization opportunities. different components and platforms.

68 BITS Pilani, Pilani Campus

 Criteria for a Connected Factory

Data Management and Advanced Analytics and Automation and Control

Connectivity Infrastructure:
Integration: Visualization: Systems:
• Network: A robust and • Data Collection: Efficient • Analytics Tools: Software • Automated Machinery:
reliable network mechanisms for collecting and algorithms for analyzing Integration of robotics and
infrastructure, including data from various sources data to extract actionable automated systems that can
wired and wireless within the factory. insights, detect patterns, and respond to data insights and
connections, to support data • Data Storage: Scalable make predictions. perform tasks with minimal
transmission between storage solutions for • Visualization: Dashboards human intervention.
devices and systems. managing large volumes of and interfaces that present • Control Systems: Advanced
• IoT Devices: Sensors, data. data in an understandable control systems that manage
actuators, and other IoT • Data Integration: Platforms and actionable format for and optimize production
devices installed on or systems that integrate decision-makers. processes based on real-
machinery, equipment, and data from different sources, time data.
production lines to collect ensuring consistency and
and transmit data. accessibility.

69 BITS Pilani, Pilani Campus

 Criteria for a Connected Factory

Cybersecurity User Training and Compliance and

Interoperability: Scalability:
Measures: Support: Standards:
• Data Security: • Standard Protocols: • Flexible • Training Programs: • Industry Standards:
Measures to protect Use of standard Architecture: Comprehensive Adherence to relevant
data integrity, communication Systems and training for staff on industry standards
confidentiality, and protocols and infrastructure that using and managing and regulations for
availability from interfaces to ensure can scale to connected systems data handling,
unauthorized access compatibility accommodate and technologies. security, and
or cyber threats. between different growth, additional • Technical Support: operational practices.
• Network Security: devices and systems. devices, and Access to technical • Quality Assurance:
Safeguards to protect • Integration with increased data support for Processes to ensure
the network Existing Systems: volume. troubleshooting and that connected
infrastructure and Ability to integrate • Adaptability: maintaining systems meet quality
connected devices with legacy systems Capability to adapt to connected factory and performance
from cyber attacks. and technologies new technologies and systems. standards.
within the factory. changing production
requirements.

70 BITS Pilani, Pilani Campus

 Benefits of Connected Factories

Increased Efficiency:
• Enhanced production efficiency through real-time monitoring,
predictive maintenance, and process optimization.

Improved Quality:
• Higher product quality due to consistent monitoring and control
of manufacturing processes.

Reduced Downtime:
• Minimized equipment downtime through predictive maintenance
and early detection of issues.

Enhanced Flexibility:
• Greater flexibility in adapting to changing production
requirements and market demands.

Cost Savings:
• Reduced operational costs through optimized resource utilization
and reduced waste.

Data-Driven Decisions:
• Better decision-making based on comprehensive data analysis
and insights.

71 BITS Pilani, Pilani Campus

 Examples of Digital Manufacturing
Siemens Digital Factory GE Aviation's Additive Manufacturing

• Siemens operates advanced digital factories that utilize its own Digital • GE Aviation uses additive manufacturing (3D printing) to produce
Enterprise Suite. These factories integrate technologies such as IoT, AI, complex jet engine components.
and digital twins to enhance manufacturing processes. • Complex Geometries: 3D printing enables the creation of intricate
• Digital Twins: Siemens uses digital twins to create virtual replicas of geometries that are difficult or impossible to achieve with traditional
physical assets, allowing for real-time monitoring and simulation. manufacturing methods.
• Predictive Maintenance: IoT sensors collect data to predict equipment • Material Efficiency: Additive manufacturing reduces material waste by
failures and schedule maintenance proactively, reducing downtime. building parts layer by layer only where needed.
• Automated Production: Advanced robotics and automation streamline • Rapid Prototyping: GE can quickly prototype and test new designs,
production processes, improving efficiency and precision. accelerating the product development cycle.

72 BITS Pilani, Pilani Campus

 Examples of Digital Manufacturing

Tesla's Gigafactory BMW's Smart Factory

• Tesla's Gigafactory incorporates digital manufacturing technologies to • BMW's smart factories leverage digital technologies to improve car
produce electric vehicle batteries and other components. manufacturing processes.
• IoT and Real-Time Data: The factory uses IoT sensors and real-time data • Collaborative Robots (Cobots): Cobots work alongside human workers
analytics to monitor production processes and optimize performance. to perform repetitive tasks, increasing efficiency and safety.
• Automation and Robotics: Extensive use of robotics and automation in • Augmented Reality (AR): AR is used for maintenance and training,
assembly lines increases production speed and reduces human error. providing real-time guidance and information to workers.
• Energy Management: Advanced energy management systems optimize • Digital Supply Chain: Integration of digital tools in the supply chain
the use of renewable energy sources, enhancing sustainability. enhances transparency and coordination with suppliers.

73 BITS Pilani, Pilani Campus

 Examples of Digital Manufacturing
Adidas Speedfactory Boeing's Digital Thread
• Adidas' Speedfactory uses digital manufacturing to produce customized • Boeing uses a "digital thread" approach to integrate data across the entire
athletic footwear. product lifecycle, from design to production and maintenance.
• Automated Production: The factory employs automated knitting machines • Unified Data Platform: A single digital platform connects design, engineering,
and robotic arms to produce shoes with minimal human intervention. manufacturing, and maintenance data, improving collaboration and decision-
• Customization: Customers can design their own shoes, which are then making.
produced on-demand, reducing inventory costs and waste. • Simulation and Testing: Digital models and simulations are used to test and
• Data-Driven Design: Data analytics inform design decisions, ensuring that validate designs before physical production, reducing development time and
products meet customer preferences and performance requirements. costs.
• Supply Chain Integration: Digital tools enhance coordination and
transparency across the global supply chain, ensuring timely delivery of parts
and materials.

74 BITS Pilani, Pilani Campus

 Examples of Digital Manufacturing
John Deere's Smart Factory Ford's Virtual Factory
• John Deere's smart factories implement digital manufacturing • Ford uses virtual factory models to simulate and optimize production
technologies to improve agricultural equipment production. processes before implementation.
• IoT and Predictive Maintenance: IoT sensors collect data from • Virtual Reality (VR): VR is used to create immersive simulations of
machinery to predict maintenance needs and optimize equipment factory layouts and workflows, identifying potential issues and
performance. improvements.
• Advanced Robotics: Robots perform tasks such as welding and • Digital Twins: Digital twins of production lines allow for real-time
assembly, increasing precision and efficiency. monitoring and optimization of manufacturing processes.
• Data Analytics: Big data analytics are used to optimize production • Collaboration Platforms: Digital collaboration tools enable engineers
schedules and improve quality control. and designers to work together remotely, enhancing innovation and
efficiency.

75 BITS Pilani, Pilani Campus

 Examples of Digital Manufacturing

Honeywell's Connected Plant Nike's Flyknit Technology

• Honeywell's Connected Plant solutions provide digital tools for • Nike's Flyknit technology uses digital manufacturing to produce
optimizing industrial operations. lightweight, durable, and sustainable footwear.
• Real-Time Monitoring: IoT sensors and data analytics provide real-time • Computerized Knitting: Automated knitting machines create seamless,
monitoring of plant operations, enabling quick responses to issues. customized uppers for shoes, reducing waste and improving fit.
• Predictive Analytics: Advanced analytics predict equipment failures • Rapid Prototyping: Digital tools enable rapid prototyping and testing of
and optimize maintenance schedules, reducing downtime and costs. new designs, accelerating the development process.
• Energy Management: Digital tools optimize energy use and improve • Sustainable Manufacturing: The Flyknit process uses less material and
sustainability in industrial operations. energy compared to traditional methods, enhancing sustainability.

76 BITS Pilani, Pilani Campus

 How the current industry is different from Industry 4.0

Technology Integration Data Utilization

Current Industry: Industry 4.0: Current Industry: Industry 4.0:

• Limited Digitization: Use of • Advanced Digitization: • Limited Data
isolated, standalone Integration of digital • Big Data Analytics:
systems for different technologies across all Analysis: Data is often Real-time data
processes (e.g., ERP processes, creating a smart siloed, with limited collection and analysis
systems, basic automation). manufacturing environment. real-time analysis and for predictive and
• Manual Processes: High • IoT and Sensors: Extensive decision-making prescriptive insights.
reliance on manual labor use of IoT devices and capabilities.
and traditional machinery sensors to collect and • Data-Driven
with limited connectivity. analyze data in real-time. • Historical Data: Data Decisions: Enhanced
• Automation and Robotics: is primarily used for decision-making
Deployment of advanced historical analysis and based on data
robotics and automation reporting. analytics, machine
systems for increased
precision and efficiency. learning, and AI
algorithms.

77 BITS Pilani, Pilani Campus

 How the current industry is different from Industry 4.0

Connectivity and Communication Flexibility and Customization

Current Industry: Industry 4.0:

Current Industry: Industry 4.0:
• Isolated Systems: • Interconnected
Limited Systems: Seamless • Mass Production: • Mass Customization:
communication communication Focus on large-scale Ability to produce
between different between machines, production of customized products
systems and systems, and humans standardized at scale, catering to
machines, leading to through the Internet products with limited individual customer
inefficiencies. of Things (IoT). flexibility. needs.
• Manual • Cyber-Physical • Rigid Processes: • Agile Manufacturing:
Coordination: Systems (CPS): Inflexible Flexible and adaptive
Dependence on Integration of physical manufacturing manufacturing
human intervention processes with digital processes that are processes that can
for coordinating systems, allowing slow to adapt to quickly respond to
different parts of the real-time monitoring changes in demand or market changes.
production process. and control. customization.

78 BITS Pilani, Pilani Campus

 How the current industry is different from Industry 4.0

Supply Chain Management Maintenance Practices

Current Industry: Industry 4.0: Current Industry: Industry 4.0:

• Linear Supply • Smart Supply • Reactive • Predictive

Chains: Traditional, Chains: Integrated, Maintenance: Maintenance: Use of
linear supply chains real-time supply Maintenance is real-time data and
with limited real-time chain management performed after a analytics to predict
visibility and systems with end-to- failure occurs, leading and prevent
responsiveness. end visibility. to unplanned equipment failures
downtime. before they occur.
• Manual Tracking: • Automated
Manual processes for Logistics: Use of • Scheduled • Condition-Based
tracking and automation and AI for Maintenance: Maintenance:
managing inventory, efficient inventory Maintenance Maintenance is
leading to management, schedules are based performed based on
inefficiencies and logistics, and on fixed intervals, the actual condition
delays. distribution. regardless of actual and performance of
equipment condition. equipment.

79 BITS Pilani, Pilani Campus

 How the current industry is different from Industry 4.0

Human-Machine Interaction Energy Efficiency

Current Industry: Industry 4.0:

Current Industry: Industry 4.0:
• High Energy • Energy
• Manual Control: • Human-Machine Consumption: Optimization: Use
Human operators Collaboration: Traditional of smart grids, IoT,
manually control Advanced interfaces
manufacturing and analytics to
machines and and collaboration
processes. between humans and
processes with less monitor and
machines (e.g., focus on energy optimize energy
• Limited Assistance:
augmented reality, AI efficiency. consumption.
Basic tools and
interfaces with limited assistants). • Limited Monitoring: • Sustainable
assistance from • Smart Interfaces: Basic monitoring of Practices: Adoption
technology. Use of intuitive, user- energy usage of sustainable
friendly interfaces for without real-time manufacturing
enhanced interaction optimization. practices to reduce
and decision-making. environmental
impact.

80 BITS Pilani, Pilani Campus

 How the current industry is different from Industry 4.0

The shift from current Industry 4.0 leverages This transformation leads
industry practices to advanced technologies to increased productivity,
such as IoT, big data flexibility, and
Industry 4.0
analytics, AI, and sustainability, ultimately
represents a automation to create driving competitive
significant smart, efficient, and advantage in the modern
transformation in responsive industrial landscape.
manufacturing. manufacturing
environments.

81 BITS Pilani, Pilani Campus

 Concluding Remarks

Readiness and Barriers for Industry

Industry 4.0: Historical Industrial Revolutions: Digital Manufacturing:
4.0 Implementation:
• We delved into the definition, • By examining Industry 1.0 through • We discussed what digital • A detailed framework was provided
technologies, and future prospects Industry 4.0, we gained an manufacturing entails, provided to measure readiness and identify
of Industry 4.0, highlighting the understanding of the technological examples, and looked at its role in barriers for implementing Industry
transformative potential of IoT, big milestones and shifts that have enhancing efficiency, flexibility, and 4.0. This included assessing
data, cloud computing, robotics, shaped the manufacturing quality in production. technological, organizational,
additive manufacturing, and landscape. Each revolution brought financial, and ecosystem readiness,
artificial intelligence in significant changes, from as well as strategies to overcome
revolutionizing manufacturing mechanization and mass identified barriers.
processes. production to automation and
digitalization.

Framework for Measuring

Case Studies: Connected Factories: Technological Advancements:
Readiness and Barriers:
• We explored numerous case • The concept and criteria for • We reviewed the key • We outlined a structured
studies in the manufacturing connected factories were technologies developed during framework for organizations to
sector, demonstrating outlined, emphasizing the each industrial revolution and assess their readiness for
practical applications of IoT, importance of connectivity, their impact on manufacturing Industry 4.0 and address
big data analysis, cloud integration, and real-time data practices, from steam engines potential barriers, ensuring a
computing, robotics, additive exchange in modern and mechanization in Industry smooth transition to digital
manufacturing, and artificial manufacturing environments. 1.0 to cyber-physical systems manufacturing.
intelligence. and smart factories in Industry
4.0.

82 BITS Pilani, Pilani Campus

BITS Pilani, Pilani Campus
 How Industry 4.0 is different ?

84 BITS Pilani, Pilani Campus

 • Siemens: Digital Factory and Automation
• Overview: Siemens implemented advanced digital technologies in its Amberg
Electronics Plant in Germany to enhance manufacturing efficiency and flexibility.
• Objective: To create a smart, highly automated factory that integrates digital and
physical systems to improve production processes and product quality.

Approach: Results:
•Digital Twins: Used digital twins to simulate and •Increased Efficiency: Achieved a production
optimize manufacturing processes before physical efficiency of over 75%, with highly automated and
implementation. flexible production lines.
•Automation: Integrated automated production lines with •Reduced Downtime: Minimized equipment downtime
robotics and IoT devices to streamline operations. through predictive maintenance and real-time
•Real-Time Monitoring: Employed sensors and data monitoring.
analytics for real-time monitoring and control of •Enhanced Quality: Improved product quality by
production systems. integrating advanced quality control systems.
85 BITS Pilani, Pilani Campus
 • General Electric (GE): Predix Platform for Industrial IoT
• Overview: GE developed the Predix platform to leverage Industrial Internet of Things (IIoT) for optimizing industrial
operations and maintenance.
• Objective: To provide a comprehensive platform for data collection, analysis, and visualization to improve asset
performance and operational efficiency.

Approach: Results:
•IoT Integration: Connected industrial assets such as •Operational Improvements: Enhanced operational
turbines, generators, and compressors to the Predix efficiency and reduced maintenance costs through
platform for data collection. predictive analytics.
•Data Analytics: Applied advanced analytics and •Asset Optimization: Improved performance and
machine learning to predict equipment failures and lifespan of industrial assets by optimizing maintenance
optimize maintenance schedules. and operational strategies.
•Visualization: Developed dashboards and interfaces •Industry Impact: Set a benchmark for IoT and data-
for real-time monitoring and decision-making. driven optimization in the industrial sector.

86 BITS Pilani, Pilani Campus

 • Bosch: AI-Powered Quality Assurance
• Overview: Bosch implemented AI-driven quality assurance systems to enhance
defect detection and product quality in its manufacturing processes.
• Objective: To utilize AI for real-time quality control and reduce defects in the
production line.

Approach: Results:
•Computer Vision: Employed AI-powered computer vision •Defect Reduction: Significantly reduced the number
systems to inspect products for defects on the assembly of defects and rework by catching issues early in the
line. production process.
•Machine Learning: Trained AI models to recognize defects •Increased Accuracy: Enhanced the accuracy of
and anomalies by analyzing high-resolution images of defect detection compared to manual inspection
products. methods.
•Integration: Integrated AI quality control systems with •Quality Consistency: Achieved consistent product
existing production equipment for automated inspection. quality across different production batches.

87 BITS Pilani, Pilani Campus

 • Tesla: Autonomous Manufacturing with AI
• Overview: Tesla utilized AI and advanced robotics to streamline its manufacturing
processes and enhance production efficiency at its Gigafactories.
• Objective: To automate production processes and improve the flexibility and
scalability of manufacturing operations.

Results:
Approach: •Increased Production Capacity: Expanded production
•Robotic Automation: Implemented AI-driven robots capacity and reduced manufacturing lead times through
for tasks such as welding, painting, and assembly in its automation and optimization.
manufacturing lines. •Quality Improvement: Enhanced product quality and
•AI Optimization: Used AI algorithms to optimize consistency through advanced AI-driven quality control
production schedules, manage supply chains, and systems.
improve quality control. •Scalability: Improved scalability and flexibility of
•Data Integration: Integrated data from various manufacturing operations to meet growing demand for
production stages to monitor and adjust processes in electric vehicles.
real-time.

88 BITS Pilani, Pilani Campus

 • 1. Readiness Assessment
• A. Technological Readiness
1. Infrastructure: Assess the current state of IT and network infrastructure to support IoT, cloud computing, and big data.
1. Criteria: Network bandwidth, data storage capacity, cybersecurity measures.

2. Automation: Evaluate the level of automation in existing processes.

1. Criteria: Use of robotics, automated machinery, control systems.

3. Data Management: Review capabilities for data collection, integration, and analytics.
1. Criteria: Data quality, integration platforms, analytics tools.

• B. Organizational Readiness
1. Leadership Commitment: Measure the commitment of leadership to drive Industry 4.0 initiatives.
1. Criteria: Vision alignment, resource allocation, strategic planning.

2. Workforce Skills: Assess the skill levels and readiness of the workforce to adapt to new technologies.
1. Criteria: Training programs, technical expertise, adaptability.

3. Change Management: Evaluate the organization’s ability to manage change and implement new processes.
1. Criteria: Change management frameworks, employee engagement, communication strategies.

• C. Financial Readiness
1. Investment Capacity: Review the financial resources available for Industry 4.0 investments.
1. Criteria: Budget allocation, funding mechanisms, ROI analysis.

2. Cost-Benefit Analysis: Conduct a cost-benefit analysis to determine the economic feasibility of Industry 4.0 projects.
1. Criteria: Initial costs, long-term benefits, risk assessment.

• D. Ecosystem Readiness
1. Supply Chain Integration: Evaluate the readiness of supply chain partners to adopt Industry 4.0 technologies.
1. Criteria: Collaboration platforms, data sharing, interoperability.

2. Regulatory Environment: Assess the regulatory and compliance landscape related to Industry 4.0.
1. Criteria: Compliance requirements, standards, industry regulations.

3. Market Dynamics: Understand market trends and customer expectations regarding digital transformation.
1. Criteria: Market demand, competitive landscape, customer feedback.

89 BITS Pilani, Pilani Campus

 • Barriers Identification
• A. Technological Barriers
1. Legacy Systems: Challenges with integrating new technologies with existing legacy systems.
1. Strategies: Phased implementation, use of middleware, modernization plans.

2. Cybersecurity: Risks associated with increased connectivity and data exchange.

1. Strategies: Robust cybersecurity protocols, regular security audits, employee training.

3. Data Management: Difficulties in managing and analyzing large volumes of data.

1. Strategies: Investment in data management tools, data governance policies, skilled data scientists.

• B. Organizational Barriers
1. Resistance to Change: Employee resistance to adopting new technologies and processes.
1. Strategies: Effective change management, clear communication, stakeholder involvement.

2. Skill Gaps: Lack of necessary skills and expertise among the workforce.
1. Strategies: Training and development programs, hiring specialized talent, partnerships with educational institutions.

3. Leadership Challenges: Lack of vision or commitment from leadership.

1. Strategies: Leadership training, alignment of strategic goals, active involvement of executives.

• C. Financial Barriers
1. High Initial Costs: Significant upfront investment required for Industry 4.0 technologies.
1. Strategies: Cost-sharing partnerships, phased investments, exploring funding opportunities.

2. Uncertain ROI: Uncertainty about the return on investment for Industry 4.0 projects.
1. Strategies: Detailed ROI analysis, pilot projects, scalable solutions.

• D. Ecosystem Barriers
1. Supplier Readiness: Lack of readiness or willingness among supply chain partners.
1. Strategies: Collaborative initiatives, joint ventures, supplier training programs.

2. Regulatory Hurdles: Regulatory challenges and compliance issues.

1. Strategies: Active engagement with regulators, staying updated on regulations, compliance frameworks.

3. Market Acceptance: Market resistance or lack of demand for Industry 4.0-enabled products.
1. Strategies: Market research, customer education, value proposition communication.

90 BITS Pilani, Pilani Campus

 • Implementation Roadmap
1. Vision and Strategy Development:
1. Define the vision for Industry 4.0.
2. Align strategic goals with the organization’s overall objectives.
3. Develop a comprehensive Industry 4.0 strategy.
2. Pilot Projects:
1. Identify key areas for pilot implementation.
2. Conduct pilot projects to test technologies and processes.
3. Evaluate outcomes and refine strategies.
3. Scalable Implementation:
1. Develop a phased implementation plan based on pilot results.
2. Scale successful pilots across the organization.
3. Continuously monitor and optimize processes.
4. Training and Development:
1. Implement ongoing training programs for employees.
2. Foster a culture of continuous learning and innovation.
3. Encourage cross-functional collaboration.
5. Collaboration and Partnerships:
1. Build partnerships with technology providers, educational institutions, and industry consortia.
2. Engage with supply chain partners to ensure ecosystem readiness.
3. Participate in industry forums and standardization bodies.
6. Continuous Improvement:
1. Establish mechanisms for continuous feedback and improvement.
2. Stay updated on emerging technologies and industry trends.
3. Adapt strategies based on evolving needs and opportunities.

91 BITS Pilani, Pilani Campus

 Forces behind Industry 4.0

Industry 4.0 is driven by a confluence of advanced technologies that are transforming

manufacturing and industrial processes.

Internet of Things (IoT)

Devices/Sensors: Connectivity: Data Processing: User Interface: • IoT involves the interconnection of physical
devices, vehicles, buildings, and other items
embedded with sensors, software, and network
connectivity.
• Physical objects
• Platforms and Impact:
equipped with • The analysis
• The means by applications • Real-Time Data Collection: IoT devices collect
sensors and and processing
which devices through which and transmit real-time data from production
actuators that of data
users interact with processes, enabling continuous monitoring and
connect to the collected by IoT
collect data from IoT systems. analysis.
internet or to devices.
their environment • Examples: Mobile • Predictive Maintenance: Data from IoT sensors
other devices. • Can occur can predict equipment failures, allowing for
and perform apps, web
• Technologies: locally (edge
dashboards, voice
proactive maintenance and reducing downtime.
actions. computing) or • Enhanced Efficiency: IoT enables better
Wi-Fi, assistants.
• Examples: Smart in the cloud. resource management, process optimization,
Bluetooth, and energy efficiency.
thermostats,
cellular • Smart Manufacturing: Integration of IoT in
wearable fitness manufacturing systems leads to smarter
networks,
trackers, industrial factories with improved decision-making
Zigbee,
machinery sensors. capabilities.
LoRaWAN.
92 BITS Pilani, Pilani Campus
 Forces behind Industry 4.0

Industry 4.0 is driven by a confluence of advanced technologies that are transforming

manufacturing and industrial processes. Big Data
Big data refers to the vast volumes of data generated
Internet of Things (IoT) from various sources, which can be analyzed to uncover
• IoT involves the interconnection of physical devices, vehicles, patterns, trends, and insights.
buildings, and other items embedded with sensors, software, Impact:
and network connectivity. Data-Driven Decision Making: Analysis of big data
Impact: helps manufacturers make informed decisions based
• Real-Time Data Collection: IoT devices collect and transmit on real-time and historical data.
real-time data from production processes, enabling Quality Control: Big data analytics can identify defects
continuous monitoring and analysis. and anomalies in production, leading to improved
• Predictive Maintenance: Data from IoT sensors can predict product quality.
equipment failures, allowing for proactive maintenance and
reducing downtime. Supply Chain Optimization: Insights from big data can
• Enhanced Efficiency: IoT enables better resource enhance supply chain management by predicting
management, process optimization, and energy efficiency. demand, optimizing inventory, and reducing costs.
• Smart Manufacturing: Integration of IoT in manufacturing Customer Insights: Understanding customer
systems leads to smarter factories with improved decision- preferences and behavior through data analysis enables
making capabilities.
the production of customized products.

93 BITS Pilani, Pilani Campus

94 BITS Pilani, Pilani Campus
 Concluding Remarks : Existing Manufacturing Paradigms and Their Limitations

Conventional manufacturing often relies on linear processes, which can be inefficient

Linear Processes: and inflexible.

Traditional methods require large inventories, leading to high storage costs and
High Inventory Costs: potential waste.

Mass production techniques limit the ability to produce customized products, reducing
Limited Customization: responsiveness to customer needs.

Manual Labor: Dependence on manual labor increases the risk of human error and limits scalability.

Slow Adaptation: Traditional systems can be slow to adapt to changes in demand or new technologies.

95 BITS Pilani, Pilani Campus

 Concluding Remarks: Industrial Revolutions 1, 2, 3, and 4

Industry 1.0 (Late 18th Industry 2.0 (Late 19th and Industry 3.0 (Mid-20th Industry 4.0 (Early 21st
Century): Early 20th Century): Century): Century):
Key Developments: Key Developments: Key Developments: Key Developments:
Mechanization using Mass production, Automation, Cyber-physical systems,
steam and water assembly lines, and computers, and IoT, AI, and advanced
power. electrification. electronics. robotics.
Impact: Smart,
Impact: Increased Impact: Dramatic Impact: Enhanced interconnected systems
production capacity increase in production precision, reduced enabling real-time data
and efficiency, but with scale and speed, but labor costs, and analysis, predictive
limited automation and also introduced improved product maintenance, and high
high reliance on human repetitive, monotonous quality, but led to job customization.
labor. work. displacement and Challenges include
required new skills. cybersecurity, skill gaps,
and integration
complexities.

96 BITS Pilani, Pilani Campus

 Concluding Remarks: Digital Manufacturing

Key benefits include: digital manufacturing also presents

challenges:
• Efficiency and Productivity: Automation and
real-time data analysis enhance efficiency • Cybersecurity: Protecting sensitive
and reduce production time. data and ensuring the security of
• Customization: Advanced technologies like connected systems.
3D printing enable on-demand production of
customized products. • Skill Requirements: Need for a
• Cost Reduction: Optimized processes and
workforce skilled in digital
predictive maintenance lower operational technologies and data analysis.
costs and reduce waste. • Initial Investment: High initial costs
• Flexibility: Digital tools enable quick for implementing digital
adaptation to changes in demand and infrastructure and technologies.
technological advancements. • Integration: Complexities in
• Quality and Consistency: Precision integrating new digital tools with
manufacturing and real-time monitoring
improve product quality and consistency.
existing systems.

97 BITS Pilani, Pilani Campus

 Future of Digital Manufacturing

Smart Factories: Advanced Sustainable Global Innovation and

Robotics: Practices: Connectivity: R&D:
Increased prevalence More sophisticated and Greater focus on Enhanced global Ongoing innovation in
of smart factories that collaborative robots sustainable connectivity enabling materials science,
leverage IoT, AI, and working alongside manufacturing more efficient supply production methods,
digital twins for humans to enhance practices, including the chain management and and digital tools, fueled
optimized operations. productivity and safety. use of renewable collaboration across by robust research and
energy sources and borders. development efforts.
recycling.

98 BITS Pilani, Pilani Campus

 Next Class on 4th Aug 2024

Forces behind Industry 4.0 (IoT, big data, cloud

2.1 computing, robotics, additive manufacturing and
artificial intelligence)
Forces
behind
Industry Connected Factories (What is connected factory and
2.2
4.0 criteria for connected factory)

2.3 How the current industry is different from Industry 4.0

99 BITS Pilani, Pilani Campus

 References

• Text Book
• Internet of Things: A Hands-On Approach by Arshdeep Bahga, Vijay Madisetti, University Press Publication,
2015.

• References
• Zhang Y. and Tao F., “Optimization of Manufacturing Systems using the Internet of Things”, 1st Edition, 2017,
Academic Press (Elsevier), UK.
• IoT Fundamentals : Networking Technologies, Protocols, and Use Cases for the Internet of Things, 1/e by
David Hanes , cisco press
• Internet of Things and Data Analytics Handbook by Hwaiyu Geng © 2017 John Wiley & Sons, Inc.
• The Internet of Things: Key Applications and Protocols Olivier Hersent, David B. 2nd Edition, Wiley
Publication
• Internet of Things: Architecture and Design Principles Rajkamal. 1st Edition, Mc Graw Hill

100 BITS Pilani, Pilani Campus

101 BITS Pilani, Pilani Campus
 Components of Big Data Analysis

Data Collection:
Sources: Sensors, social
Data Storage:
media, transaction logs, Technologies: Distributed
web scraping, etc. storage systems such as
Hadoop HDFS, NoSQL
Technologies: APIs, web databases like MongoDB, and
crawlers, data loggers. cloud storage solutions.

Data Analysis: Data Visualization:

Data Processing: Techniques: Statistical Purpose: To represent data in
Technologies: Batch analysis, machine learning, graphical formats to help
processing frameworks like data mining, natural language understand trends, patterns,
Hadoop MapReduce and real- processing (NLP), etc. and insights.
time processing frameworks Tools: R, Python (with libraries
like Apache Spark. Tools: Tableau, Power BI, D3.js,
like pandas and scikit-learn), matplotlib, etc.
SAS, Apache Spark, etc.

102 BITS Pilani, Pilani Campus

103 BITS Pilani, Pilani Campus
104 BITS Pilani, Pilani Campus
105 BITS Pilani, Pilani Campus
106 BITS Pilani, Pilani Campus
107 BITS Pilani, Pilani Campus
 Connected Factories

• Connected Factories refer to

manufacturing environments where
• various components,
• systems, and
• machines are interconnected
• through digital technologies,
• allowing for seamless communication,
• data exchange, and
• coordination across the production
process.

• This connectivity enhances operational

efficiency, improves decision-making,
and drives innovation by leveraging
real-time data and advanced analytics.

108 BITS Pilani, Pilani Campus