Write 15 applications of statistics and probability on

engineering

Statistics deals with collecting, processing, summarizing, analyzing, and

interpreting data. On the other hand, engineers and scientists deal with such
diverse issues as the development of new products, effective use of materials and
labor, solving production problems, quality improvement and reliability, and, of
course, basic research.

Depending on the field of specialization, statistics may also help

engineers in areas such as:

 Analysis of test and evaluation results on existing projects

 Data collection and interpretation
 Estimating the coefficient of thermal expansion of a metal;
 comparing two methods of cloud seeding for hail and fog suppression at
international airports;
 Comparing two or more methods of cement preparation in terms of
compressive strength;
 Comparing the effectiveness of three cleaning products in removing four
different types of stains;
 Predicting the failure time of a beam on the basis of stress applied;
 Assessing the effectiveness of a new traffic regulatory measure in reducing
the weekly rate of accidents;
 Testing a manufacturer’s claim regarding the quality of its product;
 Studying the relation between salary increases and employee productivity
in a large corporation;
 Estimating the proportion of US citizens age 18 and over who are in favor
of expanding solar energy sources; and
 Determining whether the content of lead in the water of a certain lake is
within the safety limit.
 Estimating time and resources required in projects…etc.
Basically, it’s impossible to be a good engineer without some intermediate
statistical knowledge and strong visualization and communication skills.
Application of Statistics for Electrical Engineer?
Statistics are heavily used in electrical engineering, mainly applied statistics (where
pure statistics are primarily based on theories and proofs, applied statistics have a
greater focus on problem solution.
. Electrical engineers are frequently tasked with solving production problems, requiring
data analysis, and testing to ensure quality control. They need to understand reliability
and the theories behind it when determining the risk of product failure. They need to
know how to collect data and knowing sampling theory to collect the most appropriate
and useful data sets.
1. Probability models figure largely in electrical engineering. Electrical
engineers are often managing extensive distributed systems and real-time data
monitoring in environments that are not always well controlled. These situations
introduce much in the way of variability and randomness, two fundamental
concepts in probability theory, and foundational to the study of statistics.
Particularly relevant to electrical engineers are random processes where
the engineer needs to understand the statistical properties of variability.
Learning variability assists an engineer in building reliable systems by teaching
them how to discern (and then manage) unreliable components. This also
enables an electrical engineer to accurately estimate a product’s
average values without having to test each and every product. The
development and use of models are key in determining what resources are
needed to build and implement high quality, reliable systems.
2. The importance of studying statistics includes:-
learning experimental design.
Electrical engineers may have had little exposure to the aspects of research design in
their engineering courses. An advanced degree in applied statistics would enable the
engineer to determine the appropriate design to use to solve problems. They would
not only learn which design to use but how to apply it correctly. Electrical engineers also
need to understand research methodologies and procedures to
apply electrical and other theories to projects. Engineers need to understand the right
methods in collecting data (such as field surveys) to identify and correct problems.

Much of electrical engineering is computational. Studying statistics will give an engineer

additional training in programming languages and statistical software to most effectively
analyze the data they've collected. These computational tools are used for the types of
inferences an electrical engineer is frequently called on to make including prediction and
hypothesis testing.
 3. Another critical aspect of the study of statistics for an electrical engineer is
reporting. While electrical engineers tend to develop strong visualization
skills throughout their work (as they observe designs and processes), they also
need to learn how to interpret, display, and report their results. Different outputs
require different presentations–should the data be displayed as a graph? Are the
descriptive statistics displayed effectively? Are the inferences clear and
meaningful? A robust statistics program will teach an engineer how to create
reports that are visually effective, easily interpreted, and understandable for
technical and non-technical audiences alike

Most electrical engineering programs include at least one course in statistics, but that
course (or courses) may be secondary to overall engineering concepts. Studying
statistics in a dedicated program gives the in-depth knowledge and training needed to
not only be a capable electrical engineer but an innovative one. Applied statistics are
particularly appropriate for engineers who tend to be active, "hands-on" learners. It is
also essential for the statistics program to deal with solving real-world problems for it to
be relevant to the engineer. A robust applied statistics program will also include
communication and leadership–electrical engineers should be able to use their
statistical toolset to take leadership of their projects. They will also learn the skills
necessary to collaborate effectively and efficiently.

Design of Experiments The Design of Experiments (DOE) technique is usually not discussed in
an undergraduate statistics course. However, the tool is very important for test engineers. With
the help of software such as Minitab, the design and analysis aspects of DOE become fairly
straightforward. In DOE, a problem is defined first. Second, factors and levels are chosen. Third,
the response variables to be measured are selected. Fourth, a test matrix is created using
Minitab. Finally, experiments are conducted to acquire data. Software such as Minitab can be
used to perform statistical analysis. This process is illustrated with an example from the wireless
research project discussed earlier. The result of the DOE analysis for jitter in a wireless
communication is plotted in Fig. 2. It is evident based on Fig. 2: The three major contributors to
the jitter can be identified as packet size, location, and wireless card selection

A student team in the Circuit Analysis course used a series resonant circuit to measure the
inductance of a motor coil. The test was repeated ten times with average and standard
deviation calculated instead of the single measurement typically taken by students in previous
semesters.
A student team working on a DC permanent motor project conducted statistical analysis to
create a histogram, as illustrated in Figure below to show the variation in motor speed. This
helped the students take the variation into their design considerations, instead of simply using
the nominal value of 265 rpm provided by the vendor.
Application of probability and statistics in civil engineering
4. Evaluating source of risk associated with natural events

Tornadoes, hurricanes, droughts, and earthquakes are example of natural events that pose risks to
society and on the way the construction and modification of the built and natural environments can
alter the probability of occurrence of natural events and the character and magnitude of the impact that
such events have. We then argue for the need to develop a standard of reasonable care for decisions
about the built and modified natural environment, which accounts for technical, and resource
constraints, as well as the place of natural hazard mitigation in public policy.

5. Probabilistic concept for the validation of the effectiveness of

countermeasure against early age cracking in massive concrete structures.
By calculation of the probability of thermal cracking, reliability-oriented crack criteria are defined for a
wide use in practice. The proposed model can be applied, if reliable estimations of load-independent
strains, concrete properties and restraint of the hardening concrete structure as well as of the
uncertainties of all parameters are available. Following this approach, the early-age cracking risk for
recently executed railways trough structure is evaluated by taking the uncertainty of prediction into
account.

6. Statistical analysis of weigh in motion data for bridge of load live development

The statistical concepts required and the terminologies adopted in the development of bridge live load
models are introduced

Different load affecting parameters such as gross vehicle weights, axle weights, axle spacing, average
daily number of trucks etc. are first analyzed by various stochastic processes in order to obtain the
mathematical distributions of these parameters. As a prerequisite to determine accurate bridge design
loadings.

There are also so many applications of statistics on civil engineering.

STATISTICS AND PROBABLITY on SOFTWARE ENGINEERING
Software Engineering (SE) deals with the development, maintenance and
management of high-quality software systems in a cost effective and predictable
manner.
Software development
is often perceived as a unique activity, residing at the boundary of the technical
world and the world of the developer's individuality. To fully understand the
phenomena occurring during the software development, a researcher should
address the technical, as well as" people problems" associated with the
development of software. Software engineers use statistics and probability to
fully understand the problem occurred and how to solve them.

There are a number of ways that statistics and software engineering merge;
consider the development of models and data mining. Typically, statistical
approach to models tends to involve stochastic (random) models with prior
knowledge of the data. The computer science approach, on the other hand, leans
more to algorithmic models without prior knowledge of the data. Ultimately,
these come together in attempts to solve problems.

Data mining processes for software engineering have statistical counterparts.

Consider the following:

7. Machine learning
- Machine learning is a field of computer science that gives computer systems the
ability to “learn” (i.e. progressively improve performance on a specific task) with
data, without being explicitly programmed. Machine learning explores the study
and construction of algorithms that can learn from and make predictions on data.
Machine learning is closely related to computational statistics, which also focuses
on prediction-making through the use of computers.
Example – Email
8. Engineering In reliability
-Measures the ability of a system to perform for its intended function(time) and
has tools for improving performance.
Example: -
Predictive and Preventive maintenance
Maintenance-induced failures
Transport-induced failures
Storage-induced failures
9. Quality control: -
-Quality control is a process by which entities review quality of their system, and
process control use statistics as a tool to manage conformance to specifications of
manufacturing processes and their products.
Example -
1.Competence, such as knowledge, skills, experience, and qualifications2.
Soft elements, such as personnel, integrity, confidence, organizational culture,
motivation, team
spirit, and quality relationships

10. Data science: -

-Data science is one field of software engineering which uses statistics to extract
knowledge from data in various forms, the data analysis fields such as statistics,
data mining, and predictive analytics, similar to Knowledge Discovery in
Databases.
Example –
internet search
11. Combine information: -
- One of the largest impacts of the statistical community in software engineering
concerns efforts to combine information across software engineering projects as a
means of evaluating the effects of technology, language, organization, and the
development process. Although difficult issues are posed by the need to adjust
appropriately for differences in projects.
Example
- evaluating the effects of technology
12. Data analysis: -
Which helps engineering to make decisions about several things, for example
purpose of the operation, part design characteristics, specifications and
tolerances of parts, materials, manufacturing process design, setup and tooling,
working conditions, material handling, plant layout, and workplace design.
Knowing the specifics (who, what, when, where, why, and how) of product
manufacturing assists in the development of an optimum manufacturing method.
Example
– purpose of the operation.
Applications of statistics and probability in mechanical engineering

Mechanical Engineering is very broad as a field, and many of its applications

use Statistics. Here are a few examples:

13. Calculating Material properties (strength)

If you test a number of samples, you will get a range of values. Now, you can’t
use the average, that is dangerous, and you can’t use the minimum, as you did
not have an infinite number of samples. You can however determine the
standard deviation, mean, and median, and come up with an acceptable
number as a lower bound using the data you gathered. Usually you want 3 or
more sigma.. and if you have huge range in values from test, that means your
min strength might be half of your average!

14. Process control

simple CAD work shows a “nominal” design.. but in reality there are
variations.. in height, screw torque, what have you. You need to do the same
kind of thing you do for properties above for the process! And ensure your
very worst build still will work!

15. Tolerancing

In the same was properties and processes vary, so do tolerance ranges you get
in a fabrication! Direct math of worst case on worst case tolerance is near 6
sigma, but may drive up costs for the parts if that means you have to tighten
tolerances. So you do the math, conflict by conflict, to see what you can live
with .

Nothing in life is nominal, but a range, ..and statistics helps pin down where it
won’t work.