Scribd
Upload
17 views

ANN Control

The document discusses using mathematical modeling and control systems for temperature regulation of nonlinear systems. It describes modeling a temperature process and designing controllers like PID and neural networks to control the temperature to a setpoint. Simulation software is used to implement the models and control systems.

Uploaded by

ali noman
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
17 views

ANN Control

The document discusses using mathematical modeling and control systems for temperature regulation of nonlinear systems. It describes modeling a temperature process and designing controllers like PID and neural networks to control the temperature to a setpoint. Simulation software is used to implement the models and control systems.

Uploaded by

ali noman
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

DEPARTMENT OF ELECTRICAL AND ELECTRONICS

Galgotias College Of Engineering and Technology, Greater Noida (U.P.)

ANN based control of Non-linear Systems


(202-202)

Presented By:
Guided By:-
CONTENT

● Introduction

● Mathematical Modeling

● Requirement of Mathematical Modeling

● Temperature control using PID Controller

● Artificial Neural Network


Objective

● To study and develop a mathematical model for a nonlinear temperature process.

● To design a controller to regulate the temperature of the process.

● To compare the efficiency of the neural controller with other controllers.

● Design a control system to regulate the temperature of a Non-linear system to a setpoint.

● Implement the control system and assess its performance in maintaining the desired temperature.

● Use simulation software (eg. MATLAB simulink) to implement mathematical model and control system.
Introduction

Mathematical Modelling:

● Mathematical modeling in control systems is the process of representing a real-world physical system or process using
mathematical equations, relationships, and parameters. The goal of mathematical modeling in control systems is to create a
mathematical description of the system's behavior that allows for analysis, simulation, and control design.

● Mathematical modeling is a fundamental step in control system design and analysis. It allows control engineers to study the
system's behavior, design controllers to regulate its performance, and simulate the system's response to various inputs and
disturbances. These models are crucial for optimizing control strategies and ensuring that the controlled system operates as
desired.
Requirement of Modelling:

● Understanding System Behavior: Mathematical models provide a structured way to understand and describe the behavior of complex
systems. They enable engineers and researchers to gain insights into how a system responds to different inputs, disturbances, and
conditions.
● Control System Design: Mathematical models serve as the foundation for designing control strategies. They allow control engineers to
develop, test, and fine-tune control algorithms that regulate system behavior to achieve desired outcomes.
● Predictive Control: Control systems use mathematical models to predict future system behavior, allowing for proactive control adjustments
to maintain stability, optimize performance, and achieve desired setpoints.
Temperature control using PID Controller
PID Controller

● A proportional–integral–derivative controller(PID) is a control loop mechanism employing feedback that is widely used in industrial
control systems and a variety of other applications requiring continuously modulated control.

Gc = Kp + Ki/s + Kds

● Compensator formula:

C = P + I/s + D(N/1+N/s)

● Proportional(P) = 1
● Integral(I) = 1
● Derivative(D) = 0
● Filter Coefficient(N) = 100
Artificial Neural Network

An Artificial Neural Network (ANN) in a control system refers to the use of neural networks, a type of machine
learning model, to control or regulate a system. In this context, neural networks are employed to make decisions or
take actions based on input data, with the goal of achieving desired control objectives. This can be applied to a wide
range of control systems, including industrial automation, robotics, autonomous vehicles, and more.

Here's how it generally works:

● Data Input
● Neural Network
● Control Action
● Feedback Loop
Reference

[1] Oltean, G. et al. (2007) Model Based Design and FPGA Implementation of Control Systems .
[2] Singh, Y.K. et al. (2016) Temperature Control System and its control using PID controller, https://www.ijert.org/. Available at:
https://www.ijert.org/research/temperature-control-system-and-its-control-using-pid-controller-IJERTCONV4IS02010.pdf.
[3] Reddy, Dr.H.K.M. (2013) MATLAB/SIMULINK Based Oven Temperature Control through Simulation Studies using PIDC,
https://csjournals.com/. Available at: https://csjournals.com/IJEE/PDF5-1/Manju.pdf.
[4] R. J. Rajesh, R. Preethi, P. Mehata and B. J. Pandian, "Artificial neural network based inverse model control of a nonlinear process,"
2015 International Conference on Computer, Communication and Control (IC4), Indore, India, 2015, pp. 1-6, doi:
10.1109/IC4.2015.7375581.

You might also like