Soft computing approach to control system
- 2. Introduction • Control engineering or control systems engineering is the engineering discipline that applies control theory to design systems with desired behaviors. The practice uses sensors to measure the output performance of the device being controlled and those measurements can be used to give feedback to the input actuators that can make corrections toward desired performance. • A control system is a device, or set of devices, that manages, commands, directs or regulates the behavior of other devices or systems.
- 3. Soft Computing Approach to CSE • Generally speaking, soft computing techniques resemble biological processes more closely than traditional techniques. • In computer science, soft computing is the use of inexact solutions to computationally hard tasks
- 5. Neural Network • Based on biological nervous system. • It has an architecture that tries to mimic brain mechanics to simulate intelligent behavior.
- 6. Fuzzy Logic • Fuzzy logic attempts to systematically and mathematically emulate human reasoning and decision making. • Fuzzy logic represents an excellent concept to close the gap between human reasoning and computational logic. • Variables like intelligence, credibility, trustworthiness and reputation employ subjectivity as well as uncertainty.
- 7. Genetic Algorithm • Genetic algorithms (GAs) are stochastic optimization methods based loosely on the concepts of natural selection and evolution process. • Genetic algorithms • (GAs) are the solution for optimization of hard problems quickly, reliably and accurately.
- 8. A Case Study: Speed Control of A DC Motor • Speed control means intentional change of the drive speed to a value required for performing the specific work process. • Speed control is either done manually by the operator or by means of some automatic control device.
- 10. Simulink Model
- 11. Rule Base
- 12. Response
- 13. Comparison Response Without PID With PID Fuzzy Rise Time (sec) 1.1362 0.7195 0.1 Settling Time (sec) 2.9 1.6587 0.6 Dead time (sec) 0 1 0 Peak Time (sec) 5.2388 0.2337 0 Overshoot (sec) 8.7813 0.15 0
- 14. ANFIS Model
- 15. Advantages of Soft Computing Approach to CSE • Doesn’t need any difficult mathematical calculation. • It gives better performance than any other method. • It is a real time expert system. • Intelligent control systems can be made.
- 16. Other Application & Future Scope • Intelligent control of motor systems like DC servo motor, Induction motor etc. • Intelligent control in oil refineries. • Use of intelligent control systems in power plants. • Power systems applications. • Development of smart grids using intelligent control system.
- 17. Conclusion • Due to lack in comprehensibility, conventional controllers are often inferior to the intelligent controllers. Soft computing techniques provide an ability to make decisions and learning from the reliable data or expert’s experience. Moreover, soft computing techniques can cope up with a variety of environmental and stability related uncertainties. • There is a wide range scope of applications of high performance DC motor drives in area such as rolling mills, chemical process, electric trains, robotic manipulators and the home electric appliances. They require speed controllers to perform tasks. Hence, a fuzzy based DC motor speed control system method gives a smooth speed control with less overshoot and no oscillations. • When compared to conventional controllers, SC approach provides better control. •
- 18. References • J.S.R. Jang, C.T. Sun, E. Mizutani, “Neuro- Fuzzy and Soft Computing” • Zadeh, Lotfi A., "Fuzzy Logic, Neural Networks, and Soft Computing," Communication of the ACM, March 1994, Vol. 37 No. 3, pages 77-84. • X. S. Yang, Z. H. Cui, R. Xiao, A. Gandomi, M. Karamanoglu, Swarm Intelligence and Bio-Inspired Computation: Theory and Applications, Elsevier, (2013). • Wikipedia.com