FUZZY CONTROL SYSTEM

A fuzzy control system is a control system that uses fuzzy logic, a mathematical approach to deal with uncertainty and imprecision.

There are several types of fuzzy control systems with their own unique characteristics and applications and they are as follows; Mamdani, Takagi-sugeno (T-S), type-1, type-2, hybrid, adaptive and self-tuned fuzzy systems.

Mamdani fuzzy systems use fuzzy rules and fuzzy sets to reason about uncertain systems. Mamdani fuzzy systems are simple and easy to implement.

Takagi-sugeno (T-S) fuzzy system uses fuzzy rules and linear models to reason about uncertain system. Takagi-sugeno systems are more complex than Mamdani fuzzy system but offers better performance in some applications.

Type -1 fuzzy systems uses type-1 fuzzy sets which have a fixed membership function. It is widely used in control systems and it is effective in many applications.

Type-2 fuzzy systems uses type-2 fuzzy set which have a fuzzy membership function. It is more complex that type-1 but offers better performance in handling uncertainty and imprecision.

Hybrid fuzzy system combines fuzzy logic with other control techniques such as PID or neural networks. It offers improved performance and robustness in some applications.

Adaptive fuzzy systems can adapt to changing conditions and learn from experience. It is useful in applications where the system dynamics are unknown or time varying.

Self-tuned fuzzy systems can automatically adjust its parameters to optimize performance. It is useful in applications where the system dynamics are complex or uncertain.

The basic component of a fuzzy control system is as follows; fuzzifier, knowledge base, fuzzy rule base, inference engine and defuzzifier.

The fuzzifier is a component that converts crisp input values into fuzzy sets, allowing the system to process uncertain or imprecise data. The fuzzifier maps the input values to a membership function which defines the degree of membership of the input value in a particular fuzzy set.

The knowledge base is the component that stores the knowledge about the system, including the fuzzy rules, membership functions and other relevant information. The knowledge base is used by the inference engine to make decisions.

The fuzzy rule base is the component that stores the fuzzy rules that define the relationship between the input and output variables. Fuzzy rules are typically in the form of if-then statements such as ” IF temperature is high THEN fan speed IS fast”.

The inference engine is the component that is the decision making part of the fuzzy control system. It uses the fuzzy rules and the fuzzified inputs to determine the fuzzy output. The inference engine simulates human decision making by performing approximate reasoning.

The defuzzifier is the component that converts the fuzzy output from the inference engine into a crisp output that can be used to control a physical system. The defuzzifier uses methods such as centroid or max membership to determine the output values.

The advantages of fuzzy control system are as follows; fuzzy control system can handle uncertain and imprecise data. Fuzzy control systems can adapt to changing conditions. Fuzzy control systems can be more robust than traditional control systems.

The disadvantages of fuzzy control systems are as follows; fuzzy control systems can be complex to design and implement. Fuzzy control systems require careful tuning of parameters. Fuzzy control systems can be difficult to interpret and understand.

Fuzzy control systems find widespread application in the following; industrial control applications where they are used for process control and robotics. Fuzzy control systems are used in automotive applications such as autonomous vehicles and engine control. Fuzzy control systems are used in aerospace applications such as aircraft control and navigation.

The future of fuzzy control system is based on the advances and development of the following technologies; fuzzy control systems are being integrated with other artificial intelligence techniques such as machine learning and neural networks. Research is ongoing to develop new fuzzy logic techniques and algorithms. Fuzzy control systems are being adopted by a wide range of industries and applications.

 

SOURCES:

• Fuzzy logic with engineering applications by Timothy J. Ross.
• Fuzzy systems: Modeling and control by Hung T. Nguyen and Nadipuram R. Prasad.
• Fuzzy control of industrial systems: Theory and applications edited by Terry D. Burton and Hung T. Nguyen.
• Fuzzy logic and intelligent systems by Hua Li and M. Madan Gupta.
• Fuzzy modeling and control: Theory and application by Feenand Matia, Goro Klancar and Matjaz Skrjane.