Fuzzy based control of Induction motor for Diagnosis

There are many existing techniques and commercial tools available to monitor induction motors to ensure high degree of reliability. In our project information on the health state of the motor is obtained by processing motor operating parameter such as voltage, stator line current, temperature etc.

In recent trends, artificial intelligence techniques (neural networks, fuzzy logic, and genetic algorithm) are increasingly used in monitoring and detecting faults in electric machines. Such techniques require a minimum of intelligent configuration without any modeling.

This project describes the application of fuzzy logic approach to the diagnosis of induction motor. A fuzzy logic–based system allows the transformation of heuristic terms into numerical values via fuzzy rules and membership functions. When conducting fault diagnosis, several situations may occur in which an object is not obviously “good” or “bad”, but may fall in between.

Considering that the interpretation of the condition of the induction motor as a fuzzy concept, fuzzy logic – based diagnosis approach can be developed which enables decision making to be made based on vague information. Fuzzy system relies on a set of rules.

This system might refer intermediate condition such as “little overload”, “some what secure condition”. Furthermore, the fault type determined by applying the fuzzy rules is a good indicator to evaluate the influence of motor load level on the occurred fault.

The concept of fuzzy logic (FL) was conceived by Lotfi Zadeh, a professor at the University Of California at Berkley , and presented a way of processing data by allowing partial set membership rather than crisp set membership or non - membership. This process is continued until the neural network can simulate the entire set of input-output values.Once the neural network is ready, it can be used to determine the membership values of any input data in the different fuzzy membership funtions or classes hence the crisp input is fuzzified.

This approach to set theory was not applied to control systems until the 70’s due to insufficient small-computer capability prior to that time. Professor Zadeh reasoned that people do not require precise, numerical information input, and yet they are capable of highly adaptive control.
If feedback controllers could be programmed to accept noisy imprecise input, they would be much more effective and perhaps easier to implement.