INDUCTION MOTOR ROTOR FAULT DETECTION USING ENHANCED FEED FORWARD NEURAL NETWORK
Abstract

Author(s): Sandhya Gotam, Prof. AlkaThakur

Induction motor rotor fault detection is one of hot topic in between researchers in the last decade. Reason beside this maintenance of induction motor is the major concerns in modern industry where f ailure detection on motors increases the useful life cycle on the machinery. Broken rotor bars are among the most common failures in induction motors. Early detection of faults in electrical machines are imperative because of their diversity of use in different fields. A suitable fault monitoring scheme helps to stop propagation of the failure or limit its escalation to severe degrees and thus prevents unscheduled downtimes that cause loss of production and financial income. Detection of broken rotor bar of induction motor with the help of ANN was the focus of the proposed work. The mathematical models of induction motor in both healthy as well as fault condition were developed in order to simulate the faults of varying intensity at different load conditions. Various parameters of induction motor are recorded in all the different conditions. These recorded parameters are used to train the Artificial Neural Network. The output of the ANN shows that proposed technique successfully detects the presence of broken rotor fault of induction motor. Shows better values 10-1 error at 10 epochs. Also discuss Response Time of proposed ANN detection is good as compare to other previous method. Mathematical model help of understand the basic model. The proposed shows good result as compare different methods of fault detection like SVM, fuzzy logic, DWT, FFT based. Keywords:- Induction Motor, Induction Motor Fault ,Rotor Fault Analysis and Identification, Broken Rotor Bar, Artificial Neural Network and Diagnosing Techniques.