DESIGNING ARTIFICIAL NEURAL NETWORKS FOR FAULT DETECTION IN INDUCTION MOTORS-C30

Artificial Neural Networks (ANN) is succesfully used in many areas such as fault detection, control and signal processing in our daily technology. Artificial Neural Networks have nonlineer structure and this is an effective feature that it approaches to the results of learning phase. Then, it gives results in test phase in short time (the degree about 10 to the -3 second). It is a very preferable according to the other approaching methods.

In this paper, feedforward network and error backpropagation training algorithm is used to perform the motor fault detection. The values which were used for ANN were taken from a split-phase squirrel-cage induction motor in Türk Electric Motors A.S. as a prototip. So, it was done a new application with the values.

Motor fault detection with ANN, as the inputs I (stator current) and w (angular velocity depending on rotor speed), as the outputs Nc (insulation condition) and Bc (bearing wear condition) are made and discriminated with success rate above 95% for 30000 iterations. It is considerably important to success the fault detection with e=0,8% error for Nc.

This document was part of the first European DSP Education and Research Conference that took place September 26 and 27, 1996 in Paris. For information on how TI encourages students from around the world to find innovative ways to use DSPs, see TI's World Wide Web site at www.ti.com.

*DISCLAIMER: This document was part of the DSP Solution Challenge 1995 European Team Papers. It may have been written by someone whose native language is not English. TI assumes no liability for the quality of writing and/or the accuracy of the information contained herein.

Go to the Engineering Design Center to locate information on other TI Semiconductor devices.

(c) Copyright 1998 Texas Instruments Incorporated. All rights reserved.
Trademarks, Important Notice!