Fault Tolerant Control using Artificial Neural Network For Induction Motor
Loading...
Date
2019-01
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Université de M'sila
Abstract
In this article, a fault tolerance control based on a neural network for an induction machine is
proposed, and a fault-tolerant command via backstepping control and based on an extended
Kalman filter is designed. Using the residual signal generated from some calculation passing
through the filter, a fault compensation loop of the neural network is introduced. This neural
network is a four-layered perceptron, which attempts to minimize the error induced by the
defect. In this context, a fault-tolerant control scheme is obtained. Operation characteristics of
the proposed drive are compared to the fault tolerant control based on Kalman filter to verify
effectiveness under various conditions by examining robustness of control in the presence of
defects. Simulation results are tested in matlab / simulink environment to illustrate the proposed
technique performance.
Description
Keywords
Three phases induction machine; Fault tolerant control; neural network.