JFET_V1_N4_RP5 V. Manikandan K. Ramakrishnan Dr. N. Devarajan D. Sreekanth Journal on Future Engineering and Technology 2230 – 7184 1 4 77 83 Diagnosis, State feedback, ANN, Neural Network, Fault Classifier for Sensor Fault The scope of this paper is to present a neural network approach towards sensor fault (deterioration) diagnosis in Linear Time Invariant(LTI) systems. The novelty of the approach lies in associating with each state feedback gain factor a scalar a, which is defined as the sensor healthiness factor. This scalar is made to vary from 1(no fault condition) to 0(full fault condition) in predetermined steps. The intermediate values of a portray the deterioration modes of the sensor. The Integral Absolute Error (IAE) criterion is employed for extracting the signature of the fault and the classification is done using Artificial Neural Network (ANN) classifier. The proposed diagnosis approach is applied to a dc motor system to validate the effectiveness of the technique. May - July 2006 Copyright © 2006 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=991