DEVELOPMENT OF INSTRUMENTATION SYSTEM FOR CONDITION MONITORING OF ELECTRIC DRIVES

Abstract

In modem power and production plants, continuous and trouble free operation of electric drives is an important, aspect. Faults and /or failures of electrical machinery not only cause economical losses but it may also create dangerous situations. So from economic and safety point of view there is a need for condition monitoring of large and expensive electrical drives, operating in the vital production processes. The various techniques are available for condition monitoring like Vibration Monitoring, Current Monitoring, and Temperature Monitoring etc. In the present work vibration monitoring technique employed for the detection and classification of bearing fault of induction motor. The vibration signal is analyzed in time, frequency and time-frequency domain and diagnostically important features are extracted. The extracted features are then used for the development of knowledge based model for diagnostic purpose. An on-line condition monitoring system for a 10 HP induction motor in laboratory is developed. In this system the parameters like Voltage, current and Vibration are acquired and displayed on a GUI using MATLAB. This system can acquire and process the signal simultaneously. Signal processing is useful for the feature extraction of the signal, that are further used for the formation of feature vector of the signal. Feature vector of the signal is given to our knowledge base model to detect the type of fault. So an on-line fault detection system is realized. For automatic detection of fault, a machine learning algorithm Support Vector Machine (SVM) is used SVM based classifier is built to minimize the structural misclassification risk, whereas conventional classification techniques often apply minimization of the empirical risk. It gives a better generalization capability and gives us global solution for a classification problem.