Multi Sensor Data Fusion based Condition Monitoring of Induction Motor

Abstract

With the increasing demand of technology in each and every phase of life, it should be such that the maximum people can avail it. With the advent of technology in the different areas such as defence, manufacturing process, oil refineries and power plants, the common necessity among all is the use of machinery for a long time with higher accuracy and greater sensitivity, so that maximum production can be obtained. In order to run the machinery for a long course of time and to make sure that the greater accuracy is achieved, it should be continuously monitored through some effective and reliable system. The maintenance of this machinery accounts for a large proportion of plant operating costs. Compared with the conventional scheduled maintenance strategy which is to stop the machine at pre-determined intervals, modern condition-based maintenance strategy stops the machine only before there is evidence of impending failure. With the development of cheaper sensors, it is now possible to use multi-modal sensor input to monitor machine condition in a collaborative and distributed manner. The main objective of this thesis is to focus on the development of an intelligent multi-sensored engine with the condition monitoring tools. Significant efforts aim to develop a robust methodology for sensing and analysis under harsh environments, stressing its application to the fields of monitoring, fault diagnostics analysis and robotic industrial applications. The proposed process model will be used to facilitate the implementation of a common strategy to tackle the problem associated with the condition monitoring of the Induction motor using multi sensor data fusion technology. This thesis looks in to different techniques of fault detection in induction motor and intelligent techniques to be implemented with a clear objective to diagnose the fault and its accuracy. The proposed method in this work allows continuous tracking of various types of fault in induction motor based on the offline/online data. These methods recognize the fault and diagnose them as well. In the first phase various faults are studied under different sections. After this, a suitable algorithm on WT is developed in MATLAB environment and applied on signal to detect the bearing fault. In the next phase the stator current condition is analysed for fault related to a stator current using the FIS Strategy. Finally, a hybrid fusion algorithm based on FIS is implemented for the detection of overall status of motor using the two known parameter i.e. (bearing fault & stator current).