Multi-sensor data fusion using support vector machine for motor fault detection

Motor fault diagnosis in dynamic condition is a typical multi-sensor data fusion problem. It involves the use of information collected from multiple sensors, such as vibration, sound, current, voltage, and temperature, to detect and identify motor faults. From the viewpoint of evidence theory, information obtained from each sensor can be considered as a piece of evidence, and as such, the multi-sensor based motor fault diagnosis can be viewed as the problem of evidence fusion. In this article we propose and investigate a hybrid method for fault signal classification based on sensor data fusion by using the Support Vector Machine (SVM) and Short Term Fourier Transform (STFT) techniques. We report a practical application of this hybrid model and evaluate its performance. Finally, we compare the performance of the proposed system against some other standard fault classification techniques.