Condition-Based Health Monitoring of Electrical Machines Using DWT and LDA Classifier

In the industry, continuous health monitoring of electric motors is considered as an essential requirement. The operation motor may cause malfunctions and addressing them timely a critical challenge. development efficient system based on identification electrical faults great demand. This paper addresses fault detection technique using discrete wavelet transform (DWT) algorithm for motor-based systems. have been detected through Motor Current Signature Analysis (MCSA) series procedures proposed method. Concurrently, produces frequency-based spectrum related to stator current parameters accomplish classification. study provides analysis three Phase imbalance, Rotor misalignment, High contact resistance (HCR). DWT has ability categorize input signals into approximate coefficient state low frequency detailed high signals. this research, used detect because it able processing very frequency, effectively deal with intermittent sharp that appear frequently during processing. conditional induction precise coefficients more skilled at light loads given motor-shaft relatively fast execution time compared FFT. Furthermore, comparison healthy faulty compiled by Linear Discriminant (LDA) technique, sub-application MATLAB, management purposes. LDA in PCA gives perfect results. different 100% accuracy classifier. implementation scheme will be beneficial avoiding ensuring preemptive measures are taken against these faults, production industries protected from revenue losses.