Skip to Main Content
Motor current signature analysis (MCSA) is a method of sampling the running current through a data logger at high sampling speed, followed by using mathematical tools such as fast Fourier transform (FFT) to identify relevant motor signature changes in the frequency spectrum for motor fault identification. Although there are numerous types of motor fault, research conducted by Electric Power Research Institute (EPRI) indicated that motor bearing fault accounted for more than 40% of all types of motor fault. The main aim of this paper is to evaluate the use of MCSA for detecting bearing outer raceway defect. Stage-by-stage experimental verification shows that the method of MCSA is effective in detecting bearing fault with the use of wavelet packet transformation (WPT). In addition, a novel linear application of linear regression for wavelet data analysis is applied and presented in this paper.