Fault Detection Based on Variable Weight Dynamic Time Warping for Asynchronous Motor Interturn Short Circuit

In this paper, a fault detection method based on variable weight dynamic time warping (VWDTW) is proposed for asynchronous motor interturn short circuit. The distance between two time series is calculated by dynamically assigning different weights to each position of the aligned time warping sequences. The higher the warping degree is, the higher the weight is. A reference threshold is obtained by calculating the distance between the two normal time series. Then the distance between the tested time series and the normal time series is calculated and compared with the reference threshold to determine whether the asynchronous motor is faulty. Simulation results show that the proposed method is effective in detecting interturn short circuit of asynchronous motor.