In BLDC motor applications, stator failure is a common occurrence. Therefore, this study presents a method to diagnose stator failure in BLDC motor when it is operated at a different speed. Furthermore, this study examined the motor in normal condition and the motor with a stator fault. The vibration and current signals are measured from BLDC motor operating at 400 rpm, 450 rpm and 480 rpm. The signals are recorded at a sampling rate of 10 kHz, and the time and frequency domain features are extracted from the sample signals. The distance evaluation technique is used to select the features with the highest effectiveness factor, and a combination of features in the time and frequency domains is used as a predictor in the Least Square Support Vector (LSSVM) model. The results show that the LSSVM model performs very well in diagnosing BLDC stator failure at different speeds using both vibration and current signals. The classification accuracy is 96.5% and 98.83% for vibration and current data, respectively. With its high prediction accuracy, the proposed method has the potential to be developed as a maintenance tool in the industry.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.