A Data Driven RUL Estimation Framework of Electric Motor Using Deep Electrical Feature Learning from Current Harmonics and Apparent Power

An effective remaining useful life (RUL) estimation method is of great concern in industrial machinery to ensure system reliability and reduce the risk unexpected failures. Anticipation an electric motor’s future state can improve yield a warrant reuse asset. In this paper, we present RUL framework brushless DC (BLDC) motor using third harmonic analysis output apparent power monitoring. work, mechanical BLDC monitored through coupled generator. To emphasize total generation, have analyzed trend power, which preserves characteristics real reactive AC system. A normalized modal current (NMC) used extract features from motor. Fault generator are fused Kalman filter estimate RUL. Degradation patterns for been three different scenarios predictions, attention layer optimized bidirectional long short-term memory (ABLSTM) neural network model trained. ABLSTM model’s performance evaluated based on several metrics compared with other state-of-the-art deep learning models.