Neural Networks Detect Inter-Turn Short Circuit Faults Using Inverter Switching Statistics

• DOI: 10.36227/techrxiv.19145444.v1
• Publication Date: 2022-02-11T03:54:10Z
• Authors: Mustafa Umit Oner; İlker Şahin; Ozan Keysan
• Keywords: Downtime

Early detection of an inter-turn short circuit fault (ISCF) can reduce repair costs and downtime electrical machine. In induction machine (IM) driven by inverter with a model predictive control (MPC) algorithm, the controller outputs are influenced due to fault-controller interaction. Based on this observation, study developed neural network using switching statistics detect ISCF IM. The method was non-invasive, it did not require any additional sensors. task, achieved area under receiver operating characteristics curve value 0.9992 (95% Confidence Interval: 0.9991 - 0.9992). At rated conditions, detected located 2-turns (out 104 turns per phase) 0.1 seconds, speedup more than ten times compared thresholding-based method. Moreover, we published vector data collected at various load torque shaft speed values for healthy faulty states IM, becoming first publicly available dataset.