The popularity of high-efficiency permanent magnet synchronous motors in drive systems has continued to grow in recent years. Therefore, also the detection of their faults is becoming a very important issue. The most common fault of this type of motor is the stator winding fault. Due to the destructive character of this failure, it is necessary to use fault diagnostic methods that facilitate damage detection in its early stages. This paper presents the effectiveness of spectral and bispectrum analysis application for the detection of stator winding faults in permanent magnet synchronous motors. The analyzed diagnostic signals are stator phase current, stator phase current envelope, and stator phase current space vector module. The proposed solution is experimentally verified during various motor operating conditions. The object of the experimental verification was a 2.5 kW permanent magnet synchronous motor, the construction of which was specially prepared to facilitate inter-turn short circuits modelling. The application of bispectrum analysis discussed so far in the literature has been limited to vibration signals and detecting mechanical damages. There are no papers in the field of motor diagnostic dealing with the bispectrum analysis for stator winding fault detection, especially based on stator phase current signal.

Inter-turn short circuit (ITSC) is a frequent fault of interior permanent magnet synchronous motors (IPMSM). If ITSC faults are not promptly monitored, it may result in secondary faults or even cause extensive damage to the entire motor. To enhance the reliability of IPMSMs, this paper introduces a fault diagnosis method specifically designed for identifying ITSC faults in IPMSMs. The sparse coefficients of phase current and torque are solved by clustering shrinkage stage orthogonal matching tracking (CcStOMP) in the greedy tracking algorithm.The CcStOMP algorithm can extract multiple target atoms at one time, which greatly improves the iterative efficiency. The multiple features are utilized as input parameters for constructing the random forest classifier. The constructed random forest model is used to diagnose ITSC faults with the results showing that the random forest model has a diagnostic accuracy of 98.61% using all features, and the diagnostic accuracy of selecting three of the most important features is still as high as 97.91%. The random forest classification model has excellent robustness that maintains high classification accuracy despite the reduction of feature vectors, which is a great advantage compared to other classification algorithms. The combination of greedy tracing and the random forest is not only a fast diagnostic model but also a model with good generalisation and anti-interference capability. This non-invasive method is applicable to monitoring and detecting failures in industrial PMSMs.