Data-Based Soft Fault Diagnosis of a Three-Phase DC/AC Converter

With the widespread use of power electronic equipment, accurately identifying soft faults in power electronic converters is crucial for the stable and reliable operation of power electronic equipment. This paper proposed a soft fault diagnosis method for three-phase DC/AC converter using a data-based approach. Firstly, simulation analysis is conducted on the soft faults of three-phase DCI AC converter, and appropriate test signals are selected as data sources. Then, the LSTM neural network and its variants are used to obtain fault diagnosis models. Finally, the method is validated through experiments, and the results show that it has good performance in soft fault diagnosis of the three-phase DCI AC converter.