Long Short-Term Memory Network based HVDC systems Fault Diagnosis under Knowledge Graph

To effectively extract various types of fault characteristics of HVDC systems and significantly improve the accuracy of fault diagnosis of HVDC systems, this paper proposes a fault diagnosis method for HVDC systems based on long short-term memory network (LSTM) relying on the knowledge graph platform. The LSTM model is developed using the measured data of four types of faults in an HVDC substation in southwest China. Primarily, the knowledge graph for the HVDC system is constructed. Then the fault waveforms data for the four types of faults are preprocessed and divided into the training set and test set. Furthermore, different optimizers are used to train and test the LSTM. Finally, the accuracy of fault diagnosis for the proposed strategy is calculated and compared with the commonly used fault diagnosis methods, i.e., recurrent neural network (RNN), support vector machine (SVM), and Naive Bayes classifier. The results show that the proposed method can achieve an accuracy of more than 87% for fault diagnosis of HVDC systems, which fully proves the superiority and effectiveness of the proposed method.