An AC Arc Fault Detection Method Based on FCM-LSTM-CNN

In order to solve the arc problem caused by the extensive use of power electronic devices, an AC arc fault detection method based on FCM-LSTM-CNN is proposed in this paper. The algorithm takes the arc fault generator as the data source and extracts the time domain eigenvalues, frequency domain eigenvalues and energy eigenvalues. In this paper, the feature vector is extracted from the collected arc fault data. Then fuzzy C-means clustering is used to determine the initial cluster center, and the arc fault data is analyzed digitally. Finally, the result is input to LSTM-CNN neural network, and the result of fault detection is obtained. The results show that compared with other typical arc fault detection models, the proposed fault detection model has higher accuracy and higher detection efficiency.