Research on Fast Circuit Fault Localization Technology Based on Convolutional Neural Network Algorithm

Abstract

In order to improve the accuracy and efficiency of circuit fault diagnosis, a fast fault location technique based on Convolutional Neural Network (CNN) is proposed. By constructing a multi branch CNN model and combining time-domain and frequency-domain feature extraction, the model's ability to identify different types of faults has been enhanced. The experimental results show that the proposed model exhibits excellent performance in the diagnosis of various typical faults, especially in the recognition of short circuit and open circuit faults with an accuracy rate of over 98%. In addition, the robustness and real-time performance of the model under complex operating conditions have been effectively verified, which can meet the needs of online monitoring and fault diagnosis in power systems. The results indicate that the CNN model can effectively improve the accuracy and efficiency of circuit fault location, providing a new technical means for circuit maintenance and fault diagnosis.