Intelligent Diagnosis of GIS Disconnector Faults Based on Multi-Information Fusion

This paper presents an intelligent fault diagnosis method for Gas-Insulated Switchgear (GIS) disconnectors, utilizing multi-source information fusion of torque, current, and acceleration signals. Principal Component Analysis (PCA) is employed to extract low-dimensional fault features, which are subsequently classified using an Artificial Neural Network (ANN). Simulation experiments demonstrate the accuracy and robustness of the proposed method, achieving 100% fault diagnosis accuracy across multiple load conditions. The results confirm the effectiveness of this approach in detecting and diagnosing mechanical faults in GIS disconnectors, with promising potential for real-time monitoring and maintenance in power systems.