Switchgear, as a crucial electrical equipment for control and protection, presents a range of safety issues during its operation, significantly impacting the reliability of power supply. Existing switchgear detection methods mostly focus on the analysis of two-dimensional charts, making it challenging to provide comprehensive feedback on multi-physics field states in a three-dimensional space. Therefore, this paper employs a multi-physics coupled finite element model to investigate the temperature and electric field distribution during the operational status of switchgear. It establishes a switchgear proxy model based on Radial Basis Function (RBF) neural networks by combining simulation with engineering practices. Furthermore, it investigates switchgear discharge faults and fault diagnosis algorithms based on parallel Adaptive Neuro-Fuzzy Inference Systems (ANFIS) neural networks, and subsequently achieves the visualization of switchgear status information through Unity. This research enhances the accuracy and real-time monitoring of switchgear data, realizes the data visualization of switchgear status, and offers insights for proactive switchgear maintenance.

switchgear,thermoelectric coupling,model dimensionality reduction,fault diagnosis,visualization