Electrical Fault Diagnosis Method for Tunneling Equipment Based on Fault Simulation and Optimized Particle Swarm Algorithm

To address the challenges of scarce training data and poor adaptability to dynamic working conditions in electrical fault diagnosis for tunneling equipment, this study proposes an intelligent diagnosis model based on fault simulation and Improved Particle Swarm Optimization (IPSO). By constructing multi-physics coupling dynamic equations to accurately simulate fault effects and designing an IPSO algorithm integrating Lévy flight random walk with dynamic neighborhood topology optimization, the model significantly outperforms benchmarks in dynamic load tracking error (0.13%) and vibration suppression (28.7 dB), achieving 34.7% higher parameter identification accuracy (MSE = 0.19). With 34.5% reduction in hardware resource consumption (0.9 W power, 57 MB memory), 1% false alarm/missed detection rate, and 27.9 ms response latency, the solution enables practical edge deployment. The physics-data fusion framework ensures robust generalization under load mutations and high-frequency interference, realizing high-precision low-latency diagnosis with minimal resource requirements for tunnel engineering equipment.