Intelligent Wireless Monitoring System for Circuit Breaker Fault Detection

This paper proposes an intelligent wireless monitoring system integrating grey wolf optimization and support vector machine for real-time fault detection in low-voltage circuit breakers. A wireless measurement network collects vibration signals from circuit breakers for feature extraction. An optimized support vector machine model using an improved grey wolf optimization algorithm is developed for fault diagnosis. Experiments demonstrated a 93.2% diagnosis accuracy for the model on single faults. The integrated monitoring system achieved 0.74 AUC, 0.35 F1 score, and 2.8 seconds response time, outperforming other systems. The wireless intelligent monitoring framework enabled efficient fault detection and maintenance for circuit breakers. However, limitations include small dataset size and lack of validation on real breakers. Further research on model optimization and testing on field data will be valuable. In conclusion, this paper proposed and validated an intelligent wireless monitoring system integrating grey wolf optimization and support vector machine for real-time low-voltage circuit breaker fault detection.