A state evaluation and fault diagnosis strategy for substation relay protection system integrating multiple intelligent algorithms

Ensuring the operational reliability of substation relay protection systems through rapid defect diagnosis and state assessment is crucial for maintaining power system stability. This study introduces a new diagnostic framework that combines improved particle swarm optimization, K-means clustering algorithms, support vector machine (SVM), and learning vector quantization neural networks to provide a comprehensive fault diagnosis and prediction model for relay protection systems. The model commences by identifying critical metrics for system state evaluation, employing an improved analytic hierarchy process to allocate weights to these indicators, and introducing variable weights theory to improve dependability of outcomes. The model enhances SVM with learning vector quantization for precise state prediction by utilizing operational data from substation relay protection systems. Improved particle swarm optimization optimizes key SVM parameters to improve accuracy. In order to effectively classify defect categories, the K-means clustering algorithm is implemented. The model's efficacy, stability, and comprehensive applicational potential have been confirmed through experimental trials, which represent substantial progress in the field of substation fault management.