Fault Diagnosis for Transformer Winding using Morpho-offset Feature of Oscillating Wave and CPO-XGBoost Algorithm

Accurate and effective diagnosis of transformer winding conditions is crucial for ensuring their safe and reliable operation. This paper proposes a transformer winding fault detection method based on oscillation wave analysis (OWA). Firstly, a transformer winding fault simulation platform was established to obtain OWA curves. Secondly, we propose an oscillation wave alignment method based on shape context, which can systematically extract Morpho-offset features to more comprehensively quantify the offsets of curves. The analysis results indicate that the Morpho-offset feature has a good clustering ability for fault states. Then, to enhance the XGBoost algorithm’s ability to identify winding faults, a transformer winding fault diagnosis algorithm based on XGBoost classifier optimized by the crown porcupine algorithm is proposed. Finally, the Morpho-offset features and diagnostic algorithm are integrated to identify the type, location, and degree of winding faults. Results demonstrate that the proposed method achieves an accuracy of 99.45% in identifying winding faults, with a 11.89% improvement over the unoptimized XGBoost.