An Innovative Electromechanical Joint Approach for Contact Pair Fault Diagnosis of Oil-Immersed On-Load Tap Changer

This paper presents a novel fault diagnosis method for oil-immersed on-load tap changers (OLTC) to address the issue of limited diagnostic accuracy. The proposed combines analysis mechanical vibration signals and high-frequency current from contact pair, aiming improve precision diagnosis. To begin with, an experimental platform was used simulate OLTC contact, enabling collection under different operational states. These underwent wavelet packet transform denoising, followed by correlation investigate their interrelationships across various Features were then extracted analyzed using ensemble empirical mode decomposition Hilbert–Huang transform. Subsequently, support vector machine (SVM) employed analyze both signal signal, facilitating classification state. results demonstrated that joint electrical provided comprehensive representation actual state conditions. SVM achieved error below 10% in predicting values two types, validating efficiency feasibility contacts. findings presented this offer valuable insights on-site practical OLTCs.