Xining Li

The mechanical reliability of high-voltage circuit breakers (HVCBs) is crucial for power-grid stability, yet traditional diagnostic methods rely heavily on manually extracted scalar features that can discard transient information. This paper presents a mechanism-aware diagnostic pipeline that combines synchronized coil-current, contact-travel, and spring-pressure measurements; Variational Mode Decomposition (VMD); kinematics-driven Region of Interest (ROI) alignment; Gramian Angular Field (GAF) encoding; RGB channel stacking; and ResNet-18 classification. On a controlled 220 kV experimental platform covering five operating conditions and 1500 operating-cycle samples, the framework achieved an average accuracy of 96.18% (macro-precision 96.10%, recall 96.01%, and F1-score 96.05%) under five repeated stratified 2:1 holdout evaluations. Single-channel controls obtained 88.47% for current, 90.24% for travel, and 85.13% for pressure; removal of VMD and ROI reduced accuracy to 94.72% and 93.46%, respectively. The results should be interpreted as proof-of-concept evidence on controlled simulated faults; validation on temporally separated field data, other breaker types and voltage levels, and naturally imbalanced fault distributions remains necessary before broad condition-based-maintenance deployment.

To address the practical engineering challenges of limited fault samples for high-voltage circuit breaker spring operating mechanisms and the inability of single features to fully reflect equipment status, this paper proposes a small-sample fault diagnosis method based on multi-source feature fusion and Stacking ensemble learning. First, a multi-source sensing system containing MEMS (Micro-Electro-Mechanical System) pressure and travel, coil, and motor current was constructed to achieve comprehensive monitoring of the mechanical and electrical states of a 220 kV circuit breaker; in particular, the introduction of non-invasive MEMS sensors effectively solves the difficulty of capturing static spring fatigue characteristics inherent in traditional methods. Second, a high-dimensional feature space was constructed using Savitzky–Golay filtering and physical feature extraction techniques. To address the characteristics of small-sample data distribution, a two-layer Stacking ensemble learning model based on 5-fold cross-validation was designed. This model utilizes the SVM (Support Vector Machine), RF (Random Forest), and KNN (K-Nearest Neighbors) as base classifiers and Logistic Regression as the meta-learner, achieving an adaptive fusion of the advantages of heterogeneous algorithms. True-type experimental results show that the average diagnostic accuracy of this method under normal conditions and four typical fault conditions reaches 96.1%, which is superior to single base models (the RF was 94.2%). Feature importance analysis further confirms that closing and opening pressures are the most critical features for distinguishing mechanical faults. This study provides effective theoretical basis and technical support for condition-based maintenance of high-voltage circuit breakers under small-sample conditions.