Hybrid IPSO-Optimized Machine Learning for Aging Classification of Polymeric Insulators under Dry and Wet Conditions

The surface aging of polymeric insulators, extensively employed in power systems, presents significant challenges. This aging can lead to reduced insulation performance, increased leakage currents, and a higher risk of equipment failure. This paper proposes an efficient framework that integrates a hybrid machine learning (ML) model, Extreme Gradient Boosting and Multilayer Perceptron (XGBoost-MLP), with improved PSO (IPSO) for classifying polymeric insulators' aging status under dry and wet conditions. The proposed model is evaluated using a four-fold Leave-One-Insulator-Per-Class-Out (LOIPCO) protocol to provide a robust assessment across unseen insulators. Uniform Manifold Approximation and Projection (UMAP) is applied as a data-driven dimensionality reduction technique in model improvement. The leakage current of the selected samples has been tested, and the 14 features of the time and frequency domains of the LC signal are extracted to classify insulator aging. Based on the permutation importance technique, ten features were selected in this study. Examining the suggested criteria reveals that they are strongly correlated with insulator aging. Even though XGBoost-MLP outperformed traditional models, hyperparameter optimization with an improved PSO further reduced misclassification. IPSO-XGBoost-MLP achieved the best classification accuracy. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used to analyze and interpret the results, providing insights into the factors influencing model predictions. SHAP analysis showed that PSD_mean, energy, and peak have the greatest effect on the aging classification model. In the dry insulator dataset, Peak dominates, while in the wet model, energy dominates. In both cases, Std and Ent always rank last. The outcome of this work aids in evaluating surface aging and has potential applications in the condition assessment of polymeric insulation.