A Binary Hybrid Particle Whale Optimization Framework for Feature Selection in Industrial Transformer Partial Discharge Classification

Partial discharge (PD) testing based on IEC 60270 is widely employed for assessing the insulation integrity of power transformers. Although numerous statistical descriptors can be extracted from PD measurements, redundant and irrelevant features can degrade classification performance, particularly in small datasets. This study proposes a binary hybrid particle whale optimization algorithm (BHPWOA) for multi-objective wrapper-based feature selection in transformer insulation severity classification. The analysis comprises 64 IEC 60270 partial-discharge test sessions collected from 30 power transformers. Seventeen candidate statistical, temporal, spectral, derived, and test-configuration features were evaluated; the transformer identifier (TransClass) was excluded before wrapper optimization because it would not be available for an unseen transformer. Candidate subsets were assessed with a k-nearest neighbors (KNN) classifier using five-fold StratifiedGroupKFold cross-validation grouped by TransformerID, with min–max scaling fitted exclusively within each training fold. BWOA and BSFSA achieved the best multi-objective fitness (−0.9227) with the two-feature subset {CV_PD, Exc100}, corresponding to an 88.2% reduction, 93.75% accuracy, and macro-F1 of 0.9313. BHPWOA selected five features {MeanPD, CV_PD, Exc100, Q95_PD, MeanPD_Early}, corresponding to a 70.6% reduction, 92.19% accuracy, and macro-F1 of 0.9163. Across five BHPWOA stability runs, the mean feature count was 4.6 +/− 1.02, mean accuracy was 0.909 +/− 0.021, and mean macro-F1 was 0.903 +/− 0.022; CV_PD and Exc100 were selected in all five runs. Because the same grouped partition is used for wrapper selection and reported out-of-fold performance, these values are internal, non-nested grouped-CV estimates rather than independent outer-CV estimates.