The management of electrical infrastructure maintenance has evolved significantly with the integration of artificial intelligence and machine learning technologies. This paper presents a comprehensive hybrid framework combining rule-based defect prioritization with machine learning-based failure prediction for electrical substation maintenance optimization. Using historical defect data spanning 2023–2024 from Malaysia’s Pantai Timur region encompassing Kelantan, Terengganu, and Pahang states, we developed a two-phase system: (1) a transparent multi-criteria rule-based engine for immediate defect triage, and (2) ensemble machine learning models for monthly failure forecasting. The rule-based component processes switchgear defects using business logic derived from equipment type, defect location, and severity indicators. For predictive capabilities, we compared XGBoost and Random Forest classifiers on severely imbalanced data (88.40% zero-defect months), achieving ROC-AUC scores of 0.7562 and 0.7631 respectively. The Synthetic Minority Over-Sampling Technique (SMOTE) was integrated within cross-validation pipelines to address class imbalance while preventing data leakage. Feature importance analysis revealed temporal recency (months since last defect) as the dominant predictor, validating reliability engineering principles. The XGBoost model was selected for deployment due to superior cross-validation consistency and interpretability. This hybrid approach transforms reactive maintenance strategies into proactive intelligence systems, providing both immediate prioritization and strategic forecasting for optimal resource allocation in electrical infrastructure management.