Development of Automation Maintenance Management System to Enhance Operational Efficiency for Unmanned Substations: A Case of 132kv Maweni Substation in Tanga

This study developed an automation maintenance management system to enhance operational efficiency for unmanned substations using the 132kV Maweni Substation in Tanga, Tanzania as a case study. Traditional reactive maintenance practices resulted in 65% operational efficiency and 15 unscheduled interruptions annually. A mixed-methods design combined quantitative surveys from 92 transmission professionals with qualitative expert interviews. The Relative Importance Index methodology identified seven critical technical factors with high significance (RII > 0.8): Security Protocols, Condition Monitoring, Operational Automation, Communication Redundancy, System Integration, Fault Localisation, and Remote Accessibility. Multiple regression analysis yielded a predictive model with exceptional performance (R² = 0.960), explaining 96% of maintenance efficiency variance. Twelve-month validation demonstrated improved availability from baseline 65% to 91%, with six consecutive months achieving 100% availability. The integrated system combines machine learning algorithms with real-time monitoring for intelligent work order management and predictive maintenance scheduling. Results confirm that data-driven automation significantly enhances operational reliability, reduces maintenance costs, and optimises resource allocation in unmanned electrical infrastructure.