IOT-ENABLED BATTERY HEALTH AND THERMAL SAFETY MONITORING FOR ELECTRIC VEHICLES

Abstract

The rapid expansion of electric mobility has increased the importance of reliable battery health assessment, thermal safety monitoring, predictive fault detection, and intelligent lifecycle management for electric vehicle energy storage systems. Lithium-ion battery packs operate under continuously changing charging rates, discharge loads, ambient temperatures, driving conditions, state-of-charge levels, aging characteristics, and cell-to-cell variations. Conventional battery monitoring systems primarily depend on embedded threshold rules and local battery management functions, which may provide limited capability for identifying gradual degradation, distributed thermal abnormalities, abnormal cell imbalance, communication failures, and emerging thermal safety risks before critical conditions occur. This paper proposes an IoT-Enabled Battery Health and Thermal Safety Monitoring framework for Electric Vehicles that integrates distributed sensing, battery management system data acquisition, edge preprocessing, secure IoT communication, cloudconnected analytics, machine-learning-based health assessment, thermal anomaly detection, battery state monitoring, predictive degradation analysis, digital battery profiles, secure API lifecycle management, automated model operations, and closed-loop safety decision support. The proposed methodology continuously acquires cell voltage, pack voltage, current, temperature, charging behavior, discharge behavior, thermal gradients, coolingsystem status, ambient conditions, operating load, and historical maintenance information. Edge components perform validation, noise reduction, event detection, and immediate safety screening, while cloud services provide historical analysis, fleet-level comparison, predictive modeling, and long-term degradation intelligence. The framework maintains dynamic battery health profiles that combine current observations with historical charging cycles, thermal exposure, operating conditions, and predicted risk. Machine-learning analytics identify abnormal behavior, classify health states, detect emerging thermal instability, and prioritize maintenance or safety intervention. Communication integrity controls protect distributed telemetry, structured APIs support interoperability, and model lifecycle management maintains predictive reliability under changing battery conditions. A comparative analytical evaluation demonstrates that the proposed framework can improve battery fault-detection accuracy, reduce thermal anomaly detection latency, decrease false alarms, improve early degradation identification, reduce unsafe thermal exposure, and increase battery availability compared with conventional threshold-based monitoring and standalone analytical systems. The findings indicate that IoT-enabled battery monitoring provides a scalable foundation for intelligent electric vehicle battery health management and proactive thermal safety.