ESP32-Enabled Iot Framework for Diagnostic and Prognostic Health Management of Electric Vehicle Motors and Batteries

Resumen

The rapid proliferation of electric vehicles (EVs) has heightened the demand for robust diagnostic and predictive health monitoring of critical subsystems, particularly traction motors and battery packs. To address the need for enhanced reliability, safety, and operational longevity, this research presents the design and deployment of a cost-effective, IoT-enabled condition monitoring system utilizing the ESP32 microcontroller. The architecture integrates a multi-sensor suite comprising temperature, current, voltage, vibration, and smoke sensors to facilitate continuous surveillance of the motor and battery states. Through real-time data acquisition and embedded processing, the system enables precise estimation of State of Charge (SOC) and State of Health (SOH) while identifying critical anomalies such as overcurrent, overheating, excessive mechanical vibration, and incipient thermal hazards. Processed telemetry is transmitted to a cloud-based dashboard, supporting remote visualization, instantaneous alarm notifications, and strategic predictive maintenance planning. Experimental validation demonstrates that the proposed framework identifies faults with high accuracy and responsiveness. Ultimately, this study offers a scalable and economical solution for intelligent EV health management and early-stage fault detection, contributing significantly to the dependability of modern electric mobility.