ARCHIVES

This paper presents the design and implementation of a real-time battery performance monitoring and control system using an ESP32-based embedded platform and data-driven decision logic. The proposed system continuously acquires battery voltage, current, and temperature using INA219 and LM35 sensors and processes these parameters to evaluate battery condition, operational safety, and performance status. Unlike conventional battery-monitoring methods that only display raw sensor readings, the developed system interprets sensed data through structured threshold-based decision rules derived from dataset analysis, enabling automatic classification of battery states such as normal operation, overcharge, deep discharge, overheat, thermal critical condition, high load stress, and short-circuit risk. In addition to state classification, the system estimates key battery indicators, including State of Charge (SoC) and State of Health (SoH), to provide a more informative assessment of battery condition. The processed results are displayed locally through a 16×2 LCD and remotely through a web-based dashboard, ensuring real-time visualization and user accessibility. A control mechanism is also incorporated to activate a cooling device when temperature exceeds safe operating limits, thereby improving battery protection and reducing the need for manual intervention. The overall design follows a modular architecture consisting of sensing, processing, decision, output, and control stages, making the system compact, low-cost, and scalable. By integrating sensor-based monitoring with embedded intelligence, the proposed approach enhances battery safety, operational efficiency, and reliability in practical applications such as electric vehicles, renewable-energy storage systems, portable electronics, and industrial battery management.