AI-ENHANCED BATTERY MANAGEMENT SYSTEM FOR ELECTRIC VEHICLES: REAL-TIME MONITORING AND OPTIMIZATION USING MYRIO AND LABVIEW

Abstract

This paper presents the development of a Battery Management System (BMS) console using LabVIEW simulation software for monitoring and managing lithium-ion (Li-ion) battery pack parameters such as current, voltage, temperature, and State of Charge radha.m@cit.edu.in (SoC) for Electric Vehicle (EV) applications. Li-ion batteries demand precise operating conditions and the BMS ensures safety and efficiency by continuously monitoring battery states. The SoC estimation is enhanced using the latest AI algorithm, Long Short-Term Memory (LSTM) networks, which provide improved prediction accuracy and real-time adaptability to battery operations. These AI-driven techniques enable more reliable SoC-based control, optimizing charging and discharging processes. Sensors combined with the myRIO controller feed data to the LabVIEW environment, enabling automatic charging control, SoC-based cutoffs, and temperature-based alarms. Additionally, key battery metrics—such as specific energy, specific power, cell voltage, total pack voltage, and load current—are computed from sensor data. These metrics are processed and analyzed in real time to create a user-friendly interface for monitoring, while also enabling the detection of unhealthy cells, preventing potential issues such as thermal runaway and cell imbalance. The integration of LSTM algorithms provides a more robust and efficient approach to battery management, ensuring both safety and optimal performance for EV applications.