Predicting battery state of health for electric urban mobility using Machine Learning and Simulation

I. Izco Berastegui, A. Al-Rahamneh, A. Serrano Hernandez, J. Faulin Fajardo

As cities prioritize sustainability, awareness of environmental issues has accelerated the adoption of electric vehicles (EVs). In this context, electric urban mobility plays a key role in the transition to greener transportation systems. A significant challenge in this transformation lies in extending the lifespan of EV batteries. A failure in the battery system not only disrupts the service but also lowers public trust in the technology. The core of this transition is the development of reliable Battery Management Systems (BMS) that optimize battery performance. This work investigates the role of intelligent BMS in enhancing battery state of health (SoH). By integrating Machine Learning algorithms specifically utilizing long short-term memory (LSTM) with agent-based simulation, the BMS can effectively predict potential issues to ensure uninterrupted service. Finally, the experiments were conducted using analysis from an extensive empirical battery dataset.

Palabras clave: State of Health, Electric Mobility, Machine Learning, Agent based simulation

Métodos y aplicaciones de la IO II
13 de junio de 2025  09:00
Sala de prensa (MR 13)

P. A. MAYA-DUQUE, G. Ramirez, B. Cardenas

J. Bautista Valhondo

M. Fernández de Dios, Á. M. González Rueda, J. R. Banga, J. González Díaz, D. R. Penas

A. Guerrero Portoles, M. Escoto Gomar, A. A. Juan, Á. García Sánchez, W. Chen