Series of works towards enhancement in battery thermal management systems

With the rapid increase in applications of lithium-ion battery systems especially for electrical vehicles (EVs), battery fire prevention and suppression have become vital topics to be addressed within the fire safety community. Recently, our team including Ao Li, Hengrui Liu and Anthony Chun Yin Yuen has explored innovative approaches to improve the design and reliance of battery thermal management (BTM) systems. The following are the series of publications

A novel thermal management system for battery packs in hybrid electrical vehicles utilising waste heat recovery (International Journal of Heat and Mass Transfer Vol. 195, 123199, 2022)

Integration of Computational Fluid Dynamics and Artificial Neural Network for Optimization Design of Battery Thermal Management System (Applied Thermal Engineering Vol. 215 , 118966, 2022)

Numerical investigation on the thermal management of lithium-ion battery system and cooling effect optimization (Batteries Vol. 8 (7), 69, 2022)

A novel thermal management system for hybrid electrical vehicles battery with waste heat recovery

Thermal management systems ensure the safe operating conditions and heat resilience of battery packs in hybrid electric vehicles (HEVs). More critically, it acts as the ultimate line of defence and mitigates the fire and explosion risks in case of battery thermal runaway. The current study raised a novel approach to reducing fire risks related to HEVs through a novel battery thermal management system powered by low-grade heat sources such as combustion waste heat running on steam ejectors for the first time.

Machine Learning Assisted Battery Thermal Management System for Precise Fire Detection & Prediction

Machine learning is the study of computer algorithms that improve automatically through experience and data. The implementation of machine learning techniques can be a potential method to optimise the battery system. The present modelling framework presents an innovative approach to utilising high-fidelity electro-thermal/CFD numerical inputs for ANN optimisation, potentially enhancing the state-of-art thermal management, reducing the risks of thermal runaway and battery fire outbreak.