Abstract
The widespread use of lithium-ion batteries in electric vehicles and energy storage systems demands accurate methods for predicting and diagnosing their performance, enhancing their safety and reliability. A significant challenge to their broader application is thermal runaway, a key factor compromising the safe use of these batteries. Addressing this issue, our study introduces innovative strategies for the precise prediction and prevention of lithium-ion battery failures. We employ a data-driven prognosis (DDP) approach to analyze battery failures attributed to thermal runaway. This technique effectively identifies anomalies in battery operation and detects faults in battery performance dynamics. Furthermore, we developed an electrochemical-thermal model that accurately represents the internal chemical reactions and thermal behaviors at the cellular level. This model is incorporated with the DDP algorithm to generate critical data-driven model inputs, enabling precise failure predictions. Our findings demonstrate the data-driven algorithm's effectiveness in identifying battery failures caused by thermal runaway, thereby enhancing the safety and operational reliability of electric vehicles and energy storage systems through timely alerts.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call