Abstract

Lithium-ion batteries (LiBs) with Lithium titanate oxide Li4Ti5O12(LTO) negative electrodes are an alternative to graphite-based LiBs for high power applications. These cells offer a long lifetime, a wide operating temperature, and improved safety. To ensure the longevity and reliability of the LTO cells in different applications, battery health diagnosis, and lifetime prediction are crucial. This paper examines the cycling ageing behaviour of LTO cells in two different cell temperatures under high-current cycling conditions and various cycle depth (CD) tests. The ageing behaviour is investigated via capacity degradation trend using data-driven technique based on feed-forward neural network (FFNN). The model is later validated with the experimental result collected in-house and the lifetime data provided by the manufacturer. The proposed method accurately determines the state of health (SOH) level and predicts the end of life (EOL) with an acceptable error of 5 %.

Full Text
Published version (Free)

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