[5] Tang, X., Lai, X. Zou, C., Zhou, Y., Zhu, J., Zheng, Y., & Gao, F. (2023). Detecting abnormality of battery lifetime from first-cycle data using few-shot learning. Advanced Science, 10(29), 2305315. DOI: 10.1002/advs.202305315 [PDF]

Note: We generated and used the largest known dataset of its kind from 215 commercial lithium-ion batteries of the same type controlled individually at the same operating conditions until >25% capacity fade.  All the data and associated code are shared at [Data&Code].

This work proposes a lifetime abnormality detection method for batteries based on few-shot learning and using only the first-cycle aging data. Verified with the above dataset, our method can identify all abnormal batteries, with a false alarm rate of only 3.8%. It is also found that capacity and resistance-based approaches can easily fail to screen out a large proportion of the abnormal batteries, which should be given enough attention. This work highlights the opportunities to diagnose lifetime abnormalities via “big data” analysis, without requiring additional experimental effort or battery sensors.

[4] Zhang, Y., Wik, T., Huang, Y., Bergström, J., & Zou, C. (July, 2023). Early prediction of battery life by learning from both time-series and histogram data. IFAC World Congress, Yokohama, Japan [PDF]

[3] Zhang, Y., Wik, T., Bergström, J., & Zou, C. (2023). State of health estimation for lithium-ion batteries under arbitrary usage using data-driven multi-model fusion. IEEE Transactions on Transportation Electrification. [PDF]

We develop a data-driven multi-model fusion method for SoH estimation under arbitrary usage profiles. All possible operating conditions are categorized into six scenarios. For each scenario, an appropriate feature set is extracted to indicate the SoH. Based on the obtained features, four machine learning algorithms are applied individually to train SoH estimation models using time-series data. In addition to the estimates at the current time step, a histogram data-based and online adaptive model is taken from [1] for predicting the next-step SoH. Then, a Kalman filter is applied to systematically fuse the results of all the estimation and prediction models. The proposed model fusion method is able to considerably increase the estimation accuracy and robustness while significantly tightening the confidence interval of the estimation result. 

[1] Hu, X., Yuan, H., Zou, C., Li, Z., & Zhang, L. (2018). Co-estimation of state of charge and state of health for lithium-ion batteries based on fractional-order calculus. IEEE Transactions on Vehicular Technology, 67(11), 10319-10329. Received the Best Vehicular Electronics Paper Award of the IEEE Vehicular Technology Society. [PDF]