An Accurate and Interpretable Lifetime Prediction Method for Batteries using Extreme Gradient Boosting Tree and TreeExplainer
Authors:
- 1 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1042-1048
Abstract
Lithium-ion batteries have been widely used in many fields such as electric vehicles and smart grid. Accurately predicting its lifetime is crucial for ensuring safety and accelerating battery technological development. This study aims to develop an interpretable battery lifetime prediction method based on a machine learning model by explaining the features used in the model. Firstly, the battery charge-discharge cycle data is analyzed, and five key features related to lifetime are extracted from the discharge curve of the first 100 cycles. Then, extreme gradient boosting tree (XGBoost) is built to learn the relationship between the features and the lifetime, and its optimal parameters are obtained through grid search and five-fold cross-validation. TreeExplainer is used to calculate shapley value based on game theory to quantitatively interpret and reveal the important features contributing to lifetime. Experimental results on the latest battery dataset demonstrate that XGBoost can effectively predict battery lifetime. At the same time, quantitative analysis and interpretation provide the reasons for the model decision, which improves the credibility of the prediction method and even helps to have a deeper understanding of the battery degradation mechanism.Keywords
Funding Information
- National Natural Science Foundation of China (62172448)
This publication has 20 references indexed in Scilit:
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020
- Data-driven prediction of battery cycle life before capacity degradationNature Energy, 2019
- XGBoost2016
- “Why Should I Trust You?”: Explaining the Predictions of Any Classifier2016
- An integrated unscented kalman filter and relevance vector regression approach for lithium-ion battery remaining useful life and short-term capacity predictionReliability Engineering & System Safety, 2015
- Intelligible Models for HealthCare2015
- A multiscale framework with extended Kalman filter for lithium-ion battery SOC and capacity estimationApplied Energy, 2012
- Remaining useful life estimation – A review on the statistical data driven approachesEuropean Journal of Operational Research, 2011
- A review on prognostics and health monitoring of Li-ion batteryJournal of Power Sources, 2011
- 17. A Value for n-Person Games1953