Abstract
The lithium battery state of health can provide timely warning for batteries with serious aging during operation. Therefore, it is of great importance to achieve efficient and fast state estimation of lithium batteries. This work explores the relational properties between different operating conditions to achieve accurate capacity estimation under multiple operating conditions, and the proposed technique reduces the amount of data training while ensuring high accuracy. Specifically, the battery health factor is extracted from the actual charging voltage profile segment. Secondly, the relationship of health factors under different working conditions is explored to provide a fundamental transformation property for machine learning methods. Based on this, the mapping relationship between health factors and battery capacity was constructed by the Gaussian Process Regression model. And by fusing the transformation characteristics and mapping relationships, it is used for predicting the battery capacity under different working conditions. Finally, to verify the generalization and accuracy of the developed model, capacity estimation is performed for the battery under different working conditions. Experimental results show that the model provides accurate and reliable battery capacity estimates and maintains a high level of robustness when the battery working conditions change.
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
