Abstract
To address the problems of the random and incomplete charging process of the vehicle-mounted lithium-ion batteries, this paper proposes a machine learning method that can realize state of health (SOH) estimation under random charging conditions. Firstly, the complete voltage curve prediction in the constant-current (CC) charging phase under the short-term charging scenario is realized by constructing fitting polynomials, which effectively solves the problem of feature vector acquisition in short-term random charging scenarios. Then, the effects of charging durations of different constant-current charging voltage intervals on SOH estimation are compared to determine the feature vectors. The gaussian process regression (GPR) algorithm is employed to establish the SOH of the battery. Finally, the feasibility of the proposed voltage estimation method is verified at different aging cycles and in random charging scenarios, respectively. The effectiveness of battery SOH estimation based on short-term random charging data is verified. The results show that the proposed method has good feasibility with the SOH estimation error of less than 1.64%.
Sign-in/Register to access full text options 
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.
