Abstract
State of health (SOH) prediction of supercapacitors aims to provide reliable lifetime control and avoid system failure. Gaussian process regression (GPR) has emerged for SOH prediction because of its capability of capturing nonlinear relationships between features, and tracking SOH attenuations effectively. However, traditional GPR methods based on explicit functions require multiple screenings of optimal mean and covariance functions, which results in data scarcity and increased time consumption. In this study, we propose a GPR-implicit function learning, which is a prior knowledge algorithm for calculating mean and covariance functions from a preliminary data set instead of screening. After introducing the implicit function, the average root mean square error (Average RMSE) is 0.0056 F and the average mean absolute percent error (Average MAPE) is 0.6%, where only the first 5% of the data are trained to predict the remaining 95% of the cycles, thereby decreasing the error by more than three times than previous studies. Furthermore, less cycles (i.e., 1%) are trained while still obtaining low prediction errors (i.e., Average RMSE is 0.0094 F and Average MAPE is 1.01%). This work highlights the strength of GPR-implicit function model for SOH prediction of energy storage devices with high precision and limited property data.
Highlights
State of health (SOH) prediction of supercapacitors aims to provide reliable lifetime control and avoid system failure
This work proposes an implicit function learning method to predict the SOH of SCs based on Gaussian process regression, where a preliminary data set is considered in the mean and covariance functions, and only 5% of the cycles are used as training data to predict the remaining 95% of the cycles
The predicted errors of the Gaussian process regression (GPR)-implicit function method have an Average RMSE of 0.0056 F and an Average MAPE of 0.06%, which are much lower than traditional SOH predictions with only explicit functions
Summary
State of health (SOH) prediction of supercapacitors aims to provide reliable lifetime control and avoid system failure. Li et al combined GPR with other regression methods and proposed a multi-time-scale framework for predicting the SOH and RUL of Lithium ion b atteries[30]; Wang et al used a modified kernel GPR algorithm to simulate the degradation process of batteries[31]; Hu et al designed a dual GPR model for the SOH and RUL prognosis of battery packs[32] These studies are all aimed at improving the accuracy and efficiency of the GPR methods in the prognosis of SOH and RUL, illustrating the necessity of modifying the GPR to obtain better performance
Sign-in/Register to view highlights & summary 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.
