High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression

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 attenuat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiahao Ren, Junfei Cai, Jinjin Li
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/fb1468810a154f6aa8ac62e8237402a0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fb1468810a154f6aa8ac62e8237402a0
record_format	dspace
spelling	oai:doaj.org-article:fb1468810a154f6aa8ac62e8237402a02021-12-02T17:47:36ZHigh precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression10.1038/s41598-021-91241-z2045-2322https://doaj.org/article/fb1468810a154f6aa8ac62e8237402a02021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91241-zhttps://doaj.org/toc/2045-2322Abstract 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.Jiahao RenJunfei CaiJinjin LiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jiahao Ren Junfei Cai Jinjin Li High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression
description	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.
format	article
author	Jiahao Ren Junfei Cai Jinjin Li
author_facet	Jiahao Ren Junfei Cai Jinjin Li
author_sort	Jiahao Ren
title	High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression
title_short	High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression
title_full	High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression
title_fullStr	High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression
title_full_unstemmed	High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression
title_sort	high precision implicit function learning for forecasting supercapacitor state of health based on gaussian process regression
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/fb1468810a154f6aa8ac62e8237402a0
work_keys_str_mv	AT jiahaoren highprecisionimplicitfunctionlearningforforecastingsupercapacitorstateofhealthbasedongaussianprocessregression AT junfeicai highprecisionimplicitfunctionlearningforforecastingsupercapacitorstateofhealthbasedongaussianprocessregression AT jinjinli highprecisionimplicitfunctionlearningforforecastingsupercapacitorstateofhealthbasedongaussianprocessregression
_version_	1718379505639227392

High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression

Ejemplares similares