Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model

Summary: A data-driven approach is developed to predict the future capacity of lithium-ion batteries (LIBs) in this work. The empirical mode decomposition (EMD), kernel recursive least square tracker (KRLST), and long short-term memory (LSTM) are used to derive the proposed approach. First, the LIB...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Muhammad Umair Ali, Karam Dad Kallu, Haris Masood, Kamran Ali Khan Niazi, Muhammad Junaid Alvi, Usman Ghafoor, Amad Zafar
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Computer systems organization Energy engineering Energy systems Science Q
Acceso en línea:	https://doaj.org/article/3cc3c92c679641f5826c32922126220d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3cc3c92c679641f5826c32922126220d
record_format	dspace
spelling	oai:doaj.org-article:3cc3c92c679641f5826c32922126220d2021-11-20T05:09:22ZKernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model2589-004210.1016/j.isci.2021.103286https://doaj.org/article/3cc3c92c679641f5826c32922126220d2021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2589004221012554https://doaj.org/toc/2589-0042Summary: A data-driven approach is developed to predict the future capacity of lithium-ion batteries (LIBs) in this work. The empirical mode decomposition (EMD), kernel recursive least square tracker (KRLST), and long short-term memory (LSTM) are used to derive the proposed approach. First, the LIB capacity data is split into local regeneration and monotonic global degradation using the EMD approach. Next, the KRLST is used to track the decomposed intrinsic mode functions, and the residual signal is predicted using the LSTM sub-model. Finally, all the predicted intrinsic mode functions and the residual are ensembled to get the future capacity. The experimental and comparative analysis validates the high accuracy (RMSE of 0.00103) of the proposed ensemble approach compared to Gaussian process regression and LSTM fused model. Furthermore, two times lesser error than other fused models makes this approach an efficient tool for battery health prognostics.Muhammad Umair AliKaram Dad KalluHaris MasoodKamran Ali Khan NiaziMuhammad Junaid AlviUsman GhafoorAmad ZafarElsevierarticleComputer systems organizationEnergy engineeringEnergy systemsScienceQENiScience, Vol 24, Iss 11, Pp 103286- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer systems organization Energy engineering Energy systems Science Q
spellingShingle	Computer systems organization Energy engineering Energy systems Science Q Muhammad Umair Ali Karam Dad Kallu Haris Masood Kamran Ali Khan Niazi Muhammad Junaid Alvi Usman Ghafoor Amad Zafar Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
description	Summary: A data-driven approach is developed to predict the future capacity of lithium-ion batteries (LIBs) in this work. The empirical mode decomposition (EMD), kernel recursive least square tracker (KRLST), and long short-term memory (LSTM) are used to derive the proposed approach. First, the LIB capacity data is split into local regeneration and monotonic global degradation using the EMD approach. Next, the KRLST is used to track the decomposed intrinsic mode functions, and the residual signal is predicted using the LSTM sub-model. Finally, all the predicted intrinsic mode functions and the residual are ensembled to get the future capacity. The experimental and comparative analysis validates the high accuracy (RMSE of 0.00103) of the proposed ensemble approach compared to Gaussian process regression and LSTM fused model. Furthermore, two times lesser error than other fused models makes this approach an efficient tool for battery health prognostics.
format	article
author	Muhammad Umair Ali Karam Dad Kallu Haris Masood Kamran Ali Khan Niazi Muhammad Junaid Alvi Usman Ghafoor Amad Zafar
author_facet	Muhammad Umair Ali Karam Dad Kallu Haris Masood Kamran Ali Khan Niazi Muhammad Junaid Alvi Usman Ghafoor Amad Zafar
author_sort	Muhammad Umair Ali
title	Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
title_short	Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
title_full	Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
title_fullStr	Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
title_full_unstemmed	Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
title_sort	kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/3cc3c92c679641f5826c32922126220d
work_keys_str_mv	AT muhammadumairali kernelrecursiveleastsquaretrackerandlongshorttermmemoryensemblebasedbatteryhealthprognosticmodel AT karamdadkallu kernelrecursiveleastsquaretrackerandlongshorttermmemoryensemblebasedbatteryhealthprognosticmodel AT harismasood kernelrecursiveleastsquaretrackerandlongshorttermmemoryensemblebasedbatteryhealthprognosticmodel AT kamranalikhanniazi kernelrecursiveleastsquaretrackerandlongshorttermmemoryensemblebasedbatteryhealthprognosticmodel AT muhammadjunaidalvi kernelrecursiveleastsquaretrackerandlongshorttermmemoryensemblebasedbatteryhealthprognosticmodel AT usmanghafoor kernelrecursiveleastsquaretrackerandlongshorttermmemoryensemblebasedbatteryhealthprognosticmodel AT amadzafar kernelrecursiveleastsquaretrackerandlongshorttermmemoryensemblebasedbatteryhealthprognosticmodel
_version_	1718419536320921600

Kernel recursive least square tracker and long-short term memory ensemble based battery health prognostic model

Ejemplares similares