Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive Correlation

The battery systems of electric vehicles (EVs) are directly impacted by battery temperature in terms of thermal runaway and failure. However, uncertainty about thermal runaway, dynamic conditions, and a dearth of high-quality data sets make modeling and predicting nonlinear multiscale electrochemica...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongyu Shen, Yuefeng Liu, Qiyan Zhao, Guoyue Xue, Tiange Zhang, Xiuying Tan
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Batteries
Subjects:
Online Access:https://www.mdpi.com/2313-0105/10/10/373
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205656874745856
author Hongyu Shen
Yuefeng Liu
Qiyan Zhao
Guoyue Xue
Tiange Zhang
Xiuying Tan
author_facet Hongyu Shen
Yuefeng Liu
Qiyan Zhao
Guoyue Xue
Tiange Zhang
Xiuying Tan
author_sort Hongyu Shen
collection DOAJ
description The battery systems of electric vehicles (EVs) are directly impacted by battery temperature in terms of thermal runaway and failure. However, uncertainty about thermal runaway, dynamic conditions, and a dearth of high-quality data sets make modeling and predicting nonlinear multiscale electrochemical systems challenging. In this work, a novel Mamba network architecture called BMPTtery (Bidirectional Mamba Predictive Battery Temperature Representation) is proposed to overcome these challenges. First, a two-step hybrid model of trajectory piecewise–polynomial regression and exponentially weighted moving average is created and used to an operational dataset of EVs in order to handle the problem of noisy and incomplete time-series data. Each time series is then individually labeled to learn the representation and adaptive correlation of the multivariate series to capture battery performance variations in complex dynamic operating environments. Next, a prediction method with multiple steps based on the bidirectional Mamba is suggested. When combined with a failure diagnosis approach, this scheme can accurately detect heat failures due to excessive temperature, rapid temperature rise, and significant temperature differences. The experimental results demonstrate that the technique can accurately detect battery failures on a dataset of real operational EVs and predict the battery temperature one minute ahead of time with an MRE of 0.273%.
format Article
id doaj-art-c5e151c4c3544e098878daecf93a8db1
institution OA Journals
issn 2313-0105
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Batteries
spelling doaj-art-c5e151c4c3544e098878daecf93a8db12025-08-20T02:11:01ZengMDPI AGBatteries2313-01052024-10-01101037310.3390/batteries10100373Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive CorrelationHongyu Shen0Yuefeng Liu1Qiyan Zhao2Guoyue Xue3Tiange Zhang4Xiuying Tan5School of Digital and Intelligence Industry, Inner Mongolia University of Science & Technology, Baotou 014000, ChinaSchool of Digital and Intelligence Industry, Inner Mongolia University of Science & Technology, Baotou 014000, ChinaSchool of Digital and Intelligence Industry, Inner Mongolia University of Science & Technology, Baotou 014000, ChinaSchool of Digital and Intelligence Industry, Inner Mongolia University of Science & Technology, Baotou 014000, ChinaSchool of Digital and Intelligence Industry, Inner Mongolia University of Science & Technology, Baotou 014000, ChinaSchool of Digital and Intelligence Industry, Inner Mongolia University of Science & Technology, Baotou 014000, ChinaThe battery systems of electric vehicles (EVs) are directly impacted by battery temperature in terms of thermal runaway and failure. However, uncertainty about thermal runaway, dynamic conditions, and a dearth of high-quality data sets make modeling and predicting nonlinear multiscale electrochemical systems challenging. In this work, a novel Mamba network architecture called BMPTtery (Bidirectional Mamba Predictive Battery Temperature Representation) is proposed to overcome these challenges. First, a two-step hybrid model of trajectory piecewise–polynomial regression and exponentially weighted moving average is created and used to an operational dataset of EVs in order to handle the problem of noisy and incomplete time-series data. Each time series is then individually labeled to learn the representation and adaptive correlation of the multivariate series to capture battery performance variations in complex dynamic operating environments. Next, a prediction method with multiple steps based on the bidirectional Mamba is suggested. When combined with a failure diagnosis approach, this scheme can accurately detect heat failures due to excessive temperature, rapid temperature rise, and significant temperature differences. The experimental results demonstrate that the technique can accurately detect battery failures on a dataset of real operational EVs and predict the battery temperature one minute ahead of time with an MRE of 0.273%.https://www.mdpi.com/2313-0105/10/10/373electric vehiclesmambatemperature predictionfailure diagnosismulti-step ahead prediction
spellingShingle Hongyu Shen
Yuefeng Liu
Qiyan Zhao
Guoyue Xue
Tiange Zhang
Xiuying Tan
Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive Correlation
Batteries
electric vehicles
mamba
temperature prediction
failure diagnosis
multi-step ahead prediction
title Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive Correlation
title_full Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive Correlation
title_fullStr Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive Correlation
title_full_unstemmed Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive Correlation
title_short Multi-Step Temperature Prognosis of Lithium-Ion Batteries for Real Electric Vehicles Based on a Novel Bidirectional Mamba Network and Sequence Adaptive Correlation
title_sort multi step temperature prognosis of lithium ion batteries for real electric vehicles based on a novel bidirectional mamba network and sequence adaptive correlation
topic electric vehicles
mamba
temperature prediction
failure diagnosis
multi-step ahead prediction
url https://www.mdpi.com/2313-0105/10/10/373
work_keys_str_mv AT hongyushen multisteptemperatureprognosisoflithiumionbatteriesforrealelectricvehiclesbasedonanovelbidirectionalmambanetworkandsequenceadaptivecorrelation
AT yuefengliu multisteptemperatureprognosisoflithiumionbatteriesforrealelectricvehiclesbasedonanovelbidirectionalmambanetworkandsequenceadaptivecorrelation
AT qiyanzhao multisteptemperatureprognosisoflithiumionbatteriesforrealelectricvehiclesbasedonanovelbidirectionalmambanetworkandsequenceadaptivecorrelation
AT guoyuexue multisteptemperatureprognosisoflithiumionbatteriesforrealelectricvehiclesbasedonanovelbidirectionalmambanetworkandsequenceadaptivecorrelation
AT tiangezhang multisteptemperatureprognosisoflithiumionbatteriesforrealelectricvehiclesbasedonanovelbidirectionalmambanetworkandsequenceadaptivecorrelation
AT xiuyingtan multisteptemperatureprognosisoflithiumionbatteriesforrealelectricvehiclesbasedonanovelbidirectionalmambanetworkandsequenceadaptivecorrelation