State of Charge Prediction for Electric Vehicles Based on Integrated Model Architecture

To enhance the accuracy of SOC prediction in EVs, which often suffers from significant discrepancies between displayed and actual driving ranges, this study proposes a data-driven model guided by an energy consumption framework. The approach addresses the problem of inaccurate remaining range predic...

Full description

Saved in:
Bibliographic Details
Main Authors: Min Wei, Yuhang Liu, Haojie Wang, Siquan Yuan, Jie Hu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/13/2197
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115750021300224
author Min Wei
Yuhang Liu
Haojie Wang
Siquan Yuan
Jie Hu
author_facet Min Wei
Yuhang Liu
Haojie Wang
Siquan Yuan
Jie Hu
author_sort Min Wei
collection DOAJ
description To enhance the accuracy of SOC prediction in EVs, which often suffers from significant discrepancies between displayed and actual driving ranges, this study proposes a data-driven model guided by an energy consumption framework. The approach addresses the problem of inaccurate remaining range prediction, improving drivers’ travel planning and vehicle efficiency. A PCA-GA-K-Means-based driving cycle clustering method is introduced, followed by driving style feature extraction using a GMM to capture behavioral differences. A coupled library of twelve typical driving cycle style combinations is constructed to handle complex correlations among driving style, operating conditions, and range. To mitigate multicollinearity and nonlinear feature redundancies, a Pearson-DII-based feature extraction method is proposed. A stacking ensemble model, integrating Random Forest, CatBoost, XGBoost, and SVR as base models with ElasticNet as the meta model, is developed for robust prediction. Validated with real-world vehicle data across −21 °C to 39 °C and four driving cycles, the model significantly improves SOC prediction accuracy, offering a reliable solution for EV range estimation and enhancing user trust in EV technology.
format Article
id doaj-art-692a74bdaa09400e896a29e5ea935670
institution OA Journals
issn 2227-7390
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-692a74bdaa09400e896a29e5ea9356702025-08-20T02:36:30ZengMDPI AGMathematics2227-73902025-07-011313219710.3390/math13132197State of Charge Prediction for Electric Vehicles Based on Integrated Model ArchitectureMin Wei0Yuhang Liu1Haojie Wang2Siquan Yuan3Jie Hu4School of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, ChinaTo enhance the accuracy of SOC prediction in EVs, which often suffers from significant discrepancies between displayed and actual driving ranges, this study proposes a data-driven model guided by an energy consumption framework. The approach addresses the problem of inaccurate remaining range prediction, improving drivers’ travel planning and vehicle efficiency. A PCA-GA-K-Means-based driving cycle clustering method is introduced, followed by driving style feature extraction using a GMM to capture behavioral differences. A coupled library of twelve typical driving cycle style combinations is constructed to handle complex correlations among driving style, operating conditions, and range. To mitigate multicollinearity and nonlinear feature redundancies, a Pearson-DII-based feature extraction method is proposed. A stacking ensemble model, integrating Random Forest, CatBoost, XGBoost, and SVR as base models with ElasticNet as the meta model, is developed for robust prediction. Validated with real-world vehicle data across −21 °C to 39 °C and four driving cycles, the model significantly improves SOC prediction accuracy, offering a reliable solution for EV range estimation and enhancing user trust in EV technology.https://www.mdpi.com/2227-7390/13/13/2197pure electric vehiclebattery state estimationdata-driven approachremaining driving range predictionstacking model
spellingShingle Min Wei
Yuhang Liu
Haojie Wang
Siquan Yuan
Jie Hu
State of Charge Prediction for Electric Vehicles Based on Integrated Model Architecture
Mathematics
pure electric vehicle
battery state estimation
data-driven approach
remaining driving range prediction
stacking model
title State of Charge Prediction for Electric Vehicles Based on Integrated Model Architecture
title_full State of Charge Prediction for Electric Vehicles Based on Integrated Model Architecture
title_fullStr State of Charge Prediction for Electric Vehicles Based on Integrated Model Architecture
title_full_unstemmed State of Charge Prediction for Electric Vehicles Based on Integrated Model Architecture
title_short State of Charge Prediction for Electric Vehicles Based on Integrated Model Architecture
title_sort state of charge prediction for electric vehicles based on integrated model architecture
topic pure electric vehicle
battery state estimation
data-driven approach
remaining driving range prediction
stacking model
url https://www.mdpi.com/2227-7390/13/13/2197
work_keys_str_mv AT minwei stateofchargepredictionforelectricvehiclesbasedonintegratedmodelarchitecture
AT yuhangliu stateofchargepredictionforelectricvehiclesbasedonintegratedmodelarchitecture
AT haojiewang stateofchargepredictionforelectricvehiclesbasedonintegratedmodelarchitecture
AT siquanyuan stateofchargepredictionforelectricvehiclesbasedonintegratedmodelarchitecture
AT jiehu stateofchargepredictionforelectricvehiclesbasedonintegratedmodelarchitecture