Enhancing BEV Energy Management: Neural Network-Based System Identification for Thermal Control Strategies

Kai Franke, David Hemkemeyer, Patrick Schutzeich, Lukas Schäfers, Stefan Pischinger
{"title":"Enhancing BEV Energy Management: Neural Network-Based System Identification for Thermal Control Strategies","authors":"Kai Franke, David Hemkemeyer, Patrick Schutzeich, Lukas Schäfers, Stefan Pischinger","doi":"10.4271/2024-01-3005","DOIUrl":null,"url":null,"abstract":"Modeling thermal systems in Battery Electric Vehicles (BEVs) is crucial for enhancing energy efficiency through predictive control strategies, thereby extending vehicle range. A major obstacle in this modeling is the often limited availability of detailed system information. This research introduces a methodology using neural networks for system identification, a powerful technique capable of approximating the physical behavior of thermal systems with minimal data requirements. By employing black-box models, this approach supports the creation of optimization-based control strategies, such as Model Predictive Control (MPC) and Reinforcement Learning-based control (RL). The system identification process is executed using MATLAB Simulink, with virtual training data produced by a Simulink models to establish the method's feasibility. The neural networks utilized for system identification are implemented in MATLAB code. This study conducts a comparative analysis between the white-box models and the generated black-box models, focusing on their predictive accuracy, to highlight the trade-offs and advantages inherent to each modeling approach. The findings from this study suggest that employing neural network-based black-box models can enhance the development of advanced control strategies in BEVs. As a forward-looking perspective, the research outlines a specific approach for the integration of these models into control strategy development. Furthermore, it discusses the potential for methodological enhancements and the application of the system identification process to additional thermal system components, with the overall goal of enhancing energy management in BEVs.","PeriodicalId":510086,"journal":{"name":"SAE Technical Paper Series","volume":"19 7","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"SAE Technical Paper Series","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4271/2024-01-3005","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Modeling thermal systems in Battery Electric Vehicles (BEVs) is crucial for enhancing energy efficiency through predictive control strategies, thereby extending vehicle range. A major obstacle in this modeling is the often limited availability of detailed system information. This research introduces a methodology using neural networks for system identification, a powerful technique capable of approximating the physical behavior of thermal systems with minimal data requirements. By employing black-box models, this approach supports the creation of optimization-based control strategies, such as Model Predictive Control (MPC) and Reinforcement Learning-based control (RL). The system identification process is executed using MATLAB Simulink, with virtual training data produced by a Simulink models to establish the method's feasibility. The neural networks utilized for system identification are implemented in MATLAB code. This study conducts a comparative analysis between the white-box models and the generated black-box models, focusing on their predictive accuracy, to highlight the trade-offs and advantages inherent to each modeling approach. The findings from this study suggest that employing neural network-based black-box models can enhance the development of advanced control strategies in BEVs. As a forward-looking perspective, the research outlines a specific approach for the integration of these models into control strategy development. Furthermore, it discusses the potential for methodological enhancements and the application of the system identification process to additional thermal system components, with the overall goal of enhancing energy management in BEVs.
加强 BEV 能源管理:基于神经网络的热控制策略系统识别
电池电动汽车(BEV)热系统建模对于通过预测控制策略提高能源效率,从而延长车辆续航里程至关重要。建模过程中的一个主要障碍是详细的系统信息往往有限。本研究介绍了一种使用神经网络进行系统识别的方法,这是一种强大的技术,能够以最少的数据要求逼近热系统的物理行为。通过采用黑盒模型,该方法支持创建基于优化的控制策略,如模型预测控制(MPC)和基于强化学习的控制(RL)。系统识别过程使用 MATLAB Simulink 执行,通过 Simulink 模型生成的虚拟训练数据来确定方法的可行性。用于系统识别的神经网络由 MATLAB 代码实现。本研究对白盒模型和生成的黑盒模型进行了比较分析,重点关注它们的预测准确性,以突出每种建模方法固有的权衡和优势。本研究的结果表明,采用基于神经网络的黑盒模型可以促进 BEV 先进控制策略的开发。作为一种前瞻性视角,本研究概述了将这些模型整合到控制策略开发中的具体方法。此外,研究还讨论了方法改进的潜力,以及将系统识别过程应用于其他热系统组件的可能性,其总体目标是加强 BEV 的能源管理。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信