Data-Driven Real-Time Estimation Method for Demand Torque of New Energy Buses

Menglin Li; Hongyang Xu; Hongwen He; Jingda Wu; Mei Yan; Jinghui Zhao

doi:10.1007/s42154-025-00372-w

Data-Driven Real-Time Estimation Method for Demand Torque of New Energy Buses

Menglin Li
, Hongyang Xu
, Hongwen He^*
, Jingda Wu
, Mei Yan
, Jinghui Zhao

^*此作品的通讯作者

Yanshan University
Beijing Institute of Technology
Nanyang Technological University
State Key Laboratory of Intelligent Agricultural Power Equipment

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Accurate power demand estimation is essential for improving vehicle control precision, optimizing power distribution, and enhancing energy management, with torque estimation being a critical component. However, the ideal longitudinal dynamics model ignores the actual running state of the vehicle, resulting in a large error between the calculated and actual values. To address this issue, this study proposes a data-driven real-time torque estimation framework that balances accuracy and computational efficiency for new energy buses. Key features include an online wheel radius identification approach using the least squares method, a speed-slip compensation strategy based on the extreme learning machine, and a dynamic road slope correction technique. Validation using real-world driving data demonstrates that the proposed method reduces vehicle speed RMSE by 58.45% and demand torque RMSE by 34.77%, compared to models without parameter identification.

源语言	英语
页（从-至）	421-434
页数	14
期刊	Automotive Innovation
卷	9
期	2
DOI	https://doi.org/10.1007/s42154-025-00372-w
出版状态	已出版 - 5月 2026
已对外发布	是

访问文件

10.1007/s42154-025-00372-w

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{c15a603f0a93494db0bf993c36fd5802,

title = "Data-Driven Real-Time Estimation Method for Demand Torque of New Energy Buses",

abstract = "Accurate power demand estimation is essential for improving vehicle control precision, optimizing power distribution, and enhancing energy management, with torque estimation being a critical component. However, the ideal longitudinal dynamics model ignores the actual running state of the vehicle, resulting in a large error between the calculated and actual values. To address this issue, this study proposes a data-driven real-time torque estimation framework that balances accuracy and computational efficiency for new energy buses. Key features include an online wheel radius identification approach using the least squares method, a speed-slip compensation strategy based on the extreme learning machine, and a dynamic road slope correction technique. Validation using real-world driving data demonstrates that the proposed method reduces vehicle speed RMSE by 58.45\% and demand torque RMSE by 34.77\%, compared to models without parameter identification.",

keywords = "Longitudinal dynamic model, New energy buses, Torque estimation, Wheel radius identification",

author = "Menglin Li and Hongyang Xu and Hongwen He and Jingda Wu and Mei Yan and Jinghui Zhao",

note = "Publisher Copyright: {\textcopyright} China Society of Automotive Engineers (China SAE) 2026.",

year = "2026",

month = may,

doi = "10.1007/s42154-025-00372-w",

language = "English",

volume = "9",

pages = "421--434",

journal = "Automotive Innovation",

issn = "2096-4250",

publisher = "Springer International Publishing",

number = "2",

}

TY - JOUR

T1 - Data-Driven Real-Time Estimation Method for Demand Torque of New Energy Buses

AU - Li, Menglin

AU - Xu, Hongyang

AU - He, Hongwen

AU - Wu, Jingda

AU - Yan, Mei

AU - Zhao, Jinghui

N1 - Publisher Copyright: © China Society of Automotive Engineers (China SAE) 2026.

PY - 2026/5

Y1 - 2026/5

N2 - Accurate power demand estimation is essential for improving vehicle control precision, optimizing power distribution, and enhancing energy management, with torque estimation being a critical component. However, the ideal longitudinal dynamics model ignores the actual running state of the vehicle, resulting in a large error between the calculated and actual values. To address this issue, this study proposes a data-driven real-time torque estimation framework that balances accuracy and computational efficiency for new energy buses. Key features include an online wheel radius identification approach using the least squares method, a speed-slip compensation strategy based on the extreme learning machine, and a dynamic road slope correction technique. Validation using real-world driving data demonstrates that the proposed method reduces vehicle speed RMSE by 58.45% and demand torque RMSE by 34.77%, compared to models without parameter identification.

AB - Accurate power demand estimation is essential for improving vehicle control precision, optimizing power distribution, and enhancing energy management, with torque estimation being a critical component. However, the ideal longitudinal dynamics model ignores the actual running state of the vehicle, resulting in a large error between the calculated and actual values. To address this issue, this study proposes a data-driven real-time torque estimation framework that balances accuracy and computational efficiency for new energy buses. Key features include an online wheel radius identification approach using the least squares method, a speed-slip compensation strategy based on the extreme learning machine, and a dynamic road slope correction technique. Validation using real-world driving data demonstrates that the proposed method reduces vehicle speed RMSE by 58.45% and demand torque RMSE by 34.77%, compared to models without parameter identification.

KW - Longitudinal dynamic model

KW - New energy buses

KW - Torque estimation

KW - Wheel radius identification

UR - https://www.scopus.com/pages/publications/105029187270

U2 - 10.1007/s42154-025-00372-w

DO - 10.1007/s42154-025-00372-w

M3 - Article

AN - SCOPUS:105029187270

SN - 2096-4250

VL - 9

SP - 421

EP - 434

JO - Automotive Innovation

JF - Automotive Innovation

IS - 2

ER -

Data-Driven Real-Time Estimation Method for Demand Torque of New Energy Buses

摘要

访问文件

其它文件与链接

学术指纹

引用此