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

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 -