EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-variable Demand Power Prediction for Heavy-duty Tractors Based on Multi-task Learning and Dynamic Weight Optimization

Zhijun Ren, Yan Ma, Fenggang Li, Yanming Feng, Xinfa Xu, Guowei Cao

The Archives of Automotive Engineering – Archiwum Motoryzacji · 31.03.2026 · 111 (1) · 53-74

DOI: 10.14669/am/218853 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Archives of Automotive Engineering – Archiwum Motoryzacji, online erschienen am 31.03.2026. Verfasst von Zhijun Ren und 5 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To improve the accuracy of power demand prediction for heavy-duty tractor trucks under complex working conditions, this study proposes a synchronous prediction model based on multi-task learning (MTL-A). This model innovatively synchronously predicts three key variables: vehicle speed, road slope, and acceleration, and takes driving style and road scenarios as labeled inputs to enhance the model's perception ability of complex working conditions. Firstly, a real vehicle data collection platform was established to obtain cumulative driving data of three drivers with distinct driving styles over more than 1800 kilometers in high-speed and national road scenarios. On this basis, the impact mechanism of each variable on power demand was quantitatively analyzed based on the vehicle longitudinal dynamics model, and the significant contributions of driving style and road conditions to power fluctuations were revealed. The proposed MTL-A model adopts the CNN-LSTM-Attention (CNN-LSTM-A) architecture and introduces the GradNorm algorithm to dynamically balance the loss weights in multi-task learning, thereby alleviating gradient conflicts and achieving precise multi-variable prediction in a short period. Experimental results show that compared with traditional single-task models, the average error of MTL-A model in predicting vehicle speed, slope, and acceleration is significantly reduced by 28.4%, 13.1%, and 16.3% respectively, thereby significantly improving the calculation accuracy of the final power demand. Particularly, in typical scenarios of high-speed and national roads, the power prediction error of MTL-A model is reduced by 58.40% and 41.68% respectively compared with traditional methods, fully verifying its excellent scene adaptability and prediction efficiency.

Zitieren

APA

Ren, Z., Ma, Y., Li, F., Feng, Y., Xu, X., & Cao, G. (2026). Multi-variable Demand Power Prediction for Heavy-duty Tractors Based on Multi-task Learning and Dynamic Weight Optimization. The Archives of Automotive Engineering – Archiwum Motoryzacji, 111(1), 53-74. https://doi.org/10.14669/am/218853

Vancouver

Ren Z, Ma Y, Li F, Feng Y, Xu X, Cao G. Multi-variable Demand Power Prediction for Heavy-duty Tractors Based on Multi-task Learning and Dynamic Weight Optimization. The Archives of Automotive Engineering – Archiwum Motoryzacji. 2026;111(1):53-74. doi:10.14669/am/218853

BibTeX
@article{Ren2026,
  author = {Ren, Zhijun and Ma, Yan and Li, Fenggang and Feng, Yanming and Xu, Xinfa and Cao, Guowei},
  title = {Multi-variable Demand Power Prediction for Heavy-duty Tractors Based on Multi-task Learning and Dynamic Weight Optimization},
  journal = {The Archives of Automotive Engineering – Archiwum Motoryzacji},
  year = {2026},
  volume = {111},
  number = {1},
  pages = {53--74},
  doi = {10.14669/am/218853}
}
Kostenlos starten →