Physics-informed attention on temporal fusion transformer for multivariate truck range forecasting
Automotive and Engine Technology · 02.06.2026 · 11 (1)
DOI: 10.1007/s41104-026-00172-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Automotive and Engine Technology, online erschienen am 02.06.2026. Verfasst von Chuong Dang und 1 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Daimler Truck AG.
Abstract (Originalsprache)
Accurate real-time forecasting of remaining vehicle range remains a challenge, particularly under varying payloads, road gradients, and environmental conditions. Conventional Temporal Fusion Transformers (TFTs) utilize attention mechanisms to dynamically weight historical inputs but may fail to capture explicit physical relationships that are critical for accurate predictions in heavy-duty electric trucks. This paper introduces a novel approach to integrating physical vehicle dynamics directly into the attention mechanism of TFTs. Our method, Physics-Informed Attention for TFT (PIA-TFT), modifies attention calculation by injecting physics-based relevance scores derived from vehicle speed, payload, road gradients, and other physical parameters, improving interpretability and model accuracy under operational conditions. Empirical evaluations conducted with real-world data from electric trucks demonstrate that the PIA-TFT reduces prediction errors compared to standard TFTs by up to 18%. Our approach is a step towards more physically consistent and explainable deep learning architectures for automotive forecasting tasks.
Förderung
- Daimler Truck AG
Zitieren
APA
Dang, C., & Peters, S. (2026). Physics-informed attention on temporal fusion transformer for multivariate truck range forecasting. Automotive and Engine Technology, 11(1). https://doi.org/10.1007/s41104-026-00172-2
Vancouver
Dang C, Peters S. Physics-informed attention on temporal fusion transformer for multivariate truck range forecasting. Automotive and Engine Technology. 2026;11(1). doi:10.1007/s41104-026-00172-2
BibTeX
@article{Dang2026,
author = {Dang, Chuong and Peters, Steven},
title = {Physics-informed attention on temporal fusion transformer for multivariate truck range forecasting},
journal = {Automotive and Engine Technology},
year = {2026},
volume = {11},
number = {1},
doi = {10.1007/s41104-026-00172-2}
}
EUVIMED