EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed Modified Kolmogorov–Arnold Network for CO Concentration Prediction in Gob Areas of Coal Spontaneous Combustion

Zhuoqing Li, Jie Hou iD, Longqiang Han, Xiaodong Wang

Sensors · 22.05.2026 · 26 (11) · 3292

DOI: 10.3390/s26113292 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.05.2026. Verfasst von Zhuoqing Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, China. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coal spontaneous combustion in gob areas is a major disaster endangering safe production in underground coal mines, and accurate prediction of carbon monoxide (CO), the core signature gas of coal oxidation, is critical for early warning and targeted prevention of mine fire disasters. However, CO concentration in gob areas is governed by complex gas–solid thermal–chemical multi-field coupling, presenting strong nonlinear characteristics. Traditional numerical methods suffer from prohibitive computational cost, purely data-driven models have inherent black-box defects, and conventional Physics-Informed Neural Networks (PINNs) require explicit full governing equations, which are hard to establish for such complex systems. This paper first proposes a Physics-Informed Modified Kolmogorov–Arnold Network (PIM-KAN), which deeply integrates domain physical knowledge with KAN architecture via a physics encoding layer, a residual-modified KAN layer, a multi-physics attention mechanism, and a multi-term physical consistency constraint framework. Experiments on 3125 real coal mine field samples show that the PIM-KAN achieves R2 = 0.9965 and RMSE = 0.9290 ppm, reducing RMSE by 19.5% compared with MLP, and outperforming all baseline models. Ablation studies confirm the significant contribution of each innovation module, and attention weight analysis is highly consistent with Arrhenius reaction kinetics, verifying its superior prediction accuracy, physical consistency and intrinsic interpretability.

Schlagwörter

Stichwörter der Autor:innen

Kolmogorov–Arnold networksattention mechanismcoal spontaneous combustion predictioninterpretable machine learningphysics-informed neural networks

Autor:innen und Institutionen

  • Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, China.
  • School of Resources and Safety Engineering, University of Science and Technology Beijing, Beijing 100083, China.

ORCID-Profile: Jie Hou

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, Z., Hou, J., Han, L., & Wang, X. (2026). Physics-Informed Modified Kolmogorov–Arnold Network for CO Concentration Prediction in Gob Areas of Coal Spontaneous Combustion. Sensors, 26(11), 3292. https://doi.org/10.3390/s26113292

Vancouver

Li Z, Hou J, Han L, Wang X. Physics-Informed Modified Kolmogorov–Arnold Network for CO Concentration Prediction in Gob Areas of Coal Spontaneous Combustion. Sensors. 2026;26(11):3292. doi:10.3390/s26113292

BibTeX
@article{Li2026,
  author = {Li, Zhuoqing and Hou, Jie and Han, Longqiang and Wang, Xiaodong},
  title = {Physics-Informed Modified Kolmogorov–Arnold Network for CO Concentration Prediction in Gob Areas of Coal Spontaneous Combustion},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3292},
  doi = {10.3390/s26113292}
}
Kostenlos starten →