Research on Gas Concentration Prediction Method Based on Decoupling of Temporal Feature and Dynamic Relationship Reconstruction
Fire · 24.06.2026 · 9 (7) · 267
DOI: 10.3390/fire9070267 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fire, online erschienen am 24.06.2026. Verfasst von Yongle Yan und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate multi-channel gas concentration prediction is very important for coal mine safety. However, the dynamic reconstruction of the sensor network often interferes with the input sequence. Existing models face a critical trade-off: channel-independent models are robust to sequence changes but ignore spatial coupling, while channel-dependent models overfit fixed sequences, leading to performance collapse during rearrangements. This paper presents a gas concentration prediction framework based on channel permutation-invariant interaction (CPiRi) to reconcile these limitations. CPiRi employs a spatio-temporal decoupling architecture where a frozen univariate pre-trained encoder independently extracts temporal features to ensure sequence robustness. Subsequently, a permutation-equivariant spatial module utilizes self-attention to model inter-channel gas emission relationships based on data content rather than positional indices. To achieve true permutation invariance, we introduce channel-shuffling regularization during training, forcing the model to learn content-driven relational reasoning. Evaluations on 15 real-world Chinese coal mine datasets demonstrate that CPiRi achieves highly competitive accuracy and consistently outperforms mainstream baselines in both prediction precision and structural adaptability. This study offers a robust technical pathway for gas monitoring in dynamic environments, substantially improving the reliability of intelligent mine safety systems.
Zitieren
APA
Yan, Y., Zhao, Y., & Hui, J. (2026). Research on Gas Concentration Prediction Method Based on Decoupling of Temporal Feature and Dynamic Relationship Reconstruction. Fire, 9(7), 267. https://doi.org/10.3390/fire9070267
Vancouver
Yan Y, Zhao Y, Hui J. Research on Gas Concentration Prediction Method Based on Decoupling of Temporal Feature and Dynamic Relationship Reconstruction. Fire. 2026;9(7):267. doi:10.3390/fire9070267
BibTeX
@article{Yan2026,
author = {Yan, Yongle and Zhao, Yichao and Hui, Jiuwu},
title = {Research on Gas Concentration Prediction Method Based on Decoupling of Temporal Feature and Dynamic Relationship Reconstruction},
journal = {Fire},
year = {2026},
volume = {9},
number = {7},
pages = {267},
doi = {10.3390/fire9070267}
}
EUVIMED