TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation Warning

This study addresses the problems of multi-source data redundancy, insufficient feature capture timing, and delayed risk warning in the prediction of gas concentration in fully mechanized coal-mining operations by constructing a three-pronged technical approach that integrates feature dimensionality...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanping Wang, Longcheng Zhang, Zhenguo Yan, Jun Deng, Yuxin Huang, Zhixin Qin, Yuqi Cao, Yiyang Wang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Fire
Subjects:
Online Access:https://www.mdpi.com/2571-6255/8/5/175
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327288697487360
author Yanping Wang
Longcheng Zhang
Zhenguo Yan
Jun Deng
Yuxin Huang
Zhixin Qin
Yuqi Cao
Yiyang Wang
author_facet Yanping Wang
Longcheng Zhang
Zhenguo Yan
Jun Deng
Yuxin Huang
Zhixin Qin
Yuqi Cao
Yiyang Wang
author_sort Yanping Wang
collection DOAJ
description This study addresses the problems of multi-source data redundancy, insufficient feature capture timing, and delayed risk warning in the prediction of gas concentration in fully mechanized coal-mining operations by constructing a three-pronged technical approach that integrates feature dimensionality reduction, hybrid modeling, and intelligent early warning. First, sparse kernel principal component analysis (SKPCA) is used to accomplish the feature decoupling of multi-source monitoring data, and its optimal dimensionality reduction performance is verified using long-term and short-term neural networks (LSTMs). Second, an innovative TCN–Transformer hybrid architecture is proposed. The transient fluctuation characteristics of gas concentration are captured using causal dilation convolution, while a multi-head self-attention mechanism is used to analyze the cross-scale correlation of geological mining parameters. A flood optimization algorithm (FLA) is used to establish a hyperparameter collaborative optimization framework. Compared to TCN-LSTM, CNN-GRU, and other hybrid models, the hybrid model proposed in this study exhibits superior point prediction performance, with a maximum R<sup>2</sup> of 0.980988. Finally, a dynamic confidence interval is established using the locally weighted kernel density estimation (LWD-KDE) method with an optimized bandwidth, and an unsupervised early warning mechanism for the risk of gas concentration fluctuations in coal mines is constructed. The results provide a comprehensive approach to preventing and controlling gas disasters in fully mechanized mining operations. This research effectively promotes the transformation and upgrading of coal-mine-safety-monitoring systems to an active defense paradigm.
format Article
id doaj-art-fe815a0287a44f9f81ae3c5a4b68eb0b
institution Kabale University
issn 2571-6255
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Fire
spelling doaj-art-fe815a0287a44f9f81ae3c5a4b68eb0b2025-08-20T03:47:54ZengMDPI AGFire2571-62552025-04-018517510.3390/fire8050175TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation WarningYanping Wang0Longcheng Zhang1Zhenguo Yan2Jun Deng3Yuxin Huang4Zhixin Qin5Yuqi Cao6Yiyang Wang7College of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaThis study addresses the problems of multi-source data redundancy, insufficient feature capture timing, and delayed risk warning in the prediction of gas concentration in fully mechanized coal-mining operations by constructing a three-pronged technical approach that integrates feature dimensionality reduction, hybrid modeling, and intelligent early warning. First, sparse kernel principal component analysis (SKPCA) is used to accomplish the feature decoupling of multi-source monitoring data, and its optimal dimensionality reduction performance is verified using long-term and short-term neural networks (LSTMs). Second, an innovative TCN–Transformer hybrid architecture is proposed. The transient fluctuation characteristics of gas concentration are captured using causal dilation convolution, while a multi-head self-attention mechanism is used to analyze the cross-scale correlation of geological mining parameters. A flood optimization algorithm (FLA) is used to establish a hyperparameter collaborative optimization framework. Compared to TCN-LSTM, CNN-GRU, and other hybrid models, the hybrid model proposed in this study exhibits superior point prediction performance, with a maximum R<sup>2</sup> of 0.980988. Finally, a dynamic confidence interval is established using the locally weighted kernel density estimation (LWD-KDE) method with an optimized bandwidth, and an unsupervised early warning mechanism for the risk of gas concentration fluctuations in coal mines is constructed. The results provide a comprehensive approach to preventing and controlling gas disasters in fully mechanized mining operations. This research effectively promotes the transformation and upgrading of coal-mine-safety-monitoring systems to an active defense paradigm.https://www.mdpi.com/2571-6255/8/5/175TCNtransformerSKPCAFLAdynamic kernel density estimationrisk warning
spellingShingle Yanping Wang
Longcheng Zhang
Zhenguo Yan
Jun Deng
Yuxin Huang
Zhixin Qin
Yuqi Cao
Yiyang Wang
TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation Warning
Fire
TCN
transformer
SKPCA
FLA
dynamic kernel density estimation
risk warning
title TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation Warning
title_full TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation Warning
title_fullStr TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation Warning
title_full_unstemmed TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation Warning
title_short TCN–Transformer Spatio-Temporal Feature Decoupling and Dynamic Kernel Density Estimation for Gas Concentration Fluctuation Warning
title_sort tcn transformer spatio temporal feature decoupling and dynamic kernel density estimation for gas concentration fluctuation warning
topic TCN
transformer
SKPCA
FLA
dynamic kernel density estimation
risk warning
url https://www.mdpi.com/2571-6255/8/5/175
work_keys_str_mv AT yanpingwang tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning
AT longchengzhang tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning
AT zhenguoyan tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning
AT jundeng tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning
AT yuxinhuang tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning
AT zhixinqin tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning
AT yuqicao tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning
AT yiyangwang tcntransformerspatiotemporalfeaturedecouplinganddynamickerneldensityestimationforgasconcentrationfluctuationwarning