Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional Autoencoders

There has been extensive research on the partial differential equations governing the theory of gas flow in coal mines. However, the traditional Proper Orthogonal Decomposition–Radial Basis Function (POD-RBF) reduced-order algorithm requires significant computational resources and is inefficient whe...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianxuan Hao, Lizhen Zhao, Yang Du, Yiju Tang, Fan Li, Zehua Wang, Xu Li
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/15/11/733
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153397282013184
author Tianxuan Hao
Lizhen Zhao
Yang Du
Yiju Tang
Fan Li
Zehua Wang
Xu Li
author_facet Tianxuan Hao
Lizhen Zhao
Yang Du
Yiju Tang
Fan Li
Zehua Wang
Xu Li
author_sort Tianxuan Hao
collection DOAJ
description There has been extensive research on the partial differential equations governing the theory of gas flow in coal mines. However, the traditional Proper Orthogonal Decomposition–Radial Basis Function (POD-RBF) reduced-order algorithm requires significant computational resources and is inefficient when calculating high-dimensional data for coal mine gas pressure fields. To achieve the rapid computation of gas extraction pressure fields, this paper proposes a model reduction method based on deep neural networks (DNNs) and convolutional autoencoders (CAEs). The CAE is used to compress and reconstruct full-order numerical solutions for coal mine gas extraction, while the DNN is employed to establish the nonlinear mapping between the physical parameters of gas extraction and the latent space parameters of the reduced-order model. The DNN-CAE model is applied to the reduced-order modeling of gas extraction flow–solid coupling mathematical models in coal mines. A full-order model pressure field numerical dataset for gas extraction was constructed, and optimal hyperparameters for the pressure field reconstruction model and latent space parameter prediction model were determined through hyperparameter testing. The performance of the DNN-CAE model order reduction algorithm was compared to the POD-RBF model order reduction algorithm. The results indicate that the DNN-CAE method has certain advantages over the traditional POD-RBF method in terms of pressure field reconstruction accuracy, overall structure retention, extremum capture, and computational efficiency.
format Article
id doaj-art-cea1d6b7ceb442ee919d8fa3a8d5c4a6
institution Kabale University
issn 2078-2489
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-cea1d6b7ceb442ee919d8fa3a8d5c4a62024-11-26T18:06:45ZengMDPI AGInformation2078-24892024-11-01151173310.3390/info15110733Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional AutoencodersTianxuan Hao0Lizhen Zhao1Yang Du2Yiju Tang3Fan Li4Zehua Wang5Xu Li6College of Safety Science and Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Safety Science and Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Safety Science and Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Municipal and Environmental Engineering, Henan University of Urban Construction, Pingdingshan 467036, ChinaCollege of Safety Science and Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Safety Science and Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Safety Science and Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaThere has been extensive research on the partial differential equations governing the theory of gas flow in coal mines. However, the traditional Proper Orthogonal Decomposition–Radial Basis Function (POD-RBF) reduced-order algorithm requires significant computational resources and is inefficient when calculating high-dimensional data for coal mine gas pressure fields. To achieve the rapid computation of gas extraction pressure fields, this paper proposes a model reduction method based on deep neural networks (DNNs) and convolutional autoencoders (CAEs). The CAE is used to compress and reconstruct full-order numerical solutions for coal mine gas extraction, while the DNN is employed to establish the nonlinear mapping between the physical parameters of gas extraction and the latent space parameters of the reduced-order model. The DNN-CAE model is applied to the reduced-order modeling of gas extraction flow–solid coupling mathematical models in coal mines. A full-order model pressure field numerical dataset for gas extraction was constructed, and optimal hyperparameters for the pressure field reconstruction model and latent space parameter prediction model were determined through hyperparameter testing. The performance of the DNN-CAE model order reduction algorithm was compared to the POD-RBF model order reduction algorithm. The results indicate that the DNN-CAE method has certain advantages over the traditional POD-RBF method in terms of pressure field reconstruction accuracy, overall structure retention, extremum capture, and computational efficiency.https://www.mdpi.com/2078-2489/15/11/733coal minegas extractiongas flow modelreduced-order modeldeep neural networksconvolutional autoencoders
spellingShingle Tianxuan Hao
Lizhen Zhao
Yang Du
Yiju Tang
Fan Li
Zehua Wang
Xu Li
Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional Autoencoders
Information
coal mine
gas extraction
gas flow model
reduced-order model
deep neural networks
convolutional autoencoders
title Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional Autoencoders
title_full Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional Autoencoders
title_fullStr Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional Autoencoders
title_full_unstemmed Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional Autoencoders
title_short Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and Convolutional Autoencoders
title_sort reduced order model of coal seam gas extraction pressure distribution based on deep neural networks and convolutional autoencoders
topic coal mine
gas extraction
gas flow model
reduced-order model
deep neural networks
convolutional autoencoders
url https://www.mdpi.com/2078-2489/15/11/733
work_keys_str_mv AT tianxuanhao reducedordermodelofcoalseamgasextractionpressuredistributionbasedondeepneuralnetworksandconvolutionalautoencoders
AT lizhenzhao reducedordermodelofcoalseamgasextractionpressuredistributionbasedondeepneuralnetworksandconvolutionalautoencoders
AT yangdu reducedordermodelofcoalseamgasextractionpressuredistributionbasedondeepneuralnetworksandconvolutionalautoencoders
AT yijutang reducedordermodelofcoalseamgasextractionpressuredistributionbasedondeepneuralnetworksandconvolutionalautoencoders
AT fanli reducedordermodelofcoalseamgasextractionpressuredistributionbasedondeepneuralnetworksandconvolutionalautoencoders
AT zehuawang reducedordermodelofcoalseamgasextractionpressuredistributionbasedondeepneuralnetworksandconvolutionalautoencoders
AT xuli reducedordermodelofcoalseamgasextractionpressuredistributionbasedondeepneuralnetworksandconvolutionalautoencoders