Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network

In the 3D reconstruction of coal-rock combinations fractures, in response to the problem that traditional threshold segmentation methods cannot accurately determine the threshold size between coal and rock, resulting in poor fracture segmentation performance, a new VRA-UNet coal-rock combinations fr...

Full description

Saved in:
Bibliographic Details
Main Authors: Dengke WANG, Longhang WANG, Yaguang QIN, Le WEI, Tanggen CAO, Wenrui LI, Lu LI, Xu CHEN, Yuling XIA
Format: Article
Language:zho
Published: Editorial Department of Coal Science and Technology 2025-02-01
Series:Meitan kexue jishu
Subjects:
Online Access:http://www.mtkxjs.com.cn/article/doi/10.12438/cst.2024-1441
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850215680400424960
author Dengke WANG
Longhang WANG
Yaguang QIN
Le WEI
Tanggen CAO
Wenrui LI
Lu LI
Xu CHEN
Yuling XIA
author_facet Dengke WANG
Longhang WANG
Yaguang QIN
Le WEI
Tanggen CAO
Wenrui LI
Lu LI
Xu CHEN
Yuling XIA
author_sort Dengke WANG
collection DOAJ
description In the 3D reconstruction of coal-rock combinations fractures, in response to the problem that traditional threshold segmentation methods cannot accurately determine the threshold size between coal and rock, resulting in poor fracture segmentation performance, a new VRA-UNet coal-rock combinations fracture identification model based on deep learning theory is proposed, providing an optimized solution for accurate identification of coal-rock combinations fractures. Firstly, the VGG16 module is used as the backbone feature extraction network to enhance the model’s generalization ability and prevent the initialization of model parameters from being too random. Secondly, to address the complex fracture topology and strong non-uniformity of coal-rock combinations, an attention module (ResCBAM) with spatial and channel dimensions is introduced into the up-sampling part to enhance the model's feature extraction ability and alleviate the problem of gradient disappearance. Finally, an asymmetric atrous pyramid module (AC-ASPP) utilizing convolution kernels of different scales is added at the end of the downsampling, which reduced the computational complexity and improved the computational efficiency of the model while keeping the receptive field unchanged. The effectiveness of the model is verified using a dataset of CT scan images of coal-rock combinations. The research results indicate that the VRA-UNet model performs well in crack extraction and recognition, with an average intersection to union ratio, pixel average value, and recognition accuracy of 85.22%, 90.80%, and 91.95%, respectively; Compared with mainstream segmentation networks UNet, PSPNet, DeeplabV3+, FCN, and SegNet the average intersection to union ratio of the VRA-UNet model has increased by 6.05%, 16.7%, 10.77%, 6.87%, and 6.4% respectively. The average pixel value has increased by 7.13%, 13.29%, 12.84%, 7.4%, and 7.53% and the recognition accuracy has risen by 3.82%, 14.45%, 7.4%, 5.58%, and 4.31% respectively; The fractal dimension of the fracture structure identified by VRA-UNet maintains good consistency with the fractal dimension of the original CT scan fracture structure, accurately reproducing the distribution characteristics of the internal fracture structure of the coal-rock combinations.
format Article
id doaj-art-d641911e11664a518f2aa587d4f702d0
institution OA Journals
issn 0253-2336
language zho
publishDate 2025-02-01
publisher Editorial Department of Coal Science and Technology
record_format Article
series Meitan kexue jishu
spelling doaj-art-d641911e11664a518f2aa587d4f702d02025-08-20T02:08:32ZzhoEditorial Department of Coal Science and TechnologyMeitan kexue jishu0253-23362025-02-015329610810.12438/cst.2024-14412024-1441Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet networkDengke WANG0Longhang WANG1Yaguang QIN2Le WEI3Tanggen CAO4Wenrui LI5Lu LI6Xu CHEN7Yuling XIA8State Key Laboratory Cultivation Base for Gas Geology and Gas Controll, Henan Polytechnic University, Jiaozuo 454000, ChinaState Key Laboratory Cultivation Base for Gas Geology and Gas Controll, Henan Polytechnic University, Jiaozuo 454000, ChinaPower China Huadong Engineering Corporation Limited, Hangzhou 311122, ChinaCCTEG Chongqing Research Institute, Chongqing 400037, ChinaSichuan Furong Chuannan Construction Engineering Co., Ltd., Yibin 644000, ChinaState Key Laboratory Cultivation Base for Gas Geology and Gas Controll, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Safety Science and Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaState Key Laboratory Cultivation Base for Gas Geology and Gas Controll, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454000, ChinaIn the 3D reconstruction of coal-rock combinations fractures, in response to the problem that traditional threshold segmentation methods cannot accurately determine the threshold size between coal and rock, resulting in poor fracture segmentation performance, a new VRA-UNet coal-rock combinations fracture identification model based on deep learning theory is proposed, providing an optimized solution for accurate identification of coal-rock combinations fractures. Firstly, the VGG16 module is used as the backbone feature extraction network to enhance the model’s generalization ability and prevent the initialization of model parameters from being too random. Secondly, to address the complex fracture topology and strong non-uniformity of coal-rock combinations, an attention module (ResCBAM) with spatial and channel dimensions is introduced into the up-sampling part to enhance the model's feature extraction ability and alleviate the problem of gradient disappearance. Finally, an asymmetric atrous pyramid module (AC-ASPP) utilizing convolution kernels of different scales is added at the end of the downsampling, which reduced the computational complexity and improved the computational efficiency of the model while keeping the receptive field unchanged. The effectiveness of the model is verified using a dataset of CT scan images of coal-rock combinations. The research results indicate that the VRA-UNet model performs well in crack extraction and recognition, with an average intersection to union ratio, pixel average value, and recognition accuracy of 85.22%, 90.80%, and 91.95%, respectively; Compared with mainstream segmentation networks UNet, PSPNet, DeeplabV3+, FCN, and SegNet the average intersection to union ratio of the VRA-UNet model has increased by 6.05%, 16.7%, 10.77%, 6.87%, and 6.4% respectively. The average pixel value has increased by 7.13%, 13.29%, 12.84%, 7.4%, and 7.53% and the recognition accuracy has risen by 3.82%, 14.45%, 7.4%, 5.58%, and 4.31% respectively; The fractal dimension of the fracture structure identified by VRA-UNet maintains good consistency with the fractal dimension of the original CT scan fracture structure, accurately reproducing the distribution characteristics of the internal fracture structure of the coal-rock combinations.http://www.mtkxjs.com.cn/article/doi/10.12438/cst.2024-1441coal-rock combinationscrack identificationfracture reconstructionconvolutional neural networkfractal dimension
spellingShingle Dengke WANG
Longhang WANG
Yaguang QIN
Le WEI
Tanggen CAO
Wenrui LI
Lu LI
Xu CHEN
Yuling XIA
Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network
Meitan kexue jishu
coal-rock combinations
crack identification
fracture reconstruction
convolutional neural network
fractal dimension
title Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network
title_full Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network
title_fullStr Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network
title_full_unstemmed Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network
title_short Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network
title_sort fracture identification and 3d reconstruction of coal rock combinations based on vra unet network
topic coal-rock combinations
crack identification
fracture reconstruction
convolutional neural network
fractal dimension
url http://www.mtkxjs.com.cn/article/doi/10.12438/cst.2024-1441
work_keys_str_mv AT dengkewang fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT longhangwang fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT yaguangqin fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT lewei fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT tanggencao fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT wenruili fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT luli fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT xuchen fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork
AT yulingxia fractureidentificationand3dreconstructionofcoalrockcombinationsbasedonvraunetnetwork