Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learning

Abstract The propagation of rock fractures is essential for maintaining engineering safety, yet traditional theoretical methods are burdened by challenges such as complex sample collection and lengthy prediction processes. To address these challenges, this study develops a deep learning model based...

Full description

Saved in:
Bibliographic Details
Main Authors: Runze Liu, Ziwei Wang, Yanbo Zhang, Xulong Yao, Shaohong Yan, Zhiyuan Chen, Shuai Wang, Hua Li, Qi Wang
Format: Article
Language:English
Published: Springer 2025-03-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-025-06661-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850040197714018304
author Runze Liu
Ziwei Wang
Yanbo Zhang
Xulong Yao
Shaohong Yan
Zhiyuan Chen
Shuai Wang
Hua Li
Qi Wang
author_facet Runze Liu
Ziwei Wang
Yanbo Zhang
Xulong Yao
Shaohong Yan
Zhiyuan Chen
Shuai Wang
Hua Li
Qi Wang
author_sort Runze Liu
collection DOAJ
description Abstract The propagation of rock fractures is essential for maintaining engineering safety, yet traditional theoretical methods are burdened by challenges such as complex sample collection and lengthy prediction processes. To address these challenges, this study develops a deep learning model based on an adaptive moment estimation optimized convolutional long short-term memory neural network (Adam-ConvLSTM) to predict the evolution of rock fractures. We generated a rock fracture dataset through numerical simulation and then incorporated it into a machine-learning imagework to produce a predictive model. Initially, PFC2D numerical simulations were conducted on rocks with various pore defects under uniaxial compression, resulting in five sets of fracture propagation images. These images were processed using sliding window techniques to construct a foundational dataset. Considering the spatiotemporal correlations among different rock fractures, one dataset was used to train the Adam-ConvLSTM model, yielding an initial model that accurately predicts fracture propagation for a single rock dataset. Utilizing transfer learning, this initial model was adapted and independently fine-tuned for four additional datasets with varying pore defect sizes, resulting in four distinct predictive models. These models were integrated to form a more comprehensive predictive system. In practical applications, the comprehensive model uses structure similarity index measure to align test samples with the most similar images from the model, selecting the predictive model with the most similar images for forecasting fracture evolution. Comparative validation indicates that this comprehensive model outperforms traditional methods and basic deep learning algorithms in both prediction efficiency and accuracy. This model not only enhances the efficiency and precision of rock fracture evolution forecasting but also offers a practical approach for monitoring rock mass fractures, substantially enhancing engineering safety.
format Article
id doaj-art-c4401035eb5c4548bf4c5fb2b2ebd39e
institution DOAJ
issn 3004-9261
language English
publishDate 2025-03-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-c4401035eb5c4548bf4c5fb2b2ebd39e2025-08-20T02:56:09ZengSpringerDiscover Applied Sciences3004-92612025-03-017312610.1007/s42452-025-06661-7Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learningRunze Liu0Ziwei Wang1Yanbo Zhang2Xulong Yao3Shaohong Yan4Zhiyuan Chen5Shuai Wang6Hua Li7Qi Wang8College of Science, North China University of Science and TechnologyCollege of Science, North China University of Science and TechnologyCollege of Mining Engineering, North China University of Science and TechnologyCollege of Mining Engineering, North China University of Science and TechnologyCollege of Science, North China University of Science and TechnologyCollege of Artificial Intelligence, North China University of Science and TechnologyCollege of Mining Engineering, North China University of Science and TechnologyHebei Lron and Steel Group Mining Co.,Ltd.Key Laboratory for Geo-Mechanics and Deep Underground Engineering, China University of Mining & TechnologyAbstract The propagation of rock fractures is essential for maintaining engineering safety, yet traditional theoretical methods are burdened by challenges such as complex sample collection and lengthy prediction processes. To address these challenges, this study develops a deep learning model based on an adaptive moment estimation optimized convolutional long short-term memory neural network (Adam-ConvLSTM) to predict the evolution of rock fractures. We generated a rock fracture dataset through numerical simulation and then incorporated it into a machine-learning imagework to produce a predictive model. Initially, PFC2D numerical simulations were conducted on rocks with various pore defects under uniaxial compression, resulting in five sets of fracture propagation images. These images were processed using sliding window techniques to construct a foundational dataset. Considering the spatiotemporal correlations among different rock fractures, one dataset was used to train the Adam-ConvLSTM model, yielding an initial model that accurately predicts fracture propagation for a single rock dataset. Utilizing transfer learning, this initial model was adapted and independently fine-tuned for four additional datasets with varying pore defect sizes, resulting in four distinct predictive models. These models were integrated to form a more comprehensive predictive system. In practical applications, the comprehensive model uses structure similarity index measure to align test samples with the most similar images from the model, selecting the predictive model with the most similar images for forecasting fracture evolution. Comparative validation indicates that this comprehensive model outperforms traditional methods and basic deep learning algorithms in both prediction efficiency and accuracy. This model not only enhances the efficiency and precision of rock fracture evolution forecasting but also offers a practical approach for monitoring rock mass fractures, substantially enhancing engineering safety.https://doi.org/10.1007/s42452-025-06661-7Rock fracture predictionNumerical simulationConvolutional long short-term memory neural networkAdaptive moment estimationTransfer learningStructure similarity index measure
spellingShingle Runze Liu
Ziwei Wang
Yanbo Zhang
Xulong Yao
Shaohong Yan
Zhiyuan Chen
Shuai Wang
Hua Li
Qi Wang
Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learning
Discover Applied Sciences
Rock fracture prediction
Numerical simulation
Convolutional long short-term memory neural network
Adaptive moment estimation
Transfer learning
Structure similarity index measure
title Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learning
title_full Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learning
title_fullStr Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learning
title_full_unstemmed Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learning
title_short Research on rock fracture evolution prediction model based on Adam-ConvLSTM and transfer learning
title_sort research on rock fracture evolution prediction model based on adam convlstm and transfer learning
topic Rock fracture prediction
Numerical simulation
Convolutional long short-term memory neural network
Adaptive moment estimation
Transfer learning
Structure similarity index measure
url https://doi.org/10.1007/s42452-025-06661-7
work_keys_str_mv AT runzeliu researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT ziweiwang researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT yanbozhang researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT xulongyao researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT shaohongyan researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT zhiyuanchen researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT shuaiwang researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT huali researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning
AT qiwang researchonrockfractureevolutionpredictionmodelbasedonadamconvlstmandtransferlearning