Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods

The degree of rock mass discontinuity is crucial for evaluating surrounding rock quality, yet its accurate and rapid measurement at construction sites remains challenging. This study utilizes fractal dimension to characterize the geometric characteristics of rock mass discontinuity and develops a da...

Full description

Bibliographic Details
Main Authors: Ma, Junjie, Li, Tianbin, Shirani Faradonbeh, Roohollah, Sharifzadeh, Mostafa, Wang, Jianfeng, Huang, Yuyang, Materials, Chunchi, Peng, Feng, Zhang, Hang
Format: Journal Article
Published: MDPI 2024
Online Access:http://hdl.handle.net/20.500.11937/96385
_version_ 1848766145400668160
author Ma, Junjie
Li, Tianbin
Shirani Faradonbeh, Roohollah
Sharifzadeh, Mostafa
Wang, Jianfeng
Huang, Yuyang
Materials, Chunchi
Peng, Feng
Zhang, Hang
author_facet Ma, Junjie
Li, Tianbin
Shirani Faradonbeh, Roohollah
Sharifzadeh, Mostafa
Wang, Jianfeng
Huang, Yuyang
Materials, Chunchi
Peng, Feng
Zhang, Hang
author_sort Ma, Junjie
building Curtin Institutional Repository
collection Online Access
description The degree of rock mass discontinuity is crucial for evaluating surrounding rock quality, yet its accurate and rapid measurement at construction sites remains challenging. This study utilizes fractal dimension to characterize the geometric characteristics of rock mass discontinuity and develops a data-driven surrounding rock classification (SRC) model integrating machine learning algorithms. Initially, the box-counting method was introduced to calculate the fractal dimension of discontinuity from the excavation face image. Subsequently, crucial parameters affecting surrounding rock quality were analyzed and selected, including rock strength, the fractal dimension of discontinuity, the discontinuity condition, the in-situ stress condition, the groundwater condition, and excavation orientation. This study compiled a database containing 246 railway and highway tunnel cases based on these parameters. Then, four SRC models were constructed, integrating Bayesian optimization (BO) with support vector machine (SVM), random forest (RF), adaptive boosting (AdaBoost), and gradient boosting decision tree (GBDT) algorithms. Evaluation indicators, including 5-fold cross-validation, precision, recall, F1-score, micro-F1-score, macro-F1-score, accuracy, and the receiver operating characteristic curve, demonstrated the GBDT-BO model’s superior robustness in learning and generalization compared to other models. Furthermore, four additional excavation face cases validated the intelligent SRC approach’s practicality. Finally, the synthetic minority over-sampling technique was employed to balance the training set. Subsequent retraining and evaluation confirmed that the imbalanced dataset does not adversely affect SRC model performance. The proposed GBDT-BO model shows promise for predicting surrounding rock quality and guiding dynamic tunnel excavation and support.
first_indexed 2025-11-14T11:46:29Z
format Journal Article
id curtin-20.500.11937-96385
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:46:29Z
publishDate 2024
publisher MDPI
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-963852025-01-09T06:03:09Z Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods Ma, Junjie Li, Tianbin Shirani Faradonbeh, Roohollah Sharifzadeh, Mostafa Wang, Jianfeng Huang, Yuyang Materials, Chunchi Peng, Feng Zhang, Hang The degree of rock mass discontinuity is crucial for evaluating surrounding rock quality, yet its accurate and rapid measurement at construction sites remains challenging. This study utilizes fractal dimension to characterize the geometric characteristics of rock mass discontinuity and develops a data-driven surrounding rock classification (SRC) model integrating machine learning algorithms. Initially, the box-counting method was introduced to calculate the fractal dimension of discontinuity from the excavation face image. Subsequently, crucial parameters affecting surrounding rock quality were analyzed and selected, including rock strength, the fractal dimension of discontinuity, the discontinuity condition, the in-situ stress condition, the groundwater condition, and excavation orientation. This study compiled a database containing 246 railway and highway tunnel cases based on these parameters. Then, four SRC models were constructed, integrating Bayesian optimization (BO) with support vector machine (SVM), random forest (RF), adaptive boosting (AdaBoost), and gradient boosting decision tree (GBDT) algorithms. Evaluation indicators, including 5-fold cross-validation, precision, recall, F1-score, micro-F1-score, macro-F1-score, accuracy, and the receiver operating characteristic curve, demonstrated the GBDT-BO model’s superior robustness in learning and generalization compared to other models. Furthermore, four additional excavation face cases validated the intelligent SRC approach’s practicality. Finally, the synthetic minority over-sampling technique was employed to balance the training set. Subsequent retraining and evaluation confirmed that the imbalanced dataset does not adversely affect SRC model performance. The proposed GBDT-BO model shows promise for predicting surrounding rock quality and guiding dynamic tunnel excavation and support. 2024 Journal Article http://hdl.handle.net/20.500.11937/96385 10.3390/fractalfract8120677 http://creativecommons.org/licenses/by/4.0/ MDPI fulltext
spellingShingle Ma, Junjie
Li, Tianbin
Shirani Faradonbeh, Roohollah
Sharifzadeh, Mostafa
Wang, Jianfeng
Huang, Yuyang
Materials, Chunchi
Peng, Feng
Zhang, Hang
Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods
title Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods
title_full Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods
title_fullStr Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods
title_full_unstemmed Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods
title_short Data-Driven Approach for Intelligent Classification of Tunnel Surrounding Rock Using Integrated Fractal and Machine Learning Methods
title_sort data-driven approach for intelligent classification of tunnel surrounding rock using integrated fractal and machine learning methods
url http://hdl.handle.net/20.500.11937/96385