The Rock Burst Hazard Evaluation Using Statistical Learning Approaches

The great threat and destructiveness brought by a rock burst make its prediction and prevention crucial in engineering. The rock burst hazard evaluation at project locations is an effective way of preventing rock burst since currently real-time prediction is not available. Since different control fa...

Full description

Saved in:
Bibliographic Details
Main Authors: Jie Chen, Jingkuan Gao, Yuanyuan Pu, Mingzhong Gao, Like Wei, Chong Wang, Bo Peng, Xusheng Zhao, Guangchao Zhang, Zhigang Zhang
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2021/5576480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850162083895705600
author Jie Chen
Jingkuan Gao
Yuanyuan Pu
Mingzhong Gao
Like Wei
Chong Wang
Bo Peng
Xusheng Zhao
Guangchao Zhang
Zhigang Zhang
author_facet Jie Chen
Jingkuan Gao
Yuanyuan Pu
Mingzhong Gao
Like Wei
Chong Wang
Bo Peng
Xusheng Zhao
Guangchao Zhang
Zhigang Zhang
author_sort Jie Chen
collection DOAJ
description The great threat and destructiveness brought by a rock burst make its prediction and prevention crucial in engineering. The rock burst hazard evaluation at project locations is an effective way of preventing rock burst since currently real-time prediction is not available. Since different control factors and discrimination conditions of rock burst were accepted by conventional risk determination methods, the rock burst risk determination in the same area may produce conflicting results. In this study, Naive Bayes statistical learning models based on different model prior distributions representing highly complicated nonlinear relationship between rock burst hazard and impact factors were built to evaluate the rock burst hazards. The results suggested that the Bayes statistical learning model based on a Gaussian prior has the strongest performance over four preset prior distributions. Combining the rock mechanics parameters measured in the laboratory and the stress data collected on the project sites, the proposed model was successfully employed to evaluate the kimberlite rock burst risk of a diamond mine in Canada. The Bayes statistical learning model exhibits its robustness and generalization in rock burst hazard evaluation, which can be generalized for similar engineering cases with enough supported data.
format Article
id doaj-art-fd8b2301bdfc44f18c85be2594c43c36
institution OA Journals
issn 1070-9622
1875-9203
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-fd8b2301bdfc44f18c85be2594c43c362025-08-20T02:22:39ZengWileyShock and Vibration1070-96221875-92032021-01-01202110.1155/2021/55764805576480The Rock Burst Hazard Evaluation Using Statistical Learning ApproachesJie Chen0Jingkuan Gao1Yuanyuan Pu2Mingzhong Gao3Like Wei4Chong Wang5Bo Peng6Xusheng Zhao7Guangchao Zhang8Zhigang Zhang9State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, ChinaState Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, ChinaState Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, ChinaCollege of Water Resources and Hydropower, Sichuan University, Chengdu 610065, ChinaInformation Research Institute, Ministry of Emergency Management, Beijing 100029, ChinaInformation Research Institute, Ministry of Emergency Management, Beijing 100029, ChinaSichuan Coal Industry Group Limited Liability Company, Chengdu 610091, ChinaChina Coal Technology and Engineering Group Chongqing Research Institute, Chongqing 400037, ChinaCollege of Energy and Mining Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaState Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, ChinaThe great threat and destructiveness brought by a rock burst make its prediction and prevention crucial in engineering. The rock burst hazard evaluation at project locations is an effective way of preventing rock burst since currently real-time prediction is not available. Since different control factors and discrimination conditions of rock burst were accepted by conventional risk determination methods, the rock burst risk determination in the same area may produce conflicting results. In this study, Naive Bayes statistical learning models based on different model prior distributions representing highly complicated nonlinear relationship between rock burst hazard and impact factors were built to evaluate the rock burst hazards. The results suggested that the Bayes statistical learning model based on a Gaussian prior has the strongest performance over four preset prior distributions. Combining the rock mechanics parameters measured in the laboratory and the stress data collected on the project sites, the proposed model was successfully employed to evaluate the kimberlite rock burst risk of a diamond mine in Canada. The Bayes statistical learning model exhibits its robustness and generalization in rock burst hazard evaluation, which can be generalized for similar engineering cases with enough supported data.http://dx.doi.org/10.1155/2021/5576480
spellingShingle Jie Chen
Jingkuan Gao
Yuanyuan Pu
Mingzhong Gao
Like Wei
Chong Wang
Bo Peng
Xusheng Zhao
Guangchao Zhang
Zhigang Zhang
The Rock Burst Hazard Evaluation Using Statistical Learning Approaches
Shock and Vibration
title The Rock Burst Hazard Evaluation Using Statistical Learning Approaches
title_full The Rock Burst Hazard Evaluation Using Statistical Learning Approaches
title_fullStr The Rock Burst Hazard Evaluation Using Statistical Learning Approaches
title_full_unstemmed The Rock Burst Hazard Evaluation Using Statistical Learning Approaches
title_short The Rock Burst Hazard Evaluation Using Statistical Learning Approaches
title_sort rock burst hazard evaluation using statistical learning approaches
url http://dx.doi.org/10.1155/2021/5576480
work_keys_str_mv AT jiechen therockbursthazardevaluationusingstatisticallearningapproaches
AT jingkuangao therockbursthazardevaluationusingstatisticallearningapproaches
AT yuanyuanpu therockbursthazardevaluationusingstatisticallearningapproaches
AT mingzhonggao therockbursthazardevaluationusingstatisticallearningapproaches
AT likewei therockbursthazardevaluationusingstatisticallearningapproaches
AT chongwang therockbursthazardevaluationusingstatisticallearningapproaches
AT bopeng therockbursthazardevaluationusingstatisticallearningapproaches
AT xushengzhao therockbursthazardevaluationusingstatisticallearningapproaches
AT guangchaozhang therockbursthazardevaluationusingstatisticallearningapproaches
AT zhigangzhang therockbursthazardevaluationusingstatisticallearningapproaches
AT jiechen rockbursthazardevaluationusingstatisticallearningapproaches
AT jingkuangao rockbursthazardevaluationusingstatisticallearningapproaches
AT yuanyuanpu rockbursthazardevaluationusingstatisticallearningapproaches
AT mingzhonggao rockbursthazardevaluationusingstatisticallearningapproaches
AT likewei rockbursthazardevaluationusingstatisticallearningapproaches
AT chongwang rockbursthazardevaluationusingstatisticallearningapproaches
AT bopeng rockbursthazardevaluationusingstatisticallearningapproaches
AT xushengzhao rockbursthazardevaluationusingstatisticallearningapproaches
AT guangchaozhang rockbursthazardevaluationusingstatisticallearningapproaches
AT zhigangzhang rockbursthazardevaluationusingstatisticallearningapproaches