Predicting triaxial compressive strength of high-temperature treated rock using machine learning techniques  

作　　者：Xunjian Hu Junjie Shentu Ni Xie Yujie Huang Gang Lei Haibo Hu Panpan Guo Xiaonan Gong 

机构地区：[1]Research Center of Coastal and Urban Geotechnical Engineering,Zhejiang University,Hangzhou,310058,China [2]Faculty of Engineering,China University of Geosciences(Wuhan),Wuhan,430074,China [3]School of Mechanical Engineering,North University of China,Taiyuan,030051,China [4]Beijing Urban Construction Design and Development Group Co.,Ltd.,Beijing,100037,China

出　　处：《Journal of Rock Mechanics and Geotechnical Engineering》2023年第8期2072-2082,共11页岩石力学与岩土工程学报（英文版）

基　　金：We acknowledge the funding support from the National Natural Science Foundation of China(Grant No.51778575);Postdoctoral Science Foundation of China(Grant No.2021M692481);Fundamental Research Funds for the Central Universities of China(Grant No.2042021kf0055).The authors would like to thank the anonymous reviewers and editors for their constructive suggestions which greatly improve the quality of this paper.The authors are also grateful for the permission from Elsevier.

摘　　要：The accurate prediction of the strength of rocks after high-temperature treatment is important for the safety maintenance of rock in deep underground engineering.Five machine learning(ML)techniques were adopted in this study,i.e.back propagation neural network(BPNN),AdaBoost-based classification and regression tree(AdaBoost-CART),support vector machine(SVM),K-nearest neighbor(KNN),and radial basis function neural network(RBFNN).A total of 351 data points with seven input parameters(i.e.diameter and height of specimen,density,temperature,confining pressure,crack damage stress and elastic modulus)and one output parameter(triaxial compressive strength)were utilized.The root mean square error(RMSE),mean absolute error(MAE)and correlation coefficient(R)were used to evaluate the prediction performance of the five ML models.The results demonstrated that the BPNN shows a better prediction performance than the other models with RMSE,MAE and R values on the testing dataset of 15.4 MPa,11.03 MPa and 0.9921,respectively.The results indicated that the ML techniques are effective for accurately predicting the triaxial compressive strength of rocks after different high-temperature treatments.

关 键 词：Machine learning(ML) Triaxial compressive strength Temperature Confining pressure Crack damage stress 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TU45[自动化与计算机技术—控制科学与工程]