将无损检测技术与机器学习相结合,通过建立预测模型来快速确定岩石抗拉强度已经成为热门研究方向之一。为了建立预测模型,提出一种基于多元自适应回归样条(MARS)的数据驱动建模技术,用于岩石抗拉强度预测。共收集了80组试验数据,包括施密特回弹数、干密度、点荷载强度指数以及巴西抗拉强度。所有数据被随机分为2个部分,其中70%的数据用于训练模型,剩余30%的数据用于测试模型性能。同时开发了人工神经网络、支持向量机和决策树3种数据驱动模型。选择了4种常用的模型性能评价指标,分别为均方根误差、平均绝对误差、相关系数和决定系数,以此来对所开发模型的预测性能进行比较。结果表明:所开发的智能模型均能够提供较高的预测精度,其中MARS模型性能优于其他3种模型,支持向量机和人工神经网络模型次之,决策树模型相对较差。值得一提的是,MARS模型能够通过方差分析来评估每个变量的相对重要性。研究成果有助于快速确定岩石抗拉强度。
Abstract
The prediction model which integrates non-destructive testing and machine learning has emerged as a hotspot for predicting tensile strength of rock. This paper presents a data-driven modeling approach for predicting rock’s tensile strength based on Multivariate Adaptive Regression Splines (MARS). An experimental dataset comprising 80 data sets, including Schmidt hammer rebound number, dry density, point load strength index, and Brazilian tensile strength, was collected. The dataset was randomly divided into training (70%) and testing (30%) sets. Additionally, artificial neural network (ANN), support vector machine (SVM), and decision tree (DT) techniques were utilized to develop machine learning models. The performance of the MARS model was compared with those of the DT, ANN, and SVM models. The predictive accuracy of the developed models was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MSE), coefficient of correlation, and coefficient of determination. The results manifested the satisfactory predictability of the machine learning models, with the MARS model exhibiting optimal performance, followed by SVM model, ANN model, and DT model in descending order. Notably, MARS was able to assess the relative importance of each variable through ANOVA decomposition. The model presented in this paper is conducive to rapidly obtaining the tensile strength of rock.
关键词
岩石力学 /
抗拉强度 /
多元自适应回归样条(MARS) /
机器学习 /
预测模型
Key words
rock mechanics /
tensile strength of rock /
Multivariate Adaptive Regression Splines(MARS) /
machine learning /
prediction model
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 闵 明, 张 强, 蒋斌松, 等. 实时高温下北山花岗岩劈裂试验及声发射特性[J]. 长江科学院院报, 2020, 37(3): 108-113. (MIN Ming, ZHANG Qiang, JIANG Bin-song, et al. Splitting Tests and Acoustic Emission Characteristics of Beishan Granite under Real-time High Temperature[J]. Journal of Yangtze River Scientific Research Institute, 2020, 37(3): 108-113.(in Chinese))
[2] DIEDERICHS M S,KAISER P K.Tensile Strength and Abutment Relaxation as Failure Control Mechanisms in Underground Excavations[J]. International Journal of Rock Mechanics and Mining Sciences,1999,36(1):69-96.
[3] GB/T 50266—99, 工程岩体试验方法标准[S]. 北京: 中国水利水电出版社, 2001.(GB/T 50266—99,Standard of Test Methods for Engineering Rock Mass[S]. Beijing: China Water Resources and Hydropower Press, 2001.(in Chinese))
[4] SL 264—2001, 水利水电工程岩石试验规程[S]. 北京: 中国水利水电出版社, 2001. (SL 264—2001, Specifications for Rock Tests in Water Conservancy and Hydroelectric Engineering[S]. Beijing: China Water & Power Press, 2001. (in Chinese))
[5] ISRM. Suggested Methods for Determining Tensile Strength of Rock Materials[J]. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, 1978, 15(3): 99-103.
[6] 尤明庆,苏承东.平台巴西圆盘劈裂和岩石抗拉强度的试验研究[J].岩石力学与工程学报,2004,23(18):3106-3112.(YOU Ming-qing,SU Cheng-dong.Experimental Study on Split Test with Flattened Disk and Tensile Strength of Rock[J]. Chinese Journal of Rock Mechanics and Engineering,2004,23(18):3106-3112.(in Chinese))
[7] 黄耀光, 王连国, 陈家瑞, 等. 平台巴西劈裂试验确定岩石抗拉强度的理论分析[J]. 岩土力学, 2015, 36(3): 739-748. (HUANG Yao-guang, WANG Lian-guo, CHEN Jia-rui, et al. Theoretical Analysis of Flattened Brazilian Splitting Test for Determining Tensile Strength of Rocks[J]. Rock and Soil Mechanics, 2015, 36(3): 739-748.(in Chinese))
[8] 魏 炯, 朱万成, 李如飞, 等. 岩石抗拉强度和断裂韧度的三点弯曲试验研究[J]. 水利与建筑工程学报, 2016, 14(3): 128-132, 142. (WEI Jiong, ZHU Wan-cheng, LI Ru-fei, et al. Experiment of the Tensile Strength and Fracture Toughness of Rock Using Notched Three Point Bending Test[J]. Journal of Water Resources and Architectural Engineering, 2016, 14(3): 128-132, 142.(in Chinese))
[9] 杨立云, 王志斌, 张 鹏, 等. 考虑尺寸效应和加载方式的砂岩抗拉强度统计模型[J]. 长江科学院院报, 2022, 39(11): 94-101. (YANG Li-yun, WANG Zhi-bin, ZHANG Peng, et al. A Statistical Model of Tensile Strength of Sandstone in Consideration of Size Effect and Loading Mode[J]. Journal of Yangtze River Scientific Research Institute, 2022, 39(11): 94-101.(in Chinese))
[10]COLBACK P S B.An Analysis of Brittle Fracture Initiation and Propagation in the Brazilian Test[C]∥ISRM. Proceedings of 1st ISRM Congress,Lisbon,September 25-October 1,1966: 66.
[11]CHEN C S, HSU S C. Measurement of Indirect Tensile Strength of Anisotropic Rocks by the Ring Test[J]. Rock Mechanics and Rock Engineering,2001,34(4):293-321.
[12]MISHRA D A,BASU A.Use of the Block Punch Test to Predict the Compressive and Tensile Strengths of Rocks[J]. International Journal of Rock Mechanics and Mining Sciences,2012,51:119-127.
[13]MAHDIYAR A, ARMAGHANI D J, MARTO A, et al. Rock Tensile Strength Prediction Using Empirical and Soft Computing Approaches[J]. Bulletin of Engineering Geology and the Environment, 2019, 78(6): 4519-4531.
[14]PALCHIK V,HATZOR Y H.The Influence of Porosity on Tensile and Compressive Strength of Porous Chalks[J].Rock Mechanics and Rock Engineering,2004,37(4):331-341.
[15]KILI A, TEYMEN A. Determination of Mechanical Properties of Rocks Using Simple Methods[J]. Bulletin of Engineering Geology and the Environment, 2008, 67(2): 237-244.
[16]BEHNIA D,BEHNIA M,SHAHRIAR K,et al. A New Predictive Model for Rock Strength Parameters Utilizing GEP Method[J]. Procedia Engineering,2017,191:591-599.
[17]HASANIPANAH M,ZHANG W,ARMAGHANI D J,et al. The Potential Application of a New Intelligent Based Approach in Predicting the Tensile Strength of Rock[J]. IEEE Access, 2020, 8: 57148-57157.
[18]PARSAJOO M, ARMAGHANI D J, MOHAMMED A S, et al. Tensile Strength Prediction of Rock Material Using Non-destructive Tests: A Comparative Intelligent Study[J]. Transportation Geotechnics,2021,31:100652.
[19]HUANG L, ASTERIS P G, KOOPIALIPOOR M, et al. Invasive Weed Optimization Technique-based ANN to the Prediction of Rock Tensile Strength[J]. Applied Sciences, 2019(24): 5372.
[20]ANAKCI H,PALA M.Tensile Strength of Basalt from a Neural Network[J].Engineering Geology,2007,94(1/2):10-18.
[21]YILMAZ I, YUKSEK A G. An Example of Artificial Neural Network (ANN) Application for Indirect Estimation of Rock Parameters[J]. Rock Mechanics and Rock Engineering, 2008, 41(5): 781-795.
[22]HARANDIZADEH H, ARMAGHANI D J, MOHAMAD E T. Development of Fuzzy-GMDH Model Optimized by GSA to Predict Rock Tensile Strength Based on Experimental Datasets[J]. Neural Computing and Applications, 2020, 32(17): 14047-14067.
[23]FRIEDMAN J H.Multivariate Adaptive Regression Splines[J]. The Annals of Statistics,1991,19(1):1-141.
[24]TAYLOR K E.Summarizing Multiple Aspects of Model Performance in a Single Diagram[J]. Journal of Geophysical Research: Atmospheres,2001,106(D7):7183-7192.
基金
国家自然科学基金青年基金项目(52008080)
PDF(1198 KB)
