岩体爆破效应预测的一种新方法
|
摘要
高斯过程是一种最近发展起来新的机器学习技术,对处理非线性复杂问题具有很好的适应性。岩体爆破效应与其影响因素之间是复杂的非线性关系,针对传统方法的局限性,提出一种基于高斯过程的岩体爆破效应预测的新方法,建立相应的岩体爆破效应预测模型,并应用于三峡工程坝区岩体爆破振动速度、爆破损伤深度与损伤半径的预测。通过三峡现场爆破试验数据,建立训练数据集和测试数据集,采用高斯过程方法建立爆破效应与影响因素之间的各影响因素之间的非线性映射关系。研究结果表明,岩体爆破振动速度、爆破损伤深度与损伤半径的预测结果与现场试验结果比较吻合,用高斯过程方法预测岩体爆破效应是科学可行的。与神经网络方法相比,高斯过程方法具有算法参数自适应化的特点,且适用于小样本问题,预测精度高,并易于实现,具有良好的工程应用前景。
Gaussian process(GP) is a newly developed machine learning technology based on statistical theoretical fundamentals.It has become a powerful tool for solving highly nonlinear problems.Conventional methods for forecasting of blasting effect in rock mass often meet great difficulty since relationship between blasting effect and its influencing factors is highly complicated nonlinear one.A new method based on GP is proposed for forecasting of blasting effect in rock mass.The method is applied to blasting engineering of the Three Gorges project in China for forecasting of vibration speed,damage depth and damage radius in rock mass.The field experiments of rock blasting are preformed to obtain the training samples and test samples.Nonlinear mapping relationship between blasting effect and its influencing factors can be constructed by GP learning with the training samples.The prediction results for vibration speed,damage depth and damage radius in rock mass using the method are in good agreement with observations.The results of case studies show that the method is feasible,effective and simple to implement for forecasting of blasting effect prediction in rock mass.It has merits of self-adaptive parameters determination and better capacity for solving nonlinear small sample problems comparing with the artificial neural networks method.The good performance of GP model makes it very attractive for a wide range of application in geotechnical engineering.
Gaussian process(GP) is a newly developed machine learning technology based on statistical theoretical fundamentals.It has become a powerful tool for solving highly nonlinear problems.Conventional methods for forecasting of blasting effect in rock mass often meet great difficulty since relationship between blasting effect and its influencing factors is highly complicated nonlinear one.A new method based on GP is proposed for forecasting of blasting effect in rock mass.The method is applied to blasting engineering of the Three Gorges project in China for forecasting of vibration speed,damage depth and damage radius in rock mass.The field experiments of rock blasting are preformed to obtain the training samples and test samples.Nonlinear mapping relationship between blasting effect and its influencing factors can be constructed by GP learning with the training samples.The prediction results for vibration speed,damage depth and damage radius in rock mass using the method are in good agreement with observations.The results of case studies show that the method is feasible,effective and simple to implement for forecasting of blasting effect prediction in rock mass.It has merits of self-adaptive parameters determination and better capacity for solving nonlinear small sample problems comparing with the artificial neural networks method.The good performance of GP model makes it very attractive for a wide range of application in geotechnical engineering.
引文
[1]黄理兴,陈奕柏.我国岩石动力学研究状况与发展[J].岩石力学与工程学报,2003,22(11):1 881–1 886.(HUANG Lixing,CHEN Yibai.Rock dynamics in China:past,present and future[J].Chinese Journal of Rock Mechanics and Engineering,2003,22(11):1 881–1 886.(in Chinese))
[2]陈超,甘德清,张云鹏.预裂爆破效果的综合模糊评价模型[J].河北理工学院学报,2001,23(4):14–18.(CHEN Chao,GAN Deqing,ZHANG Yunpeng.The fuzzy synthesize model of evaluating blasting effect[J].Journal of Hebei Institute of Technology,2001,23(4):14–18.(in Chinese))
[3]杨溢,张智宇,庙延钢,等.灰色关联分析在预裂爆破振动分析中的应用[J].云南冶金,2001,30(5):1–3.(YANG Yi,ZHANG Zhiyu,MIAO Yangang,et al.Application of gray association analysis for analyzing vibration in presplitting blasting[J].Yunnan Metallurgy,2001,30(5):1–3.(in Chinese))
[4]ZHU H B,WU L.Application of gray correlation analysis and artificial neural network in rock mass blasting[J].Journal of Coal Science and Engineering,2005,11(1):44–47.
[5]许全军,刘强,聂渝军,等.爆破地震峰值预报神经网络研究[J].爆炸与冲击,1999,19(2):133–138.(XU Quanjun,LIU Qiang,NIE Yujun,et al.Study on neural network prediction on peak particle amplitude of blasting ground vibration[J].Explosion and Shock Waves,1999,19(2):133–138.(in Chinese))
[6]陈德志,朱瑞赓,徐顺香.基于BP神经网络的路堑爆破对邻近民房安全预测的研究[J].岩石力学与工程学报,2002,21(增2):2 554–2 557(CHEN Dezhi,ZHU Ruigeng,XU Shunxiang.BP neural network study on safety prediction for civil houses adjacent to roadcut blasting[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(Supp.2):2 554–2 557.(in Chinese))
[7]王长友,唐又驰,刘涛.光面爆破效果BP神经网络预测[J].辽宁工程技术大学学报,2005,24(1):73–75.(WANG Changyou,TANG Youchi,LIU Tao.Study on forecasting smooth-surface blasting effects based on BP neural network[J].Journal of Liaoning Technical University,2005,24(1):73–75.(in Chinese))
[8]MACKAY D J C.Introduction to Gaussian processes[R].Cambridge:Cavendish Laboratory,Cambridge University,UK,1998.
[9]WILLIAMS C K I.Prediction with Gaussian processes:from the linear regression to linear prediction and beyond[C]//Learning and Inference in Graphical Models.[S.l.]:Kluwer Academic Press,1998:599–621.
[10]SEEGER M.Gaussian processes for machine learning[J].International Journal of Neural System,2004,14(2):69–106.
[11]CASTO L,OPPER M.Sparse online Gaussian process[J].Neural Computation,2002,14(3):641–668.
[12]BRAHIM-BELHOUARI S,BERMAK A.Gaussian process for nonstationary times series prediction[J].Computational Statistics and Data Analysis,2004,47(4):705–712.
[13]熊志化,张继承,邵惠鹤.基于高斯过程的软测量建模[J].系统仿真学报,2005,17(4):793–794,800.(XIONG Zhihua,ZHANG Jicheng,SHAO Huihe.GP-based soft sensor modeling[J].Journal of System Simulation,2005,17(4):793–794,800.(in Chinese))
[14]RASMUSSEN C E,WILLIAMS K I.Gaussian processes for machine learning[M].Massachusetts:MIT Press,2006.
[15]蔡德所.基于前馈网络的岩体爆破效应预测研究[J].岩土工程学报,1997,19(1):43–49.(CAI Desuo.Forecast research on effect of vibration and damage in rock mass blasting[J].Chinese Journal of Geotechnical Engineering,1997,19(1):43–49.(in Chinese))
[2]陈超,甘德清,张云鹏.预裂爆破效果的综合模糊评价模型[J].河北理工学院学报,2001,23(4):14–18.(CHEN Chao,GAN Deqing,ZHANG Yunpeng.The fuzzy synthesize model of evaluating blasting effect[J].Journal of Hebei Institute of Technology,2001,23(4):14–18.(in Chinese))
[3]杨溢,张智宇,庙延钢,等.灰色关联分析在预裂爆破振动分析中的应用[J].云南冶金,2001,30(5):1–3.(YANG Yi,ZHANG Zhiyu,MIAO Yangang,et al.Application of gray association analysis for analyzing vibration in presplitting blasting[J].Yunnan Metallurgy,2001,30(5):1–3.(in Chinese))
[4]ZHU H B,WU L.Application of gray correlation analysis and artificial neural network in rock mass blasting[J].Journal of Coal Science and Engineering,2005,11(1):44–47.
[5]许全军,刘强,聂渝军,等.爆破地震峰值预报神经网络研究[J].爆炸与冲击,1999,19(2):133–138.(XU Quanjun,LIU Qiang,NIE Yujun,et al.Study on neural network prediction on peak particle amplitude of blasting ground vibration[J].Explosion and Shock Waves,1999,19(2):133–138.(in Chinese))
[6]陈德志,朱瑞赓,徐顺香.基于BP神经网络的路堑爆破对邻近民房安全预测的研究[J].岩石力学与工程学报,2002,21(增2):2 554–2 557(CHEN Dezhi,ZHU Ruigeng,XU Shunxiang.BP neural network study on safety prediction for civil houses adjacent to roadcut blasting[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(Supp.2):2 554–2 557.(in Chinese))
[7]王长友,唐又驰,刘涛.光面爆破效果BP神经网络预测[J].辽宁工程技术大学学报,2005,24(1):73–75.(WANG Changyou,TANG Youchi,LIU Tao.Study on forecasting smooth-surface blasting effects based on BP neural network[J].Journal of Liaoning Technical University,2005,24(1):73–75.(in Chinese))
[8]MACKAY D J C.Introduction to Gaussian processes[R].Cambridge:Cavendish Laboratory,Cambridge University,UK,1998.
[9]WILLIAMS C K I.Prediction with Gaussian processes:from the linear regression to linear prediction and beyond[C]//Learning and Inference in Graphical Models.[S.l.]:Kluwer Academic Press,1998:599–621.
[10]SEEGER M.Gaussian processes for machine learning[J].International Journal of Neural System,2004,14(2):69–106.
[11]CASTO L,OPPER M.Sparse online Gaussian process[J].Neural Computation,2002,14(3):641–668.
[12]BRAHIM-BELHOUARI S,BERMAK A.Gaussian process for nonstationary times series prediction[J].Computational Statistics and Data Analysis,2004,47(4):705–712.
[13]熊志化,张继承,邵惠鹤.基于高斯过程的软测量建模[J].系统仿真学报,2005,17(4):793–794,800.(XIONG Zhihua,ZHANG Jicheng,SHAO Huihe.GP-based soft sensor modeling[J].Journal of System Simulation,2005,17(4):793–794,800.(in Chinese))
[14]RASMUSSEN C E,WILLIAMS K I.Gaussian processes for machine learning[M].Massachusetts:MIT Press,2006.
[15]蔡德所.基于前馈网络的岩体爆破效应预测研究[J].岩土工程学报,1997,19(1):43–49.(CAI Desuo.Forecast research on effect of vibration and damage in rock mass blasting[J].Chinese Journal of Geotechnical Engineering,1997,19(1):43–49.(in Chinese))
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心