基于人工神经网络模型的岩石特性预测
|
摘要
近年来,软计算技术被用作替代的统计工具。如人工神经网络(ANN)被用于开发预测模型来估计所需的参数。在本研究中,通过利用冲击钻进过程中的一些钻进参数(气压、推力、钻头直径、穿透率)和所产生的声级,建立了预测岩石性质的神经网络模型。在实验室中所产生的数据,用于开发预测岩石特性(如单轴抗压强度、耐磨性、抗拉强度和施密特回弹数)的神经网络模型,并使用各种预测性能指标对所建模型进行检验,结果表明人工神经网络模型适用于岩石性质的预测。
In recent years,soft computing technology has been used as an alternative statistical tool.The artificial neural network(ANN)is used to develop predictive models to estimate the required parameters.In this study,a neural network model for predicting rock properties was established by using some of the drilling parameters(pressure,thrust,bit diameter,penetration)and the resulting sound level during the impact drilling process.Data generated in the laboratory was used for the development of neural network models that predict rock properties such as uniaxial compressive strength,wear resistance,tensile strength,and Schmidt rebound number.The models were tested with various predictive performance indicators and the results show that the artificial neural network model is suitable for the prediction of rock properties.
In recent years,soft computing technology has been used as an alternative statistical tool.The artificial neural network(ANN)is used to develop predictive models to estimate the required parameters.In this study,a neural network model for predicting rock properties was established by using some of the drilling parameters(pressure,thrust,bit diameter,penetration)and the resulting sound level during the impact drilling process.Data generated in the laboratory was used for the development of neural network models that predict rock properties such as uniaxial compressive strength,wear resistance,tensile strength,and Schmidt rebound number.The models were tested with various predictive performance indicators and the results show that the artificial neural network model is suitable for the prediction of rock properties.
引文
[1] T.N.Singh,R.Kanchan,A.K.Verma,et al.,An intelligent approach for prediction of triaxial properties using unconfined uniaxial strength[J].Min.Eng.2003,(5),12-16.
[2]葛宏伟,梁艳春,刘玮,等.人工神经网络与遗传算法在岩石力学中的应用[J].岩石力学与工程学报,2004,23(9):1542-1550.GE Hongwei,LIANG Yanchun,LIU Wei,et al.Application of artificial neural network and genetic algorithms to rock mechanics[J].Chinese Journal of Rock Mechanics and Engineering,2002,23(9):1542-1550.
[3] Masood.Estimation of sound level produced during drilling of igneous rock samples using aportable drill set-up[J].Procedia Earth and Planetary Science,2015,(11):469-482.
[4] Sonmez H.,Gokceoglu C.,Nefeslioglu H.A.,et al.Estimation of rock modulus-For intact rocks with an artificial neural network and for rock masses with a new empirical equation[J].International Journal of Rock Mechanics and Mining Sciences,2006,43:224-235.
[5]魏莉萍.利用人工神经元网络预测岩石及岩体力学性态的研究[D].北京:北方交通大学,1993.WEI Liping.Study on the prediction of rock and rock mechanics by artificial neural network[D].Beijing:North Jiaotong University,1993.
[6] Zborovjan M.,Lesso I.,Dorcak L.Acoustic identification of rocks during drilling process[J].Journal of Acta Montanistica Slovaca,2003,8(4):91-93.
[7] Miklusova V.,Usalova L.,Ivanicova L.,et al.Acoustic signal-new feature in monitoring of rock disintegration process[J].Contributions to Geophysics and Geodesy,2006,36:125-133.
[8] Harsha Vardhan,Ch.S.N.Murthy.An experimental investigation of jack hammer drill noise with special emphasis on drilling in rocks of different compressive strengths[J].Journal of Noise Control Engineering,2007,55(3):282-293.
[9] Singh T.N.,Kanchan R.,Verma A.K.,et al.An intelligent approach for prediction of triaxial properties using unconfined uniaxial strength[J].Mining Engineering Journal,2003,(5):12-16.
[10] Janach W.,Merminod A.Rock abrasivity test with a modified Schmidt hammer[J].International Journal of Rock Mechanics and Mining Sciences,1982,19:43-45.
[11] Hornik K,Stinchombe J,White H.Multilayer feed forward networks are universal approximators[J].Neural Networks,1989,2:359-366.
[2]葛宏伟,梁艳春,刘玮,等.人工神经网络与遗传算法在岩石力学中的应用[J].岩石力学与工程学报,2004,23(9):1542-1550.GE Hongwei,LIANG Yanchun,LIU Wei,et al.Application of artificial neural network and genetic algorithms to rock mechanics[J].Chinese Journal of Rock Mechanics and Engineering,2002,23(9):1542-1550.
[3] Masood.Estimation of sound level produced during drilling of igneous rock samples using aportable drill set-up[J].Procedia Earth and Planetary Science,2015,(11):469-482.
[4] Sonmez H.,Gokceoglu C.,Nefeslioglu H.A.,et al.Estimation of rock modulus-For intact rocks with an artificial neural network and for rock masses with a new empirical equation[J].International Journal of Rock Mechanics and Mining Sciences,2006,43:224-235.
[5]魏莉萍.利用人工神经元网络预测岩石及岩体力学性态的研究[D].北京:北方交通大学,1993.WEI Liping.Study on the prediction of rock and rock mechanics by artificial neural network[D].Beijing:North Jiaotong University,1993.
[6] Zborovjan M.,Lesso I.,Dorcak L.Acoustic identification of rocks during drilling process[J].Journal of Acta Montanistica Slovaca,2003,8(4):91-93.
[7] Miklusova V.,Usalova L.,Ivanicova L.,et al.Acoustic signal-new feature in monitoring of rock disintegration process[J].Contributions to Geophysics and Geodesy,2006,36:125-133.
[8] Harsha Vardhan,Ch.S.N.Murthy.An experimental investigation of jack hammer drill noise with special emphasis on drilling in rocks of different compressive strengths[J].Journal of Noise Control Engineering,2007,55(3):282-293.
[9] Singh T.N.,Kanchan R.,Verma A.K.,et al.An intelligent approach for prediction of triaxial properties using unconfined uniaxial strength[J].Mining Engineering Journal,2003,(5):12-16.
[10] Janach W.,Merminod A.Rock abrasivity test with a modified Schmidt hammer[J].International Journal of Rock Mechanics and Mining Sciences,1982,19:43-45.
[11] Hornik K,Stinchombe J,White H.Multilayer feed forward networks are universal approximators[J].Neural Networks,1989,2:359-366.