Constitutive Model Identification of Rock Based on Artificial Intelligence

Abstract:

The Identification of rock constitutive model is a typical nonlinear system problem; introduction of the intelligent methods has greatly stimulated the research. In this paper, genetic algorithm , BP neural network and genetic programming are used in the identification of constitutive model ,the capacity of three intelligent methods in the model identification is compared ,whose results show that genetic algorithm can largely reduce the probability of trapping into localized optimum solution by means of its global searching ability ,however , because its pre-assumption of constitutive model has already lead to some error ,its fitting results are not so good . BP neural network and genetic programming need not pre-assume the structure of constitutive model ,the nonlinear mapping expressions between stress and strain are obtained by self-organization and self-learning .But ,the determination of BP neural network structure is experience-depending and time-consuming . In addition, genetic programming need not define its structure, so long as the functional set and terminal set are chosen, after series of genetic operations, the nonlinear relations between variables are outputted, therefore, the operation of genetic programming is simple which realize the visualization of the constitutive equations.

• Periodical: Advanced Materials Research (Volumes 368-373)
• Pages: 2509-2516
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.368-373.2509
• Online since: October 2011
• Authors: Sheng Jun Sha, Xiao Hao, Shu Hua Zhai
• Keywords: Constitutive Model, Genetic Algorithm (GA), Genetic Programming, Pattern Identification

References

[1] GAO Wei, FENG Xia-ting .Some studies on intelligent identification of geo-material constitutive model[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(s2):2532-2538.

[2] ZHU Zhen-de, XU Wei- ya. Visco-elastic constitutive model recognition of rock mass and its engineering application[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(11):1605-1609.

[3] CHEN Bing-rui,FENG Xia-ting ,DING Xiu-li. Rheological model and parameters identification of rock based on pattern search and least-square techniques[J]. Chinese Journal of Rock Mechanics and Engineering, 2005,24(2)：207-211.

[4] LI Ji-liang, GAOQian,REN Tian-gui.Engineering materials constitutive modeling and its parameters back analysis[J].Journal of Hebei Institute of Technology,2000,229(04):1-11 .

[5] TAN Yun-liang ,WANG Chun-qiu. A fast approaching model for rock constitutive equation by radial basis function neural network[J]. Chinese Journal of Geotechnical Engineering, 2001,23(1):1-4.

[6] CENG Jing ,WANG Jing-tao. Two neural network models for saturated clay constitutive relations under different stress paths [J]. Journal of Huazhong University of Science and Technology(Nature Science Edition), 2002,30(3):68-70.

[7] Dershowitz W.S , Einstein H.H.,application of artificical intelligence to problem of rock mechnics ,25th U.S Symposium on rock mechanics ,1984,483-494.

[8] Zhang Qing. Application of neural network models to rock mechanics and rock engineering, international journal of Rock mechanics and mining science ,1991,28(6),535-540.

DOI: 10.1016/0148-9062(91)91130-j

[9] FENG Xia-ting, WANG Yong-jia .Some thoughts concerning the development of intelligent rock mechanics ,ISRM new journal ,oct.2000:6(2),14-17.

[10] FENG Xia-ting. Introduction to Intelligent Rock Mechanics [M]. Beijing：Science Press,2000.

[11] GAO Wei, DENG Ying-ren.Identification of the geometrical constitutive model based on genetic algorithm [J].Chinese Journal of Rock Mechanics and Engineering, 2002, 21 (1):9-12.

[12] GAO Wei, DENG Ying-ren.Back analysis in geotechnical engineering based on fast convergent genetic algorithm [J] .Chinese Journal of Geotechnical Engineering, 2002 ,21 (1) :9-12.

[13] GAO Wei, DENG Ying-ren.Back analysis of rock mass parameters based on evolutionary algorithm[J]. .Journal of Hydraulic Engineering,2000 ,(8) :1 - 5.

[14] GAO Wei, DENG Ying-ren. A new algorithm for identification of geometrical model based on an ecological competition model [J]. Chinese Journal of Geotechnical Engineering,2002,24(1):93-97.

[15] HU Zhi-ling, FAN Hou-bin, LUO Li-juan. Identification of rheological model based on genetic algorithm and overlay model[J]. Chinese Journal of Applied Mechanics, 2005,22(03):364-368.

[16] Lang,XIE Kang-he. Application of artificial neural networks to geotechnical engineering [J]. China Civil Engineering Journal,2002,35(4):77–81.

[17] WANG Xu,WANG Hong,WANG Wen-hui. The Principle and Application of Artificial Neural Network[M]. Shenyang:Northeast University Press，2000.

[18] CHANG Bin,LI Ning,MA Yu-kuo. Improvement and application of ANN method in stress and deformation predictions during tunnel excavation[J]. Chinese Journal of Rock Mechanics and Engineering,2004,23(7):1 132–1 135.

[19] YUN Qing-xia. Evolutionary algorithm. Metallurgy industry publishing house:2000.

[20] YUN Qing-xia,WANG Zhan-quan.Genetic algorithm and genetic programming. Metallurgy industry publishing house:1997.

[21] KozaJ.R. Genetic programming: on the programming of computer by means of nature selection .Cambridge: The MIT press.1992.

[22] KozaJ.R. Genetic programming 2 .The MITpress:1994.

[23] Silva S, Almeida J (2003). Dynamic maximum tree depth - A simple technique for avoiding bloat in tree-based GP. In Cantú-Paz E, Foster JA, Deb K, et al. (eds),Proceedings of GECCO-2003, Springer Verlag.1776--1787.

DOI: 10.1007/3-540-45110-2_69

[24] Silva S, Costa E (2004). Dynamic limits for bloat control - variations on size and depth. To appear in Proceedings of GECCO-2004, Springer Verlag.666-677.

DOI: 10.1007/978-3-540-24855-2_74

[25] LI Ji-liang .Study of artificial neutral constitutive modeling of rocks and ANN's application to deformation prediction of roadway (D), Beijing: University of Science and Technology Beijing,1999.