基于计算智能的岩土力学模型参数反演方法及其工程应用
|
摘要
最优估计的岩土力学模型参数是通过比较现场观测到的信息数据与理论模型得到的模型数据的差异而得到的。通过定义目标函数,将参数识别反问题转化为优化问题处理。随着计算机智能计算方法的不断进步和现场观测手段以及观测精度的不断提高,根据现场观测数据进行岩土力学模型参数反演具有良好的应用前景,根据反演的岩土力学模型参数进行反馈设计,可以不断完善和修正原来的工程设计参数。
基于梯度搜索方法的参数反演方法缺陷在于无法保证搜索到全局最优解,其主要原因在于观测误差的存在和模型误差的存在。Tihonov(1963)证明,如果正问题(ForwardProblem)是线性的,那么,反问题的解存在、唯一并且连续地依赖于观测数据(稳定)。关于地下水反问题和热传导反问题以及位移反分析的数值试验发现,当正问题是线性时,如果当不考虑观测数据的观测误差时,反问题的解是唯一的,也就是说,目标函数是凸函数,正如Tihonov所指出的那样;但是,当考虑到观测数据的观测误差时,即使正问题是线性的,反问题的目标函数是非凸的,反问题解是不惟一的。观测误差越大,目标函数的局部极小值数目越多。
遗传算法是一种基于达尔文“自然选择、适者生存”生物进化思想的全局搜索算法,其致命的缺陷在于早熟(Premature)特性。通过将模拟退火算法嵌入到遗传算法中,建立了一种新的锦标赛选择策略。该选择策略使得在种群进化初期,各个个体被选择的概率基本相等,保证了进化过程中种群的多样性,有效解决遗传算法的早熟问题。而随着种群的进化,模拟退火算法中的退火温度逐步降低,使得适应度高(目标函数小)的个体被选择的概率增加,加快了算法的收敛速度;当接近种群进化结束时,只有适应度高的个体被选中。
人工神经网络具有自适应、自组织和学习能力。在网络训练过程中采用改进的BP算法,通过对学习算子的优化搜索,大大提高了网络的收敛速度,解决了BP算法迭代过程中目标函数振荡问题。数值算例表明,所提出的改进的BP算法进行岩土材料参数识别收敛速度和识别精度都得到提高。将所建立的遗传—人工神经网络应用到水电站混凝土大坝和岩石基础滲透系数反演和岩土边坡稳定性分析预测工程中,表明具有很高的预测精度。
与传统的基于梯度搜索的优化方法相比,模拟退火算法具有良好的全局收敛特性。岩土模型参数识别反问题转化为组合优化问题,提出了模拟退火算法识别未知的热传导系数和边界条件问题,算法具有良好的抗观测噪音能力。反问题的不适定性由解的不唯一性和不稳定性来表征,模拟退火算法具有解决这一问题的能力。通过与梯度搜索算法相对比,数值模拟计算结果显示了所提出模拟退火反演方法的有效性和适用性。该反演方法可以用于求解线性或者非线性、稳态和瞬态材料热传导参数识别和边界条件识别问题。
根据自然界中不同类型蚂蚁的分工特性,在蚁群算法中增加了“侦察”蚂蚁,该侦察蚂蚁负责搜索信息素非常低的路径(反问题的解),使得算法具有快速搜索到新的更优解的能力,同时有效地避免蚁群算法的“趋同”特性。同时,将遗传算法中的最优个体保留策略应用到蚁群算法,增强了蚁群算法的全局收敛特性和解的精度。由于蚁群算法采用“地毯式”搜索,收敛速度十分有限,特别是对于需要多次求解正问题的岩土力学参数反演问题,其计算速度尤其突出。通过对蚁群算法的改进,将模拟退火算法与蚁
人连理T人学博卜学位论文
群算法相结合,建立了模拟退火一蚁群算法,该混合优化方法能够充分利用蚁群算法的
信息素蒸发和全局修正特性以及模拟退火算法的快速“邻域”搜索特性,加快了蚁群算
法的收敛速度和全局收敛特性。该方法可以用来识别二维或三维、稳态或非稳态地下水
流动模型的渗透系数和储水系数问题,以及地下水渗流污染源辨识问题。
结合丰满发电厂、白山发电厂和云峰发电厂的改进和扩建工程,根据现场观测数据,
包括坝基扬压力、漏水量和坝体变形观测数据,建立了基于计算智能的混凝土大坝和岩
土力学参数反演方法。针对现有基于梯度优化反演所存在的缺陷,提出了基于遗传算法、
人工神经网络、模拟退火算法和蚁群算法的参数辨识方法,编制了FORTRAN程序软件,
并且应用到所涉及的不同性质问题的工程实践。数值算例和工程实际应用结果表明,所
建立的参数反演方法具有良好的鲁棒性和全局收敛特性,与基于梯度搜索的反演方法相
对比,大坝变形预报值与工程实际观测值对比具有较高的预测精度。将所提出的智能反
演方法应用到白山水电站混凝土大坝和岩石基础渗透系数反演和消能塘渗流场计算以
及参数优化,根据参数反演结果和渗流场模拟计算结果进行反馈设计,节约工程成本接
近1000万元,取得了明显的社会效益和经济效益。
基金资助:国家自然科学基金(基金号:10072014,59779003),高校博士点基金(基
金号2000014107)
关键词:岩土工程,
蚁群算法
论文类型:应用基础
中图分类号:0357.3
参数反演,计算智能,遗传算法,模拟退火算法,人工神经网络,
TU452,TV6423
The solution of inverse problem in geotechnical engineering usually requires optimization of an objective function describing the difference between measured and simulated data. The inverse problem is formulated as optimization problem by defining an objective function. With the improvement of computational intelligences and the enhancement of measuring precisions, the parameter identification in geotechnical engineering has been developed. Based on the identified parameter values, the original design parameters will be modified and improved.Most optimization algorithms used for parameter estimation in geotechnical engineering are gradient-type methods that have the disadvantages of being very sensitive to the initial guesses of parameters and being prone to convergence to local minima. The shortcomings of gradient-based optimization methods lies in that they can not converge into global optimum value of the objective function because there are measuring errors and model errors. Tihonov proved that if the solution of the forward problem is linear in the parameters, then solutions of inverse problem exists, in unique, and depends continuously on the measurement data. The numerical computation results show that the objective function of inverse problem is non-convex while the measurement errors are consider into.Genetic algorithm is a global optimum procedure that is based on Darwin's evolutionary theory. The drawback of genetic algorithm is premature characteristic. The simulated annealing is combined with genetic algorithm. The new tournament selection strategy is proposed. The chosen probability of every individual is equal to each other at starting period. The diversity of population is guaranteed and the premature problem of simple genetic algorithm is overcome. With the population evolutionary, the temperature of simulated annealing algorithm decreases and the chosen probability of having good solution individual will increase.Artificial neural networks have self-adaptive, self-organization and leaning abilities. The modified BP algorithm is presented by optimization of leaning step-size. The convergence rate of neural network is improved and oscillation problem is effectively solved during the iteration process. The numerical simulation results show, compared with traditional BP algorithm, the convergence rate and identification precision can be improved.Compared with gradient-based optimization methods, simulated annealing algorithm is recognized to have better capability to find the global optimal solution. The inverse problem of identifying aquifer parameters is treated as a combinational optimization problem. The numerically computational results show that the procedure developed in the paper is capable of dealing with both unknown heat transfer coefficient and unknown surface temperature, and has ability to fitting measurement noise. The ill-posedness of the inverse problem as characterized by instability and non-uniqueness is overcome by using simulated annealing algorithm. The effectiveness and flexibility of presented inversion technique are evaluated and compared with descent search method.Ant colony optimization is applied into the parameter identification of geotechnical engineering and its application domain is developed. The ant colony optimization is presented
to identify the transmissivity and storage coefficient for a two-dimensional, unsteady state groundwater flow model. The convergence rate of ant colony optimization is slow because the algorithm finds the solutions by using pattern search. To speed up the rate of convergence and enhance inversion precision, the simulated annealing is applied to help ant colony optimization. The new simulated annealing-ant colony optimization is presented. The new hybrid inversion algorithm has the advantages of information evaporation of ant colony optimization and the speed searching characteristic of simulated annealing.Based upon the dividing-work characteristic of natural ants, the scout ant is applied to ant colony optimization. The scout ant finds better
基于梯度搜索方法的参数反演方法缺陷在于无法保证搜索到全局最优解,其主要原因在于观测误差的存在和模型误差的存在。Tihonov(1963)证明,如果正问题(ForwardProblem)是线性的,那么,反问题的解存在、唯一并且连续地依赖于观测数据(稳定)。关于地下水反问题和热传导反问题以及位移反分析的数值试验发现,当正问题是线性时,如果当不考虑观测数据的观测误差时,反问题的解是唯一的,也就是说,目标函数是凸函数,正如Tihonov所指出的那样;但是,当考虑到观测数据的观测误差时,即使正问题是线性的,反问题的目标函数是非凸的,反问题解是不惟一的。观测误差越大,目标函数的局部极小值数目越多。
遗传算法是一种基于达尔文“自然选择、适者生存”生物进化思想的全局搜索算法,其致命的缺陷在于早熟(Premature)特性。通过将模拟退火算法嵌入到遗传算法中,建立了一种新的锦标赛选择策略。该选择策略使得在种群进化初期,各个个体被选择的概率基本相等,保证了进化过程中种群的多样性,有效解决遗传算法的早熟问题。而随着种群的进化,模拟退火算法中的退火温度逐步降低,使得适应度高(目标函数小)的个体被选择的概率增加,加快了算法的收敛速度;当接近种群进化结束时,只有适应度高的个体被选中。
人工神经网络具有自适应、自组织和学习能力。在网络训练过程中采用改进的BP算法,通过对学习算子的优化搜索,大大提高了网络的收敛速度,解决了BP算法迭代过程中目标函数振荡问题。数值算例表明,所提出的改进的BP算法进行岩土材料参数识别收敛速度和识别精度都得到提高。将所建立的遗传—人工神经网络应用到水电站混凝土大坝和岩石基础滲透系数反演和岩土边坡稳定性分析预测工程中,表明具有很高的预测精度。
与传统的基于梯度搜索的优化方法相比,模拟退火算法具有良好的全局收敛特性。岩土模型参数识别反问题转化为组合优化问题,提出了模拟退火算法识别未知的热传导系数和边界条件问题,算法具有良好的抗观测噪音能力。反问题的不适定性由解的不唯一性和不稳定性来表征,模拟退火算法具有解决这一问题的能力。通过与梯度搜索算法相对比,数值模拟计算结果显示了所提出模拟退火反演方法的有效性和适用性。该反演方法可以用于求解线性或者非线性、稳态和瞬态材料热传导参数识别和边界条件识别问题。
根据自然界中不同类型蚂蚁的分工特性,在蚁群算法中增加了“侦察”蚂蚁,该侦察蚂蚁负责搜索信息素非常低的路径(反问题的解),使得算法具有快速搜索到新的更优解的能力,同时有效地避免蚁群算法的“趋同”特性。同时,将遗传算法中的最优个体保留策略应用到蚁群算法,增强了蚁群算法的全局收敛特性和解的精度。由于蚁群算法采用“地毯式”搜索,收敛速度十分有限,特别是对于需要多次求解正问题的岩土力学参数反演问题,其计算速度尤其突出。通过对蚁群算法的改进,将模拟退火算法与蚁
人连理T人学博卜学位论文
群算法相结合,建立了模拟退火一蚁群算法,该混合优化方法能够充分利用蚁群算法的
信息素蒸发和全局修正特性以及模拟退火算法的快速“邻域”搜索特性,加快了蚁群算
法的收敛速度和全局收敛特性。该方法可以用来识别二维或三维、稳态或非稳态地下水
流动模型的渗透系数和储水系数问题,以及地下水渗流污染源辨识问题。
结合丰满发电厂、白山发电厂和云峰发电厂的改进和扩建工程,根据现场观测数据,
包括坝基扬压力、漏水量和坝体变形观测数据,建立了基于计算智能的混凝土大坝和岩
土力学参数反演方法。针对现有基于梯度优化反演所存在的缺陷,提出了基于遗传算法、
人工神经网络、模拟退火算法和蚁群算法的参数辨识方法,编制了FORTRAN程序软件,
并且应用到所涉及的不同性质问题的工程实践。数值算例和工程实际应用结果表明,所
建立的参数反演方法具有良好的鲁棒性和全局收敛特性,与基于梯度搜索的反演方法相
对比,大坝变形预报值与工程实际观测值对比具有较高的预测精度。将所提出的智能反
演方法应用到白山水电站混凝土大坝和岩石基础渗透系数反演和消能塘渗流场计算以
及参数优化,根据参数反演结果和渗流场模拟计算结果进行反馈设计,节约工程成本接
近1000万元,取得了明显的社会效益和经济效益。
基金资助:国家自然科学基金(基金号:10072014,59779003),高校博士点基金(基
金号2000014107)
关键词:岩土工程,
蚁群算法
论文类型:应用基础
中图分类号:0357.3
参数反演,计算智能,遗传算法,模拟退火算法,人工神经网络,
TU452,TV6423
The solution of inverse problem in geotechnical engineering usually requires optimization of an objective function describing the difference between measured and simulated data. The inverse problem is formulated as optimization problem by defining an objective function. With the improvement of computational intelligences and the enhancement of measuring precisions, the parameter identification in geotechnical engineering has been developed. Based on the identified parameter values, the original design parameters will be modified and improved.Most optimization algorithms used for parameter estimation in geotechnical engineering are gradient-type methods that have the disadvantages of being very sensitive to the initial guesses of parameters and being prone to convergence to local minima. The shortcomings of gradient-based optimization methods lies in that they can not converge into global optimum value of the objective function because there are measuring errors and model errors. Tihonov proved that if the solution of the forward problem is linear in the parameters, then solutions of inverse problem exists, in unique, and depends continuously on the measurement data. The numerical computation results show that the objective function of inverse problem is non-convex while the measurement errors are consider into.Genetic algorithm is a global optimum procedure that is based on Darwin's evolutionary theory. The drawback of genetic algorithm is premature characteristic. The simulated annealing is combined with genetic algorithm. The new tournament selection strategy is proposed. The chosen probability of every individual is equal to each other at starting period. The diversity of population is guaranteed and the premature problem of simple genetic algorithm is overcome. With the population evolutionary, the temperature of simulated annealing algorithm decreases and the chosen probability of having good solution individual will increase.Artificial neural networks have self-adaptive, self-organization and leaning abilities. The modified BP algorithm is presented by optimization of leaning step-size. The convergence rate of neural network is improved and oscillation problem is effectively solved during the iteration process. The numerical simulation results show, compared with traditional BP algorithm, the convergence rate and identification precision can be improved.Compared with gradient-based optimization methods, simulated annealing algorithm is recognized to have better capability to find the global optimal solution. The inverse problem of identifying aquifer parameters is treated as a combinational optimization problem. The numerically computational results show that the procedure developed in the paper is capable of dealing with both unknown heat transfer coefficient and unknown surface temperature, and has ability to fitting measurement noise. The ill-posedness of the inverse problem as characterized by instability and non-uniqueness is overcome by using simulated annealing algorithm. The effectiveness and flexibility of presented inversion technique are evaluated and compared with descent search method.Ant colony optimization is applied into the parameter identification of geotechnical engineering and its application domain is developed. The ant colony optimization is presented
to identify the transmissivity and storage coefficient for a two-dimensional, unsteady state groundwater flow model. The convergence rate of ant colony optimization is slow because the algorithm finds the solutions by using pattern search. To speed up the rate of convergence and enhance inversion precision, the simulated annealing is applied to help ant colony optimization. The new simulated annealing-ant colony optimization is presented. The new hybrid inversion algorithm has the advantages of information evaporation of ant colony optimization and the speed searching characteristic of simulated annealing.Based upon the dividing-work characteristic of natural ants, the scout ant is applied to ant colony optimization. The scout ant finds better
引文
[1] 孙钧.岩土力学反演问题的随机理论与方法.汕头:汕头大学出版社,1996
[2] 王芝银,李云鹏.地下工程位移反分析法及程序.西安:陕西科技出版社,1993
[3] 冯夏庭.智能岩石力学导论.北京:科学出版社,2000
[4] 杨林德.岩土工程问题的反演理论与工程实践.北京:科学出版社,1996
[5] 吕爱钟.岩石力学反问题.北京:煤炭工业出版社,1998
[6] Skurai S. Back analysis of measured displacement of tunnel. Rock Mech. And Rock Eng, 1983, 16(3): 173-180
[7] 王家映.地球物理反演理论.武汉:中国地质大学出版社,1998
[8] Jaquard P. Permeability distribution from field pressure data. Soc. Pet. Eng. J., 1965, 5(4): 281-294
[9] Jahns. H O A rapid method for obtaining a two-dimensional reservior description from well pressure response data. Soc. Pet. Eng. J., 1966, 6(4): 351-327
[10] Neuman. S P A statistical approach to the inverse problem of aquifer hudrology, 3: improved solution method and added perspective. Water Resour. Res, 1980, 16(2): 331-346
[11] Kavanagh K T. Finite element application in the characterization of elastic solid. Int. J Solids Structures, 1972, (7): 11-23
[12] Gioda G. Direct search solution of an inverse problem in elastic-plasticity, identification of cohesion, friction angle and in-situ stress by pressure tunnel tests. Int. Num. Methods in Eng., 1980, (15): 1823-1834
[1
[13] Gioda G. Numerical identification of soil structure interaction pressure. Int. J. For Num & Anal. Meth. In Geomech, 1981, (5): 33-56
[14] 杨志法.位移反分析在地下工程设计中的初步应用.地下工程,1981,(2):20-24
[15] 郭怀志,马启超.岩体初始应力场的分析方法.岩土工程学报,1983,5(3):303-308
[16] V. U. Nguyen. Back calculation of slope failure by the secant method. Geotechnique, 1984
[17] 王芝银.地下巷道考虑空间效应的增量反分析.西安矿业学院学报,1987,7(4):13-21
[18] 吴中如.混凝土坝观测资料的反分析.河海大学学报,1989,17(2):10-18
[19] 胡维俊.拱坝反分析的多点拟合法.水利学报,1991,(7):27-33
[20] 朱岳明.岩体渗透系数反分析的最优估计方法.岩土工程学报,1991,13(4):71-76
[21] H. Sonmez. A practical procedure for the back analysis of slope failure in closely jointed rock masses. Int. J. Rock Mech. Min. Sci, 1998, 35(2): 219-233
[22] 强天驰,周维垣,杨若琼.拱坝多参数优化反演方法及其应用.岩石力学与工程学报,2000,19(增):997-1000
[23] 杨林德,吴蔺,周汉杰.反演分析中量测误差的传递与仪表选择.土木工程学报,2000,33(1):78-84
[24] 吕爱钟,蒋斌松,尤春安.位移反分析有限元网格划分范围的研究.土木工程学报,1999,32(2):26-31
[25] 李守巨,刘迎曦,王登刚.岩体初始应力场识别的随机方法.岩土力学,2000,21(2):126-129
[26] 王华宁,吕爱钟.巷道裂隙岩体的损伤参数辨识.岩土工程学报,2001,23(5):593-596
[27] 曹国金,苏超,姜弘道.一种三维优化位移反演分析法.岩土力学,2001,22(3):303-308
[28] William Yeh. Review of parameter identification procedures in groundwater hydrology. The inverse problem. Water Resources Research, 1986, 22(2): 95-108
[29] 王芝银,杨志法,王思敬.岩石力学位移反演分析回顾与进展.力学进展,1998,28(4):488-499
[30] Leec S R. Identifying probable failure modes for underground openings using a neural network, Int. J of Rock Mech. & Geomech. Abstr, 1991, 28(6): 377-386
[31] Najjar Y M. Utilizing computational neural networks for evaluating the permeability of compacted clay liners. Geotechnical and geological Engineering, 1996, (14): 193-212
[32] 冯夏庭.智能岩石力学(2)参数与模型的智能辨识.岩石力学与工程学报,1999,18(3):497-502
[33] 李守巨,刘迎曦,王登刚.基于人工神经网络的岩体渗透系数反演方法及其工程应用.岩石力学与工程学报,2002,21(4)
[34] Meulenkamp E Application of neural networks for the prediction of the unconfined compressive strength from Equotip hardness. Int. J. of Rock mechanics and mining Sciences, 1999, 36: 29-39
[35] 周保生.巷道围岩参数的人工神经网络预测.岩土力学,1999,20(1):22-25
[36] X. Cao. Application of artificial neural networks to load identification. Computers & structures, 1998, 69: 63-78
[37] 梁艳春.人工神经网络应用于地下洞室围岩参数识别的研究.模式识别与人工智能,1996,9(1):70-76
[38] 冯夏庭,张治强,杨成祥.位移反分析的进化神经网络方法研究.岩石力学与工程学报,1999,1(5):497-502
[39] Friswell. M I. A combined genetic eigensnetivity algorithm for the location of damage in structures. Comput. Struc, 1998, 69: 547-556
[40] Sankar K N. Velocity inversion in cross-hole seismic tomography by counter-propagation neural network, genetical gorithmand evolutionary programming techniques. Geophys. J. Int, 1999, 138: 108-124
[4
[41] Yi Huang. Application of artificial neural networks to predictions of aggregate quality parameters. Int. J. of Rock mechanics and mining sciences, 1999, 36: 551-561
[42] Najjar Y M. Utilizing computational neural networks for evaluating the permeability of compacted clay liners. Geotechnical and geological Engineering, 1996, 14: 193-212
[43] C. S. Huang. A neural network approach for structural identification and diagnosis of a building from seismic response data. Earthquake Engineering and Structural Dynamics, 2003, 32: 187-206
[44] G. Lightbody. Multi-layer perceptron based modeling of nonlinear systems. Fuzzy Sets and System, 1996, 79: 93-112
[45] J. W. Denton. A comparison of nonlinear optimization methods for supervised learning in M. Jamialahmadi. Relationship of permeability, porosity and depth using anartificial neural network Journal of Petroleum. Science and Engineering, 2000, 26: 235-239
[46] Hsien-cheng Chang. Lithofacies identi(?)cation using multiple adaptive resonance theory neural networks and group decision expert system. Computers & Geosciences, 2000, 26: 591-601
[47] Chang H.-C., Chert H.-C., Fang J.-H. Lithology determination from well logs with fuzzy associative memory neural network. IEEE Transactions on Geoscience and Remote Sensing, 1997, 35(3): 773-780
[48] Liang Y. C. Neural identification of rock parameters using fuzzy adaptive learning parameters. Computers and Structures, 2003, 81: 2373-2382
[49] Waszczyszyn Z, Ziemianski L. Neural networks in mechanics of structures and materials-new results and prosoects of applications. Comput Struct. 2001, 79: 2261-76
[50] 李守巨,刘迎曦,王登刚.基于遗传算法的岩体初始应力场反演.煤炭学报,2001,26(1):13-17
[51] 王登刚,刘迎曦,李守巨.岩土工程位移反分析的遗传算法.岩石力学与工程学报,2000,19(增):979-982
[52] McKinney D. Genetic algorithm solution of groundwater management models. Water Resour. Res, 1994, 30(6): 1897-1906
[53] 高玮,颖人.用快速遗传算法进行岩土工程反分析.土工程学报,2001,23(1):120-122
[54] 刘杰,王嫒.体流变参数反演的加速遗传算法.坝观测与土工测试,2001,25(6):24-27
[55] c. wang. Ientification of dynamic rock properties using a genetic algorithm. int, j. rock mech. min. sci, 2004, 41(3)
[56] Cieniawski S. E, Wayland J, Ranjithan S. sing genetic algorithms to solve multiobjective groundwater monitoring problem. Water Resour. Res, 1995, (2): 99-409
[57] Ritzel, B. J, Eheart J. W, Ranjithan S. Using genetic algorithms to solve a multiobjective groundwater pollution containment problem. Water Resour. Res, 1994, 30 (5): 1589-1603
[58] Yang J, Soh C. K. Structural optimization by genetic algorithms with tournament selection. Comput. Civil Engng, 1997, (3): 195-200
[59] Costa. Lino, Evolutionary algorithms approach to the solution of mixed integer non-linear programming problems. Computers and Chemical Engineering, 2001, 25: 257-266
[60] Tomonari Furukawa. An automated system for simulation and parameter identification of inelastic constitutive models. Comput. Methods Appl. Mech. Engrg, 2002, 191: 2235-2260
[61] Friswell M. I. A combined genetic eigensnetivity algorithm for the location of damage in structures. Comput. Struc., 1998, 69: 547-556
[62] Potts J. C. The development and evaluation of an improved genetic algorithm based on migration and artificial selection. IEEE Trans. On SMC, 1994, 24(1): 73-86
[63] Kirkpatrick S. Optimization by simulated annealing. Science, 1983, 220: 671-680
[64] Nakao, Shinsuke. Hydraulic well testing inversion for modeling fluid flow in fractured rocks using simulated annealing: a case study at Raymond field site, California. Journal of Applied Geophysics, 2000, 45(3): 203-223
[65] Mauldon A. D. An inversion technique for developing models for fluid flow in fracture systems using simulated annealing. Water Resour. Res., 1993, 29(3): 3775-3789
[66] Nakan S. Sensitivity study on hydraulic well testing inversion using simulated annealing. Groud Water, 1999, 37(5): 736-747
[67] 李守巨,刘迎曦.基于模拟退火法的含水层参数非线性反演.西安交通大学学报,2001,35(5):546-548
[68] Nestor V. Q. Efficient global optimization for hydraulic fracturing treatment design. J. of Petroleum Science and Engineering, 2002, 35(1): 151-166
[69] Zheng C. Parameter structure identification using tabu search and simulated annealing. Advaces in Water Resources, 1996, 19(4): 215-224
[70] 魏连伟.基于模拟退火算法的水文地质参数识别.天津大学学报,2003,36(5):618-621
[71] 张晖.引入模拟退火机制的新型遗传算法.电子科技大学学报,2003,32(1):39-42
[72] Wang P. P. An efficient approach for successively perturbed grounwater models. Advances in Water Resources, 1998: 499-508
[73] Dougherty D. E. Optimal groundwater management, 1: simulated annealing. Water Resour. Res., 1991, 27(10): 2493-2508
[74] Marryott R. A. Optimal groundwater management, 2: application of simulated annealing to a field-scale contamination site. Water Resour. Res., 1993, 29(4): 847-860
[75] 姚姚.地球物理北线性反演模拟退火方法的改进.地球物理学报,1995,38(5):643-651
[76] 姚振兴.时间域内有限地震断层的反演问题.地球物理学报.1997,40(5):691-701
[77] 刘鹏程,纪晨.改进模拟退火-单纯形综合反演方法.地球物理学报.1995,38(2):199-205
[78] Sambridge M. Geophysical inversion with a neighbourhood algorithm-Ⅰ. Geophys. J. Int, 1999, 138: 479-494
[79] 姚振兴.波阻抗反演的混合最优化算法.地球物理学进展,1999,14(2):1-6
[80] Chunduru R. Hybrid optimization methods for geophysical inversion. Geophysics, 1997, 62: 1196-1207
[81] Sen M. Nonlinear one-dimensional seismic waveform inversion using simulated annealing. Geophysics, 1991, 56: 1624-1638
[82] 肖广智,李守巨,刘迎曦.基于模拟退火算法的爆炸冲击荷载参数反演法.辽宁工程技术大学学报,2001,20(4):417-419
[2] 王芝银,李云鹏.地下工程位移反分析法及程序.西安:陕西科技出版社,1993
[3] 冯夏庭.智能岩石力学导论.北京:科学出版社,2000
[4] 杨林德.岩土工程问题的反演理论与工程实践.北京:科学出版社,1996
[5] 吕爱钟.岩石力学反问题.北京:煤炭工业出版社,1998
[6] Skurai S. Back analysis of measured displacement of tunnel. Rock Mech. And Rock Eng, 1983, 16(3): 173-180
[7] 王家映.地球物理反演理论.武汉:中国地质大学出版社,1998
[8] Jaquard P. Permeability distribution from field pressure data. Soc. Pet. Eng. J., 1965, 5(4): 281-294
[9] Jahns. H O A rapid method for obtaining a two-dimensional reservior description from well pressure response data. Soc. Pet. Eng. J., 1966, 6(4): 351-327
[10] Neuman. S P A statistical approach to the inverse problem of aquifer hudrology, 3: improved solution method and added perspective. Water Resour. Res, 1980, 16(2): 331-346
[11] Kavanagh K T. Finite element application in the characterization of elastic solid. Int. J Solids Structures, 1972, (7): 11-23
[12] Gioda G. Direct search solution of an inverse problem in elastic-plasticity, identification of cohesion, friction angle and in-situ stress by pressure tunnel tests. Int. Num. Methods in Eng., 1980, (15): 1823-1834
[1
[13] Gioda G. Numerical identification of soil structure interaction pressure. Int. J. For Num & Anal. Meth. In Geomech, 1981, (5): 33-56
[14] 杨志法.位移反分析在地下工程设计中的初步应用.地下工程,1981,(2):20-24
[15] 郭怀志,马启超.岩体初始应力场的分析方法.岩土工程学报,1983,5(3):303-308
[16] V. U. Nguyen. Back calculation of slope failure by the secant method. Geotechnique, 1984
[17] 王芝银.地下巷道考虑空间效应的增量反分析.西安矿业学院学报,1987,7(4):13-21
[18] 吴中如.混凝土坝观测资料的反分析.河海大学学报,1989,17(2):10-18
[19] 胡维俊.拱坝反分析的多点拟合法.水利学报,1991,(7):27-33
[20] 朱岳明.岩体渗透系数反分析的最优估计方法.岩土工程学报,1991,13(4):71-76
[21] H. Sonmez. A practical procedure for the back analysis of slope failure in closely jointed rock masses. Int. J. Rock Mech. Min. Sci, 1998, 35(2): 219-233
[22] 强天驰,周维垣,杨若琼.拱坝多参数优化反演方法及其应用.岩石力学与工程学报,2000,19(增):997-1000
[23] 杨林德,吴蔺,周汉杰.反演分析中量测误差的传递与仪表选择.土木工程学报,2000,33(1):78-84
[24] 吕爱钟,蒋斌松,尤春安.位移反分析有限元网格划分范围的研究.土木工程学报,1999,32(2):26-31
[25] 李守巨,刘迎曦,王登刚.岩体初始应力场识别的随机方法.岩土力学,2000,21(2):126-129
[26] 王华宁,吕爱钟.巷道裂隙岩体的损伤参数辨识.岩土工程学报,2001,23(5):593-596
[27] 曹国金,苏超,姜弘道.一种三维优化位移反演分析法.岩土力学,2001,22(3):303-308
[28] William Yeh. Review of parameter identification procedures in groundwater hydrology. The inverse problem. Water Resources Research, 1986, 22(2): 95-108
[29] 王芝银,杨志法,王思敬.岩石力学位移反演分析回顾与进展.力学进展,1998,28(4):488-499
[30] Leec S R. Identifying probable failure modes for underground openings using a neural network, Int. J of Rock Mech. & Geomech. Abstr, 1991, 28(6): 377-386
[31] Najjar Y M. Utilizing computational neural networks for evaluating the permeability of compacted clay liners. Geotechnical and geological Engineering, 1996, (14): 193-212
[32] 冯夏庭.智能岩石力学(2)参数与模型的智能辨识.岩石力学与工程学报,1999,18(3):497-502
[33] 李守巨,刘迎曦,王登刚.基于人工神经网络的岩体渗透系数反演方法及其工程应用.岩石力学与工程学报,2002,21(4)
[34] Meulenkamp E Application of neural networks for the prediction of the unconfined compressive strength from Equotip hardness. Int. J. of Rock mechanics and mining Sciences, 1999, 36: 29-39
[35] 周保生.巷道围岩参数的人工神经网络预测.岩土力学,1999,20(1):22-25
[36] X. Cao. Application of artificial neural networks to load identification. Computers & structures, 1998, 69: 63-78
[37] 梁艳春.人工神经网络应用于地下洞室围岩参数识别的研究.模式识别与人工智能,1996,9(1):70-76
[38] 冯夏庭,张治强,杨成祥.位移反分析的进化神经网络方法研究.岩石力学与工程学报,1999,1(5):497-502
[39] Friswell. M I. A combined genetic eigensnetivity algorithm for the location of damage in structures. Comput. Struc, 1998, 69: 547-556
[40] Sankar K N. Velocity inversion in cross-hole seismic tomography by counter-propagation neural network, genetical gorithmand evolutionary programming techniques. Geophys. J. Int, 1999, 138: 108-124
[4
[41] Yi Huang. Application of artificial neural networks to predictions of aggregate quality parameters. Int. J. of Rock mechanics and mining sciences, 1999, 36: 551-561
[42] Najjar Y M. Utilizing computational neural networks for evaluating the permeability of compacted clay liners. Geotechnical and geological Engineering, 1996, 14: 193-212
[43] C. S. Huang. A neural network approach for structural identification and diagnosis of a building from seismic response data. Earthquake Engineering and Structural Dynamics, 2003, 32: 187-206
[44] G. Lightbody. Multi-layer perceptron based modeling of nonlinear systems. Fuzzy Sets and System, 1996, 79: 93-112
[45] J. W. Denton. A comparison of nonlinear optimization methods for supervised learning in M. Jamialahmadi. Relationship of permeability, porosity and depth using anartificial neural network Journal of Petroleum. Science and Engineering, 2000, 26: 235-239
[46] Hsien-cheng Chang. Lithofacies identi(?)cation using multiple adaptive resonance theory neural networks and group decision expert system. Computers & Geosciences, 2000, 26: 591-601
[47] Chang H.-C., Chert H.-C., Fang J.-H. Lithology determination from well logs with fuzzy associative memory neural network. IEEE Transactions on Geoscience and Remote Sensing, 1997, 35(3): 773-780
[48] Liang Y. C. Neural identification of rock parameters using fuzzy adaptive learning parameters. Computers and Structures, 2003, 81: 2373-2382
[49] Waszczyszyn Z, Ziemianski L. Neural networks in mechanics of structures and materials-new results and prosoects of applications. Comput Struct. 2001, 79: 2261-76
[50] 李守巨,刘迎曦,王登刚.基于遗传算法的岩体初始应力场反演.煤炭学报,2001,26(1):13-17
[51] 王登刚,刘迎曦,李守巨.岩土工程位移反分析的遗传算法.岩石力学与工程学报,2000,19(增):979-982
[52] McKinney D. Genetic algorithm solution of groundwater management models. Water Resour. Res, 1994, 30(6): 1897-1906
[53] 高玮,颖人.用快速遗传算法进行岩土工程反分析.土工程学报,2001,23(1):120-122
[54] 刘杰,王嫒.体流变参数反演的加速遗传算法.坝观测与土工测试,2001,25(6):24-27
[55] c. wang. Ientification of dynamic rock properties using a genetic algorithm. int, j. rock mech. min. sci, 2004, 41(3)
[56] Cieniawski S. E, Wayland J, Ranjithan S. sing genetic algorithms to solve multiobjective groundwater monitoring problem. Water Resour. Res, 1995, (2): 99-409
[57] Ritzel, B. J, Eheart J. W, Ranjithan S. Using genetic algorithms to solve a multiobjective groundwater pollution containment problem. Water Resour. Res, 1994, 30 (5): 1589-1603
[58] Yang J, Soh C. K. Structural optimization by genetic algorithms with tournament selection. Comput. Civil Engng, 1997, (3): 195-200
[59] Costa. Lino, Evolutionary algorithms approach to the solution of mixed integer non-linear programming problems. Computers and Chemical Engineering, 2001, 25: 257-266
[60] Tomonari Furukawa. An automated system for simulation and parameter identification of inelastic constitutive models. Comput. Methods Appl. Mech. Engrg, 2002, 191: 2235-2260
[61] Friswell M. I. A combined genetic eigensnetivity algorithm for the location of damage in structures. Comput. Struc., 1998, 69: 547-556
[62] Potts J. C. The development and evaluation of an improved genetic algorithm based on migration and artificial selection. IEEE Trans. On SMC, 1994, 24(1): 73-86
[63] Kirkpatrick S. Optimization by simulated annealing. Science, 1983, 220: 671-680
[64] Nakao, Shinsuke. Hydraulic well testing inversion for modeling fluid flow in fractured rocks using simulated annealing: a case study at Raymond field site, California. Journal of Applied Geophysics, 2000, 45(3): 203-223
[65] Mauldon A. D. An inversion technique for developing models for fluid flow in fracture systems using simulated annealing. Water Resour. Res., 1993, 29(3): 3775-3789
[66] Nakan S. Sensitivity study on hydraulic well testing inversion using simulated annealing. Groud Water, 1999, 37(5): 736-747
[67] 李守巨,刘迎曦.基于模拟退火法的含水层参数非线性反演.西安交通大学学报,2001,35(5):546-548
[68] Nestor V. Q. Efficient global optimization for hydraulic fracturing treatment design. J. of Petroleum Science and Engineering, 2002, 35(1): 151-166
[69] Zheng C. Parameter structure identification using tabu search and simulated annealing. Advaces in Water Resources, 1996, 19(4): 215-224
[70] 魏连伟.基于模拟退火算法的水文地质参数识别.天津大学学报,2003,36(5):618-621
[71] 张晖.引入模拟退火机制的新型遗传算法.电子科技大学学报,2003,32(1):39-42
[72] Wang P. P. An efficient approach for successively perturbed grounwater models. Advances in Water Resources, 1998: 499-508
[73] Dougherty D. E. Optimal groundwater management, 1: simulated annealing. Water Resour. Res., 1991, 27(10): 2493-2508
[74] Marryott R. A. Optimal groundwater management, 2: application of simulated annealing to a field-scale contamination site. Water Resour. Res., 1993, 29(4): 847-860
[75] 姚姚.地球物理北线性反演模拟退火方法的改进.地球物理学报,1995,38(5):643-651
[76] 姚振兴.时间域内有限地震断层的反演问题.地球物理学报.1997,40(5):691-701
[77] 刘鹏程,纪晨.改进模拟退火-单纯形综合反演方法.地球物理学报.1995,38(2):199-205
[78] Sambridge M. Geophysical inversion with a neighbourhood algorithm-Ⅰ. Geophys. J. Int, 1999, 138: 479-494
[79] 姚振兴.波阻抗反演的混合最优化算法.地球物理学进展,1999,14(2):1-6
[80] Chunduru R. Hybrid optimization methods for geophysical inversion. Geophysics, 1997, 62: 1196-1207
[81] Sen M. Nonlinear one-dimensional seismic waveform inversion using simulated annealing. Geophysics, 1991, 56: 1624-1638
[82] 肖广智,李守巨,刘迎曦.基于模拟退火算法的爆炸冲击荷载参数反演法.辽宁工程技术大学学报,2001,20(4):417-419