基于遗传算法的新安江模型日模拟参数优选研究

在概念性水文模型的参数率定中,目前还没有一个传统优化方法能够提供保证足够高效和稳定性的算法。为了克服传统优化方法中局部收敛性的缺点,近年来利用遗传算法通过计算机准确稳定地进行概念性水文模型的参数优选的尝试得到越来越多的重视和发展。目前优选水文模型待定参数,大多是从次洪模型的方面去讨论,有关日模拟模型的遗传算法参数优选讨论的较少。本文系统分析了基于遗传算法的新安江模型日模拟参数的自动优选,同时针对遗传算法在模型参数众多的情况下时间效率低下问题,通过利用新安江模型参数分层原理与模型参数敏感性分析对优选结果影响,提出一套简化的日模型参数遗传算法优选方案。经过流域模拟检验,该优选方案可行,运行效率高,可以作为类似模型遗传算法参数率定快速、有效的方案。     

基于混合遗传算法估计van Genuchten方程参数

van Genuchten(VG)方程是最常用的土壤水分特征曲线方程,其参数取值的精度直接影响到土壤水分运动方程计算的精度.该文建立了VG方程参数的优化模型,构建遗传算法与Levenberg-Marquardt算法相结合的混合遗传算法对其进行求解,并进行了数值试验.结果表明采用混合遗传算法比普通遗传算法不但提高了收敛效率,而且收敛迭代次数也大大减少;采用混合遗传算法估计参数的精度比非线性单纯形法和阻尼最小二乘法要高一些,而且不需要给参数初值.因此,混合遗传算法可以作为估计VG方程参数的一种新方法.     

群居蜘蛛优化算法在水文频率分析中的应用

水文频率分析在参数估计过程中常采用智能优化适线法,如蚁群算法、遗传算法、粒子群算法、模拟退火算法等,但这些算法模型参数难以有效确定,导致寻优结果存在不稳定的不足。为了克服传统优化适线法的缺陷,在系统阐述群居蜘蛛优化算法基本原理的基础上,将群居蜘蛛优化算法用于水文频率曲线的参数确定中,并与传统的参数估计方法(矩法、权函数法、概率权重矩法、遗传算法)加以比较。实例结果表明,该方法搜索效率高,寻优结果稳定,能较好获得参数的最优解。     

白山抽水蓄能泵站地下厂房的岩体力学参数反演

根据白山抽水蓄能泵站地下厂房开挖过程中的变形观测数据,提出了一种基于响应面法的岩体力学参数反演方法。该方法利用响应面函数建立了岩体力学参数与围岩变形之间的非线性关系。通过有限元数值模拟确立了响应面函数中的系数。定义参数反演的目标函数,将参数反演问题转化为优化问题。分别采用拟牛顿优化算法和遗传算法求解参数反演的目标函数,得到了地下厂房的岩体力学参数。根据反演确定的岩体力学参数,对地下厂房围岩的开挖变形进行了数值模拟,研究表明,有限元模拟的地下厂房与现场观测值基本一致,验证了反演方法的有效性。     

一种土的非线性弹性本构模型参数的反演方法

旨在提出一种土的非线性弹性本构模型参数反演的方法。以现今普遍实行的地基载荷试验为基础,依据遗传算法的组合优化理论,采用正演计算和遗传算法优化相结合的方式,建立了土层非线性弹性本构模型参数反演的方法;并依据某黄土场地地基载荷试验数据,实施了黄土土层非线性弹性本构模型参数反演的全过程。计算结果表明,所建立的方法可以实现土层非线性弹性本构模型中相互关联的多个参数的组合优化,并在对初始值要求较低的情况下,可以获得良好的参数反演精度。从而为土的变形特性分析和土与其中及相邻结构的共同作用分析,提供了较好的土体本构模型参数的确定方法。     

基于十进制遗传算法的含水层参数的反演

含水层参的反演是一个复杂的非线性优化问题，针对传统二进制遗传算法收敛性能差的缺陷，提出了反演含水层参数的十进制遗传算法.以直线隔水边界附近的井流模型为例，讨论了十进制遗传算法在含水层参数反演中的应用，并与二进制遗传算法的进行比较.结果表明，该方法在含水层参数的反演中不仅是可行的，而且具有较好的确定性和较高的精度;与二进制遗传算法相比，十进制遗传算法的收敛性较好，省时高效，且表示较为自然，容易引入相关领域知识.同时，结合实例的分析结果得出种群的规模对算法的收敛性没有明显的影响。     

Application of Seagull Optimization Algorithm Log Interpretation to Shale Gas Reservoir of Well H in Sichuan Basin Yuxi Block

Due to the diversity of mineral types in shale gas reservoirs, it is difficult to establish reservoir parameter volume model by conventional log interpretation methods. The optimization log interpretation method can evaluate complex lithology reservoirs effectively, and the key is optimization algorithm. With the newly proposed seagull optimization algorithm method, we calculate the mineral and physical parameters of shale gas reservoir in Well H of Yuxi block, Sichuan Basin, and compare with the genetic algorithm and the genetic algorithm-complex hybrid algorithm. It shows that calculation results of seagull optimization algorithm optimization log interpretation match well with core analysis data, and calculation error is small, calculation speed is fast. Seagull optimization algorithm also makes up for the shortcomings of premature convergence and easy to fall into local optimization of genetic algorithm, the need for secondary optimization and slow search speed of genetic-complex hybrid algorithm. It provides a reference for the application of seagull optimization algorithm in other shale gas reservoirs regions.     

控制差异沉降的桩筏基础桩径优化分析方法

桩径优化是桩筏基础以差异沉降最小化为目标的基础优化分析的重要组成部分。基于桩筏基础通用分析方法,结合遗传算法提出了包含非线性约束条件的以差异沉降控制为目标的桩筏基础桩径优化分析模型,并给出了优化分析的实施步骤。通过示例说明了桩径优化的实施情况,对比给出了优化前后基础沉降、桩基荷载分布与筏板分担比、筏板弯矩和剪力结果。最后通过参量分析研究了筏板厚度、桩基参量和土体参量对最优桩径确定的影响程度,桩长和土体特性对桩径优化结果影响显著,而桩体材料特性和筏板厚度对桩径优化结果影响不大。     

改进的遗传算法及其在渗流参数反演中的应用

利用水头实测资料,以裂隙组的渗透系数比例因子为待反演的参数向量,在采用基本遗传算法进行参数反演研究的基础上,针对裂隙岩体无压渗流参数反问题计算量过大,目标参数众多以及参数可能变化范围大等特点,提出了一种混合遗传算法求解此类问题,力求克服简单遗传算法在解决此类问题时存在的局部搜索能力弱、易出现早熟收敛及计算量大等缺陷,并通过典型岩坡渗流算例进行验证,同时给出了基本遗传算法、传统单纯形算法的反演成果。计算结果表明,该方法保持了基本遗传算法优点,并有效地提高了算法的运行效率,从而为求解裂隙岩体无压渗流参数反问题等计算量大的系列问题提供了新的途径。     

遗传模拟退火的BP算法在冲击地压中的应用

冲击地压的预测、预报的研究,大多数仍停留在简单的统计研究和单因素的预测方面,因而,结果也不十分理想。笔者采用多层前向网络对该问题进行数学建模,网络的训练算法采用基于遗传模拟退火的BP优化算法。该算法是在遗传算法中引入模拟退火机制,将其同BP算法结合,形成一个混合的优化算法。新算法既有神经网络的学习能力和鲁棒性,又有遗传算法的强全局随机搜索能力。同时,利用华丰矿冲击地压的实际监测数据,通过遗传算法的主要性能指标对新算法的参数进行了比较研究,得到优化后的一组参数。利用该参数,对冲击地压的神经网络模型的结构、权值和阈值进行了优化,得到了非全连接的优化神经网络模型。最后,利用该模型对华丰矿冲击地压进行了短期最大震级的预报。预测结果的相对误差率平均为 7.84 %,预测效果比较理想。     

Intelligent model selection with updating parameters during staged excavation using optimization method

Various constitutive models have been proposed, and previous studies focused on identifying parameters of specified models. To develop the smart construction, this paper proposes a novel optimization-based intelligent model selection procedure in which parameter identification is also performed during staged excavation. To conduct the model selection, a database of seven constitutive models accounting for isotropic or anisotropic yield surface, isotropic or anisotropic elasticity, or small strain stiffness for clayey soils is established, with each model numbered and deemed as one additional parameter for optimization. A newly developed real-coded genetic algorithm is adopted to evaluate the performance of simulation against field measurement. As the process of optimization goes on, the soil model exhibiting good performance during simulation survives from the database and model parameters are also optimized. For each excavation stage, with the selected model and optimized parameters, wall deflection and ground surface settlement of the subsequent unexcavated stage are predicted. The proposed procedure is repeated until the entire excavation is finished. This proposed procedure is applied to a real staged excavation with field data, which demonstrates its effectiveness and efficiency in engineering practice with highlighting the importance of anisotropic elasticity and small strain stiffness in simulating excavation. All results demonstrate that the current study has both academic significance and practical significance in providing an efficient and effective approach of adaptive optimization-based model selection with parameters updating in engineering applications.

     

确定多重现期暴雨公式参数的二次优化算法

四参数非线性多重现期暴雨公式在城市排水规划设计中有着广泛的应用。搜索算法与最小二乘法是优化计算的两个简单有效的方法,不过单独直接用于求解四参数非线性多重现期暴雨公式的参数比较困难。提出耦合最小二乘法及搜索算法确定多重现期暴雨公式参数的二次优化算法,该方法可以一次得到多重现期暴雨强度公式的参数,参数优化过程不需要图解。研究表明,计算结果比较客观;成果精度高,例题的平均绝对均方差为0.035mm/min。与遗传算法、蚁群算法等比较,该方法计算原理容易理解,计算简便,可以用Excel进行参数优化计算。     

Comparison of two inverse analysis techniques for learning deep excavation response

Performance observation is a necessary part of the design and construction process in geotechnical engineering. For deep urban excavations, empirical and numerical methods are used to predict potential deformations and their impacts on surrounding structures. Two inverse analysis approaches are described and compared for an excavation project in downtown Chicago. The first approach is a parameter optimization approach based on genetic algorithm (GA). GA is a stochastic global search technique for optimizing an objective function with linear or non-linear constraints. The second approach, self-learning simulations (SelfSim), is an inverse analysis technique that combines finite element method, continuously evolving material models, and field measurements. The optimization based on genetic algorithm approach identifies material properties of an existing soil model, and SelfSim approach extracts the underlying soil behavior unconstrained by a specific assumption on soil constitutive behavior. The two inverse analysis approaches capture well lateral wall deflections and maximum surface settlements. The GA optimization approach tends to overpredict surface settlements at some distance from the excavation as it is constrained by a specific form of the material constitutive model (i.e. hardening soil model); while the surface settlements computed using SelfSim approach match the observed ones due to its ability to learn small strain non-linearity of soil implied in the measured settlements.     

混合加速遗传算法在流域模型参数优化中的应用

在实编码遗传算法中加入单纯形搜索算子和加速搜索算子,提出了混合加速遗传算法.通过实例对该法与其它一些遗传算法进行了比较.并在大坳流域模型的参数优选中得到成功的应用.结果表明,混合加速遗传算法具有直观、简便、快速及适用性强等特点,是一种既可以较大概率搜索全局最优解,又能进行局部细致搜索的优秀非线性优化方法.     

基于遗传算法的岩土力学参数反演及其在 ABAQUS中的实现

岩土工程优化反分析是一个典型的复杂非线性函数优化问题,采用全局优化算法是解决这个问题的理想途径。结合ABAQUS有限元软件,提出遗传算法与有限元联合反演法,将有限元程序作为一个单独模块嵌入到遗传算法程序中,以测点的实测值与计算值建立误差函数,编制了遗传算法反演分析程序。并给出应用实例验证了该法的有效性,表明该方法可应用于岩土工程中的反演分析工作。     

水文模型参数多目标率定及最优非劣解优选

针对概念性水文模型参数众多、相互制约,且多目标参数优化率定最优参数求解困难、易受决策者主观因素影响的问题,采用多目标优化算法对水文模型参数进行率定,得到模型参数最优非劣解集,在此基础上,引入最小最大后悔值决策理论,并结合Pareto支配基本理论,提出了一种多目标最优非劣解选取准则。以柘溪流域为研究对象,采用三目标MOSCDE优化率定新安江模型的参数,并与单目标SCE-UA优化结果进行对比分析。结果表明,提出的非劣解选取方法可以有效从大规模非劣解集中筛选出最优非劣解,大大缩短参数率定耗时。     

Evaluation of complex petroleum reservoirs based on data mining methods

In this study, we introduce the application of data mining to petroleum exploration and development to obtain high-performance predictive models and optimal classifications of geology, reservoirs, reservoir beds, and fluid properties. Data mining is a practical method for finding characteristics of, and inherent laws in massive multi-dimensional data. The data mining method is primarily composed of three loops, which are feature selection, model parameter optimization, and model performance evaluation. The method’s key techniques involve applying genetic algorithms to carry out feature selection and parameter optimization and using repeated cross-validation methods to obtain unbiased estimation of generalization accuracy. The optimal model is finally selected from the various algorithms tested. In this paper, the evaluation of water-flooded layers and the classification of conglomerate reservoirs in Karamay oil field are selected as case studies to analyze comprehensively two important functions in data mining, namely predictive modeling and cluster analysis. For the evaluation of water-flooded layers, six feature subset schemes and five distinct types of data mining methods (decision trees, artificial neural networks, support vector machines, Bayesian networks, and ensemble learning) are analyzed and compared. The results clearly demonstrate that decision trees are superior to the other methods in terms of predictive model accuracy and interpretability. Therefore, a decision tree-based model is selected as the final model for identifying water-flooded layers in the conglomerate reservoir. For the reservoir classification, the reservoir classification standards from four types of clustering algorithms, such as those based on division, level, model, and density, are comparatively analyzed. The results clearly indicate that the clustering derived from applying the standard K-means algorithm, which is based on division, provides the best fit to the geological characteristics of the actual reservoir and the greatest accuracy of reservoir classification. Moreover, the internal measurement parameters of this algorithm, such as compactness, efficiency, and resolution, are all better than those of the other three algorithms. Compared with traditional methods from exploration geophysics, the data mining method has obvious advantages in solving problems involving calculation of reservoir parameters and reservoir classification using different specialized field data. Hence, the effective application of data mining methods can provide better services for petroleum exploration and development.     

Selection of sand models and identification of parameters using an enhanced genetic algorithm

Numerous constitutive models of granular soils have been developed during the last few decades. As a consequence, how to select an appropriate model with the necessary features based on conventional tests and with an easy way of identifying parameters for geotechnical applications has become a major issue. This paper aims to discuss the selection of sand models and parameters identification by using genetic algorithm. A real‐coded genetic algorithm is enhanced for the optimization with high efficiency. Models with gradually varying features (elastic‐perfectly plastic modelling, nonlinear stress–strain hardening, critical state concept and two‐surface concept) are selected from numerous sand models as examples for optimization. Conventional triaxial tests on Hostun sand are selected as the objectives in the optimization. Four key points are then discussed in turn: (i) which features are necessary to be accounted for in constitutive modelling of sand; (ii) which type of tests (drained and/or undrained) should be selected for an optimal identification of parameters; (iii) what is the minimum number of tests that should be selected for parameter identification; and (iv) what is the suitable and least strain level of objective tests to obtain reliable and reasonable parameters. Finally, a useful guide, based on all comparisons, is provided at the end of the discussion. Copyright © 2015 John Wiley & Sons, Ltd.     

A surrogate-based simulation–optimization approach application to parameters’ identification for the HydroGeoSphere model

A systematic approach is needed to use water more productively, because water shortages limit socio-economic development in many parts of the world. The aim of this paper is to establish a surrogate-based simulation–optimization approach to identify parameter values for a fully integrated surface water and groundwater flow coupling simulation. A surface water and groundwater flow coupling simulation model was implemented using HydroGeoSphere (HGS) model and the parameter sensitivities in the model were analyzed using local sensitivity analysis method. The parameters that exerted a large influence on the output results of the HGS model were then selected as stochastic variables, and the stochastic variable data sets were generated using the latin hypercube sampling (LHS) method, which, thereby, were used as inputs in HGS model to obtain the corresponding outputs. On the basis of input and output data sets, a kriging surrogate model of the HGS model was then established and verified, and parameter values of HGS model were identified using a surrogate-based simulation–optimization approach. The results of this study show that parameters that exert a large influence on the simulation output results include hydraulic conductivity, porosity, the van genuchten parameter (\(\alpha\)), and channel manning coefficient. The established kriging surrogate model is an ideal alternative to the HGS model for simulating and predicting, while optimal parameter values can be identified effectively and accurately using the established approach. The results of this research reveal that huge computational loads can be mitigated while using the kriging surrogate as an alternative for a simulation model in the solution process of optimization model.     

抽水试验资料的遗传算法反演水文地质参数

基于MATLAB遗传工具箱的遗传算法是一种借鉴生物界自然选择和自然遗传机制的全局最优化随机搜索算法。它以其简单通用、鲁棒性强、适于并行处理及高效等显著特点,在各领域得到了广泛的应用。结合抽水试验实例采用遗传算法反演水文地质参数,并将所求参数与配线法和直接图解法所得参数进行对比分析。结果显示,遗传算法所求参数的计算降深与实测降深吻合程度高,方便快捷,不失为一种有效的水文地质参数求解方法。