基于PINNs算法的地下水渗流模型求解及参数反演

地下水渗流模型的渗流流速计算（正向求解）和渗流参数反演（反向求解）工程意义重要，但目前能同时解决两类问题的算法较少。针对该问题，引入了物理信息神经网络（PINNs）算法，并加入硬约束进行改进，在正向求解方面，分别建立了渗流方程与达西定律耦合的水头、流速同时求解方法（PINNs-H-I），以及先计算水头再通过自动微分求解流速的计算方法（PINNs-H-II）。对于反向求解，分别采用单（多）物理场神经网络模型的PINNs算法反演均质（非均质）渗流参数。通过算例分析表明，相比软约束PINNs算法，通过施加硬约束可同时改善正向求解和反向求解的性能，另外在正向渗流速度计算中PINNs-H-II方法具有更高的计算精度，同时单（多）物理场神经网络模型PINNs算法反演的均质（非均质）渗流参数与实际值符合较好。     

位移反分析的APSO-WNN模型研究及应用

用改进粒子群优化算法对小波神经网络进行优化，从而提出改进粒子群算法优化小波神经网络模型（APSO-WNN）。该模型具有小波变换的良好时频局域化性质、良好时域和频域分辨能力及传统神经网络的自学习功能；同时用改进的粒子群优化法进行全局最优搜索，快速收敛到全局最优解，使其具有良好的逼近能力、容错能力和较强的鲁棒性。因此，该计算模型适合解决具有复杂非线性和模糊性特点的岩土工程问题。为证明该模型的优越性，同时将该计算模型与传统遗传算法神经网络用于三峡船闸高边坡4种介质弹性模量的位移反分析计算，结果表明不论是优化精度还是收敛时间，该算法都较遗传算法有明显提高。最后利用APSO-WNN反演的弹性模量参数进行测点位移预测，预测表明各个测点的计算位移值与监测值吻合较好，说明该模型在岩土工程位移反分析中具有良好的实际应用价值。     

岩土工程参数反演的一种新方法

介绍了新近提出的一种模拟进化算法——粒子群算法,相对于其他进化算法,粒子群算法的优势在于简单、易实现且收敛快。把该算法引入岩土工程参数反演领域,同时为了克服粒子群算法后期搜索效率降低的缺陷,把单纯形法嵌入到粒子群算法中,提出岩土工程参数反演的一种新方法——基于粒子群算法和单纯形法的混合算法。算例表明,混合算法在参数反演计算中体现出良好的优化性能和很快的收敛速度,是一种新颖可行的参数反演方法。     

场分布参数的声波层析成像反演

温度场、渗流场和应力场等参数的检测是岩土工程领域中重要课题,利用场参数与声学参数的对应关系,通过声波层析成像技术可获取工程体内部的场分布特征。将描述物理场分布特征的偏微分方程转化为平滑算子,实现了物理场分布规律对层析成像反演过程的约束,提高了反演解释的精度。最后,通过数值模拟,说明了该方法的特点。     

基于蚁群算法的土石坝土体参数反演

介绍了新近为求解复杂组合优化问题而提出的蚁群算法。将蚁群算法运用于土石坝土体参数反演问题的求解:先对反演参数的搜索空间进行离散,将参数反演问题转化成一个组合优化问题;再针对土体参数反演问题的特点,改进蚁群算法,并将其用于土体参数的反演计算。算例表明,改进蚁群算法可有效求解土石坝土体参数反演问题。     

岩锚梁非绝热温升试验反分析研究及应用

混凝土热学参数的准确性直接影响仿真计算结果的工程应用价值,通过工程现场的非绝热温升试验获得这些参数不仅可靠而且经济。混凝土热学参数辨识是一个复杂的寻优问题,优化算法的选取是其中一个关键因素。PSO算法具有很强的可塑性,通过对约束条件的处理,将该算法应用于工地现场的混凝土非绝热温升试验反演计算中,并验证了反演结果的合理性,然后依据这些参数,采用三维有限单元法对工程岩锚梁混凝土施工期的温度场和应力场进行反馈计算,从而指导岩锚梁的施工。工程实例表明,PSO算法对多参数的复杂问题具有较强的寻优能力,是一种简单且易于实现的优化算法,值得在工程上推广应用。     

基于BP神经网络的矩形沉井下沉土体参数反演研究

各类型的人工神经网络智能算法均在岩土工程参数反演和预测方面得到了广泛应用,但大部分研究都主要集中在坝体、桩基和隧道工程方面,较少应用于沉井基础形式的工程。BP神经网络算法对于施工过程中岩土结构参数的时空变化非常敏感,适用于研究沉井这类经历显著地质扰动和动态位移的基础形式。依托龙潭长江大桥南部锚碇沉井基础项目,运用有限元参数建模,将沉井下沉动态过程划分为多个工况,在不影响模拟精度的情况下,提高了计算效率,得到了多组土体参数与沉井结构应力响应之间的数据组。使用该数据组训练BP神经网络模型,并将现场监测的沉井应力输入到BP神经网络模型中,反演得到了对应的土体参数,分析其变化规律,总结了沉井动态受力特点。该研究结果有助于完善助沉方案,在解决突沉、拒沉等问题方面起到了关键作用。     

大体积混凝土水化热温度场的MATLAB算法

结合工程实例,介绍了大体积混凝土温度场的MATLAB算法。在计算中使用等效热传导方程考虑通冷却水对混凝土温度场的影响,在此基础上使用MATLAB的偏微分方程求解器求解热传导方程,对大体积混凝土承台浇筑后15d的温度场进行了计算,并与实测值进行了对比,结果表明计算精度完全可以满足工程应用要求。此外,与传统理论算法和有限元算法相比,该算法计算效率较高,可为同类问题的计算提供参考。     

基于人工神经网络的快速法载荷试验数据处理

人工神经网络方法因能够模拟岩土工程问题中各参数之间的非线性关系而在岩土工程中有越来越多的应用。根据 BP 神经网络算法,利用 VB 语言编制了计算程序,通过对工程实例的分析,说明人工神经网络方法适用于快速法载荷试验的数据处理过程,可以较好的预测各级荷载作用下的稳定沉降量。     

基于改进粒子群算法CHPSO-DS的面板 坝堆石体力学参数反演

面板堆石坝堆石体力学参数反演优化问题是一个多变量、多约束的混合非线性规划问题,当正演过程用神经网络模拟器替代后,高效快捷的优化算法成为解决问题的关键.提出一种用以解决这一复杂优化问题的混合算法--混沌直接搜索粒子群(CHPSO-DS)算法.在改进的算法中,首先结合混沌优化思想对粒子群进行初始化,减轻粒子初始位置的选择对算法优化性能的影响;利用直接搜索法克服了粒子群算法后期搜索效率降低的缺陷,提高算法局部搜索能力.为证明该算法的优越性,同时将该算法与遗传算法(GA)用于水布垭面板堆石坝堆石体力学参数的位移反分析计算中.实践证明,利用CHPSO-DS算法搜索时能快速收敛到全局最优解,且算法具有较强的鲁棒性;两算法对比结果也表明,不论是优化精度还是收敛时间,CHPSO-DS算法都较GA有明显提高.最后利用CHPSO-DS算法反演的堆石体力学参数进行测点沉降预测,结果表明各个测点的计算位移值与监测值吻合较好,说明CHPSO-DS算法在复杂岩土工程位移反分析中具有良好的实际应用价值,值得进一步研究和推广.     

人工神经网络在岩土工程中的应用

人工神经网络在近几年来发展迅速。基于人工神经网络的方法在岩土工程中得到了广泛的应用。神经网络的模型很多 ,很多学者在他们的研究中采用了BP神经网络。通过对BP神经网络方法与传统方法进行比较发现有其独特的优点。由于岩土工程中的问题的复杂性 ,在已知量与未知量之间存在很强的非线性关系。这种非线性关系通过人工神经网络可以很好地映射。笔者认为神经网络在岩土工程中是可行的 ,必将会引起更多的岩土工程师的兴趣     

Neural Networks in Civil Engineering: 1989–2000

The first journal article on neural network application in civil/structural engineering was published by in this journal in 1989. This article reviews neural network articles published in archival research journals since then. The emphasis of the review is on the two fields of structural engineering and construction engineering and management. Neural networks articles published in other civil engineering areas are also reviewed, including environmental and water resources engineering, traffic engineering, highway engineering, and geotechnical engineering. The great majority of civil engineering applications of neural networks are based on the simple backpropagation algorithm. Applications of other recent, more powerful and efficient neural networks models are also reviewed. Recent works on integration of neural networks with other computing paradigms such as genetic algorithm, fuzzy logic, and wavelet to enhance the performance of neural network models are presented.     

Steady-state temperature distribution in a tetragonal solid

ABSTRACT

The main objective of the project is to use a simple numerical technique to find out the temperature distribution in each of the three planes of the block. For many practical problems, numerical methods to solve partial differential equations (PDEs) are required. Conventional finite element or finite-difference codes have a difficulty to obtain precise solutions because of the need for an exceedingly fine mesh, which leads to often prohibitive CPU time. While conventional methods exhibit such a difficulty, some practical problems even require solutions guaranteed. The Laplace equation is one of the important PDEs in physics and engineering, describing the phenomenology of electrostatics among others, and various problems for the Laplace equation require highly precise and verified solutions. We present an alternative approach based on numerical method by computer programming in order to find the temperature distribution in the three-dimensional solid.     

Neural Networks in Structural Engineering

In the past few years literature on computational civil engineering has concentrated primarily on artificial intelligence (Al) applications involving expert system technology. This article discusses a different Al approach involving neural networks. Unlike their expert system counterparts, neural networks can be trained based on observed information. These systems exhibit a learning and memory capability similar to that of the human brain, a fact due to their simplified modeling of the brain's biological function. This article presents an introduction to neural network technology as it applies to structural engineering applications. Differing network types are discussed. A back-propagation learning algorithm is presented. The article concludes with a demonstration of the potential of the neural network approach. The demonstration involves three structural engineering problems. The first problem involves pattern recognition; the second, a simple concrete beam design; and the third, a rectangular plate analysis. The pattern recognition problem demonstrates a solution which would otherwise be difficult to code in a conventional program. The concrete beam problem indicates that typical design decisions can be made by neural networks. The last problem demonstrates that numerically complex solutions can be estimated almost instantaneously with a neural network.     

Neural Network Approaches to Aid Simple Truss Design Problems

Abstract: Diverse problems in engineering may be solved accurately with computers. In structural engineering, many solution techniques exist. Over the past few years, neural networks have evolved as a new computing paradigm, and many engineering applications have been studied. This paper describes configuring and training of a neural network for a truss design application and explores the possible roles for neural networks in structural design problems. The specific problem considered is a simple truss design where, given a geometry and a loading, economical cross-sectional areas of all the members are to be selected. For this problem, a two-layer neural network is trained using the back-propagation algorithm with patterns representing optimal designs for diverse loading conditions. The performance of the trained neural network is evaluated with a sample problem.     

Artificial neural network optimized by differential evolution for predicting diameters of jet grouted columns

A novel and effective artificial neural network (ANN) optimized using differential evolution (DE) is first introduced to provide a robust and reliable forecasting of jet grouted column diameters. The proposed computational method adopts the DE algorithm to tackle the difficulties in the training and performance of neural networks and optimize the four quintessential hyper-parameters (i.e. the epoch size, the number of neurons in a hidden layer, the number of hidden layers, and the regularization parameter) that govern the neural network efficacy. This approach is further enhanced by a stochastic gradient optimization algorithm to allow ‘expensive’ computation efforts. The ANN-DE is first trained using a prepared jet grouting dataset, then verified and compared with the prevalent machine learning tools, i.e. neural networks and support vector machine (SVM). The results show that, the ANN-DE outperforms the existing methods for predicting the diameter of jet grouting columns since it well balances training efficiency and model performance. Specifically, the ANN-DE achieved root mean square error (RMSE) values of 0.90603 and 0.92813 for the training and testing phases, respectively. The corresponding values were 0.8905 and 0.9006 for the optimized ANN, then, 0.87569 and 0.89968 for the optimized SVM, respectively. The proposed paradigm is bound to be useful for solving various geotechnical engineering problems regardless of multi-dimension and nonlinearity.     

算子识别反问题模型优化与数据优化的联合反演技术

针对算子识别反问题,分析了解的不适定性与模型误差、数据误差的关系,建立了基于模型优化和数据优化的联合反演技术,提出了适合同时处理数字式数据与非数字式数据的量化单调消噪方法。建立了数值反演可靠性概念,包括正演算子可靠性、正演计算可靠性、测量设计可靠性、反演算法可靠性、反演计算可靠性、测量数据可靠性,并建立了相应的可靠性定量评估方法。通过一个岩土工程的算子识别反问题的工程应用与数值试验说明:其一,这一联合反演技术实质是一门系统性的优化技术,能够显著提高数值反演的可靠性和准确度;其二,应用可靠性定量评估方法,能够客观地、定量地获得反问题解估计的质量评定。     

岩土工程时间序列预报问题初探

 对岩土工程中的时间序列预报问题进行了研究, 认为: 在该类问题中, 灰色建模存在着一定的问题, 通过两个实例指出神经元网络是解决岩土工程时间序列预报问题的有效方法。     

Analysis of stochastic systems in continuum physics: Some developments of the stochastic adaptive interpolation method

This paper deals with the analysis of stochastic systems in continuum physics which are modelled by a random partial differential equation using the so called stochastic adaptive interpolation method. This paper proposes some developments of the method, mainly oriented towards the solution of stochastic inverse problems.