Structural Engineering Applications with Augmented Neural Networks

This paper presents an augmented neural network (ANN), a novel neural network architecture, and examines its efficiency and accuracy for structural engineering applications. The proposed architecture is that of a standard backpropagation neural network with augmented neurons, that is, logarithm neurons and exponent neurons are added to the network's input and output layers. The principles of augmented neural networks are (1) the augmented neurons are highly sensitive in the boundary domain, thereby facilitating construction of accurate mapping in the model's boundary domain, and (2) the network denotes each input variable with multiple input neurons, thus allowing a highly interactive function on hidden neurons to be easily formed. Therefore, the hidden neurons can more easily construct an accurate network output for a highly interactive mapping model. Experimental results demonstrate that the network's logarithm and exponent neurons provide a markedly enhanced network architecture capable of improving the network's performance for structural engineering applications.     

Effect of Representation on the Performance of Neural Networks in Structural Engineering Applications

Abstract: The pattern-mapping, pattern-classification, and optimization capabilities of neural networks have been used to solve a number of structural analysis and design problems. Most applications exploit the pattern-mapping capability and are based on the back-propagation paradigm for neural networks. There are a number of factors that influence the performance of these networks. This paper initially discusses these factors and the domain-dependent and -independent techniques presently available for improving performance. The paper then considers the effect of representation, selected for the input/output pattern pairs, on the performance of these networks and demonstrates that representations based on dimensionless terms, derived from dimensional analysis, lead to improved performance. It is shown that dimensional analysis provides a representational framework, with reduced dimensionality and embedded domain knowledge, within which effective learning can take place and that this representational change can be used to enhance the domain-independent and -dependent techniques presently available for improving performance of these networks.     

Recurrent Neural Networks for Structural Optimization

This paper presents an improvement for an artificial neural network paradigm that has shown significant potential for successful application to a class of optimization problems in structural engineering. The artificial neural network paradigm includes algorithms that belong to the class of single-layer, relaxation-type recurrent neural networks. The suggested improvement enhances the convergence performance and involves a technique that sets the values of weight parameters of the recurrent neural network algorithm. The complete procedure of solving an optimization problem with a single-layer, relaxation-type recurrent neural network is introduced. The discrete Hopfield network is employed to solve the weighted matching problem. A set of simulation experiments is performed to analyze the performance of the discrete Hopfield network. Simulation results confirm that the discrete Hopfield network locates a locally optimal solution after each relaxation once the weight parameters are specified as defined in the suggested technique.     

神经网络在结构优化设计中的应用

人工种经网络因其具有一些显著的特征而被广泛应用于许多领域，本文就人工种经网络在结构优化中的应用作了一些探讨，并编制了工程结构优化的神经网络计算程度，最后，对一实例进行了计算分析。     

神经网络在民用建筑设计工程中的应用

经过多年的发展,人工神经网络在传感器信息处理、信号处理、自动控制、知识处理、运输与通信等领域都取得了较大的发展,但是在建筑设计工程方面却涉猎较少.本文简述神经网络的发展和基本原理(包括模糊联想记忆),重点研究分析神经网络(FAM网)在民用建筑设计工程中的应用.在此基础上,提出了建筑设计领域应用神经网络尚需进一步研究的问题.     

From Neural Networks to Qualitative Models in Environmental Engineering

As an alternative to physical models, artificial neural networks (ANNs) are a valuable forecast tool in environmental sciences. They can be used effectively due to their learning capabilities and their low computational costs. Once all relevant variables of the system are identified and put into the network, it works quickly and accurately. However, one of the major shortcomings of neural networks is that they do not reveal causal relationships between major system components and thus are unable to improve the explicit knowledge of the user. Another problem is due to the fact that reasoning is only done from the inputs to the outputs. In cases where the opposite is requested (i.e., deriving inputs leading to a given output), neural networks can hardly be used. To overcome these problems, we introduce a novel approach for deriving qualitative information out of neural networks. Some of the resulting rules can directly be used by a qualitative simulator for producing possible future scenarios. Because of the explicit representation of knowledge, the rules should be easier to understand and can be used as a starting point for creating models wherever a physical model is not available. Moreover, the resulting rules are well adapted to be used in decision support systems. We illustrate our approach by introducing a network for predicting surface ozone concentrations and show how rules can be derived from the network and how the approach can be naturally extended for use in decision support systems.     

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.     

Structural Health Monitoring via Measured Ritz Vectors Utilizing Artificial Neural Networks

Abstract:   A pattern recognition approach for structural health monitoring (SHM) is presented that uses damage-induced changes in Ritz vectors as the features to characterize the damage patterns defined by the corresponding locations and severity of damage. Unlike most other pattern recognition methods, an artificial neural network (ANN) technique is employed as a tool for systematically identifying the damage pattern corresponding to an observed feature. An important aspect of using an ANN is its design but this is usually skipped in the literature on ANN-based SHM. The design of an ANN has significant effects on both the training and performance of the ANN. As the multi-layer perceptron ANN model is adopted in this work, ANN design refers to the selection of the number of hidden layers and the number of neurons in each hidden layer. A design method based on a Bayesian probabilistic approach for model selection is proposed. The combination of the pattern recognition method and the Bayesian ANN design method forms a practical SHM methodology. A truss model is employed to demonstrate the proposed methodology.     

基于卷积神经网络的结构损伤识别研究进展

为系统梳理基于卷积神经网络的工程结构损伤识别方法的发展脉络和研究现状,分别从结构损伤的识别目的和在不同类型结构中的应用两方面进行了归类、分析和评价。介绍了卷积神经网络的基本结构和评价指标,回顾了卷积神经网络的研究和应用历程。在损伤的识别目的方面,主要针对混凝土结构损伤的分类、定位和分割,详细介绍了基于不同类型卷积神经网络的结构损伤识别方法,即基于分类的方法、基于回归的方法和像素级的图像分割算法; 分析了各类方法所使用的卷积神经网络模型的结构特点、计算流程、训练方法和损伤识别性能。在不同类型结构的损伤识别方面,分析了卷积神经网络在砌体结构、钢结构桥梁和古建筑木结构裂缝识别中的应用。最后,基于对卷积神经网络优缺点的思考,提出了发展建议和展望。结果表明:训练样本中结构损伤的多样性对模型的损伤识别效果影响较大; 现有基于卷积神经网络的损伤分割方法模型参数较多,计算量大; 采用数据增广和迁移学习方法可有效防止模型过拟合,提高模型训练效率; 针对微小损伤和不同类型结构损伤的识别,此类方法的性能有待提高。     

基于神经网络的高层建筑结构体系选择

高层建筑结构初步设计中很重要的一项就是要确定结构体系,结构体系的选择是受许多因素影响的。本文提出了一个基于神经网络的专家系统来帮助设计人员选择恰当的结构体系,它利用了人工智能领域中的神经网络来存贮专家的设计经验,结果表明此方法是很有效的。     

Recurrent Neural Networks for Uncertain Time‐Dependent Structural Behavior

Abstract: In this article, an approach is introduced which permits the numerical prediction of future structural responses in dependency of uncertain load processes and environmental influences. The approach is based on recurrent neural networks trained by time‐dependent measurement results. Thereby, the uncertainty of the measurement results is modeled as fuzzy processes which are considered within the recurrent neural network approach. An efficient solution for network training and prediction is developed utilizing α‐cuts and interval arithmetic. The capability of the approach is demonstrated by means of the prediction of the long‐term structural behavior of a reinforced concrete plate strengthened by a textile reinforced concrete layer.     

人工神经网络在强夯工程中的运用分析与讨论

鉴于当前人工神经网络在岩土工程中的应用越来越广泛的情况下 ,本文分析和比较了多种人工神经网络模型对强夯问题的适用性和可靠性 ,并提出了几个人工神经网络在应用过程中应注意的问题 ,使之能够更好地指导强夯工程实践     

基于人工神经网络市政工程安全评价模型的研究

引对传统的市政工程安全评价方法存在的局限性，把市政工程看作一个复杂的人机，环境系统，将人工神经网络基本理论引入市政工程的安全评价中，建立较全面的市政工程安全评价指标体系，构建基于人工神经网络的非线性安全评价模型，并验证评价模型的可靠性。     

Artificial Neural Networks for Predicting the Response of Structural Systems with Viscoelastic Dampers

Abstract: Passive energy dissipation systems have been identified as one of the modern structural protective systems against seismic disturbances. Research and development activities are on globally to develop appropriate design procedures and suitable technology for application in the field. Structural systems with energy‐dissipating devices call for rigorous nonlinear analysis, which is a complex one and the results are highly sensitive to the type of input motion and component behavior assumed in the analysis. The Federal Emergency Management Agency 273 (FEMA 273) (1997) has suggested simplified procedures for replacing the original nonlinear system by an equivalent linear system. Recently, artificial intelligence (AI) techniques based on artificial neural networks (ANN) have been profitably used for solving complex problems of an iterative nature. Combining the equivalent model with an appropriate AI technique would help one to quickly predict the dynamic response of such yielding systems. This article highlights the feed forward back‐propagation neural network using the Levenberg–Marquardt algorithm for predicting the response quantity of systems with energy‐dissipating devices. The neural network is trained to reflect the nonlinear relationship of strength, stiffness, and damping existing in the system. The methodology developed is illustrated and validated with a chosen example from the FEMA 274 and is found to predict well the average peak displacement, base shear, and roof displacement. Based on these, the sensitivity studies have been carried out and the influence of each parameter on the results have been brought out. It may be noted that sensitivity details and the influence of each parameter do not show up in the regular time‐series analysis. The main advantage of the methodology and the network developed is in quick preliminary decision on the amount and the number of dampers required to reduce peak displacement for a new design as well as for retrofitting.     

管幕工程地表变形的人工神经网络预测研究

管幕工法是一种新型的地下空间暗挖技术.国内首次应用于上海市中环线浦西段的北虹路下立交工程.该工法为解决软土地区超大断面地下工程的施工变形问题开创了新的领域.管幕工法虽然可以减少对周边环境的影响,但并不能完全消除.作者在充分研究钢管幕顶进施工过程中引起的地表变形特征基础上,建立相应的预测模型,应用人工神经网络智能滚动预测方法,对管幕工程的地表变形进行预测研究.研究表明：人工神经网络的一步滚动预测可以满足实际的工程需要,但精度相对偏低.而多步滚动预测虽可以得到较高的预测精度,但在实际工程应用中还需解决量的优化问题.     

Tide Prediction Using Neural Networks

Prediction of tides at a subordinate station located in the interior of an estuary or a bay is normally done by applying an empirical correction factor to observations at some standard or reference station. This paper presents an objective way to do so with the help of the neural network technique. In complex field conditions this approach may look more attractive to apply. Prediction of high water and low water levels as well as that of continuous tidal curves is made at three different locations. The networks involved are trained using alternative training algorithms. Testing of the networks indicated satisfactory reproduction of actual observations. This was further confirmed by a high value of the accompanying correlation coefficient. Such a correlation was better than the one obtained through use of the statistical linear regression model. The training algorithm of cascade correlation involved the lowest training time and hence is found to be more suitable for adaptive training purpose.     

Solid Modeling in Structural Engineering

The importance of using a solid-modeling system in the computer-aided design of three-dimensional objects has been widely recognized. In Structural Engineering applications, solid-modeling systems that represent a structure are much more useful than conventional three-dimensional wire-frame models of that structure. Although the realistic, color-shaded display produced by solid-modeling systems are often thought to be its focus, graphic rendering is just one of the applications drawing from the central computerized model. In this article, we will briefly review solid-modeling concepts, components, terminology, and look at the role played by computer graphics.     

Neural Networks for Wave Height Interpolation

Information on the heights of ocean waves at a site can be collected by a variety of instruments—each involving different methods of data retrieval and synthesis. Typically, sensing of wave heights by satellite requires the wave information to be presented in the form of values that are averaged over space and time intervals. In order to use such data for operational applications, it then becomes necessary to derive the wave heights over shorter intervals from their values available over long durations. This paper attempts to do this by employing the technique of neural networks. A simple three–layered feedforward network trained with the supervised backpropagation technique was used. The values of monthly mean significant wave heights available at different grid locations around the Indian coastline were given as input to obtain the output of weekly mean wave heights at the same locations. Analysis of the results indicated usefulness of the neural network technique in wave height interpolation problems.     

Representing Design Knowledge with Neural Networks

Neural networks have been used in a number of civil engineering applications because of their ability to implicitly learn an input–output relationship. Typically, the applications involve deriving an input–output relationship for problems that may be too complex to model mathematically, computationally expensive, or difficult to solve using the traditional procedural computing approach. Heuristic design knowledge used by structural engineers when performing structural design often falls in the latter category of being difficult to represent procedurally. Neural networks have been investigated for the representation of heuristic design knowledge, and the results of this investigation and the lessons learned regarding neural network training are presented.     

Real-Time Flood Forecasting Using Neural Networks

Real-time forecasting of stream flows during storms provides an essential input to operational flood management. This work is usually very complex owing to the uncertain and unpredictable nature of the underlying phenomena. The technique of neural networks therefore was applied to model it. Forecasting of flood values during storms with a lead time of one and more hours was made using a selected sequence of past flood values observed at a specific location. Training of the network was done with the help of three alternative methods, viz., error backpropagation, conjugate gradient, and cascade correlation. Resulting flood forecasts were found to be satisfactory—especially when warning time was the least.