A Structural Damage Neural Network Monitoring System

Abstract: Traditional methods for structural monitoring and damage assessment have been implemented largely through visual inspection and on-site tests. A system for automating this process should be able to record the various signatures of the structure to be monitored and issue a warning signal if there is a damage-related change in those signatures. In this paper, a general system for structural damage monitoring is proposed based on observations of other researchers and the results obtained from a case study of a physical and analytical model of a five-story steel frame. The proposed diagnostic system utilizes neural networks for identifying the damage associated with changes in structural signatures. The system is independent of the type of signatures used for monitoring. Two sets of neural networks were developed. The first set was trained with the results of a series of shaking-table experiments, while the second set was trained with the output produced from a finite-element model of the same test structure. The results show that the proposed system provides a suitable framework for automatic structural monitoring.     

基于MATLAB神经网络的高层建筑结构选型研究

随着土木工程技术的发展,结构选型在高层建筑结构设计中的重要性越来越明显。但是由于高层建筑结构选型是一个非常复杂的问题,本文提出应用MATLAB神经网络方法对高层建筑进行结构选型。并用MATLAB语言编制了人工神经网络高层建筑结构选型专家系统使选型过程简单明了。结果表明此方法可行,可以帮助设计人员选择恰当的结构型式。     

基于BP神经网络的建筑结构隔震初步设计系统

基于BP人工神经网络,以建筑结构的抗震设防类别、设防烈度、场地类别、地震分组、高宽比、长宽比、刚度,质量和面积为主要影响因子,以隔震后结构的最大层剪力比和支座最大位移作为输出结果,建立一个隔震初步设计系统.经25个训练样本对该网络进行训练后,利用15个测试样本对网络进行了测试.通过测试结果与实际设计结果的对比,网络的平...     

Structural Monitoring System Based on Sensitivity Analysis and a Neural Network

A design procedure for a structure's monitoring system using sensitivity analysis and a neural network is developed. The monitoring system is to be used to monitor damage to members critically affecting the overall safety of structures. Recently, many techniques for evaluating the damage of isolated members and models of simple structures have been investigated. However, actual structures are large, and their complex behavior may not be based on damage of isolated members or their simple models. To monitor large structures realistically, structures' data on behavior at many points need to be monitored. Identifying the optimal locations and numbers of these monitoring points and assessing the safety of the entire structure from the limited data are the monitoring system design problem. The procedure presented for this design problem is a two-step process. In the first step, using sensitivity analysis and damage-assessment techniques, individual members are ranked according to their influence on the failure probability of the entire structure or according to their effect on the abnormal behavior of the structure. Based on the rank, critical members are identified. In the second step, sensitivity analysis and a neural network are used to determine the optimal locations. In addition, the optimal number of sensors for monitoring damage to the critical members selected in step 1 is also suggested. Truss and frame examples are used to show the validity and applicability of the monitoring system design procedure.     

A Wavelet Support Vector Machine‐Based Neural Network Metamodel for Structural Reliability Assessment

Wavelet neural network (WNN) has been widely used in the field of civil engineering. However, WNN can only effectively handle problems of small dimensions as the computational cost for constructing wavelets of large dimensions is prohibitive. To expand the application of WNN to higher dimensions, this article develops a new wavelet support vector machine (SVM)‐based neural network metamodel for reliability analysis. The method first develops an autocorrelation wavelet kernel SVM and then uses a set of wavelet SVMs with different resolution as the activation function of WNN. The output of network is obtained through aggregating outputs of different wavelet SVMs. The method takes advantage of the excellent capacities of SVM to handle high‐dimensional problems and of the attractive properties of wavelet to represent complex functions. Four examples are given to demonstrate the application and effectiveness of the proposed method.     

RBF网络的结构动力响应预测

由于结构主动控制对地震反应振动控制的高效性,使主动控制在建筑结构振动控制领域中,具有广阔的应用前景,但是主动控制存在难以建立一个精确的数学模型,存在时滞效应等问题.神经网络不需要建立精确的数学模型,只是通过学习输入输出训练样本数据,就可归纳出隐含在系统输入输出中的关系;应用神经网络预测结构响应可以解决主动控制中的时滞问题,为控制决策提供依据.用RBF神经网络对结构响应进行预测,以期能为结构主动控制提供一种新的思路.     

卷积神经网络在结构损伤诊断中的应用

对卷积神经网络(CNN)在工程结构损伤诊断中的应用进行了深入探讨; 以多层框架结构节点损伤位置的识别问题为研究对象,构建了可以直接从结构动力反应信号中进行学习并完成分类诊断的基于原始信号和傅里叶频域信息的一维卷积神经网络模型和基于小波变换数据的二维卷积神经网络模型; 从输入数据样本类别、训练时间、预测准确率、浅层与深层卷积神经网络以及不同损伤程度的影响等多方面进行了研究。结果表明:卷积神经网络能从结构动力反应信息中有效提取结构的损伤特征,且具有很高的识别精度; 相比直接用加速度反应样本,使用傅里叶变换后的频域数据作为训练样本能使CNN的收敛速度更快、更稳定,并且深层CNN的性能要好于浅层CNN; 将卷积神经网络用于工程结构损伤诊断具有可行性,特别是在大数据处理和解决复杂问题能力方面与其他传统诊断方法相比有很大优势,应用前景广阔。     

Selection of Methodology for Neural Network Modeling of Constitutive Hystereses Behavior of Soils

Classic constitutive modeling of geomaterials based on the elasticity and plasticity theories suffers from limitations pertaining to formulation complexity, idealization of behavior, and excessive empirical parameters. This article capitalizes on the modeling capabilities of neural networks as substitutes for the classic approaches. The neural network–based modeling overcomes the difficulties encountered in understanding the underlying microscopic processes governing the material's behavior by redirecting the efforts into learning the cause-effect relations from behavioral examples. Several methodologies are presented and cross-compared for effectiveness in approximating a theoretical hysteresis model resembling stress-strain behavior. The most effective methodology was used in modeling the constitutive behavior of an experimentally tested soil and produced models that simulated the real behavior of the soil with high accuracy. Although these models are empirical, they are retrainable and thus, unlike classic constitutive modeling techniques, can be revised and generalized easily when new data become available.     

采暖系统利用神经网络的运行方案

由于不带恒温阀的常规采暖系统在一定时期内还会大量存在,而现有的质量并调方案建立在“静态”基础上,忽略了系统的热惰性,使系统逐时供热量与需热量不一致,造成系统热用户室温偏高或偏低,即降低了供热品质,又浪费能源。本文利用神经网络理论,建立了一种常规采暖系统的自适应控制方案。模拟结果显示,这种“动态”运行方案克服了常规“静态”运行方案的缺点。     

用人工神经网络方法估计桥梁在温度作用下的挠度行为

桥梁结构的挠度变化除了与车辆、人群等荷载有关之外,还与环境的作用密切相关,在大跨径桥梁结构安全监测系统中进行结构安全状态评估时需要知道桥梁结构在环境作用下的行为,以便分离环境与例如汽车、人群等荷载的不同影响。挠度变化是桥梁结构安全监测系统中反应桥梁安全状态最直观的参数之一,荷载与环境的作用、结构材料的变异都可以通过挠度的变化表现出来。但是通常所测得的挠度是桥梁在环境温度、车辆荷载等综合作用下的总响应,而不同荷载条件作用可以使得结构产生同样的挠度,由于不同的荷载条件可以引起同样的挠度但是产生不同的应力,因此将挠度分类是十分必要的。本文尝试用神经网络方法通过实测值来模拟温度与挠度之间的非线性关系,并用它来预测桥梁由温度所产生的挠度变化,从而可以将这温度产生的挠度值从实时的总挠度中分离出来,以便进行其他部分挠度评估的分析。     

徐汇日月光天幕结构选型与设计

徐汇日月光天幕造型为马鞍形自由曲面,视觉效果要求简洁通透,塔楼柱位受到限制,天幕支承条件较差。结构设计中创新性地采用了"局部张弦单层网壳+谷状柱"的结构体系。重点阐述了天幕结构体系选型优化的思路和结构布置优化的全过程,介绍了天幕结构的结构布置、静动力特性、预应力索索力、整体稳定性和极限承载力,考察了地震作用下塔楼侧移对天幕结构的影响。此外,对菱形区格内钢拉杆的布置方式进行了对比优化。分析结果表明,"局部张弦单层网壳+谷状柱"同时满足建筑美学要求和结构力学要求,实现了通过结构营造建筑观感的构想。     

热负荷预测中应用神经网络模型的研究

区域供热热负荷的变化是典型的非线性变化，供热系统在确定建设规模，制定运行、检修计划方面面临许多因素的影响。本文对神经网络BP算法供热热负荷预测方面的应用在理论上做了一些研究，并引入实例对所建模型进行训练和检验，取得比较满意的效果。     

A Backpropagation Neural Network Model for Semi-rigid Steel Connections

Abstract: The analysis of semirigid steel structure connections based on exact theoretical modeling, which is demanding and time consuming if all the nonlinear parameters of the problem are taken into account, can be avoided provided that enough experimental measurements exist and an appropriate predictor can be constructed from them. A supervised learning backpropagation neural network approach is proposed in this paper for the construction of this model free predictor. A number of experimental momentrotation curves for single-angle and single-plate beam-to-column connections are used in this paper to train the neural network. The trained network provides us with an estimator for the mechanical behavior of the steel structure connection element.     

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.     

地下水资源系统人工神经网络模型的建立与应用

本文从人工神经网络的基本原理出发建立了地下水资源系统的人工神经网络的普适模型,并用实例加以验证,结果表明该模型是正确适用的。     

人工神经网络在HVAC系统的应用

阐述了构成人工神经网络(ANN)的M-P神经元模型的结构、输出输入的函数关系及人工神经网络中最常用的学习规则———BP网络。综述了人工神经网络在暖通空调系统中的应用,包括预期平均评价指标(PMV)的预测、房间冷负荷的预测、能量管理、故障诊断及其他应用。介绍了BP网络的改进算法。     

供热管网土建结构选型与经济成本探讨

介绍了热网土建结构的分类、铺设方式;分析了影响供热管网成本的主要因素及措施.     

粘土本构关系的神经网络模型

土的本构关系是土力学与工程的一个重要理论和实际问题。本文改变传统的数学建模方法,运用神经网络方法,建立一个粘土的非线性本构关系模型。神经网络方法;较传统方法建模方便,精度提高。     

基于高效神经网络的框架结构节点损伤的多重分步识别方法

提出了基于神经网络的框架结构节点损伤的多重分步识别方法,建立了用于框架结构节点损伤识别的高效神经网络法。根据节点损伤的多重分步识别思路,把节点损伤识别主要分为四步:第一步利用神经网络建立损伤异常过滤器对节点损伤进行预警;第二步以频率构造的组合指标作为神经网络输入向量,对节点损伤进行初步定位;第三步以归一化的应变模态差绝对值作为神经网络输入向量,对节点损伤进行具体定位;第四步以应变模态差绝对值作为神经网络输入向量,对节点损伤程度进行识别。针对三跨四层的框架结构进行了节点损伤识别数值模拟,结果表明:应用神经网络技术,采用多重分步识别方法,简化了网络的结构,能够有效地对框架结构节点损伤进行预警、定位和定量。