Nonparametric Identification of a Building Structure from Experimental Data Using Wavelet Neural Network

Abstract:   This study presents a wavelet neural network-based approach to dynamically identifying and modeling a building structure. By combining wavelet decomposition and artificial neural networks (ANN), wavelet neural networks (WNN) are used for solving chaotic signal processing. The basic operations and training method of wavelet neural networks are briefly introduced, since these networks can approximate universal functions. The feasibility of structural behavior modeling and the possibility of structural health monitoring using wavelet neural networks are investigated. The practical application of a wavelet neural network to the structural dynamic modeling of a building frame in shaking tests is considered in an example. Structural acceleration responses under various levels of the strength of the Kobe earthquake were used to train and then test the WNNs. The results reveal that the WNNs not only identify the structural dynamic model, but also can be applied to monitor the health condition of a building structure under strong external excitation.     

Enhancing Neural Network Traffic Incident-Detection Algorithms Using Wavelets

Researchers have presented freeway traffic incident-detection algorithms by combining the adaptive learning capability of neural networks with imprecision modeling capability of fuzzy logic. In this article it is shown that the performance of a fuzzy neural network algorithm can be improved through preprocessing of data using a wavelet-based feature-extraction model. In particular, the discrete wavelet transform (DWT) denoising and feature-extraction model proposed by Samant and Adeli (2000) is combined with the fuzzy neural network approach presented by Hsiao et al. (1994). It is shown that substantial improvement can be achieved using the data filtered by DWT. Use of the wavelet theory to denoise the traffic data increases the incident-detection rate, reduces the false-alarm rate and the incident-detection time, and improves the convergence of the neural network training algorithm substantially.     

A Neuro-Fuzzy Logic for ATIS Stand-Alone Control Systems: Structure, Calibration, and Analyses

Abstract:   An Advanced Traveler Information System (ATIS) stand-alone operation scheme is formulated as a bi-level optimization problem. The scheme logic attempts to optimize the network overall travel time by adjusting the path proportions while guessing the signal phase split decisions. An approximate simulation-based optimization algorithm is devised as an example of the logic operating this scheme. The logic is then replicated by a fuzzy-logic control system. Neural nets are utilized to develop the knowledge base of the fuzzy system and to calibrate the fuzzy set parameters. The neural nets utilize data replicates generated by the approximate simulation-based optimization algorithm. The calibration and effectiveness results of the fuzzy control system are presented.     

改进的边坡岩体稳定性预测模型研究

由于边坡岩体的结构与物理力学性质表现出宏观和微观上的不连续性和高度的非线性等特点,其稳定性受地质因素和工程因素等的综合影响,这些因素大部分具有随机性、模糊性、可变性等不确定性特点,因此,边坡工程是不确定的、非线性的、动态开放性的复杂大系统,传统分析方法往往难以准确地描述这种复杂的非线性特征,因而对大型复杂边坡的稳定性进行准确预测预报尚存在一定的困难。提出了基于模拟退火交替迭代算法神经网络的边坡安全系数预测方法,在相同的初始条件下,用该方法和经典网络进行了比较,得出前者的优越性和有效性。在综合分析边坡岩体变形失稳破坏模式及其影响因素的基础上,采用了表征边坡岩体稳定性分析的复合指标为预测模型的影响因子。并利用该方法对收集到的水电工程边坡实例进行学习,对未学习过的边坡实例进行推广预测,取得了较好的效果,其预测精度明显优于经典算法BP神经网络。由此说明所提出的预测模型能够快速、准确地获取不同方案下的边坡安全系数,为选择经济合理的边坡设计方案提供了新的思路。     

基于微粒群算法和模糊神经网络的火灾探测研究

针对火灾探测的特点,将模糊系统和神经网络有机结合,实现模糊系统设计参数的自动调整。采用符合国家标准明火、阴燃火以及厨房环境下的干扰火等作为模糊神经网络的训练样本和测试样本,依据模糊神经网络算法要求,完成了网络结构的设计,并给出相应的计算模型,利用微粒群算法对网络的权值进行学习与训练。结果表明,该算法在探测国家标准火的火灾状态方面具有有效性和可行性。     

基于遗传神经网络的坝基岩体渗透系数识别

基于坝基岩体渗流场正演分析的数学模型，通过观测渗流区域地下水运动的动态信息反演坝基岩体的渗透系数。将遗传算法和神经网络相结合，所建立的遗传神经网络具有较快的训练速度和较强的泛化能力。数值算例表明，遗传神经网络在求解坝基岩体渗透系数反演问题中具有较高的计算效率和识别精度。     

Machine Learning in Engineering Analysis and Design: An Integrated Fuzzy Neural Network Learning Model

Applying neural network computing to structural engineering problems has received increasing interest, with particular emphasis placed on a supervised neural network with the backpropagation (BP) learning algorithm. In this article, we present an integrated fuzzy neural network (IFN) learning model by integrating a newly developed unsupervised fuzzy neural network (UFN) reasoning model with a supervised learning model in structural engineering. The UFN reasoning model is developed on the basis of a single-layer laterally connected neural network with an unsupervised competing algorithm. The IFN learning model is compared with the BP learning algorithm as well as with a counterpropagation learning algorithm (CPN) using two engineering analysis and design examples from the recent literature. This comparison indicates not only a superior learning performance in solved instances but also a substantial decrease in computational time for the IFN learning model. In addition, the IFN learning model is applied to a complicated engineering design problem involving steel structures. The IFN learning model also demonstrates superior learning performance in a complicated structural design problem with a reasonable computational time.     

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。     

基于模糊逻辑与神经网络的高层结构半主动控制

根据剪切型结构动力特性提出AVSD开关控制律。把开关控制律作为专家知识,利用模糊逻辑转化为模糊控制规则。为了进行时滞和结构动力特性时变的控制补偿,采用神经网络在线自适应跟踪辨识方法进行在线辨识和响应预测。最后以某框架结构为例进行仿真分析,结果表明这一方法控制效果及鲁棒性好、实际应用方便可靠。     

Modelling of structural response and optimization of structural control system using neural network and genetic algorithm

This paper proposes an integrated approach to the modelling and optimization of structural control systems in tall buildings. In this approach, an artificial neural network is applied to model the structural dynamic responses of tall buildings subjected to strong earthquakes, and a genetic algorithm is used to optimize the design problem of structural control systems, which constitutes a mixed‐discrete, nonlinear and multi‐modal optimization problem. The neural network model of the structural dynamic response analysis is included in the genetic algorithm and is used as a module of the structural analysis to estimate the dynamic responses of tall buildings. A numerical example is presented in which the general regression neural network is used to model the structural response analysis. The modelling method, procedure and the numerical results are discussed. Two Los Angeles earthquake records are adopted as earthquake excitations. Copyright © 2000 John Wiley & Sons, Ltd.     

A Dynamic Bus-Arrival Time Prediction Model Based on APC Data

Abstract:   Automatic passenger counter (APC) systems have been implemented in various public transit systems to obtain bus occupancy along with other information such as location, travel time, etc. Such information has great potential as input data for a variety of applications including performance evaluation, operations management, and service planning. In this study, a dynamic model for predicting bus-arrival times is developed using data collected by a real-world APC system. The model consists of two major elements: the first one is an artificial neural network model for predicting bus travel time between time points for a trip occurring at given time-of-day, day-of-week, and weather condition; the second one is a Kalman filter-based dynamic algorithm to adjust the arrival-time prediction using up-to-the-minute bus location information. Test runs show that this model is quite powerful in modeling variations in bus-arrival times along the service route .     

国际工程索赔中神经网络的应用

针对传统BP算法的缺陷,提出了一种采用L-M算法来加快收敛速度改进的BP神经网络,建立了基于LMBP神经网络的非线性系统,并利用该网络模型来预测工程索赔出现的可能性,并通过具体的仿真以及实践结果验证了LMBP网络的有效性,为承包商的工程索赔管理提出了一个新途径。     

Real‐Time System Identification: An Algorithm for Simultaneous Model Class Selection and Parametric Identification

In this article, a novel Bayesian real‐time system identification algorithm using response measurement is proposed for dynamical systems. In contrast to most existing structural identification methods which focus solely on parametric identification, the proposed algorithm emphasizes also model class selection. By embedding the novel model class selection component into the extended Kalman filter, the proposed algorithm is applicable to simultaneous model class selection and parametric identification in the real‐time manner. Furthermore, parametric identification using the proposed algorithm is based on multiple model classes. Examples are presented with application to damage detection for degrading structures using noisy dynamic response measurement.     

A hybrid neural network strategy for identification of structural parameters

This paper presents a multistage identification scheme for structural damage detection using modal data. Previous studies of damage assessment using neural networks mostly involved training a backpropagation neural network (BPN) to learn damage patterns that were obtained either experimentally or by simulation for different damage cases. Damage identification for large structures, especially those involving multiple member damage, could result in large training data sets that require a large BPN and consequently greater computational effort. The proposed scheme involves using a counterpropagation neural network (CPN) in the first stage for sorting the training data into clusters and giving an approximate guess of the damage extent within a very short time. After an approximate estimate of the damage is obtained, a new set of training patterns of reduced size is generated using the CPN prediction. In the second stage, a BPN trained with the Levenberg–Marquardt algorithm is used to learn the new training data and predict a more accurate result. A superior convergence and a substantial decrease in central processing unit (CPU) time are observed for three numerical examples.     

索膜结构风振响应的神经网络辅助参数分析方法

针对非线性动力时程分析法求解大规模索膜结构风振响应时动力时程分析的次数受到限制而导致一些参数组合下的响应统计值难以预测的问题,引入神经网络,通过少量样本的训练,建立了参数与结构响应间的映射关系。结果表明:提出的神经网络辅助参数分析方法计算效率高、预测精度令人满意,是一种获取足够数据的有效途径;通过该方法可以得到响应统计量及风振系数随平均风速和索、膜预应力变化的规律,为设计风荷载和结构构件极端响应的计算提供了科学依据。     

Investigating Driver Injury Severity in Traffic Accidents Using Fuzzy ARTMAP

This paper applies fuzzy adaptive resonance theory MAP (fuzzy ARTMAP) neural networks to analyze and predict injury severity for drivers involved in traffic accidents. The paper presents a modified version of fuzzy ARTMAP in which the training patterns are ordered using the K–means algorithm before being presented to the neural network. The paper presents three applications of fuzzy ARTMAP for analyzing driver injury severity for drivers involved in accidents on highways, signalized intersections, and toll plazas. The analysis is based on central Florida's traffic accident database. Results showed that the ordered fuzzy ARTMAP proved to reduce the network size and improved the performance. To facilitate the application of fuzzy ARTMAP, a series of simulation experiments to extract knowledge from the models were suggested. Results of the fuzzy ARTMAP neural network showed that female drivers experience higher severity levels than male drivers. Vehicle speed at the time of an accident increases the likelihood of high injury severity. Wearing a seat belt decreases the chance of having severe injuries. Drivers in passenger cars are more likely to experience a higher injury severity level than those in vans or pickup trucks. Point of impact, area type, driving under the influence, and driver age were also among the factors that influence the severity level.     

基于自适应集成神经网络的火灾预测方法

针对传统火灾预测方法存在误报和漏报的问题,提出了一种基于自适应集成神经网络的火灾预测方法。首先,在信息层采用速率检测算法将不同类型传感器检测到的奇异数据输入到网络模型中。其次,在特征层采用长短期记忆网络（LSTM）和径向基前馈神经网络（RBF-BPNN）构建集成网络学习不同输入参数下的火灾特征,最后,在决策层设计模糊逻辑控制系统推理输出火灾报警等级。实验结果表明,该方法具有更高的预测精度。     

Identification Model for Dam Behavior Based on Wavelet Network

Abstract:   Dam behavior is conventionally evaluated with identification models of deformation, seepage, stress, and crack opening. The identification model needs to be described with a complicated and nonlinear function. Wavelet networks based on wavelet frames were used to establish the identification models of dam behavior for the first time. Firstly, time-frequency analysis for training data was implemented to determine the original structure of the wavelet network. Next, a new method was proposed for iterative elimination of the redundant neurons according to the dependency between the network output and the nodes in the hidden layer. In this method, rough sets theory was used to calculate the dependency. Lastly, this article built the identification models for the displacement and cracks of one concrete arch-dam with the trained wavelet network. The models can represent the connection between loads and the behavior of the dam. The numerical example shows that the proposed models are reasonable, and the denoising effect of the signal is remarkable.     

基于PNN神经网络的地下水水质评价及应用

概率神经网络是一种训练速度快、网络稳定、应用相当广泛的人工神经网络方法,它通过利用线性学习算法来解决非线性问题,在模式识别的分类问题中得到了广泛的应用。本文在阐述概率神经网络(PNN)原理的基础上,以我国地下水环境质量标准(GB/T14848-93)为训练样本,建立概率神经网络(PNN)模型,并将该网络模型运用于地下水水质评价。通过与灰色聚类法、模糊评判法和指标分类法比较,验证了该模型更为准确、可靠。     

桁架结构损伤识别的数据融合方法研究

以数据融合技术进行桁架结构的单损伤和多损伤识别。通过研究基于频率的结构损伤理论,分析归一化的频率和损伤位置的关系;利用小波概率神经网络的算法对决策融合进行修正,建立基于小波概率神经网络的数据融合结构损伤识别模型。运用结构计算软件计算了一典型桁架结构的频率,并融合为小波概率神经网络算法的输入特征向量,并对桁架算例模型结构进行损伤识别。通过桁架不同位置的损伤情况,验证该方法的有效性,并提出工程应用中应注意的问题。研究结果表明,基于小波概率神经网络算法的数据融合技术是一种比较可靠的损伤识别方法,具有良好的工程应用前景。