Dynamic Wavelet Neural Network for Nonlinear Identification of Highrise Buildings

Abstract:   Recently, the authors presented a multiparadigm dynamic time-delay fuzzy wavelet neural network (WNN) model for nonparametric identification of structures using the nonlinear autoregressive moving average with exogenous inputs. Compared with conventional neural networks, training of a dynamic neural network for system identification of large-scale structures is substantially more complicated and time consuming because both input and output of the network are not single valued but involve thousands of time steps. In this article, an adaptive Levenberg–Marquardt least-squares algorithm with a backtracking inexact linear search scheme is presented for training of the dynamic fuzzy WNN model. The approach avoids the second-order differentiation required in the Gauss–Newton algorithm and overcomes the numerical instabilities encountered in the steepest descent algorithm with improved learning convergence rate and high computational efficiency. The model is applied to two highrise moment-resisting building structures, taking into account their geometric nonlinearities. Validation results demonstrate that the new methodology provides an efficient and accurate tool for nonlinear system identification of high-rising buildings.     

A novel machine learning‐based algorithm to detect damage in high‐rise building structures

A novel model is presented for global health monitoring of large structures such as high‐rise building structures through adroit integration of 2 signal processing techniques, synchrosqueezed wavelet transform and fast Fourier transform, an unsupervised machine learning technique, the restricted Boltzmann machine, and a recently developed supervised classification algorithm called neural dynamics classification (NDC) algorithm. The model extracts hidden features in the frequency domain of the denoised measured response signals recorded by sensors on different elevations or floors of a structure. The extracted features are used as an input of the NDC to detect and classify the global health of the structure into categories such as healthy, light damage, moderate damage, severe damage, and near collapse. The proposed model is validated using the data obtained from a 3D 1:20 scaled 38‐story reinforced concrete building structure. The results are compared with 3 other supervised classification algorithms: k‐nearest neighbor (KNN), probabilistic neural networks (PNN), and enhanced PNN (EPNN). NDC, EPNN, PNN, and KNN yield maximum average accuracies of 96%, 94%, 92%, and 82%, respectively.     

模型参数误差对用神经网络进行结构损伤识别的影响

通过理论推导得到了模型参数误差对损伤引起模态参数改变的贡献的表达式,用该式可指导神经网络输入参数的选择和输入向量的构造.理论分析表明,适当地构造输入向量,可以减小模型参数误差对结构损伤识别的影响.在采用BP网络和合适的输入向量后,还用数值模拟的方式对一榀六层框架的损伤识别进行了确定性研究和概率分析,结果表明,用神经网络进行结构损伤识别,受模型参数误差的影响很小,在训练神经网络时,10%的模型参数误差是可以接受的.最后,用一个两层钢框架的实验数据验证了神经网络在有模型误差时的识别能力.     

StructNet: A Neural Network for Structural System Selection

Abstract: This paper describes StructNet, a computer application developed to select the most effective structural member materials given a building project's attributes. The system analyzes 15 parameters of a building project (e.g., available site space, budget, height) and determines the most appropriate structural system for the beam, column, and slab structural members. This paper first describes the process for selecting a structural system for a building. It was very important to understand this process before determining the best type and structure for the computer application. Then a comparison between a neural network approach and a rule-based expert-system approach for this application is presented. A discussion of the reasons for selecting a neural network approach is given. The StructNet application is described in detail, including the testing of the network. Along with the testing of the network is a discussion of how varying the learning rate and error limit affect the performance of the neural network application. The testing of the network shows that the program can reasonably select the same structural system types as the expert used to collect the training project data. Since the system will be used only as a preliminary tool to limit the number of possible structural systems for a project, the accuracy of the system is acceptable. However, additional experimentation needs to be conducted to determine the accuracy and practical use of this application. The final sections of the paper discuss the lack of adequate testing procedures for neural networks used in applications for unstructured or ill-defined decision making. The use of these types of networks and their relevance to the civil engineering computer field are also discussed.     

Nonlinear Identification of Dynamic Systems Using Neural Networks

A neural-network-based method is proposed for the modeling and identification of a discrete-time nonlinear hysteretic system during strong earthquake motion. The learning or modeling capability of multilayer neural networks is explained from the mathematical point of view. The main idea of the proposed neural approach is explained, and it is shown that a multilayer neural network is a general type of NARMAX model and is suitable for the extreme nonlinear input-output mapping problems. Numerical simulation of a three-story building and a real structure (a bridge in Taiwan) subjected to several recorded earthquakes are used here to demonstrate the proposed method. The results illustrate that the neural network approach is a reliable and feasible method.     

耦合台风天气预报模式和实测数据的神经网络风速预测

基于准定常假定,风荷载与风速平方成正比.为了实现对结构的台风动力效应进行分析预测,建立了耦合数值天气预报(weather research and forecast,WRF)模式和现场实测数据的风速预测神经网络模型,开展台风短期风速的高精度预测.利用该模型对2017年"泰利"和2018年"康妮"的台风风场进行模拟和预测...     

Identification of stiffness degradation in structures using wavelet analysis

An approach for structural health monitoring (SHM) and damage detection using a wavelet based time-frequency technique is presented here. The characteristics of dynamic responses of structures are studied by wavelet analysis. Inferences are drawn from the wavelet coefficients obtained. Numerical simulation data are used for the purpose of illustration. Two examples (i) a bi-linear structure with breakable springs causing stiffness degradation and (ii) a hysteretic system with continuous variation in stiffness with non-linearity involving displacement and velocity response are considered. Information regarding the stiffness degradation and temporal location of damage are successfully obtained from the wavelet coefficients of the response. The effect of system degradation is reflected in the time-frequency characteristics of the response and inferences on stiffness degradation can be obtained even without any apriori knowledge of the original structural system.     

Decentralized Parametric Damage Detection Based on Neural Networks

In this paper, based on the concept of decentralized information structures and artificial neural networks, a decentralized parametric identification method for damage detection of structures with multi-degrees-of-freedom (MDOF) is conducted. First, a decentralized approach is presented for damage detection of substructures of an MDOF structure system by using neural networks. The displacement and velocity measurements from a substructure of a healthy structure system and the restoring force corresponding to this substructure are used to train the decentralized detection neural networks for the purpose of identifying the corresponding substructure. By using the trained decentralized detection neural networks, the difference of the interstory restoring force between the damaged substructures and the undamaged substructures can be calculated. An evaluation index, that is, relative root mean square (RRMS) error, is presented to evaluate the condition of each substructure for the purpose of health monitoring. Although neural networks have been widely used for nonparametric identification, in this paper, the decentralized parametric evaluation neural networks for substructures are trained for parametric identification. Based on the trained decentralized parametric evaluation neural networks and the RRMS error of substructures, the structural parameter of stiffness of each subsystem can be forecast with high accuracy. The effectiveness of the decentralized parametric identification is evaluated through numerical simulations. It is shown that the decentralized parametric evaluation method has the potential of being a practical tool for a damage detection methodology applied to structure-unknown smart civil structures.     

考虑土-结构动力相互作用影响的结构神经网络控制

将人工神经网络控制理论应用于软弱地基上建筑结构地震反应的主动控制分析中。通过训练神经控制器NNC (Neural networkController)预测结构控制力 ,由神经模仿器NNE (Neural networkEmulator)预测结构对地震力的反应来修正NNC的输入 ,从而实现结构的主动控制。数值模拟表明 ,神经网络控制系统能够有效地控制结构的地震反应 ,且对地震输入有很好的自适应性 ,在设计神经网络控制系统时 ,应考虑土—结构动力相互作用的影响。     

基于耗能差指数和SIR模型的#br# 结构易损性及可恢复能力评估

传统结构地震易损性中结构地震响应指标对损伤反映不充分,且无法为结构震后可恢复性评估提供准确的初始损伤指标。针对上述不足和结构地震可恢复能力评估的需求,提出运用基于弹塑性耗能差的损伤指数进行结构地震易损性评价的方法。建立可推演出指定地震动强度和超越概率下的损伤指数的计算方法。利用SIR模型能够描述系统损伤和恢复动态演变过程的特点,提出基于该模型的单体建筑结构和区域建筑群的性能水平恢复函数模型及结构的恢复能力计算方法,从而表征建筑结构群体在地震激励下的“直接损伤 间接损伤 恢复”全过程。以单体结构和区域结构为算例进行易损性分析和震后可恢复性评估,结果表明：基于弹塑性耗能差的损伤指数具有真实可靠和机理明确的特点,在离散性和相关性方面均优于传统指标。SIR可恢复性能评估模型较常用恢复函数模型更为精准,简单高效且适合推广到区域建筑集群体当中,是对现有区域恢复性能评估框架的有益补充。     

A Wavelet-Based Approach to Identifying Structural Modal Parameters from Seismic Response and Free Vibration Data

Abstract:   This work presents the use of a discrete wavelet transform to determine the natural frequencies, damping ratios, and mode shapes of a structure from its free vibration or earthquake response data. The wavelet transform with orthonormal wavelets is applied to the measured acceleration responses of a structural system, and to reconstruct the discrete equations of motion in various wavelet subspaces. The accuracy of this procedure is numerically confirmed; the effects of mother wavelet functions and noise on the ability to accurately estimate the dynamic characteristics are also investigated. The feasibility of the present procedure to elucidate real structures is demonstrated through processing the measured responses of steel frames in shaking table tests and the free vibration responses of a five-span arch bridge with a total length of 440 m.     

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。     

Author Index to Volume 18

Abstract:   Route guidance system (RGS) is considered as a low-cost alternative for reducing congestion by providing real-time information to drivers to redistribute traffic in space and time so as to use roadway networks more efficiently. This article focuses on the behavioral component, one of the three components (the other two being dynamic traffic component and information supply strategy component) of a practical RGS developed through a 4-year project at the University of Delaware. Development of the behavioral model is based on the premise that different drivers perceive and behave differently in response to the information provided. Understanding the behavior of RGS-equipped drivers' acceptance or nonacceptance of provided information is essential for understanding the reliability of the system. Backpropagation neural network with its ability to map complex input–output relationships has been used to structure the model. This model was tested on two networks under both recurring and nonrecurring congestion. A comparative analysis of the measures of effectiveness revealed that the performance of the developed RGS is significantly better than the performance under existing non-RGS conditions.     

Parametric Identification for a Truss Structure Using Axial Strain

Abstract:   The increasing use of advanced sensing technologies such as optic fiber Bragg grating and embedded piezoelectric sensors necessitates the development of strain-based identification methodologies. In this study, a three-step neural networks based strategy, called direct soft parametric identification (DSPI), is presented to identify structural member stiffness and damping parameters directly from free vibration-induced strain measurements. The rationality of the strain based DSPI methodology is explained and the theoretical basis for the construction of a strain-based emulator neural network (SENN) and a parametric evaluation neural network (PENN) are described according to the discrete time solution of the state space equation of structural free vibration. The accuracy, robustness, and efficacy of the proposed strategy are examined using a truss structure with a known mass distribution. Numerical simulations indicate that the average relative errors of identified structural properties were less than 5% and relatively insensitive to measurement noises .     

The structural performance of monolithic intersecting walls in a tall reinforced concrete building

Results of the seismic performance assessment of a new structural system that has been used in a 54‐story reinforced concrete building are presented. The structure, which is still under construction, and has a ‘Y‐shape’ form, utilizes a special structural system that does not include any beams or columns. Instead, walls and slabs are used for carrying both gravitational and lateral loads. The general distinctions of the system are discussed. The structural efficiency of the system is compared with other conventional systems in some existing tall buildings. The seismic responses and dynamic behavior of the structure that were achieved by conducting various analyses are presented. The effects of analysis method, as well as some other parameters such as modeling assumptions and bidirectional earthquake excitation on the linear responses, are studied. The influence of the number of modes and design spectrum on the spectral analysis results is discussed. Using dynamic analysis, the real heightwise distribution of lateral loads occurring during an earthquake is presented. Copyright © 2007 John Wiley & Sons, Ltd.     

Wavelet-Based Structural Health Monitoring of Earthquake Excited Structures

Abstract:   The article presents a wavelet-based structural health monitoring technique for structures subjected to an earthquake excitation utilizing the instantaneous modal information. The instantaneous mode shape information is first extracted from the vibration response data collected during an earthquake event by using a wavelet packet sifting process. A confidence index (CI) is proposed to validate the results obtained. The identified normalized instantaneous mode shapes in conjunction with the corresponding CIs can be effectively used to monitor damage development in the structure. The effectiveness of the proposed approach is illustrated for two damage scenarios, sudden stiffness loss and progressive stiffness degradation, and different base excitations including three real earthquake signals and a random signal. Consistently good results were obtained in all cases. Issues related to robustness of the method in the presence of a measurement noise and sensitivity to damage severity are discussed.     

Comparison of Structural Deterioration Models for Stormwater Drainage Pipes

Abstract:   Structural deterioration of pipes is the continuing reduction of load bearing capacity, which can be characterized through structural defects. Structural deterioration has been a major concern for asset managers in maintaining the required performance of stormwater drainage systems in Australia. Condition assessment using closed circuit television (CCTV) inspection is often carried out to assess the deteriorating condition of individual pipes. In this study, two models were developed using ordered probit and neural networks (NNs) techniques for predicting the structural condition of individual pipes. The predictive performances were compared using CCTV data collected for a local government authority in Melbourne, Australia. The significant input factors to the outputs of both models were also identified. The results showed that the NN model was more suitable for modeling structural deterioration than the ordered probit model. The hydraulic condition, pipe size, and pipe location were found to be significant factors for this case study.     

Comparison of Neural Networks and Gravity Models in Trip Distribution

Abstract:  Transportation engineers are commonly faced with the question of how to extract information from expensive and scarce field data. Modeling the distribution of trips between zones is complex and dependent on the quality and availability of field data. This research explores the performance of neural networks in trip distribution modeling and compares the results with commonly used doubly constrained gravity models. The approach differs from other research in several respects; the study is based on both synthetic data, varying in complexity, as well as real-world data. Furthermore, neural networks and gravity models are calibrated using different percentages of hold out data. Extensive statistical analyses are conducted to obtain necessary sample sizes for significant results. The results show that neural networks outperform gravity models when data are scarce in both synthesized as well as real-world cases. Sample size for statistically significant results is forty times lower for neural networks.     

Modeling and predicting building's energy use with artificial neural networks: Methods and results

This paper discusses how neural networks, applied to predict energy consumption in buildings, can advantageously be improved, guided by statistical procedures, such as hypothesis testing, information criteria and cross validation. Recent literature has provided evidence that such methods, commonly used independently, when exploited together, can improve the selection and estimation of neural models.We use such an approach to design feed forward neural networks for modeling energy use and predicting hourly load profiles, where both the relevance of input variables and the number of free parameters are systematically treated. The model building process is divided in three parts: (a) the identification of all potential relevant input, (b) the selection of hidden units for this preliminary set of inputs, through an additive phase and (c) the remove of irrelevant inputs and useless hidden units through a subtractive phase.The predictive performance of short term predictors is also examined with regard to prediction horizon. A comparison of the predictive ability of a single-step predictor iteratively used to predict 24 h ahead and a 24-step independently designed predictor is presented.The performance of the developed models and predictors was evaluated using two different data sets, the energy use data of the Energy Prediction Shootout I contest, and of an office building, located in Athens. The results show that statistical analysis as an integral part of neural models, gives a valuable tool to design simple, yet efficient neural models for building energy applications.     

基于解耦子波和优化神经网络的大坝变形预测

针对提高神经网络对大坝变形的预测能力,在对Murtagh提出的、小波与神经网络相结合的、用于复杂时间序列预测的“三阶段”策略进行改进的基础上,发展了一个解耦子波和优化神经网络优势联合的预测模型。首先,利用冗余Haar小波变换的拟小波包特性提出了基于能量谱主峰重构的动力解耦空间构建技术,并将其替代“三阶段”策略中的第1阶段,从而为神经网络的应用创建了良好的平台;再者,利用最优脑外科医生进行网络结构修剪,建立了神经网络自身优化的“优化–时新窗”技术,并将其替代“三阶段”策略中的第2阶段,从而优化了神经网络的内部环境。改进后的模型增强了对复杂动力系统的适应和处理能力。在大坝变形预测应用中,多个评价指标说明,该模型的性能比“三阶段”策略有显著提高。