Ramin Ghiasi

Seismic response prediction is a challenging problem and is significant in every stage during a structure’s life cycle. Deep neural network has proven to be an efficient tool in the response prediction of structures. However, a conventional neural network with deterministic parameters is unable to predict the random dynamic response of structures. In this paper, a deep Bayesian convolutional neural network is proposed to predict seismic response. The Bayes-backpropagation algorithm is applied to train the proposed Bayesian deep learning model. A numerical example of a three-dimensional building structure is utilized to validate the performance of the proposed model. The result shows that both acceleration and displacement responses can be predicted with a high level of accuracy by using the proposed method. The main statistical indices of prediction results agree closely with the results from finite element analysis. Furthermore, the influence of random parameters and the robustness...

Over the past two decades, a large volume of research has been carried out in the area of damage detection of structural systems and the field of Structural Health Monitoring (SHM) has become a major field of research. The research in SHM has been mainly in two distinct areas: a) development of sensing technologies and hardware for identifying the location and the severity of damage, and b) development of diagnostics and computational tools for the analysis and interpretation of the structural response data in order to identify the location and the time of occurrence of the damage. Despite extensive work carried out in the area of diagnostics, a comprehensive and accurate methodology that can be used in conjunction with the hardware and to identify the time, location and the extent of the damage, with a high degree of reliability and especially taking into account the inherent uncertainties is still lacking. In order to address some of the current shortcomings in this area, in this study, structural damage detection is performed incorporating several methods of Artificial Intelligence (AI) including back-propagation neural networks (BPNN), Least Square Support Vector Machines (LS-SVMs), Adaptive Neural-Fuzzy Inference System (ANFIS), radial basis function neural network (RBFN), Large Margin Nearest Neighbor (LMNN), Extreme Learning Machine (ELM), Gaussian process (GP) and the comparative results are presented. By considering dynamic behaviour of a structure as input variables, seven AI methods are constructed, trained and tested to detect the location and severity of damage in civil structures. The variation of running time, mean square error (MSE), number of training and testing data, and other indices for measuring the accuracy in the prediction are defined and calculated in order to inspect advantages as well as the shortcomings of each algorithm. The results indicate that ELM and LS-SVM models have better performance in predicting location/severity of damage than other methods. It is our hope these types of comparative studies lead to the development of more comprehensive, accurate and powerful diagnostic methods.

Abstract—Model updating method has received increasing attention in damage detection structures based on measured modal parameters. Therefore, a probability-based damage detection (PBDD) procedure based on a model updating procedure is presented in this paper, in which a one-stage model-based damage identification technique based on the dynamic features of a structure is investigated. The presented framework uses a finite element updating method with a Monte Carlo simulation that considers the uncertainty caused by measurement noise. Enhanced ideal gas molecular movement (EIGMM) is used as the main algorithm for model updating. Ideal gas molecular movement (IGMM) is a multiagent algorithm based on the ideal gas molecular movement. Ideal gas molecules disperse rapidly in different directions and cover all the space inside. This is embedded in the high speed of molecules, collisions between them and with the surrounding barriers. In IGMM algorithm to accomplish the optimal solutions, ...

Structural Health Monitoring (SHM) is rapidly developing as a multi-disciplinary technology solution for condition assessment and performance evaluation of civil infrastructures. It consists of three parts: data collection, data processing (feature extraction/selection), and decision-making (feature classification). In this research, for effectively reducing a dimension of SHM data, various methods are proposed such as advanced feature extraction, feature subset selection using optimization algorithm, and effective surrogate model based on artificial intelligence methods. These frameworks enhance the capability of the SHM process to tackle with uncertainties and big data problem. To reach such goals, a framework based on three main blocks are proposed here: feature extraction block using wavelet pocket relative energy (WPRE), feature selection block using improved version of binary harmony search algorithm and finally feature classification block using wavelet weighted least square ...

Vibration based techniques of structural damage detection using model updating method, are computationally expensive for large-scale structures. In this study, after locating precisely the eventual damage of a structure using modal strain energy based index (MSEBI), To efficiently reduce the computational cost of model updating during the optimization process of damage severity detection, the MSEBI of structural elements is evaluated using properly trained cascade feed-forward neural network (CFNN). In order to achieve an appropriate artificial neural network (ANN) model for MSEBI evaluation, a set of feed-forward artificial neural networks which are more suitable for non-linear approximation, are trained. All of these neural networks are tested and the results demonstrate that the CFNN model with logsigmoid hidden layer transfer function is the most suitable ANN model among these selected ANNs. Moreover, to increase damage severity detection accuracy, the optimization process of da...

Magnetorheological elastomeric (MRE) material is a novel type of material that can adaptively change the rheological property rapidly, continuously, and reversibly when subjected to real-time external magnetic field. These new type of MRE materials can be developed by employing various schemes, for instance by mixing carbon nanotubes or acetone contents during the curing process which produces functionalized multiwall carbon nanotubes (MWCNTs). In order to study the mechanical and magnetic effects of this material, for potential application in seismic isolation, in this paper, different mathematical models of magnetorheological elastomers are analyzed and modified based on the reported studies on traditional magnetorheological elastomer. In this regard, a new feature identification method, via utilizing curvelet analysis, is proposed to make a multi-scale constituent analysis and subsequently a comparison between magnetorheological elastomer nanocomposite and traditional magnetorheo...

Automatic crack identification for pipeline analysis utilizes three-dimensional (3D) image technology to improve the accuracy and reliability of crack identification. A new technique that integrates a deep learning algorithm and 3D shadow modeling (3D-SM) is proposed for the automatic identification of corrosion cracks in pipelines. Since the depth of a corrosion crack is below the surrounding area of the crack, a shadow of the crack is projected when the crack is exposed under light sources. In this study, we analyze the shadow areas of cracks through 3D shadow modeling (3D-SM) and identify the evolving cracks through the shape analysis of the shadows. To denoise the 3D images, the connected domain analysis is implemented so that the shadow groups of the evolving cracks can be retained and the scattered shadow groups that occur due to insignificant defects can be eliminated. Moreover, a novel deep neural network is developed to process the 3D images. The proposed automatic crack id...

Automatic crack identification for pipeline analysis utilizes three-dimensional (3D) image technology to improve the accuracy and reliability of crack identification. A new technique that integrates a deep learning algorithm and 3D shadow modeling (3D-SM) is proposed for the automatic identification of corrosion cracks in pipelines. Since the depth of a corrosion crack is below the surrounding area of the crack, a shadow of the crack is projected when the crack is exposed under light sources. In this study, we analyze the shadow areas of cracks through 3D shadow modeling (3D-SM) and identify the evolving cracks through the shape analysis of the shadows. To denoise the 3D images, the connected domain analysis is implemented so that the shadow groups of the evolving cracks can be retained and the scattered shadow groups that occur due to insignificant defects can be eliminated. Moreover, a novel deep neural network is developed to process the 3D images. The proposed automatic crack id...

Rapid detection of damages in civil engineering structures, in order to assess their possible disorders and as a result produce competent decision making, are crucial to ensure their health and ultimately enhance the level of public safety. In traditional intelligent health monitoring methods, the features are manually extracted depending on prior knowledge and diagnostic expertise. Inspired by the idea of unsupervised feature learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed here for intelligent health monitoring of civil engineering structures. In the first stage, Nystrom method is used for automatic feature extraction from structural vibration signals. In the second stage, Moving Kernel Principal Component Analysis (MKPCA) is employed to classify the health conditions based on the extracted features. In this paper, KPCA has been implemented in a new form as Moving KPCA for effectively segmenting large da...

Generally, updating a finite element model can be considered as an optimization problem where its physical parameters may be adjusted such that analytically computed features, using the updated FE model, are consistent with those obtained from experimentally. The objective function can be defined as a sum of squared difference between analytically computed and experimentally measured data. To meet this goal in this paper therefore, for efficiently reducing the computational cost of the model during the optimization process of damage detection, the structural response is evaluated using properly a trained surrogate model. Surrogate models have received increasing attention for use in detecting damage of structures based on vibration modal parameters. However, uncertainties existing in the measured vibration data may lead to false or unreliable output results from such model. Here, an efficient approach based on Monte Carlo simulation is proposed to take into account the effect of unc...

Abstract—Surrogate model has received increasing attention for use in detecting damage of structures based on vibration modal parameters. However, uncertainties existing in the measured vibration data may lead to false or unreliable output result from such model. In this study, an efficient approach based on Monte Carlo simulation is proposed to take into account the effect of uncertainties in developing a surrogate model. The probability of damage existence (PDE) is calculated based on the probability density function of the existence of undamaged and damaged states. The kriging technique allows one to genuinely quantify the surrogate error, therefore it is chosen as metamodeling technique. Enhanced version of ideal gas molecular movement (EIGMM) algorithm is used as main algorithm for model updating. The developed approach is applied to detect simulated damage in numerical models of 72-bar space truss and 120bar dome truss. The simulation results show the proposed method can perfo...

Utilizing surrogate models based on artificial intelligence methods for detecting structural damages has attracted the attention of many researchers in recent decades. In this study, a new kernel based on Littlewood-Paley Wavelet (LPW) is proposed for Extreme Learning Machine (ELM) algorithm to improve the accuracy of detecting multiple damages in structural systems. ELM is used as metamodel (surrogate model) of exact finite element analysis of structures in order to efficiently reduce * :يكينورتكلا تسپ ،تابتاكم لوئسم : rghiasi.s@gmail.com D ow nl oa de d fr om jc m e. iu t.a c. ir at 3 :5 8 IR S T o n W ed ne sd ay M ar ch 4 th 2 02 0 [ D O I: 10 .1 88 69 /a ca dp ub .jc m e. 36 .1 .1 ]

Hysteresis is a nonlinear phenomenon observed in the dynamic response behavior of numerous structural systems under high intensity cyclic or random loading, as well as in numerous mechanical and electromagnetic systems. For several decades, hysteretic response analysis of structural systems has been widely studied and numerous hysteresis models have been proposed and utilized in order to reproduce and better understand the complex hysteretically degrading behavior of structural systems. An important area of research in this regard has been the parameter identification of hysteretic systems. In this paper, we propose a modified Prandtl–Ishlinskii model to simulate the asymmetric hysteresis, which is the complex behavior in structural systems. In addition, a new approach based on particle swarm optimization and least-mean square algorithm is utilized for parameter identification of this hysteresis model. Finally, the model is applied in structural dynamic response analysis of a base i...

Advanced sensor network techniques recently allow collecting large amounts of data for structural health monitoring and damage detection, while how to effectively interpret these complex sensor data to technical information poses many challenges. This paper presents a machine learning algorithm for processing of big data collected from the sensor networks of civil structure. The proposed approach consists of training and monitoring phases. The training phase was focused on the extracting statistical features and conducting Moving Kernel Principal Component Analysis (MKPCA) in order to derive the damage sensitive indices. The monitoring phase included tracking of errors associated with the derived models. The main goal was to analyze the efficiency of the developed system for health monitoring of the benchmark experimental data with the 17 different damage scenarios. In this paper KPCA has been implemented in a new form as Moving KPCA (MKPCA) for effectively segmenting large data and for determining the changes, as data are continuously collected. Numerical results revealed that, the proposed health monitoring system has a satisfactory performance for the detection of the damage scenarios in three-story frame aluminum structure. Furthermore, enhanced version of KPCA methods exhibited significantly improvement in sensitivity, accuracy and effectiveness over conventional methods.

Abstract Despite advances in computer capacity, the enormous computational cost of running complex engineering simulations makes it impractical to rely exclusively on simulation for the purpose of structural health monitoring. To cut down the cost, surrogate models, also known as metamodels, are constructed and then used in place of the actual simulation models. In this study, structural damage detection is performed using two approaches. In both cases ten popular metamodeling techniques including Back-Propagation Neural Networks (BPNN), Least Square Support Vector Machines (LS-SVMs), Adaptive Neural-Fuzzy Inference System (ANFIS), Radial Basis Function Neural network (RBFN), Large Margin Nearest Neighbors (LMNN), Extreme Learning Machine (ELM), Gaussian Process (GP), Multivariate Adaptive Regression Spline (MARS), Random Forests and Kriging are used and the comparative results are presented. In the first approach, by considering dynamic behavior of a structure as input variables, ten metamodels are constructed, trained and tested to detect the location and severity of damage in civil structures. The variation of running time, mean square error (MSE), number of training and testing data, and other indices for measuring the accuracy in the prediction are defined and calculated in order to inspect advantages as well as the shortcomings of each algorithm. The results indicate that Kriging and LS-SVM models have better performance in predicting the location/severity of damage compared with other methods. In the second approach, after locating precisely the eventual damage of a structure using modal strain energy based index (MSEBI), to efficiently reduce the computational cost of model updating during the optimization process of damage severity detection, the MSEBI of structural elements is evaluated using a properly trained surrogate model. The results indicate that after determining the damage location, the proposed solution method for damage severity detection leads to significant reduction of computational time compared to finite element method. Furthermore, engaging colliding bodies optimization algorithm (CBO) by efficient surrogate model of finite element (FE) model, maintains the acceptable accuracy of damage severity detection.

Modal macro strain-based damage identification is a promising approach since it has the advantages of high sensitivity and effectiveness over other related methods. In this paper, a basalt fiber-reinforced polymer (BFRP) pipeline system is used for analysis by using long-gauge distributed fiber Bragg grating (FBG) sensors. Dynamic macro strain responses are extracted to form modal macro strain (MMS) vectors. Both longitudinal distribution and circumferential distribution plots of MMS are compared and analyzed. Results show these plots can reflect damage information of the pipeline based on the previous work carried out by the authors. However, these plots may not be good choices for accurate detection of damage information since the model is 3D and has different flexural and torsional effects. Therefore, by extracting MMS information in the circumferential distribution plots, a novel deep neural network is employed to train and test these images, which reflect the important and key ...

A fuzzy logic system (FLS) with a new sliding window defuzzifier is developed for damage detection. The effect of changes in the damage evaluation parameter (frequency) due to uncertainty in material properties is explored and the results of the probabilistic analysis are used to ...

A fuzzy logic system (FLS) with a new sliding window defuzzifier is developed for damage detection. The effect of changes in the damage evaluation parameter (frequency) due to uncertainty in material properties is explored and the results of the probabilistic analysis are used to ...

Over the past two decades, a large volume of research has been carried out in the area of damage detection of structural systems and the field of Structural Health Monitoring (SHM) has become a major field of research. In this study, structural damage detection is performed incorporating several methods of Artificial Intelligence (AI) including Least Square Support Vector Machines (LS-SVMs), Adaptive Neural-Fuzzy Inference System (ANFIS), radial basis function neural network (RBFNN), Large Margin Nearest Neighbors (LMNN) and the comparative results are presented. By considering dynamic behavior of a structure as input variables, four AI methods are constructed, trained and tested to detect the location and severity of damage in civil structures. The results indicate that LS-SVM models have better performance in predicting location/severity of damage than other methods.