Search

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 of the proposed model are discussed. [ABSTRACT FROM AUTHOR]

Monitoring the mass of liquid absorption in laminated composite structures, that have a direct contact surface with working liquid-like pipes, is very important in order to prevent the sudden collapse of the structures because of the degradations in strength and mechanical properties over time. An electrical capacitance sensor technique has been applied for monitoring the mass of liquid absorption, over the time, in laminated composite pipelines by measuring the change of dielectric characteristics of composite pipelines subjected to an internal hydrostatic pressure load of water and thermal effect. Results show the technique is very effective. However, a major difficulty in utilizing this technique is that it is highly time consuming to be used for monitoring, in addition to the detection efforts that it requires to calculate the mass of liquid absorption that exerts high cost and loss of additional time in monitoring. In this paper, a deep neural network model is used to estimate the mass of liquid absorption in glass fiber reinforced epoxy laminated composite pipelines by extracting the features from datasets from experimental and numerical measurements of the electrical capacitance sensor. The experimental and numerical data used in this paper to train and test the new deep neural network model are collected from the literature and the finite element model of the electrical capacitance sensor system respectively. The results show an excellent agreement between the finite element model data, available experimental data, and those predicted by a deep neural network with an average error of 0.067%, and show that the proposed method achieves satisfactory performance with 86.34% accuracy, 82.83% regression rate and 83.74% F-score. The proposed approach overcomes the difficult problem of saving time and effort to accurately detect the mass of liquid absorption over the time, and provides a promising approach for a wider application of this intelligent model. • A FEM is established for monitoring the mass of water absorption over time (M%) of the composite pipeline. • The M% of the composite pipeline is analyzed using the electrical capacitance sensor (ECS) technique. • The ECS results are verified using a dataset of experimental work adapted from literature. • Trained and tested the Convolutional Neural Network (CNN) by the electrical potential difference between ECS electrodes. • The M% over time of composite pipeline is predicted and compared with the FEM outputs and available experimental results. [ABSTRACT FROM AUTHOR]

Over the past two decades, an increasing number of large-scale structures have been built around the world. Constructing these structures has been a time consuming and highly expensive process. Thus, providing a structural health monitoring system to guarantee their proper functionality is important. In recent years, the advancement of technology and artificial intelligence methods based on signal processing and machine learning has attracted the attention of researchers. The challenges currently exist in the field of structural health monitoring to identify and classify damages to achieve high accuracy in a health-monitoring program. The presence of noise in measurement, various exciting load types, and varying environmental conditions cause difficulty in the practical identification and classification of damage in structures. Recent studies have employed finite element modeling to test the effectiveness of proposed methods for identifying damages in structures. However, detecting damage in real-world structures as mentioned above, presents unique difficulties, and the effectiveness of the proposed methods for damage detection in real-world structures remains uncertain. In order to improve the performance of damage detection methods and increase the accuracy of these methods as much as possible, the most important action is to identify damage sensitive data in the structure. The next challenge is to choose a high performance algorithm for damage identification and classification. One of the advanced algorithms, which has a very high ability to extract the desired features from the measured data, is the XGBoost algorithm. This algorithm has recently attracted the attention of researchers and has been used in different fields. So far, the ability of this algorithm has not been examined in the field of damage detection in order to extract desirable features. This article deals with the identification, classification, and severity of damages in the SMC benchmark bridge, which is an existing megastructure in the real world, as well as the IASC-ASCE benchmark structure, whose responses were taken under applied loads in the laboratory environment. First, using the XGBoost algorithm, the importance of the features extracted from the sensors' data is evaluated, and then the features, which are effective in the damage detection process, are selected. The results of this algorithm indicate that only by selecting 6 features from a large volume of data, the best performance can be achieved and selecting more does not help increase efficiency. In the next step, the Stacking method, which is a hybrid machine learning algorithm for damage classification, is evaluated and compared with some conventional machine learning algorithms that have been used in previous studies. The Stacking method stands out as the top performer with an average accuracy rate of 93.1%, leading to the conclusion that it is the most effective approach. Finally, by applying the presented algorithm to the two mentioned structures, its validation is appraised. [ABSTRACT FROM AUTHOR]

Highlights • An effective strategy to use metamodels (surrogate models), for model updating in structural health monitoring. • A comparative study of ten most common metamodeling techniques used for damage detection and the severity of damage; the first such study in SHM research. • A novel optimization algorithm, Colliding Bodies, CBO, with and without surrogate models for damage severity and computational efficiency. • Proposed application of this approach for general hysteretic degradation of a structure subjected to external excitations. • Identified LS-SVM as the most promising tool, combined with metamodels, for damage severity assessment. 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. [ABSTRACT FROM AUTHOR]