Search

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]

• Propose a novel deep learning model based on Runge-Kutta recurrent neural network (RKRNN) with prior knowledge to realize structural system identification and seismic response prediction. • Formulate a partition training strategy to train the proposed neural network to improve the efficiency of training. • Utilize three numerical examples to valid the feasibility of RKRNN model including a linear three degrees of freedom system, a nonlinear single degree of freedom system with Bouc-Wen hysteresis and a simply supported bridge. • Site monitoring data from a bridge located in California has been used to further validate the proposed approach. In the seismic analysis of structural systems, dynamic response prediction is an essential problem and is significant in every stage during the structural life cycle. Conventionally, response analysis is carried out by numerical analysis. However, when the structural parameter is unknown, the establishment of a numerical model will be difficult. Enlightened by the Runge-Kutta (RK) numerical algorithm, this paper proposes a novel recurrent neural network named Runge-Kutta recurrent neural network (RKRNN) to realize the seismic response prediction. A partition training strategy is formulated to train the proposed neural network and to improve the efficiency of training. The proposed model can be trained by using a limited number of samples. Three numerical examples are utilized to validate the feasibility of RKRNN model including a linear three degrees of freedom (DOFs) system, a nonlinear single DOF system with Bouc-Wen hysteresis, and a numerical reinforced concrete bridge model. Additionally, the site monitoring data from a real-world bridge is utilized to further validate the proposed network. The results show that the proposed RKRNN model can effectively and efficiently predict the structural response under seismic load and exhibits robustness to noise, with good potential for applications in engineering practice. [ABSTRACT FROM AUTHOR]

In recent years, the application of structural control strategies to attenuate the dynamic response of civil engineering structures subjected to human-induced and environmental loads has once again received much attention. The hardware involved in providing effective control, the stochastic nature of the dynamic excitation, the number of distinct variables required to determine the dissipating forces, and the nature of the control approach are a few of the parameters involved in determining the efficacy of structural control systems. However, the primary parameter to determine the overall performance of a smart adaptive structure is the implementation of a control algorithm that would conveniently counteract the external known and/or unknown excitation by providing additional force input through control devices. The control algorithm to be adopted should be robust, multi-purpose, and simple to design and implement. Moreover, the control algorithm should provide the flexibility in selecting performance objectives for a holistically effective response reduction. This paper focuses on providing a comprehensive review of control algorithms implemented in structural control engineering. This article first provides an overview of the fundamental concepts pertaining to the vibration control of structures subjected to dynamic excitations. Next, an exhaustive review of different types of control algorithms that feed the input signal to active-type control devices is conducted. Thereafter, important benchmark applications in the field of structural control in civil engineering are presented. Finally, conclusions are presented on the advantages and drawbacks of each control strategy and recommendations are presented for further research in this area. [ABSTRACT FROM AUTHOR]

• Investigated uncertainties in FE model updating from measurement and modeling errors. • Employed information entropy measure criterion for optimum sensor placement in system identification. • Presented a novel nonlinear FE model updating framework using EKF and UKF. • Investigated uncertainties in nonlinear FE model updating framework. • Used information entropy measure criterion to determine optimal response utilization in FE model updating. In this work, we developed a framework for identifying frame-type structures regarding the measurement uncertainty and the uncertainty involved in inherent and structural parameters. The identification process is illustrated and examined on a one-eight-scale four-story moment-resisting steel frame under seismic excitation using two well-known recursive schemes: the Extended Kalman filter (EKF) and Unscented Kalman Filter (UKF) methods. The nonlinear system equations were assessed by applying a first-order instantaneous linearization approach through the EKF method. In contrast, the UKF algorithm employs several sample points to estimate moments of random variables' nonlinear transformations. A nonlinear transformation is applied to distribute sample points to derive the precise mean and covariance up to the second order of any nonlinearity. Accordingly, it is theoretically expected that the UKF algorithm is more capable of identifying the nonlinear systems and determining the unknown parameters than the EKF algorithm. The capability of the EKF and UKF algorithms was assessed by considering a 4-story moment-resisting steel frame with several inherent uncertainties, including the material behavior model, boundary conditions, and constraints. In addition to these uncertainties, the combination of acceleration and displacement responses of different structural levels is employed to evaluate the capability of the algorithms. The information entropy measure is used to investigate further the uncertainty of a group of established model parameters. As highlighted, a good agreement is observed between the results using the information entropy measure criterion and those using the UKF and EKF algorithms. The results illustrate that using the responses of fewer levels placed in the proper positions may lead to improved outcomes than those of more improperly positioned levels. [ABSTRACT FROM AUTHOR]

[Display omitted] • Proposes a novel deep learning model that utilizes both 1DCNN and RNN variants. • Uses the attention mechanism to improve the performance of the 1DCNN-RNN variant. • Uses raw acceleration time-series type of sequential data as the input data. • Compares the proposed model with equivalent dl -based model architectures. • Moreover, examines the environmental variable which affects structural response. In recent years, by emerging deep learning (DL) based algorithms, researchers have been exploring dl -based models to identify structural damage through data-driven approaches. dl -based data-driven techniques using autonomous feature extraction from raw sequential data are more robust under environmental variations. Extraction of robust features while considering the sequential dependencies will significantly improve the accuracy of damage identification by these techniques. In this regard, various architectures of dl -based models have been proposed. This study presents a novel dl -based model that utilizes both one-dimensional convolutional neural network (1DCNN) and recurrent neural network (RNN) variants using an attention mechanism. Attention mechanism improves the performance of the 1DCNN-RNN variants model precisely when its input data is raw acceleration time-history, as a kind of sequential data. The IASC-ASCE phase II and Qatar University grandstand simulator benchmarks are used to evaluate the proposed model by comparing its performance with dl -based neural network architectures that could be equivalent to this combination. Moreover, the environmental variable which affects structural response is also examined. Results demonstrate that the CNN-ATT-biGRU model architecture has the best accuracy and appropriate training time and model size among nine compared architectures. [ABSTRACT FROM AUTHOR]

This work presents an experimental and a numerical studies on the effect of the phenomenon of porosity on the mechanical properties of Glass Fiber Reinforced Polymer (GFRP). In a first part, material elaboration, as well as its characterization using a three-point bending test to extract the basic mechanical properties of the material, is considered. In a second part, a finite element model is created to simulate the problem of air bubbles broadly. Several cases of different shapes and sizes are simulated. The results show a significant effect on the reduction of load in both tensile and bending cases as the size of the bubbles increases. Furthermore, the second part includes the application of the Artificial Neural Network-Enhanced Jaya Algorithm (ANN-E JAYA) to predict the reduction of the tensile load as a function of different crack lengths obtained from an Extended Finite Element Method (XFEM) model. Next, to verify the accuracy of provided application , a comparison is made with two other applications such as Artificial Neural Network-Jaya Algorithm (ANN-JAYA) and Artificial Neural Network-Particle Swarm Optimization (ANN-PSO). The results of the three algorithms show good convergence, with a slight increase in accuracy for ANN-E JAYA. MATLAB code and data used in this article can be found at https://github.com/Samir-Khatir/GFRP-ANN-E-JAYA.git. [ABSTRACT FROM AUTHOR]

This work presents an experimental and a numerical studies on the effect of the phenomenon of porosity on the mechanical properties of Glass Fiber Reinforced Polymer (GFRP). In a first part, material elaboration, as well as its characterization using a three-point bending test to extract the basic mechanical properties of the material, is considered. In a second part, a finite element model is created to simulate the problem of air bubbles broadly. Several cases of different shapes and sizes are simulated. The results show a significant effect on the reduction of load in both tensile and bending cases as the size of the bubbles increases. Furthermore, the second part includes the application of the Artificial Neural Network-Enhanced Jaya Algorithm (ANN-E JAYA) to predict the reduction of the tensile load as a function of different crack lengths obtained from an Extended Finite Element Method (XFEM) model. Next, to verify the accuracy of provided application , a comparison is made with two other applications such as Artificial Neural Network-Jaya Algorithm (ANN-JAYA) and Artificial Neural Network-Particle Swarm Optimization (ANN-PSO). The results of the three algorithms show good convergence, with a slight increase in accuracy for ANN-E JAYA. MATLAB code and data used in this article can be found at https://github.com/Samir-Khatir/GFRP-ANN-E-JAYA.git. [ABSTRACT FROM AUTHOR]

• A novel hybrid strategy (HJDEA) based on Jaya and differential evolution algorithm is proposed. • A noise insensitive objective function is established based on adjacent acceleration correlation function. • An attractive combination of HJDEA and gradient search method is proposed to further improve performance. • Alterations of both stiffness and mass parameters are considered in the damage model. • Studies on shear-type frame, cantilever beam and ASCE benchmark structure are conducted to verify the effectiveness of the proposed methods. To solve the optimization-based structural damage identification problem, a novel hybrid algorithm based on Jaya and differential evolution algorithm (HJDEA) is proposed to detect, locate and quantify structural damages by effectively incorporating the powerful local exploitation capacity of Jaya algorithm and global exploration capability of differential evolution. Meanwhile, Hammersley sequence initialization and Lévy flight search mechanism are introduced into HJDEA to further improve convergence rate and refining the quality of the best solution. Four different algorithms, genetic algorithm, particle swarm optimization, Jaya and the proposed HJDEA are employed for comparative study. In addition, the objective function is established by adjacent acceleration correlation function so as to avoid false identification caused by defining improper reference point. The performance of the proposed damage identification strategy based on HJDEA and adjacent acceleration correlation function is investigated with numerical examples involving an 8-DOF lumped mass model and a cantilever beam, as well as an experimental study of the ASCE benchmark structure under white noise excitation. Results show that the proposed hybrid identification method is accurate, efficient and robust in the identification of the damage existence, location and severity of stiffness and mass parameters even with partial output-only responses and 20% noise-polluted measurements. [ABSTRACT FROM AUTHOR]