Efficient Artificial neural networks based on a hybrid metaheuristic optimization algorithm for damage detection in laminated composite structures

Abstract In this paper, we propose an efficient Artificial Neural Network (ANN) based on the global search capacity of evolutionary algorithms (EAs) to identify damages in laminated composite structures. With remarkable advances, ANN has taken off over the last decades. However, ANN also has major drawbacks relating to local minima issues because it applies backpropagation algorithms based on gradient descent (GD) techniques. This leads to a substantial reduction in the effectiveness and accuracy of ANN. Some researchers have been come up with some solutions to tackle the local minimal problems of ANN by looking for starting beneficial points to eliminate initial local minima based on the global search capacity of stochastic algorithms. Nevertheless, it is commonly acknowledged that those solutions are no longer useful or even counterproductive in some cases if the network contains too many local minima distributed deeply in the search space. Hence, we propose a novel approach applying the fast convergence speed of GD techniques of ANN and the global search capacity of EAs to train the network. The core idea is that EAs are employed to work parallel with ANN during the process of training the network. This guarantees that the network possibly determines the best solution fast and avoids getting stuck in local minima. To enhance the efficiency of the global search capacity, in this work, a hybrid metaheuristic optimization algorithm (HGACS) of EAs is also proposed, which possibly gains the advantages of both Genetic Algorithm (GA) and Cuckoo Search (CS). GA is applied to generate initial populations with the best quality derived from the ability of crossover and mutation operators, whereas CS with global search capacity is used to seek the best solution. Moreover, to deal with the large amount of data utilized to train the network, a vectorization technique is applied for the data of the objective function, which considerably decreases the computational cost. The obtained results prove that the proposed method is superior to traditional ANN, other hybrid-ANNs, and HGACS in terms of accuracy, and significantly reduces computational time compared with HGACS.

[1]  H. Tran-Ngoc,et al.  Model Updating for Nam O Bridge Using Particle Swarm Optimization Algorithm and Genetic Algorithm , 2018, Sensors.

[2]  Ganggang Sha,et al.  Multiple damage detection in laminated composite beams by data fusion of Teager energy operator-wavelet transform mode shapes , 2020 .

[3]  Huan X. Nguyen,et al.  Data-Driven Structural Health Monitoring Using Feature Fusion and Hybrid Deep Learning , 2020, IEEE Transactions on Automation Science and Engineering.

[4]  A. Bahrami,et al.  Using GA–ANN algorithm to optimize soft magnetic properties of nanocrystalline mechanically alloyed Fe–Si powders , 2009 .

[5]  Trung Nguyen-Thoi,et al.  An efficient approach for optimal sensor placement and damage identification in laminated composite structures , 2018, Adv. Eng. Softw..

[6]  Bui Ngoc Dung,et al.  Multiple vehicles detection and tracking for intelligent transport systems using machine learning approaches , 2019 .

[7]  Jamal A. Abdalla,et al.  Prediction of shear strength and behavior of RC beams strengthened with externally bonded FRP sheets using machine learning techniques , 2020 .

[8]  Gregory E. Fasshauer,et al.  Analysis of natural frequencies of composite plates by an RBF-pseudospectral method , 2007 .

[9]  Timon Rabczuk,et al.  Machine-learning interatomic potentials enable first-principles multiscale modeling of lattice thermal conductivity in graphene/borophene heterostructures , 2020, Materials Horizons.

[10]  H. Tran-Ngoc,et al.  An efficient artificial neural network for damage detection in bridges and beam-like structures by improving training parameters using cuckoo search algorithm , 2019, Engineering Structures.

[11]  Chien H. Thai,et al.  Computational optimization for porosity-dependent isogeometric analysis of functionally graded sandwich nanoplates , 2020 .

[12]  Samir Khatir,et al.  An efficient approach for model updating of a large-scale cable-stayed bridge using ambient vibration measurements combined with a hybrid metaheuristic search algorithm , 2020 .

[13]  H. Tran-Ngoc,et al.  An efficient hybrid TLBO-PSO-ANN for fast damage identification in steel beam structures using IGA , 2020 .

[14]  H. Tran-Ngoc,et al.  Damage detection in truss bridges using transmissibility and machine learning algorithm : application to Nam O bridge , 2020 .

[15]  António J.M. Ferreira,et al.  Static deformations and vibration analysis of composite and sandwich plates using a layerwise theory and RBF-PS discretizations with optimal shape parameter , 2008 .

[16]  K. M. Liew,et al.  SOLVING THE VIBRATION OF THICK SYMMETRIC LAMINATES BY REISSNER/MINDLIN PLATE THEORY AND THEp-RITZ METHOD , 1996 .

[17]  Chen Wanji,et al.  Free vibration of laminated composite and sandwich plates using global–local higher-order theory , 2006 .

[18]  Thiago A.M. Guimarães,et al.  On the modeling of nonlinear supersonic flutter of multibay composite panels , 2020 .

[19]  Edwin Reynders,et al.  An efficient approach to model updating for a multispan railway bridge using orthogonal diagonalization combined with improved particle swarm optimization , 2020 .

[20]  Zuozhou Pan,et al.  A two-stage method based on extreme learning machine for predicting the remaining useful life of rolling-element bearings , 2020 .

[21]  G. Bonnet,et al.  First-order shear deformation plate models for functionally graded materials , 2008 .

[22]  H. Tran-Ngoc,et al.  A novel machine-learning based on the global search techniques using vectorized data for damage detection in structures , 2020 .

[23]  Xiaoying Zhuang,et al.  An efficient optimization approach for designing machine learning models based on genetic algorithm , 2020, Neural Computing and Applications.

[24]  Samir Khatir,et al.  A modified transmissibility indicator and Artificial Neural Network for damage identification and quantification in laminated composite structures , 2020 .

[25]  Craig Przybyla,et al.  Predicting the effects of microstructure on matrix crack initiation in fiber reinforced ceramic matrix composites via machine learning , 2020 .

[26]  Yufeng Xing,et al.  Three-dimensional thermo-mechanical solutions of cross-ply laminated plates and shells by a differential quadrature hierarchical finite element method , 2019, Composite Structures.

[27]  Samir Khatir,et al.  Damage assessment in composite laminates using ANN-PSO-IGA and Cornwell indicator , 2019 .

[28]  Tanmoy Mukhopadhyay,et al.  Machine learning based stochastic dynamic analysis of functionally graded shells , 2020 .