Search

This paper presents the effectiveness of a hybrid YUKI-RANDOM-FOREST, Particle Swarm Optimization-YUKI (PSO-YUKI), and balancing composite motion optimization algorithm (BCMO) based on artificial neural networks (ANN) for the best prediction of patch design considering the maximum principal stress. The study compares the maximum principal stress in a damaged pipe under different composite patch designs. Robust models have been developed and utilized in various applications. The research investigates the influence of cracks on the mechanical characteristics of API X70 steel in a test pipe under critical pressure. The numerical model employs the extended finite element method (XFEM) to simulate notches. Extending the optimization technique, the study examines the effect of crack presence in a pipeline section under internal pressure without and with composite repairs on the maximum principal stress. The sensitivity of stress is analyzed with respect to the design parameters of the composite patch. Finally, YUKI-RANDOM-FOREST, NN-PSO-YUKI, and NN-BCMO, with different parameters and hidden layer sizes are employed to predict the maximum principal stress under different composite patch designs, and yielding minimal error. Once the database was built, our model was prepared to predict various situations at the composite patch level. Compared to other methods, the obtained results with hybrid YUKI-RANDOM-FOREST are effective. The investigation technique is relevant to real-world engineering applications, structural safety control, and design processes. [ABSTRACT FROM AUTHOR]

This paper is concerned with the optimal design of axial probes, commonly used in the Non-Destructive Testing (NDT) of tube boiling in steam generators. The goal is to improve the low-frequency Foucault-current imaging of these deposits by designing a novel probe. The approach uses a combination of an inverse problem solver with global optimization to find the optimal probe characteristics by minimizing a function of merit defined using image processing techniques. The evaluation of the function of merit is computationally intensive and a surrogate optimization approach is used, incorporating a multi-particle search algorithm. The proposed design is validated through numerical experiments and aims to improve the accuracy and efficiency of identifying deposits in steam generator tubes. [ABSTRACT FROM AUTHOR]

Purpose: Although damage's location detection by Wavelet Transforms (WTs) is quantitive, damage's level detection is qualitative. It is a weakness of wavelet transform that cannot detect the level of damages quantitatively. For overcoming this weakness, this paper proposes a novel robust approach for quantifying the damage level of rectangular laminated composite plates using a combination of wavelet transforms and Artificial Neural Networks (WT-ANN). Methods: The finite element method generates two-dimensional signals of vibration amplitudes in the rectangular laminated composite plates. Next, a two-dimensional WTs is applied to the signals to generate wavelet coefficients and wavelet modulus. An artificial neural network is developed to quantify damage's level based on damage locations detected by wavelet transform and fundamental natural frequency. Results: Findings demonstrate that it is possible to quantify damages in rectangular laminated composite plates with high accuracy (R = 0.992). A disturbing phenomenon in damage identification techniques based on wavelet transform is discovered and called "edge noise". Conclusion: Results show that the proposed WT-ANN technique can detect all single-damage scenarios with very high accuracy by eliminating edge noises. [ABSTRACT FROM AUTHOR]

The dynamic experimental and numerical analysis of cracked beams has been studied with the aim of quantifying the influence of depth crack on the dynamic response of steel beams. Artificial Neural Method ANN has been used where a numerical simulation was improved in Matlab. A finite element model has also been developed by using the Ansys software, and the obtained results were compared with exact crack length. The study takes into account different hidden layer values in order to determine the sensitivity of the predicted crack depth. The results show that the response of the beam (frequencies) is strongly related to the crack depth, which significantly affects the beam behavior, especially when the crack is very deep where the ANN allows us to identify the crack in lower computational time. Based on the provided results, we can detect that the effect of hidden layer size can affect the results. [ABSTRACT FROM AUTHOR]

The friction of two bodies in relative motion is accompanied by several phenomena such as elevation of temperature. The aim of this work is to calculate the braking temperature of the brake disc of an aircraft during the landing phase, using a calculation code based on Finite Element Method (FEM) and the analytical method of Newcomb. This investigation uses two kinds of disc — full and real disc (original version mounted on the aircraft) — and three braking disc materials such as the cast irons FG15, FG20 and FG25. The result showed that the numbers of holes and slots existing in the real disc has no influence on the braking temperature compared to the full disc. On the other hand, all brake disc materials have almost the same thermal behavior. Both models, analytical and numerical, provided acceptable results. [ABSTRACT FROM AUTHOR]

Abstract This paper proposes a two-stage approach for damage assessment in beam-like structures using two-dimensional Isogeometric Analysis (IGA) and Finite Element Method (FEM) combined with optimization techniques. In the first stage, the Local Frequencies Change Ratio (LFCR) indicator and a newly developed damage indicator based on normalized Modal Strain Energy Indicator (nMSEDI) are introduced to locate effectively the potential damaged elements. In order to verify nMSEDI, different scenarios based on single and multiple damages are studied using numerical experiments. In the second stage, the Teaching-Learning-Based Optimization Algorithm (TLBO) is utilized and its performance is compared with that of Particle Swarm Optimization (PSO) and Bat Algorithm (BA). The three optimizations techniques are combined with IGA using nMSEDI as objective function. In addition, experimental vibration tests using laboratory steel been are conducted to validate the proposed technique. The obtained results clearly indicate that the proposed approach can be used to determine accurately and efficiently both damage location and severity in beam-like structures. [ABSTRACT FROM AUTHOR]

Fretting fatigue is a destructive failure that usually occurs in the parts or components in the aviation field. One of the important research topics in fretting fatigue is the prediction of crack initiation location. This paper proposed a new prediction methodology of crack initiation location, which is a deep learning model based on the statistical bootstrapping technique and finite element method (FEM). In this work, two kinds of deep learning models, namely Model-I and Model-II, are established based on different input features, and with the crack initiation location as output feature. The input features of Model-I are the contact load, the tangential load, the cyclic axial stress, and the radius of the fretting pad. In Model-II, one additional feature, namely the half contact-width, is considered. Firstly, three different normalization methods (Max-min, Zero-mean, and Nonlinear) are compared. It is found that the prediction of deep learning models based on the Zero-mean is the most accurate and stable. Then, through the study of sample size reliability, it is found that the prediction accuracy gradually increases initially then becomes stable with the increase of the sampling number. The estimated intervals also gradually become narrowed and then stable. Further, another highlight from the comparison between the performance of Model-I and Model-II is that with the physical-mechanical reasoning factor as additional input features, a more stable and accurate estimated crack initiation location can be obtained from deep learning models. The range of estimated intervals is also effectively narrowed. As an alternative to FEM, the computational efficiency of deep learning is at least 30% higher. The range of estimated intervals for crack initiation location are limited to 250 μ m and the errors between predictions and target values are lower than 5%. Therefore, the deep learning method proposed in this paper can effectively and efficiently predict fretting fatigue crack initiation location. [ABSTRACT FROM AUTHOR]

In this paper, a technique is presented for the detection and localization of an open crack in beam-like structures using experimentally measured natural frequencies and the Particle Swarm Optimization (PSO) method. The technique considers the variation in local flexibility near the crack. The natural frequencies of a cracked beam are determined experimentally and numerically using the Finite Element Method (FEM). The optimization algorithm is programmed in MATLAB. The algorithm is used to estimate the location and severity of a crack by minimizing the differences between measured and calculated frequencies. The method is verified using experimentally measured data on a cantilever steel beam. The Fourier transform is adopted to improve the frequency resolution. The results demonstrate the good accuracy of the proposed technique. [ABSTRACT FROM AUTHOR]

This paper presents a methodology for damage detection and localization in composite beams using vibration data, Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The data was acquired by developing a program that performs dynamic analysis of unidirectional graphite-epoxy composite beams based on the Finite Element Method (FEM). The objective function makes use of natural frequencies and Modal Assurance Criterion. The proposed methodology is validated using numerically simulated data and experimental data. A comparative study between the performances of PSO and GA in detecting multiple and single damage scenarios is carried out. Then, the effect of noise is investigated by taking different noise levels in the modal data. It appears that the noise has a negligible effect on the performance of the presented approaches. [ABSTRACT FROM AUTHOR]

Floating is a dangerous phenomenon for aircrafts and usually ends with plane rupture. It can be used to characterize a dynamic instability of the structure. Floating phenomenon is usually due to an interaction between aerodynamics, elasticity and inertial forces. It appears at a determinate speed of flight called critical floating speed. The aim of the present study is to determine the floating critical speed of an aircraft wing in a subsonic fan by means of experimental tests and numerical simulations using the commercial Finite Element Analysis package ANSYS CFX. The obtained experimental results are in good agreement with those obtained using the numerical approach. [ABSTRACT FROM AUTHOR]

In this paper, a new hybrid YUKI-ANN is implemented for Structural Health Monitoring (SHM) of laminated composite plates. A finite element model is constructed and used to identify damage at five randomly selected elements in a laminated composite plate. The process of damage identification is divided into two main steps, namely damage localization and quantification. During the localization step, damaged elements are identified using a damage indicator based on Modal Strain Energy change ratio (MSEcr). After excluding the healthy elements, the level of damage is predicted using ANN modified with four optimization algorithms: Arithmetic Optimizing Algorithm (AOA), Balancing Composite Motion Optimization (BCMO), Particle Swarm Optimization (PSO), and YUKI algorithm. The performance of these optimization algorithms is evaluated, and it is found that the YUKI algorithm (YA) outperforms AOA, BCMO, and PSO algorithms without exception. YA gives better predictions with lower errors when compared to PSO and BCMO algorithms with equivalent computational time. In some cases, AOA provides slightly better predictions than YA, but the computational time for these predictions is eight times more that of YA. If both performance and efficiency are considered, YA seems to be the best choice. Find the MATLAB code for YUKI-ANN at https://github.com/Brahim-Benaissa/YUKI_ANN. [ABSTRACT FROM AUTHOR]

This paper presents an approach of inverse damage detection and localization based on model reduction. The problem is formulated as an inverse problem where an optimization algorithm is used to minimize the cost function expressed as the normalized difference between a frequency vector of the tested structure and its numerical model. A finite element model of bi-dimensional monolithic composite beam reinforced by a graphite-epoxy is used to define a numerical model of the tested structure in which different scenarios of damage are considered by stiffness reduction. Then, calculations are made on a reduced model built by the technique of proper orthogonal decomposition coupled by radial basis functions. The accuracy of the method is verified through different damage configurations. The results show that the developed algorithm is a feasible methodology of predicting damage in short computing time and with high accuracy. The effect of noise on the accuracy of the results is investigated in some cases for the structure under consideration. [ABSTRACT FROM AUTHOR]

• Improved GWO using PSO. • Inverse problem using GWO and IGWO. • Crack identification. • Experimental validation for crack identification. This paper introduces an inverse problem for crack identification in two-dimensional structures using eXtend Finite Element Method (XFEM) associated with original Grey Wolf Optimization (GWO) and improved GWO using Particle Swarm Optimization (PSO) (IGWO). Static analysis with different boundary conditions and experimental modal analysis of cracked plates with varying crack length, positions, and orientation are used to test the accuracy of IGWO compared with the original GWO. The objective function is based on vertical measured strain and is computed at each iteration. The obtained results indicate that IGWO provides more accurate results than GWO based on convergence study and the error between exact and estimated results. Next, another application based on dynamic experimental cracked plates is used to improve Artificial Neural Network (ANN) parameters using GWO and IGWO. The frequencies and crack lengths are used as input and output for vertical and horizontal cracks in the plates. Thus, the model can be used for the prediction of crack length. IGWO can select the best parameters for better prediction compared with GWO. [ABSTRACT FROM AUTHOR]

• Enhanced flexibility indicator for damage detection. • Atom Search Optimization for damage quantification. • Complex planar truss and space truss dome structures. • Damage assessment in Canton Tower. In this paper, an enhanced damage indicator using a flexibility index is presented and applied to different complex structures to predict the exact location of damage. Finite Element Method (FEM) is used to model three complex structures, namely a 37-bar planar truss, a 52-bar planar truss, and a 52-bar space truss (Dome structure) to study the effectiveness of the proposed indicator. Single and multiple damage scenarios with different damage levels are considered. The results show that the proposed indicator provides an accurate location of damage. Next, to quantify the damage and assess its severity, two optimization techniques, namely Atom Search Optimization (ASO) and Salp Swarm Optimizer (SSA), which are recently invented, are used to solve an inverse problem. The objective function is based on the measured and calculated enhanced damage indicators. Both optimization techniques provide good results, however the convergence performance and CPU time are better for ASO than SSA. Finally, the proposed approach is tested using a benchmark structure, namely a high-rise tower (Guangzhou TV Tower) to predict the damage location at different floors. The results indicate that the proposed methodology is accurate and fast to predict single and multiple damages. [ABSTRACT FROM AUTHOR]

Metal/ceramic functionally graded materials (FGMs) have been increasingly used for impact-resistant applications because of their ability to combine the strength of both components. However, understanding the local response of FGMs under ballistic impact conditions remains a complex nonlinear problem. Moreover, performing experimental investigations is difficult due to technical limitations in measuring critical parameters such as stress, strain, and pressure. That is why research in this field also concentrates on modeling methodologies, such as numerical simulations. In this study, a finite element model (FEM) was implemented to investigate the behavior of a particular metal/ceramic-based FGM impacted with fragment-simulating projectiles (FSPs). The studied FGMs, exhibiting an elastoplastic behavior, were composed of aluminum (Al) and silicon carbide (SiC). The ceramic volume fraction (Vc) varies according to a power-law distribution, through the thickness. Their effective material properties were evaluated using a homogeneization-based self-consistent method. FGM's dynamic behavior was described using the dynamic Tamura-Tomota-Ozawa model (DTTO). The numerical simulations were in good correlation with experimental results. The importance of the DTTO model's introduction and the calibration of the plastic strain criterion in the failure modeling of FGMs were highlighted. In addition, it was observed that the variation in the composition exponent and grading continuity of mechanical properties has a significant effect on the predicted ballistic limit. It was finally noted that a linearly-composed 5-layerbased specimen exhibited a higher level of ballistic resistance. [ABSTRACT FROM AUTHOR]

• A new prediction method for fretting fatigue crack initiation lifetime. • A combination of deep neural network, Findley parameter and finite element method. • Accurate prediction of fretting fatigue lifetime. In the aviation field, the crack initiation stage could be the dominant one of the whole damage failure process of components subjecting to fretting fatigue. Thus, getting an accurate prediction of the crack initiation lifetime become an important topic in research of fretting fatigue problems. In this work, a new prediction method for fretting fatigue crack initiation lifetime is proposed, which is based on Deep Neural Network (DNN), Findley Parameter (FP) and Finite Element Method (FEM). Input features are shear stress amplitude and maximum normal stress in the critical plane, and crack initiation lifetime is set as the output target. Dropout and bootstrapping are considered to improve the performance of DNN. Through comparative analysis, it is shown that this new proposed approach can effectively predict the fretting fatigue crack initiation lifetime. The prediction accuracy and stability are greatly improved compared with the theoretical formulation based on FP. [ABSTRACT FROM AUTHOR]

Abstract In this paper, a Structural Health Monitoring (SHM) technique for damage identification in beam-like and truss structures using Frequency Response Function (FRF) data coupled with optimization techniques is presented. Genetic Algorithm (GA) and Bat Algorithm (BA) are used to estimate the location and severity of damage. The damage in the structures is simulated by reduction in rigidity of specific members. Both optimization techniques are coupled with modelled structures using Finite Element Method (FEM). The approach is based on minimizing an objective function by comparing measured and calculated FRFs. The results show that better accuracy is obtained using BA than using GA in terms of precision and computational time. Furthermore, it is found that the proposed approach provides faster solution than other approaches in the literature. [ABSTRACT FROM AUTHOR]

The durability and simplicity of the programming of meta-heuristic algorithms make them important in the optimization field. This paper presents a novel application for double cracks identification in Carbon Fiber Reinforced Polymer (CFRP) cantilever beams based on experimental and numerical analyses using enhanced optimization techniques. A new hybrid algorithm Particle Swarm Optimization and YUKI (PSO-YUKI) is proposed and combined with Radial Basis Functions (RBF) for solving fast inverse problems. The direct problem is based on the results of the dynamic experimental test of CFRP laminate, measuring the dynamics characteristics of a healthy beam, and the variation in the response corresponding to different scenarios of double cracks with different depths. The Finite Element Method (FEM) is used to simulate this vibrational behavior considering double cracks in different locations. The goal is creating an accurate damage identification method that has a high computational performance, based on the idea of building models that combines the vibrational responses issued from the experiments and simulations. The suggested method is tested based on collected data from numerical and experimental modal analyses in the case of undamaged and damaged CFRP laminates to demonstrate its accuracy and efficiency. The provided results show the robustness of PSO-YUKI compared with PSO for double cracks depth identification. The Matlab Code of PSO-YUKI can be found at https://github.com/Samir-Khatir/Hybrid-PSO-YUKI-.git. [ABSTRACT FROM AUTHOR]

• Damage detection in high-rise buildings. • Finite element model updating using a link between SAP2000 commercial software and MATLAB. • Inverse problem using a bio-inspired meta-heuristic optimization algorithm, named Termite life cycle optimizer (TLCO). In this paper, for the first time, a damage assessment technique for a high-rise concrete structure is presented. This structure has sixteen stories, a total height of 57 m and its total long and short spans are 33 m. Especially, this structure has the appearance of shear wall and core wall elements, which has not yet investigated in the literature. For this purpose, a new Finite Element (FE) model updating technique is proposed based on the development of a successful program, which makes a link between SAP2000 commercial software and MATLAB program. This program allows the user to create a continuous two-way data exchange between SAP2000 and MATLAB. Thus, the process of parameters updating in the FE model in SAP2000 can be implemented by command in the code instead of by point-click procedures. The process of structural damage assessment is then secured by inverse methods. This method will be handled by a bio-inspired meta-heuristic optimization algorithm, namely Termite Life Cycle Optimizer (TLCO), which is proposed by the authors recently. The parameters in TLCO are fixed. Therefore, it is not necessary for the user to set the initial parameters, which is an effective strategy compared to other algorithms. The results obtained in this study show a significant improvement in the damage identification of large-scale structures. [ABSTRACT FROM AUTHOR]

• A new methodology for multi-parameter identification of concrete dams is proposed. • For the first time, polynomial chaos expansion and slime mould algorithm are integrated. • A very high computational efficiency is achieved using the proposed methodology. This paper presents a novel methodology that combines polynomial chaos expansion and slime mould algorithm for multi-parameter identification of concrete dams. This methodology not only incorporates the merits of low computational cost in the polynomial chaos expansion and fast convergence of slime mould algorithm, but also considers the priori uncertainty in the input parameters by introducing statistical probability theory. By considering two examples with different complexity, this paper verifies the effectiveness of the proposed method with a univariate simply supported beam model, followed by a complex multivariate dam model to demonstrate its practicability in real engineering problems. In addition, parameter sensitivity analysis of the dam model is conducted at an extremely low cost by polynomial chaos expansion based on Sobol' indices. Furthermore, the conventional parameter identification methods based on optimization methods directly combined with the finite element model are employed for comparison, highlighting two distinct advantages of the proposed method: (i) the proposed method improves the computational efficiency by nearly 52 times while ensuring a high accuracy, and (ii) the classical non-population optimization algorithm, Bayesian optimization, is used for comparison, revealing the outstanding performance of slime mould algorithm in terms of convergence speed and robustness. The application of the proposed algorithm is not only limited to dams, but also it can be extended to any structure. [ABSTRACT FROM AUTHOR]

• New improved ANN using Jaya and BCMO. • Fast prediction of the peak load and absorbed energy of dynamic brittle fracture. • Experimental tests in specimens of steel pipeline Drop Weight Tear Test (DWTT). • Numerical and Experimental validation. In this paper, a robust technique is presented to predict the peak load and crack initiation energy of dynamic brittle fracture in X70 steel pipes using an improved artificial neural network (IANN). The main objective is to investigate the behaviour of API X70 steel based on two experimental tests, namely Drop Weight Tear Test (DWTT) and the Charpy V-notch impact (CVN), for steel pipe specimens. The mechanical properties in the brittle fracture behaviour of API X70 steel pipes are predicted utilizing numerical approaches with different crack lengths. Next, to simulate the impact of API X70 steel pipes at lower temperatures through a numerical approach, a cohesive approach using the extended Finite Element Method (XFEM) is used. The data obtained are used as input for the proposed IANN using Balancing Composite Motion Optimization (BCMO), Particle Swarm Optimization (PSO) and Jaya optimization algorithms, to predict the peak load values and crack initiation energy of dynamic brittle fractures in API X70 steel with different crack lengths. The results show the effectiveness of ANN-PSO and ANN-BCMO based on the convergence of the results and the accuracy of the prediction of the peak load and crack initiation energy. Note that, the source codes are publicly available at https://github.com/Samir-Khatir/JAYA-ANN.git. [ABSTRACT FROM AUTHOR]