Damage detection in GFRP composite structures by improved artificial neural network using new optimization techniques

Zara, A.; Belaidi, Idir; Khatir, Samir; Ouladbrahim, Abdelmoumin; Boutchicha, Djilali; Wahab, Magd Abdel

doi:10.1016/j.compstruct.2022.116475

Cited by 35 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, MATLAB software is used to make a connection between inputs and outputs using the Jaya and E-Jaya algorithm, to determine the peak load to starting failure and maximum displacement under the effect of a bending load (see Figure 8). Many studies have previously used this technique, where more details can be found, such as Zara et al (2023), who studied the detection of different crack lengths using several improved optimization techniques, such as enhanced Jaya ANN based on experimental natural frequency results. Also, Fahem et al (2023) predicted the strength and tensile load reduction in a GFRP composite using Jaya's improved algorithm.…”

Section: Improved Ann Using Jaya and E-jayamentioning

confidence: 99%

Numerical study of the influence of layers number and their orientation in a CFRP using improved ANN based on Enhanced Jaya

Oulad Brahim

2024

HCMCOUJS - Advances in Computational Structures

View full text Add to dashboard Cite

The advancement of technology in the field of artificial intelligence has facilitated significant progress in various areas, particularly in optimizing the structural configuration of multilayer composites. This study's primary objective is to investigate how geometric parameters, such as fiber orientation and the number of layers influence the mechanical properties of these materials. To predict fracture toughness in bending tests, we employed a hybrid optimization technique (E-Jaya-ANN) and compared it with the Jaya-ANN method to assess the improved approach's accuracy. Furthermore, we developed a numerical model based on the Hashin damage criterion using ABAQUS software to anticipate the response of composite specimens (CFRP) when subjected to a bending load. We validated the reliability of the code results by comparing them with experimental data. Subsequently, we generated a series of numerical results, representing various practical scenarios, to serve as the foundation for training an artificial neural network (ANN). This enabled us to obtain an enhanced architecture for the laminate layers.

show abstract

Section: Improved Ann Using Jaya and E-jayamentioning

confidence: 99%

Numerical study of the influence of layers number and their orientation in a CFRP using improved ANN based on Enhanced Jaya

Oulad Brahim

2024

HCMCOUJS - Advances in Computational Structures

View full text Add to dashboard Cite

show abstract

“…To improve the diagnosis model, the authors optimized the meta-parameters of DSAE using the enhanced whale optimization algorithm (EWOA), which included the dropout parameter, the weight decay coefficient, the learning rate, and the hidden layer neuron numbers. An example of ANN techniques applying optimization algorithms to detect composite damage can be found in [ 344 ]. The results in this paper showed how recent optimization techniques have been used to calibrate the influential parameters during the training of ANN, including Jaya, Whale Optimization Algorithm (WOA), enhanced Jaya (E-Jaya), and Arithmetic Optimization Algorithm (AOA).…”

Section: Optimization Algorithmsmentioning

confidence: 99%

A Systematic Review of Optimization Algorithms for Structural Health Monitoring and Optimal Sensor Placement

Hassani

Dackermann

2023

Sensors

View full text Add to dashboard Cite

In recent decades, structural health monitoring (SHM) has gained increased importance for ensuring the sustainability and serviceability of large and complex structures. To design an SHM system that delivers optimal monitoring outcomes, engineers must make decisions on numerous system specifications, including the sensor types, numbers, and placements, as well as data transfer, storage, and data analysis techniques. Optimization algorithms are employed to optimize the system settings, such as the sensor configuration, that significantly impact the quality and information density of the captured data and, hence, the system performance. Optimal sensor placement (OSP) is defined as the placement of sensors that results in the least amount of monitoring cost while meeting predefined performance requirements. An optimization algorithm generally finds the “best available” values of an objective function, given a specific input (or domain). Various optimization algorithms, from random search to heuristic algorithms, have been developed by researchers for different SHM purposes, including OSP. This paper comprehensively reviews the most recent optimization algorithms for SHM and OSP. The article focuses on the following: (I) the definition of SHM and all its components, including sensor systems and damage detection methods, (II) the problem formulation of OSP and all current methods, (III) the introduction of optimization algorithms and their types, and (IV) how various existing optimization methodologies can be applied to SHM systems and OSP methods. Our comprehensive comparative review revealed that applying optimization algorithms in SHM systems, including their use for OSP, to derive an optimal solution, has become increasingly common and has resulted in the development of sophisticated methods tailored to SHM. This article also demonstrates that these sophisticated methods, using artificial intelligence (AI), are highly accurate and fast at solving complex problems.

show abstract

“…A summary of these studies based on the aims of the present study, focusing on the identification method, types of cracks, etc. [1][2][3][4][5][6][7][8][9][10][11][12][13][14], is presented in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

A novel hybrid multi-stage probabilistic algorithm for the damage detection of carbon nanotube panels by considering the uncertainty of materials and mechanical properties

Khayat,

Amoushahi

2024

Preprint

View full text Add to dashboard Cite

Composite materials have a high level of uncertainty (intrinsic and non-intrinsic) due to the manufacturing process as well as the placement of different phases of their constituent materials. These uncertainties can be identified in both macro and micro scales. Identifying the behavior of structures made of composite materials without taking into account the uncertainties, whether due to identification or modeling, can lead to unrealistic results, especially in the dynamic behavior of structures. One of these cases is the identification of damage types in composite structures which is usually done by using dynamic responses. Damages in composite materials or structures usually occur during construction or operation. The correct modeling of uncertainty sources is one of the most important factors in identifying the geometry, location, and severity of damages accurately. The uncertainties related to the position and placement of carbon nanotubes (CNTs) can cause noticeable changes in the characteristics of composite materials reinforced with CNTs. For this reason, in the present study, we identified damages in CNT panels by considering all possible sources of uncertainty. A probabilistic multi-stage reliability-based method was proposed in this study to detect damage in these structures. In order to model the intrinsic and non-intrinsic sources of uncertainty, a modified point estimation method (MPEM) was used. In addition, an enhanced differential quadrature (DQ) method was used to model the CNT panels. In each step of the proposed algorithm, the probability of damage in each element of the panels was calculated by analyzing the possible damages. According to the results of the previous step, the elements with a low failure probability were gradually sifted in the next steps. The sieved elements in each step were considered as intact elements in the next step. This systematic filtering of design variables can simultaneously reduce the dimensions and speed up the optimization problem. Finally, the probability of damage was calculated based on the probability density function of various damage severities and positions. The developed approach was applied for damage detection on a laboratory-tested plate to illustrate the efficiency of the proposed method. The effects of using different damage positions and severity levels on the diagnosis results were discussed. The results demonstrated that the number of frequencies and modes of vibration required to identify the position and severity of damages accurately is different according to the damage scenarios and the percentage of uncertainty.

show abstract

Damage detection in GFRP composite structures by improved artificial neural network using new optimization techniques

Cited by 35 publications

References 37 publications

Numerical study of the influence of layers number and their orientation in a CFRP using improved ANN based on Enhanced Jaya

Numerical study of the influence of layers number and their orientation in a CFRP using improved ANN based on Enhanced Jaya

A Systematic Review of Optimization Algorithms for Structural Health Monitoring and Optimal Sensor Placement

A novel hybrid multi-stage probabilistic algorithm for the damage detection of carbon nanotube panels by considering the uncertainty of materials and mechanical properties

Contact Info

Product

Resources

About