Design optimization of laminated composite structures using artificial neural network and genetic algorithm

Liu, Xiaoyang; Qin, Jianguang; Zhao, Kai; Featherston, Carol Ann; Kennedy, David; Jing, Yucai; Yang, Guotao

doi:10.1016/j.compstruct.2022.116500

Cited by 33 publications

(8 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Liao et al 17 employ two models, each with two ANNs, for strength and stiffness predictions. Liu et al 18 focus on buckling effects. Unlike these previous multi-step models, the present approach requires only a single step.…”

Section: Discussionmentioning

confidence: 99%

“…As with the previously mentioned articles, there are recent studies where the use of neural networks as metamodels to analyze applications and study the response of laminated composite materials is combined. For example, to predict the strength value of a compound, 17 and for structural buckling analysis, 18 and also for machining optimization in structural applications. 19 In developing metamodels based on ML, the input and output parameters are diverse and focused on the property to be analyzed.…”

Section: Introductionmentioning

confidence: 99%

“…19 In developing metamodels based on ML, the input and output parameters are diverse and focused on the property to be analyzed. For instance, in a study by Liu et al, 18 the laminate configuration (fiber steering and thickness) is introduced as inputs for an artificial neural network, whose function is to predict the performance of a part manufactured with laminated composite materials.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural networks modeling of strain energy density and Tsai-Wu index in laminated composites

Ledesma-Orozco,

Galvis-Chacón,

Rodríguez-Sánchez

2024

Journal of Composite Materials

View full text Add to dashboard Cite

In laminated composite materials design, optimization mainly targets the stacking sequence configuration, which is defined by the lamina thickness and fiber orientations within each layer. Recent studies emphasize the increasing role of Machine Learning in promoting innovative composite designs by facilitating the accurate modeling of essential properties such as strength and stiffness. This study introduces two metamodels that utilize feed-forward artificial neural networks, taking laminate thickness and fiber steering angles as input parameters. The output variables, including strain energy density and the Tsai-Wu failure index, enable the prediction of stacking sequence configurations for laminated materials, a capability confirmed in a case study. The results showcase neural network models with the ability to predict these variables, achieving coefficients of determination above 0.90 for testing data. Consequently, this modeling approach has the potential to be a tool for designers, aiding in decision-making processes for the subsequent optimization of stiffness and strength in structural components made of laminated composite materials.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural networks modeling of strain energy density and Tsai-Wu index in laminated composites

Ledesma-Orozco,

Galvis-Chacón,

Rodríguez-Sánchez

2024

Journal of Composite Materials

View full text Add to dashboard Cite

show abstract

“…The ML model is trained using the RF method which is widely appreciated for its high accuracy, robustness, and ease of use in bridge engineering [29]. The RF model operates through an ensemble learning strategy, wherein it constructs multiple decision trees (DT) and combines their predictions to enhance accuracy [30]. Each DT utilizes a tree-like structure, with internal nodes representing attributes and branches indicating potential attribute values [31].…”

Section: Rule12mentioning

confidence: 99%

Machine Learning-Driven Ontological Knowledge Base for Bridge Corrosion Evaluation

Jiang,

Li,

Yang

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

In bridge maintenance, assessing structural performance requires adherence to rules outlined in safety and regulatory standards which can be effectively and formally represented in both human and machine-readable formats using ontologies. However, ontology-based semantic inference alone falls short when faced with the complicated mathematical operations required for structural analysis. The increasing digitization of bridge engineering has opened doors to data-driven prediction methods. Machine learning (ML)-based models, in particular, have the capacity to learn from historical data and forecast future structural performance with remarkable accuracy. This paper introduces an innovative approach that integrates ML models with an ontological knowledge base for evaluating bridge corrosion. Web Ontology Language and Semantic Web Rule Language are combined to develop the knowledge base. Random forest algorithm is used to train the ML model with a good agreement (coefficient of determination of 0.989 and root mean square error of 1.200). A Python-based module is designed to seamlessly integrate ML predictions with ontologybased semantic inference. The proposed approach not only infers the corrosion ratings based on the rules defined in the Network Rail standard, but also infers the structural safety performance based on predicted structural response under the action of corrosion. To demonstrate the effectiveness of the developed method in enabling accurate and rational evaluations, a real bridge in the UK is showcased as a practical application.

show abstract

“…Currently, this material can no longer be described as "new". Moreover, its field of application has largely opened to more "popular" fields: sports (tennis, cycling, skiing), automobile [13][14][15][16][17][18], wind energy [19][20], aerospace [21][22][23], railway [24][25], nautical [26][27], civil engineering [28][29][30], biomechanical industries [31][32][33][34][35][36].…”

Section: Introductionmentioning

confidence: 99%

Effect of plant short fibers on the mechanical properties of carbon fiber reinforced epoxy matrix by using FEM based numerical homogenization technique

I. Haddouch,

I. Mouallif,

M. Benhamou

et al. 2024

IJNeaM

View full text Add to dashboard Cite

In this study, we utilized the material design library in Ansys Product 2022 R1 to analyze the impact of short plant fibers on the mechanical properties of epoxy resin. We employed the representative volume element (RVE) approach and examined different volume fractions up to 50%. The technique employed in this study was multi-scale modeling based on the finite element method (FEM) for numerical homogenization. Subsequently, we used the same software to develop a five-layer laminated composite. The samples were based on epoxy resin enriched with short plant fibers at fractions of 20% and 30%, as well as pure epoxy resin. The laminated composites were reinforced with carbon fibers. The objective of this study was to analyze the mechanical response of each sample during a tensile test, focusing on multiple parameters. The sought-after results included total deformation, directional deformation, equivalent and elastic stress (Von-mises). The samples containing epoxy resin enriched with 30% of short hemp fibers exhibited remarkable mechanical strength compared to the other samples. These results suggest that the incorporation of short hemp fibers into the matrix led to a significant improvement in the mechanical strength of the composite.

show abstract

Design optimization of laminated composite structures using artificial neural network and genetic algorithm

Cited by 33 publications

References 69 publications

Neural networks modeling of strain energy density and Tsai-Wu index in laminated composites

Neural networks modeling of strain energy density and Tsai-Wu index in laminated composites

Machine Learning-Driven Ontological Knowledge Base for Bridge Corrosion Evaluation

Effect of plant short fibers on the mechanical properties of carbon fiber reinforced epoxy matrix by using FEM based numerical homogenization technique

Contact Info

Product

Resources

About