Identification of damage properties of glass/epoxy laminates using machine learning models

Jalali, Seyed Siavash; Mahzoon, Mojtaba; Mohammadi, Hossein

doi:10.1016/j.ijimpeng.2023.104510

Cited by 4 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1,2 Composites are used in different industries, such as aerospace, defense, automotive parts, sports equipment, marine sectors, etc. [3][4][5][6][7] Many studies have been carried out in the last few decades to analyze the impact of ply orientations in different loading cases. Bhatia et al 8,9 reported the effect of ply orientations in tension and compression loading cases.…”

Section: Introductionmentioning

confidence: 99%

“…Demand for fiber‐reinforced polymer (FRP) composite materials for different engineering applications has increased because of their higher specific strength and stiffness properties, superior fatigue life, excellent corrosion resistance and ease of tailoring properties 1,2 . Composites are used in different industries, such as aerospace, defense, automotive parts, sports equipment, marine sectors, etc 3–7 . Many studies have been carried out in the last few decades to analyze the impact of ply orientations in different loading cases.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A parametric study on patch repaired quasi‐isotropic laminate in high‐velocity impact environment: Experimental and numerical investigation

Sahoo,

Chennamsetti,

Arockiarajan

2024

Polymer Composites

View full text Add to dashboard Cite

In this work, the post‐repair behavior of a quasi‐isotropic laminate was studied in a high‐velocity impact environment. The composite laminates were repaired using an external bonded patch repair procedure. Impact tests were performed to understand the effect of patch size and the result of filling the damaged region with a neat epoxy and hardener mixture. Two different size square patches, such as 30 and 50 mm, were used to analyze the effect of patch size. A continuum damage mechanics‐based model was developed and incorporated into a finite element model interface to estimate the optimum patch size and patch stacking sequence for the impact environment. In the finite element model, the intralaminar failure criteria were implemented using the ABAQUS‐VUMAT user subroutine, and the interlaminar failure criteria were implemented using the inbuilt cohesive contact properties. The 30 mm patch with resin filled in the damaged region performed better than the other combination patches. Also, placing 45° plies toward the outer layer of the patches showed lower damage compared to the patches in which 45° plies were placed at the inner surfaces.Highlights Post‐repair impact behavior of repaired laminates was examined. Impact of patch dimension and resin filling in the damaged area was analyzed. A 3‐D finite element model was developed to optimize patch parameters. Continuum damage mechanics model has been incorporated with VUMAT subroutine. Interface between lamina has been modeled using cohesive contact.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A parametric study on patch repaired quasi‐isotropic laminate in high‐velocity impact environment: Experimental and numerical investigation

Sahoo,

Chennamsetti,

Arockiarajan

2024

Polymer Composites

View full text Add to dashboard Cite

show abstract

“…Additionally, model interpretability is a crucial issue, especially in highly complex composite material systems [ 36 , 40 , 41 , 42 ]. Machine learning has paved a new path for composite material research, providing more efficient and economical means to predict and understand material performance.…”

Section: Introductionmentioning

confidence: 99%

Experimental and Numerical Investigation Integrated with Machine Learning (ML) for the Prediction Strategy of DP590/CFRP Composite Laminates

Hu,

Wei,

Wang

et al. 2024

Polymers

View full text Add to dashboard Cite

This study unveils a machine learning (ML)-assisted framework designed to optimize the stacking sequence and orientation of carbon fiber-reinforced polymer (CFRP)/metal composite laminates, aiming to enhance their mechanical properties under quasi-static loading conditions. This work pioneers the expansion of initial datasets for ML analysis in the field by uniquely integrating the experimental results with finite element simulations. Nine ML models, including XGBoost and gradient boosting, were assessed for their precision in predicting tensile and bending strengths. The findings reveal that the XGBoost and gradient boosting models excel in tensile strength prediction due to their low error rates and high interpretability. In contrast, the decision trees, K-nearest neighbors (KNN), and random forest models show the highest accuracy in bending strength predictions. Tree-based models demonstrated exceptional performance across various metrics, notably for CFRP/DP590 laminates. Additionally, this study investigates the impact of layup sequences on mechanical properties, employing an innovative combination of ML, numerical, and experimental approaches. The novelty of this study lies in the first-time application of these ML models to the performance optimization of CFRP/metal composites and in providing a novel perspective through the comprehensive integration of experimental, numerical, and ML methods for composite material design and performance prediction.

show abstract

Advanced computational modelling of composite materials

Cheng,

Liu,

Tan

2024

Engineering Fracture Mechanics

View full text Add to dashboard Cite

Identification of damage properties of glass/epoxy laminates using machine learning models

Cited by 4 publications

References 31 publications

A parametric study on patch repaired quasi‐isotropic laminate in high‐velocity impact environment: Experimental and numerical investigation

A parametric study on patch repaired quasi‐isotropic laminate in high‐velocity impact environment: Experimental and numerical investigation

Experimental and Numerical Investigation Integrated with Machine Learning (ML) for the Prediction Strategy of DP590/CFRP Composite Laminates

Advanced computational modelling of composite materials

Contact Info

Product

Resources

About