Machine learning algorithms for delaminations detection on composites panels by wave propagation signals analysis: Review, experiences and results

Monaco, E.; Rautela, M.; Gopalakrishnan, S.; Ricci, F.

doi:10.1016/j.paerosci.2024.100994

Cited by 2 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, the use of machine learning (ML) algorithms to evaluate the mechanical properties and performances of composite structures under diverse loading and environmental conditions has attracted increasing attention. For instance, transfer learning, a subset of ML, shows the potential to adapt to environmental and operational variabilities, thereby accurately identifying these properties [ 18 , 19 , 20 ]. This trend is attributed to the accuracy of the models and their robustness across several applications.…”

Section: Introductionmentioning

confidence: 99%

Effects of Seawater on Mechanical Performance of Composite Sandwich Structures: A Machine Learning Framework

Osa-uwagboe,

Udu,

Silberschmidt

et al. 2024

Materials

View full text Add to dashboard Cite

Sandwich structures made with fibre-reinforced plastics are commonly used in maritime vessels thanks to their high strength-to-weight ratios, corrosion resistance, and buoyancy. Understanding their mechanical performance after moisture uptake and the implications of moisture uptake for their structural integrity and safety within out-of-plane loading regimes is vital for material optimisation. The use of modern methods such as acoustic emission (AE) and machine learning (ML) could provide effective techniques for the assessment of mechanical behaviour and structural health monitoring. In this study, the AE features obtained from quasi-static indentation tests on sandwich structures made from E-glass fibre face sheets with polyvinyl chloride foam cores were employed. Time- and frequency-domain features were then used to capture the relevant information and patterns within the AE data. A k-means++ algorithm was utilized for clustering analysis, providing insights into the principal damage modes of the studied structures. Three ensemble learning algorithms were employed to develop a damage-prediction model for samples exposed and unexposed to seawater and were loaded with indenters of different geometries. The developed models effectively identified all damage modes for the various indenter geometries under different loading conditions with accuracy scores between 86.4 and 95.9%. This illustrates the significant potential of ML for the prediction of damage evolution in composite structures for marine applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Effects of Seawater on Mechanical Performance of Composite Sandwich Structures: A Machine Learning Framework

Osa-uwagboe,

Udu,

Silberschmidt

et al. 2024

Materials

View full text Add to dashboard Cite

show abstract

Machine Learning Algorithms for Prediction and Characterization of Cohesive Zone Parameters for Mixed-Mode Fracture

Ramian,

Elhajjar

2024

J. Compos. Sci.

View full text Add to dashboard Cite

Fatigue and fracture prediction in composite materials using cohesive zone models depends on accurately characterizing the core and facesheet interface in advanced composite sandwich structures. This study investigates the use of machine learning algorithms to identify cohesive zone parameters used in the fracture analysis of advanced composite sandwich structures. Experimental results often yield non-unique solutions, complicating the determination of cohesive parameters. Numerical determination can be time-consuming due to fine mesh requirements near the crack tip. This research evaluates the performance of Support Vector Regression (SVR), Random Forest (RF), and Artificial Neural Network (ANN) machine learning methods. The study uses features extracted from load–displacement responses during the fracture of the Asymmetric Double-Cantilever Beam (ADCB) specimen. The inputs include the displacement at the maximum load (δ*), the maximum load (Pmax), the total area under the load–displacement curve (At), and the initial slope of the linear region of the load–displacement curve (m). There are two objectives in this research: the first is to investigate which method performs best in identifying the interfacial cohesive parameters between the honeycomb core and carbon-epoxy facesheets, while the second objective is to reduce the dimensionality of the dataset by reducing the number of input features. Reducing the number of inputs can simplify the models and potentially improve the performance and interpretability. The results show that the ANN method produced the best results, with a mean absolute percentage error (MAPE) of 0.9578% and an R-squared (R²) value of 0.7932. These values indicate a high level of accuracy in predicting the four cohesive zone parameters: maximum normal contact stress (σI), critical fracture energy for normal separation (GI), maximum equivalent tangential contact stress (σII), and critical fracture energy for tangential slip (GII).

show abstract

Machine learning algorithms for delaminations detection on composites panels by wave propagation signals analysis: Review, experiences and results

Cited by 2 publications

References 31 publications

Effects of Seawater on Mechanical Performance of Composite Sandwich Structures: A Machine Learning Framework

Effects of Seawater on Mechanical Performance of Composite Sandwich Structures: A Machine Learning Framework

Machine Learning Algorithms for Prediction and Characterization of Cohesive Zone Parameters for Mixed-Mode Fracture

Contact Info

Product

Resources

About