Kriging and dimension reduction techniques for delamination detection in composites using electrical resistance tomography

Díaz-Montiel, Paulina; Escalona-Galvis, Luis Waldo; Venkataraman, Satchi

doi:10.1080/0305215x.2021.1980786

Cited by 3 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Te main contribution of this work is that it explores the integration of the ERT NDE method with several well-known machine learning algorithms to identify, classify, and characterize delamination and matrix cracking damage in composites. Te obtained accuracy of the proposed ML algorithms to detect and classify these independent damage modes was up to 95%, outperforming previous similar studies in which Kriging surrogate models were implemented [35]. To the best of our knowledge, no other article in the literature has reported a similar evaluation before.…”

Section: Introductionsupporting

confidence: 48%

“…Matrix cracking damage afects mainly the resistivity ρ 2 and ρ 3 of the laminate. After undergoing damage, the homogenized efective resistivity ρ * 2 of the laminate can be expressed as follows [35]:…”

Section: Electrical Resistance Tomography For Structural Health Monit...mentioning

confidence: 99%

“…A schematic of the 2D FE model of the composite laminate can be observed in Figure 2. Te reader is referred to Diaz-Montiel et al [35] for more information on the details of the FE modeling.…”

Section: Application Of Machine Learning Techniques For Damage Classi...mentioning

confidence: 99%

“…For resistance responses and descriptor vector predictions, we utilized the following metrics to evaluate and compare the proposed ML models with the Kriging method [35,55]. Te maximum relative error (maxRE) and the maximum root-mean-square error (maxRMSE) metrics are described in equations ( 17) and ( 18), respectively, as follows:…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…However, accurate representation of the internal damage state of a composite laminate also requires quantifcation of the matrix cracking damage mode, as these cracks reduce the transverse and shear strength of composites, leading to interlaminar failure [34]. Diaz-Montiel et al [35] used a surrogate-based optimization approach for assessing the damage state of composites with both delamination and transverse matrix cracking using Kriging surrogates. Tese metamodeling techniques successfully characterized delamination cracks in the presence of matrix cracking, but they could not accurately describe the homogenized efect of the matrix cracking density on the electrical variations measured at the surface electrodes.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Classification and Characterization of Damage in Composite Laminates Using Electrical Resistance Tomography and Supervised Machine Learning

Diaz-Escobar

Díaz-Montiel

Venkataraman

et al. 2023

Structural Control and Health Monitoring

Self Cite

View full text Add to dashboard Cite

Electrical resistance tomography (ERT) is a nondestructive evaluation technique that uses the internal conductivity variations of materials to assess structural integrity. Due to the low instrumentation required, the widespread use of ERT in the aerospace industry for monitoring the accumulation of damage in aircraft components can lead to significant reductions in inspections and maintenance costs. However, implementing the ERT method for mapping the damage state of structural components made of carbon fiber reinforced polymeric (CFRP) composites is challenging due to the inability of this method to distinguish between damage modes such as delamination and matrix cracking. This article explores the combined use of ERT and machine learning algorithms such as neural networks, random forests, k-nearest neighbors, and support vector machines to classify and characterize delamination and matrix cracking damage in CFRP laminates. Results show that the proposed classification algorithms can successfully estimate the damage severity of delaminated composites in the presence of matrix cracking. Similarly, the classification algorithms can characterize these independent damage modes with an accuracy of 95%. The algorithms showed robustness to predict the electrical resistance variations of damaged composites and characterize delamination and matrix cracking damage even when intrinsic noise was considered. Although neural networks characterized damage with the highest accuracy, these algorithms were also the most sensitive to noise. For applications where instrumentation noise cannot be completely removed from the ERT signals, the use of nearest neighbors is thus recommended.

show abstract

Section: Introductionsupporting

confidence: 48%

Section: Electrical Resistance Tomography For Structural Health Monit...mentioning

confidence: 99%

Section: Application Of Machine Learning Techniques For Damage Classi...mentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Classification and Characterization of Damage in Composite Laminates Using Electrical Resistance Tomography and Supervised Machine Learning

Diaz-Escobar

Díaz-Montiel

Venkataraman

et al. 2023

Structural Control and Health Monitoring

Self Cite

View full text Add to dashboard Cite

show abstract

Damage detection in non-planar carbon fiber-reinforced polymer laminates via electrical impedance tomography with surface-mounted electrodes and directional sensitivity matrices

Sannamani

Gao

Chen

et al. 2022

Composites Science and Technology

View full text Add to dashboard Cite

A new framework for predicting tensile stress of natural rubber based on data augmentation and molecular dynamics simulation data

Hu,

Liu,

Chen

et al. 2024

J Mater Inf

View full text Add to dashboard Cite

This study addresses the challenge of predicting the tensile stress of natural rubber with limited molecular dynamics simulation data, which is a crucial mechanical property for this material. Molecular dynamics (MD) simulations are limited by their scale and computational cost, making it difficult to obtain sufficient data to train machine learning algorithms. To overcome this limitation, we propose a machine learning framework involving three stages: (1) utilizing a Variational Autoencoder (VAE) to rapidly expand the data diversity; (2) employing Ordinary Kriging (OK) to label the VAE-generated virtual samples; and (3) training gradient enhanced regression [Gradient Boosting Regression (GBR)] models by using relevant data on tensile stress in natural rubber. The results demonstrate that the generated data exhibits enhanced rationality, significantly improving the accuracy and reliability of various regression models. This approach provides an effective solution to the problem of data scarcity in MD simulations.

show abstract

Kriging and dimension reduction techniques for delamination detection in composites using electrical resistance tomography

Cited by 3 publications

References 30 publications

Classification and Characterization of Damage in Composite Laminates Using Electrical Resistance Tomography and Supervised Machine Learning

Classification and Characterization of Damage in Composite Laminates Using Electrical Resistance Tomography and Supervised Machine Learning

Damage detection in non-planar carbon fiber-reinforced polymer laminates via electrical impedance tomography with surface-mounted electrodes and directional sensitivity matrices

A new framework for predicting tensile stress of natural rubber based on data augmentation and molecular dynamics simulation data

Contact Info

Product

Resources

About