Robust Principal Component Thermography for Defect Detection in Composites

Abstract

Pulsed Thermography (PT) data are usually affected by noise and as such most of the research effort in the last few years has been directed towards the development of advanced signal processing methods to improve defect detection. Among the numerous techniques that have been proposed, principal component thermography (PCT)—based on principal component analysis (PCA)—is one of the most effective in terms of defect contrast enhancement and data compression. However, it is well-known that PCA can be significantly affected in the presence of corrupted data (e.g., noise and outliers). Robust PCA (RPCA) has been recently proposed as an alternative statistical method that handles noisy data more properly by decomposing the input data into a low-rank matrix and a sparse matrix. We propose to process PT data by RPCA instead of PCA in order to improve defect detectability. The performance of the resulting approach, Robust Principal Component Thermography (RPCT)—based on RPCA, was evaluated with respect to PCT—based on PCA, using a CFRP sample containing artificially produced defects. We compared results quantitatively based on two metrics, Contrast-to-Noise Ratio (CNR), for defect detection capabilities, and the Jaccard similarity coefficient, for defect segmentation potential. CNR results were on average 40% higher for RPCT than for PCT, and the Jaccard index was slightly higher for RPCT (0.7395) than for PCT (0.7010). In terms of computational time, however, PCT was 11.5 times faster than RPCT. Further investigations are needed to assess RPCT performance on a wider range of materials and to optimize computational time.

Data Enhancement via Low-Rank Matrix Reconstruction in Pulsed Thermography for Carbon-Fibre-Reinforced Polymers

“…Furthermore, the PCA is a linear decomposition function that is sensitive to over-illumination and non-uniform heating more than other types of noise. In our previous research, we proved that Robust PCT [10] can improve the detectability of deeper defects in composites. Moreover, the PLST is sensitive to gradient.…”

“…They successfully overcame the difficulties arising from real data and built an automatic online monitoring system for anomaly detection. Ebrahimi et al [10] proposed the orthogonal inexact augmented lagrange multiplier (OIALM). This study demonstrates its efficiency for defect enhancement capabilities over mixed and various types of defects typically addressed in IRT in composite materials.…”

“…They evaluated the quality of the image after the combination of pre-processing with pulsed phase thermography (PPT) [9] or PCT and found that pre-processing improved some results. Ebrahimi et al [10] showed that the low-rank matrix computed by RPCA-PCP via Inexact ALM when used with PT data does not provide optimal results; nonetheless, this method has not been investigated as a pre-processing method nor as a post-processing method. Several state-of-the-art IRNDT methods, i.e., PPT, PCT and Partial Least Square Thermography (PLST) [11,12], have been chosen to evaluate the approaches.…”

Multiscale Analysis of Solar Loading Thermographic Signals for Wall Structure Inspection

“…To list some examples, candid covariance-free incremental PCT [17] improves the calculate on of the conventional PCT, sparse PCT [18,19] better separates different types of information by introducing sparsity constraints into the loadings, sparse moving window PCT [20] pays more attention to the time-wise correlations by using the moving window technique, and generative PCT [21] adopts the state-of-the-art generative adversarial network, which is a branch of deep learning, to achieve image augmentation and enhance the detection performance of PCT. Other extensions of PCT include robust PCT [22], etc. In [2], PCT was used to analyze the thermal data collected in the experiment of solar loading thermography.…”