A thermographic data augmentation and signal separation method for defect detection

Defining the Thermal Features of Sub-Surface Reinforcing Fibres in Non-Polluting Thermo–Acoustic Insulating Panels: A Numerical–Thermographic–Segmentation Approach

Natural fibres present ozone-friendly solutions in the field of construction. The attenuation of the sound and heat losses is an important feature in such type of materials above all, when used in non-woven fabrics and fibre-reinforced composites. Hemp fibres show robust insulation performance; this research work should be considered beneficial to the development of a non-destructive thermographic methodology, which can address the thermal barrier (typically applied on multi-layer panel) effects. The intent is to assess the integrity of the sub-surface reinforcing glass fibres; such integrity state will help confer the rigidity and the resistance to mechanical stresses. The testing proposed in this study can be further developed in a laboratory right after the manufacturing process of similar type of components. The testing needs preliminary numerical simulations to help guide the selection of the appropriate pre- and post-processing algorithms combined with or without segmentation operators. A set of numerical and experimental tests were performed through controlled thermal stimulation while recording the thermal responses. The study also highlights the advantages, disadvantages, and future development of the presented technique and methodologies.

Enhanced Defect Detection in Carbon Fiber Reinforced Polymer Composites via Generative Kernel Principal Component Thermography

Increasing machine learning methods are being applied to infrared non-destructive assessment for internal defects assessment of composite materials. However, most of them extract only linear features, which is not in accord with the nonlinear characteristics of infrared data. Moreover, limited infrared images tend to restrict the data analysis capabilities of machine learning methods. In this work, a novel generative kernel principal component thermography (GKPCT) method is proposed for defect detection of carbon fiber reinforced polymer (CFRP) composites. Specifically, the spectral normalization generative adversarial network is proposed to augment the thermograms for model construction. Sequentially, the KPCT method is used by feature mapping of all thermogram data using kernel principal component analysis, which allows for differentiation of defects and background in the dimensionality-reduced data. Additionally, a defect-background separation metric is designed to help the performance evaluation of data analysis methods. Experimental results on CFRP demonstrate the feasibility and advantages of the proposed GKPCT method.

Spatial-Neighborhood Manifold Learning for Nondestructive Testing of Defects in Polymer Composites

Robust Soft Sensor with Deep Kernel Learning for Quality Prediction in Rubber Mixing Processes

Although several data-driven soft sensors are available, online reliable prediction of the Mooney viscosity in industrial rubber mixing processes is still a challenging task. A robust semi-supervised soft sensor, called ensemble deep correntropy kernel regression (EDCKR), is proposed. It integrates the ensemble strategy, deep brief network (DBN), and correntropy kernel regression (CKR) into a unified soft sensing framework. The multilevel DBN-based unsupervised learning stage extracts useful information from all secondary variables. Sequentially, a supervised CKR model is built to explore the relationship between the extracted features and the Mooney viscosity values. Without cumbersome preprocessing steps, the negative effects of outliers are reduced using the CKR-based robust nonlinear estimator. With the help of ensemble strategy, more reliable prediction results are further obtained. An industrial case validates the practicality and reliability of EDCKR.

Generative Independent Component Thermography for Improved Defect Detection of Carbon Fiber Composites

Generative Principal Component Thermography for Enhanced Defect Detection and Analysis

Domain adaptation transfer learning soft sensor for product quality prediction

Orthogonal Locality Preserving Projections Thermography for Subsurface Defect Detection

Independent component thermography for non-destructive testing of defects in polymer composites

Non-destructive defect evaluation of polymer composites via thermographic data analysis: A manifold learning method