Proximity based automatic defect detection in quadratic frequency modulated thermal wave imaging

Abstract Automatic and reliable anomaly detection without human intervention is a challenging task in thermal wave imaging. For this purpose, various processing algorithms proposed earlier are outperforming one another to exhibit smaller and deeper anomalies. Machine learning-based defect detection approaches are attracting the research community due to their reliable performance on employing over the stimulated thermal response in active thermography. The present article explores the deployment of local outlier factor (LOF), one-class support vector machine (OCSVM), and isolation forest (IF) algorithms over an experimental carbon fiber reinforced polymer specimen with artificially drilled flat bottom holes of different sizes at different depths to verify the detection capability of these approaches in Quadratic frequency modulated thermal wave imaging even with noisy synthetic data. In addition, a quantitative study has been performed using various thermographic and machine learning based performance metrics.

[2]  Wai Lok Woo,et al.  Temporal and spatial deep learning network for infrared thermal defect detection , 2019, NDT & E International.

[3]  Junyan Liu,et al.  Reliability Assessment for Time-Slice Enhanced Bidirectional Thermal Wave Radar Thermography of Hybrid C/GFRP Defects , 2021, IEEE Transactions on Industrial Informatics.

[4]  Yang Wang,et al.  The Feature Recognition of CFRP Subsurface Defects Using Low-Energy Chirp-Pulsed Radar Thermography , 2020, IEEE Transactions on Industrial Informatics.

[5]  Guangyuan Li,et al.  Defect Depth Determination in Laser Infrared Thermography Based on LSTM-RNN , 2020, IEEE Access.

[6]  V. S. Ghali,et al.  Empirical mode decomposition approach for defect detection in non-stationary thermal wave imaging , 2016 .

[7]  Zbigniew Suszyński,et al.  Processing of thermographic sequence using Principal Component Analysis , 2015 .

[8]  Ravibabu Mulaveesala,et al.  Comparative Data Processing Approaches for Thermal Wave Imaging Techniques for Non-Destructive Testing , 2011 .

[9]  Xavier Maldague,et al.  Application of Deep Learning in Infrared Non-Destructive Testing , 2018 .

[10]  V. S. Ghali,et al.  Artificial neural networks based quantitative evaluation of subsurface anomalies in quadratic frequency modulated thermal wave imaging , 2019, Infrared Physics & Technology.

[11]  Mohammed A. Omar,et al.  Automatic defects detection in CFRP thermograms, using convolutional neural networks and transfer learning , 2019, Infrared Physics & Technology.

[12]  Ravibabu Mulaveesala,et al.  Quadratic Frequency Modulated Thermal Wave Imaging for Non-Destructive Testing , 2012 .

[13]  A. Sharma,et al.  Novel Analytical Approach for Estimation of Thermal Diffusivity and Effusivity for Detection of Osteoporosis , 2020, IEEE Sensors Journal.

[14]  Suneet Tuli,et al.  Defect detection by pulse compression in frequency modulated thermal wave imaging , 2005 .

[15]  S. Tuli,et al.  Theory of frequency modulated thermal wave imaging for nondestructive subsurface defect detection , 2006 .

[16]  Kaixin Liu,et al.  Generative Principal Component Thermography for Enhanced Defect Detection and Analysis , 2020, IEEE Transactions on Instrumentation and Measurement.

[17]  V. S. Ghali,et al.  Quantitative subsurface analysis using frequency modulated thermal wave imaging , 2018 .

[18]  X. Maldague,et al.  A Method of Defect Depth Estimation for Simulated Infrared Thermography Data with Deep Learning , 2020, Applied Sciences.

[19]  Xavier Maldague,et al.  A study of defect depth using neural networks in pulsed phase thermography: modelling, noise, experiments , 1998 .

[20]  Michael Ying Yang,et al.  Two-stream convolutional neural network for non-destructive subsurface defect detection via similarity comparison of lock-in thermography signals , 2020, NDT & E International.

[21]  V. S. Ghali,et al.  Chirp Z transform based enhanced frequency resolution for depth resolvable non stationary thermal wave imaging. , 2017, The Review of scientific instruments.

[23]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[24]  V. S. Ghali,et al.  Decision tree-based subsurface analysis using Barker coded thermal wave imaging , 2020 .

[25]  Hongmei Li,et al.  Bearing Fault Diagnosis with a Feature Fusion Method Based on an Ensemble Convolutional Neural Network and Deep Neural Network , 2019, Sensors.

[26]  Wontae Kim,et al.  Thermographic Inspection of Internal Defects in Steel Structures: Analysis of Signal Processing Techniques in Pulsed Thermography , 2020, Sensors.

[27]  Wontae Kim,et al.  Application of thermal wave imaging and phase shifting method for defect detection in Stainless steel , 2016 .

[28]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[29]  Ravibabu Mulaveesala,et al.  Barker coded thermal wave imaging for defect detection in carbon fibre-reinforced plastics , 2011 .