Transient Thermography for Flaw Detection in Friction Stir Welding: A Machine Learning Approach

A systematic computational method to simulate and detect subsurface flaws, through nondestructive transient thermography, in aluminum (AL) sheets and friction stir (FS) welded sheets is proposed in this article. The proposed method relies on feature extraction methods and a data-driven machine learning modeling structure. Here, we propose the use of a multilayer perceptron feed-forward neural network with feature extraction methods to improve the flaw-probing depth of transient thermography inspection. Furthermore, for the first time, we propose thermographic signal linear modelling (TSLM), a hyper-parameter-free feature extraction technique for transient thermography. The new feature extraction and modeling framework was tested with out-of-sample experimental transient thermography data, and results show effectiveness in subsurface flaw detection of up to 2.3 mm deep in AL sheets [99.8% true positive rate (TPR) and 92.1% true negative rate (TNR)] and up to 2.2  mm deep in FS welds (97.2% TPR and 87.8% TNR).

[1]  A. Smith,et al.  Defects in Friction Stir Welding of Steel , 2018, Metallography, Microstructure, and Analysis.

[2]  Takahide Sakagami,et al.  Applications of pulse heating thermography and lock-in thermography to quantitative nondestructive evaluations , 2002 .

[3]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[4]  C. Enăchescu,et al.  Approximation Capabilities of Neural Networks , 2008 .

[5]  Darryl P Almond,et al.  Long pulse excitation thermographic non-destructive evaluation , 2017 .

[6]  Tapan Kumar Pal,et al.  Evaluation of dissimilar friction stir lap joints using digital X-ray radiography , 2014 .

[7]  Shrestha Ranjit,et al.  Investigation of lock-in infrared thermography for evaluation of subsurface defects size and depth , 2015 .

[8]  Antonino Squillace,et al.  The use of infrared thermography for nondestructive evaluation of joints , 2004 .

[9]  Alice E. Smith,et al.  Bias and variance of validation methods for function approximation neural networks under conditions of sparse data , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[10]  Daniel L. Balageas,et al.  Common tools for quantitative pulse and step-heating thermography – part II: experimental investigation , 2015 .

[11]  Nik Rajic,et al.  Principal component thermography for flaw contrast enhancement and flaw depth characterisation in composite structures , 2002 .

[12]  Constantinos Soutis,et al.  Recent developments in advanced aircraft aluminium alloys , 2014 .

[13]  Caner Özdemii̇r.  Wiley Series in Microwave and Optical Engineering , 2012 .

[14]  Herbert Kaplan,et al.  Practical Applications of Infrared Thermal Sensing and Imaging Equipment , 1993 .

[15]  B. Li,et al.  The study on defects in aluminum 2219-T6 thick butt friction stir welds with the application of multiple non-destructive testing methods , 2011 .

[16]  Luis S. Rosado,et al.  Advanced technique for non-destructive testing of friction stir welding of metals , 2010 .

[17]  A. S. Sekhar,et al.  Non-destructive Evaluation of Friction Stir Welded Joints by X-ray Radiography and Infrared Thermography , 2014 .

[18]  C. Enkchescu,et al.  Approximation Capabilities of Neural Networks , 2008 .

[19]  Jue Hu,et al.  Pattern Deep Region Learning for Crack Detection in Thermography Diagnosis System , 2018, Metals.

[20]  Namgyu Kim,et al.  Deep learning–based autonomous concrete crack evaluation through hybrid image scanning , 2019, Structural Health Monitoring.

[21]  C. Maierhofer,et al.  Development of standards for flash thermography and lock-in thermography , 2014 .

[22]  Xavier Maldague,et al.  Advances in pulsed phase thermography , 2002 .

[23]  Adolfo Cobo,et al.  Signal to noise ratio (SNR) comparison for pulsed thermographic data processing methods applied to welding defect detection , 2010 .

[25]  W. P. Winfree,et al.  Neural Network Based Processing of Thermal NDE Data for Corrosion Detection , 1993 .

[26]  Jing Xie,et al.  Improving visibility of rear surface cracks during inductive thermography of metal plates using Autoencoder , 2018, Infrared Physics & Technology.

[27]  Nikolas Rajic,et al.  A comparison of image processing algorithms for thermal nondestructive evaluation , 2003, SPIE Defense + Commercial Sensing.

[28]  Ramsey F. Hamade,et al.  Nondestructive detection of defects in friction stir welded lap joints using computed tomography , 2019, Materials & Design.

[29]  Weiping Huang,et al.  Sizing Subsurface Defects in Metallic Plates by Square Pulse Thermography Using an Oriented Gradient Map , 2016 .

[30]  Giovanni Maria Carlomagno,et al.  REVIEW ARICLE: Recent advances in the use of infrared thermography , 2004 .

[31]  L. Dubourg,et al.  Non-destructive detection of lack of penetration defects in friction stir welds , 2012 .

[32]  Xavier Maldague,et al.  Infrared thermography processing based on higher-order statistics , 2010 .

[33]  Julio Molleda,et al.  Infrared Thermography for Temperature Measurement and Non-Destructive Testing , 2014, Sensors.

[34]  V. Badheka,et al.  Friction stir welding of aluminium alloys: An overview of experimental findings – Process, variables, development and applications , 2019 .

[35]  Francesco Ciampa,et al.  Recent Advances in Active Infrared Thermography for Non-Destructive Testing of Aerospace Components , 2018, Sensors.

[36]  G. R. Suresh,et al.  Automatic Diagnosis of Breast Cancer using Thermographic Color Analysis and SVM Classifier , 2016 .

[37]  R. Waugh.  Development of Infrared Techniques for Practical Defect Identification in Bonded Joints , 2015 .

[38]  P. Kah,et al.  Investigation of weld defects in friction-stir welding and fusion welding of aluminium alloys , 2015, International Journal of Mechanical and Materials Engineering.

[39]  S. Marinettia,et al.  Statistical analysis of IR thermographic sequences by PCA , 2003 .

[40]  Rene de Jesus Romero-Troncoso,et al.  Recent Industrial Applications of Infrared Thermography: A Review , 2019, IEEE Transactions on Industrial Informatics.

[41]  W. Swiderski,et al.  The Characterization of Defects in Multi-Layered Composite Materials by Thermal Tomography Methods , 2009 .

[42]  Matthias GOLDAMMER,et al.  Active Thermography for Dimensional Measurements on Gas Turbine Components , .