Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling
The paper describes the implementation of 3D numerical simulation in machine learning models used in infrared thermographic nondestructive testing. The enhancement of generalizability of such models emerges as a decisive factor for producing trust-worthy test results. First, it is demonstrated tha...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gruppo Italiano Frattura
2024-08-01
|
| Series: | Fracture and Structural Integrity |
| Subjects: | |
| Online Access: | https://www.fracturae.com/index.php/fis/article/view/5022 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841564493035864064 |
|---|---|
| author | Vladimir Vavilov Arsenii Chulkov Alexey Moskovchenko |
| author_facet | Vladimir Vavilov Arsenii Chulkov Alexey Moskovchenko |
| author_sort | Vladimir Vavilov |
| collection | DOAJ |
| description |
The paper describes the implementation of 3D numerical simulation in machine learning models used in infrared thermographic nondestructive testing. The enhancement of generalizability of such models emerges as a decisive factor for producing trust-worthy test results. First, it is demonstrated that the models trained on datasets with fixed parameters yield limited defect detection capabilities. The concept of training datasets, which include subtle variations in material thickness, thermal conductivity, as well as various combinations of material density and heat capacity, provides the best learning results and a noticeable ability to identify defects in all test datasets. Second, the model robustness in respect to noise is explored to demonstrate its ability to withstand additive and multiplicative random noise. Third, potentials of some known techniques of thermographic data processing, such as Thermographic Signal Reconstruction, Fast Fourier Transform and Temperature Contrast, are examined. In particular, the use of the Temperature Contrast data ensured sensitivity (True Positive Rate) better than 98% across all test datasets.
|
| format | Article |
| id | doaj-art-cae62bebbc4c4decbf612f50b64cfee0 |
| institution | Kabale University |
| issn | 1971-8993 |
| language | English |
| publishDate | 2024-08-01 |
| publisher | Gruppo Italiano Frattura |
| record_format | Article |
| series | Fracture and Structural Integrity |
| spelling | doaj-art-cae62bebbc4c4decbf612f50b64cfee02025-01-02T22:40:30ZengGruppo Italiano FratturaFracture and Structural Integrity1971-89932024-08-01187010.3221/IGF-ESIS.70.10Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical ModelingVladimir Vavilov0Arsenii Chulkov1Alexey Moskovchenko2https://orcid.org/0000-0002-2813-2529Tomsk Polytechnic University, RussiaTomsk Polytechnic University, RussiaUniversity of West Bohemia, Czech Republic The paper describes the implementation of 3D numerical simulation in machine learning models used in infrared thermographic nondestructive testing. The enhancement of generalizability of such models emerges as a decisive factor for producing trust-worthy test results. First, it is demonstrated that the models trained on datasets with fixed parameters yield limited defect detection capabilities. The concept of training datasets, which include subtle variations in material thickness, thermal conductivity, as well as various combinations of material density and heat capacity, provides the best learning results and a noticeable ability to identify defects in all test datasets. Second, the model robustness in respect to noise is explored to demonstrate its ability to withstand additive and multiplicative random noise. Third, potentials of some known techniques of thermographic data processing, such as Thermographic Signal Reconstruction, Fast Fourier Transform and Temperature Contrast, are examined. In particular, the use of the Temperature Contrast data ensured sensitivity (True Positive Rate) better than 98% across all test datasets. https://www.fracturae.com/index.php/fis/article/view/5022Infrared ThermographyNondestructive testingMachine LearningNumerical SimulationDefect Detection |
| spellingShingle | Vladimir Vavilov Arsenii Chulkov Alexey Moskovchenko Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling Fracture and Structural Integrity Infrared Thermography Nondestructive testing Machine Learning Numerical Simulation Defect Detection |
| title | Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling |
| title_full | Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling |
| title_fullStr | Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling |
| title_full_unstemmed | Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling |
| title_short | Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling |
| title_sort | enhancing generalizability of a machine learning model for infrared thermographic defect detection by using 3d numerical modeling |
| topic | Infrared Thermography Nondestructive testing Machine Learning Numerical Simulation Defect Detection |
| url | https://www.fracturae.com/index.php/fis/article/view/5022 |
| work_keys_str_mv | AT vladimirvavilov enhancinggeneralizabilityofamachinelearningmodelforinfraredthermographicdefectdetectionbyusing3dnumericalmodeling AT arseniichulkov enhancinggeneralizabilityofamachinelearningmodelforinfraredthermographicdefectdetectionbyusing3dnumericalmodeling AT alexeymoskovchenko enhancinggeneralizabilityofamachinelearningmodelforinfraredthermographicdefectdetectionbyusing3dnumericalmodeling |