Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling; Fracture and Structural Integrity; Vol. 18, iss. 70

Detalles Bibliográficos
Parent link:Fracture and Structural Integrity.— .— Cassino: Italian Group of Fracture
Vol. 18, iss. 70.— 2024.— P. 177-191
Autor principal: Chulkov A. O. Arseniy Olegovich
Autor Corporativo: National Research Tomsk Polytechnic University (570)
Otros Autores: Moskovchenko A. I. Aleksey Igorevich, Vavilov V. P. Vladimir Platonovich
Sumario:Title screen
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.
Текстовый файл
Lenguaje:inglés
Publicado: 2024
Materias:
Acceso en línea:https://doi.org/10.3221/IGF-ESIS.70.10
Formato: Electrónico Capítulo de libro
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=675030

MARC

LEADER 00000naa0a2200000 4500
001 675030
005 20240930110353.0
090 |a 675030 
100 |a 20240930d2024 k||y0rusy50 ba 
101 0 |a eng 
102 |a IT 
135 |a drcn ---uucaa 
181 0 |a i   |b  e  
182 0 |a b 
183 0 |a cr  |2 RDAcarrier 
200 1 |a Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling  |f Arsenii Chulkov, Alexey Moskovchenko, Vladimir Vavilov 
203 |a Текст  |b визуальный  |c электронный 
283 |a online_resource  |2 RDAcarrier 
300 |a Title screen 
320 |a References: 34 tit. 
330 |a 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. 
336 |a Текстовый файл 
461 1 |t Fracture and Structural Integrity  |n Italian Group of Fracture  |c Cassino 
463 1 |t Vol. 18, iss. 70  |v P. 177-191  |d 2024 
610 1 |a Infrared thermography 
610 1 |a Nondestructive Testing 
610 1 |a Machine learning 
610 1 |a Numerical simulation 
610 1 |a Defect detection 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
700 1 |a Chulkov  |b A. O.  |c specialist in the field of non-destructive testing  |c Deputy Director for Scientific and Educational Activities; acting manager; Senior Researcher, Tomsk Polytechnic University, Candidate of Technical Sciences  |f 1989-  |g Arseniy Olegovich  |9 16220 
701 1 |a Moskovchenko  |b A. I.  |g Aleksey Igorevich 
701 1 |a Vavilov  |b V. P.  |c Specialist in the field of dosimetry and methodology of nondestructive testing (NDT)  |c Doctor of technical sciences (DSc), Professor of Tomsk Polytechnic University (TPU)  |f 1949-  |g Vladimir Platonovich  |9 16163 
712 0 2 |a National Research Tomsk Polytechnic University  |c (2009- )  |9 27197  |4 570 
801 0 |a RU  |b 63413507  |c 20240930 
850 |a 63413507 
856 4 |u https://doi.org/10.3221/IGF-ESIS.70.10  |z https://doi.org/10.3221/IGF-ESIS.70.10 
942 |c CR