Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect Detection
Infrared thermography is a non-destructive testing method used to detect defects in materials and structures. Machine learning algorithms have been applied to thermographic data to automate the defect detection process. Data preparation and feature extraction are crucial factors affecting ML model r...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Engineering Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4591/51/1/5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850261053100785664 |
|---|---|
| author | Alexey Moskovchenko Michal Svantner |
| author_facet | Alexey Moskovchenko Michal Svantner |
| author_sort | Alexey Moskovchenko |
| collection | DOAJ |
| description | Infrared thermography is a non-destructive testing method used to detect defects in materials and structures. Machine learning algorithms have been applied to thermographic data to automate the defect detection process. Data preparation and feature extraction are crucial factors affecting ML model results, especially in thermographic data analysis. This study focuses on automating the detection of impact damage in carbon fiber-reinforced polymer materials using flash-pulse thermography and ML algorithms. Various machine learning models and data pre-processing techniques were evaluated for their effectiveness in detecting and locating impact damage. The results demonstrated that the combination of the K-nearest neighbors model with the differential absolute contrast data processing method achieved the highest balanced accuracy. Other combinations, such as Gaussian support vector machine model with raw data and K-nearest neighbor with thermographic signal reconstruction derivative data, also exhibited promising performances. |
| format | Article |
| id | doaj-art-3af3fceb0cd2452589d96836e182afb4 |
| institution | OA Journals |
| issn | 2673-4591 |
| language | English |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Engineering Proceedings |
| spelling | doaj-art-3af3fceb0cd2452589d96836e182afb42025-08-20T01:55:31ZengMDPI AGEngineering Proceedings2673-45912023-10-01511510.3390/engproc2023051005Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect DetectionAlexey Moskovchenko0Michal Svantner1New Technologies—Research Centre, University of West Bohemia, 301 00 Pilsen, Czech RepublicNew Technologies—Research Centre, University of West Bohemia, 301 00 Pilsen, Czech RepublicInfrared thermography is a non-destructive testing method used to detect defects in materials and structures. Machine learning algorithms have been applied to thermographic data to automate the defect detection process. Data preparation and feature extraction are crucial factors affecting ML model results, especially in thermographic data analysis. This study focuses on automating the detection of impact damage in carbon fiber-reinforced polymer materials using flash-pulse thermography and ML algorithms. Various machine learning models and data pre-processing techniques were evaluated for their effectiveness in detecting and locating impact damage. The results demonstrated that the combination of the K-nearest neighbors model with the differential absolute contrast data processing method achieved the highest balanced accuracy. Other combinations, such as Gaussian support vector machine model with raw data and K-nearest neighbor with thermographic signal reconstruction derivative data, also exhibited promising performances.https://www.mdpi.com/2673-4591/51/1/5thermographyinfraredmachine learningthermographic data processingimpact damagecomposite |
| spellingShingle | Alexey Moskovchenko Michal Svantner Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect Detection Engineering Proceedings thermography infrared machine learning thermographic data processing impact damage composite |
| title | Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect Detection |
| title_full | Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect Detection |
| title_fullStr | Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect Detection |
| title_full_unstemmed | Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect Detection |
| title_short | Thermographic Data Processing and Feature Extraction Approaches for Machine Learning-Based Defect Detection |
| title_sort | thermographic data processing and feature extraction approaches for machine learning based defect detection |
| topic | thermography infrared machine learning thermographic data processing impact damage composite |
| url | https://www.mdpi.com/2673-4591/51/1/5 |
| work_keys_str_mv | AT alexeymoskovchenko thermographicdataprocessingandfeatureextractionapproachesformachinelearningbaseddefectdetection AT michalsvantner thermographicdataprocessingandfeatureextractionapproachesformachinelearningbaseddefectdetection |