G. T. Vesala, V. S. Ghali, Y. Naga Prasanthi, B. Suresh
{"title":"Parametric Study of Anomaly Detection Models for Defect Detection in Infrared Thermography","authors":"G. T. Vesala, V. S. Ghali, Y. Naga Prasanthi, B. Suresh","doi":"10.1134/S1061830923600600","DOIUrl":null,"url":null,"abstract":"<p>In the current NDT 4.0 revolution, machine learning and artificial intelligence have emerged as the major enablers for non-destructive testing and evaluation (NDT&E) of industrial components. However, recent developments in active thermal NDT (TNDT) support its use as a practical method for checking a range of industrial components. Additionally, recent post-processing research in TNDT has developed several machine learning models to replace human interaction and offer automatic defect detection. However, the smaller area of the flaws and their related few thermal profiles than the wide sound area, leading to imbalanced datasets, make it difficult to train a supervised deep neural. Recently added to TNDT are anomaly detection models and one-class classifiers, both of which are commonly applied machine learning models to real-world issues. The accuracy and other important metrics in autonomous defect detection are influenced by the hyper-parameters of these models, such as contamination factor, volume of training data, and initialization parameter of the relevant model. The current paper investigates how initialization parameters affect these models' TNDT capabilities for automated flaw detection. Using quadratic frequency modulated thermal wave imaging (QFMTWI), a carbon fiber-reinforced polymer specimen with variously sized artificially produced back-holes at different depths is examined. A good hyper-parameter for automatic flaw identification is chosen after qualitatively comparing testing accuracy, precision, recall, F-score, and probability.</p>","PeriodicalId":764,"journal":{"name":"Russian Journal of Nondestructive Testing","volume":"59 12","pages":"1259 - 1271"},"PeriodicalIF":0.9000,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Russian Journal of Nondestructive Testing","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1134/S1061830923600600","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MATERIALS SCIENCE, CHARACTERIZATION & TESTING","Score":null,"Total":0}
引用次数: 0
Abstract
In the current NDT 4.0 revolution, machine learning and artificial intelligence have emerged as the major enablers for non-destructive testing and evaluation (NDT&E) of industrial components. However, recent developments in active thermal NDT (TNDT) support its use as a practical method for checking a range of industrial components. Additionally, recent post-processing research in TNDT has developed several machine learning models to replace human interaction and offer automatic defect detection. However, the smaller area of the flaws and their related few thermal profiles than the wide sound area, leading to imbalanced datasets, make it difficult to train a supervised deep neural. Recently added to TNDT are anomaly detection models and one-class classifiers, both of which are commonly applied machine learning models to real-world issues. The accuracy and other important metrics in autonomous defect detection are influenced by the hyper-parameters of these models, such as contamination factor, volume of training data, and initialization parameter of the relevant model. The current paper investigates how initialization parameters affect these models' TNDT capabilities for automated flaw detection. Using quadratic frequency modulated thermal wave imaging (QFMTWI), a carbon fiber-reinforced polymer specimen with variously sized artificially produced back-holes at different depths is examined. A good hyper-parameter for automatic flaw identification is chosen after qualitatively comparing testing accuracy, precision, recall, F-score, and probability.
期刊介绍:
Russian Journal of Nondestructive Testing, a translation of Defectoskopiya, is a publication of the Russian Academy of Sciences. This publication offers current Russian research on the theory and technology of nondestructive testing of materials and components. It describes laboratory and industrial investigations of devices and instrumentation and provides reviews of new equipment developed for series manufacture. Articles cover all physical methods of nondestructive testing, including magnetic and electrical; ultrasonic; X-ray and Y-ray; capillary; liquid (color luminescence), and radio (for materials of low conductivity).