PHASED ARRAY TESTING DATA GENERATION THROUGH GENERATIVE ADVERSARIAL NETWORKS AND ADAPTIVE DISCRIMINATOR AUGMENTATION

PHASED ARRAY TESTING DATA GENERATION THROUGH GENERATIVE ADVERSARIAL NETWORKS AND ADAPTIVE DISCRIMINATOR AUGMENTATION

Alves, Misael Pedro Conceição; Purificação, Carlos Alberto Campos da; Franklin, Taniel Silva

Full Article:

"Non-destructive testing is used to detect faults and verify structuralproperties. Its main advantage is that it does not alter material properties. Currently,this testing and evaluation process is done manually. Using classification and featuredetection algorithms is a possibility to evaluate data obtained by sensors faster andmore efficiently. However, the lack of data volume to train and evaluate with safetymodels is one of the barriers to employing such methods. This work proposes usinggenerative adversarial neural networks to generate synthetic images of nondestructive tests obtained by ultrasonic sensors to improve the performance ofclassification models and assist the learning process. "

"Non-destructive testing is used to detect faults and verify structuralproperties. Its main advantage is that it does not alter material properties. Currently,this testing and evaluation process is done manually. Using classification and featuredetection algorithms is a possibility to evaluate data obtained by sensors faster andmore efficiently. However, the lack of data volume to train and evaluate with safetymodels is one of the barriers to employing such methods. This work proposes usinggenerative adversarial neural networks to generate synthetic images of nondestructive tests obtained by ultrasonic sensors to improve the performance ofclassification models and assist the learning process. "

Palavras-chave: - -

DOI: 10.5151/siintec2024-393284

Referências bibliográficas

• [1] "1VIRKKUNEN, I. et al. Augmented Ultrasonic Data for Machine Learning. 2019.
• [2] Available at: <https://arxiv.org/abs/1903.11399> Accessed on: 02 Feb. 2024.
• [3] 2KARRAS, T. et al. Training Generative Adversarial Networks with Limited Data.
• [4] 2020. Available at: <https://arxiv.org/abs/2006.06676> Accessed on: 11 Mar. 2024.
• [5] 3BETZALEL, E. et al. A Study on the Evaluation of Generative Models. 2022.
• [6] Available at: <https://arxiv.org/abs/2206.10935> Accessed on: 15 Mar. 2024.
• [7] 4GOODFELLOW, I. J. et al. Generative Adversarial Networks. 2014. Available at
• [8] <https://arxiv.org/abs/1406.2661> Accessed on: 25 Jan. 2024."

Como citar:

Alves, Misael Pedro Conceição; Purificação, Carlos Alberto Campos da; Franklin, Taniel Silva; "PHASED ARRAY TESTING DATA GENERATION THROUGH GENERATIVE ADVERSARIAL NETWORKS AND ADAPTIVE DISCRIMINATOR AUGMENTATION", p-1219-1226. In: . São Paulo: Blucher, 2024.
ISSN 23577592, DOI 10.5151/siintec2024-393284