GANs and alternative methods of synthetic noise generation for domain adaption of defect classification of Non-destructive ultrasonic testing

TL;DR

This paper explores synthetic noise generation methods, including GAN-based and semi-analytical approaches, to improve defect classification in ultrasonic testing with limited training data, achieving significant performance gains.

Contribution

It introduces four novel synthetic data generation methods leveraging GANs and semi-analytical simulations for better domain adaptation in ultrasonic defect classification.

Findings

Significant improvement in classification F1 scores using synthetic data.

GAN-based method with task-specific modifications achieved the highest F1 score of 0.843.

Fully simulated noise data alone yielded lower performance, highlighting the importance of hybrid approaches.

Abstract

This work provides a solution to the challenge of small amounts of training data in Non-Destructive Ultrasonic Testing for composite components. It was demonstrated that direct simulation alone is ineffective at producing training data that was representative of the experimental domain due to poor noise reconstruction. Therefore, four unique synthetic data generation methods were proposed which use semi-analytical simulated data as a foundation. Each method was evaluated on its classification performance of real experimental images when trained on a Convolutional Neural Network which underwent hyperparameter optimization using a genetic algorithm. The first method introduced task specific modifications to CycleGAN, to learn the mapping from physics-based simulations of defect indications to experimental indications in resulting ultrasound images. The second method was based on combining real experimental defect free images with simulated defect responses. The final two methods fully simulated the noise responses at an image and signal level respectively. The purely simulated data produced a mean classification F1 score of 0.394. However, when trained on the new synthetic datasets, a significant improvement in classification performance on experimental data was realized, with mean classification F1 scores of 0.843, 0.688, 0.629, and 0.738 for the respective approaches.