Uhlig Sebastian, Alkhasli Ilkin, Schubert Frank, Tschöpe Constanze, Wolff Matthias
Fraunhofer Institute for Ceramic Technologies and Systems, IKTS, Dresden, Germany; Fraunhofer IKTS Cognitive Material Diagnostics Project Group, KogMat(D), Cottbus, Germany.
Fraunhofer Institute for Ceramic Technologies and Systems, IKTS, Dresden, Germany.
Ultrasonics. 2023 Sep;134:107041. doi: 10.1016/j.ultras.2023.107041. Epub 2023 May 18.
Ultrasonic Testing (UT) has seen increasing application of machine learning (ML) in recent years, promoting higher-level automation and decision-making in flaw detection and classification. Building a generalized training dataset to apply ML in non-destructive evaluation (NDE), and thus UT, is exceptionally difficult since data on pristine and representative flawed specimens are needed. Yet, in most UT test cases flawed specimen data is inherently rare making data coverage the leading problem when applying ML. Common data augmentation (DA) strategies offer limited solutions as they don't increase the dataset variance, which can lead to overfitting of the training data. The virtual defect method and the recent application of generative adversarial neural networks (GANs) in UT are sophisticated DA methods targeting to solve this problem. On the other hand, well-established research in modeling ultrasonic wave propagations allows for the generation of synthetic UT training data. In this context, we present a first thematic review to summarize the progress of the last decades on synthetic and augmented UT training data in NDE. Additionally, an overview of methods for synthetic UT data generation and augmentation is presented. Among numerical methods such as finite element, finite difference, and elastodynamic finite integration methods, semi-analytical methods such as general point source synthesis, superposition of Gaussian beams, and the pencil method as well as other UT modeling software are presented and discussed. Likewise, existing DA methods for one- and multidimensional UT data, feature space augmentation, and GANs for augmentation are presented and discussed. The paper closes with an in-detail discussion of the advantages and limitations of existing methods for both synthetic UT training data generation and DA of UT data to aid the decision-making of the reader for the application to specific test cases.
近年来，超声波检测（UT）领域对机器学习（ML）的应用不断增加，推动了缺陷检测和分类方面更高水平的自动化和决策制定。由于需要原始且具有代表性的缺陷样本数据，构建用于在无损检测（NDE）中应用ML的通用训练数据集，进而应用于UT，异常困难。然而，在大多数UT测试案例中，有缺陷的样本数据本身就很稀少，这使得数据覆盖成为应用ML时的首要问题。常见的数据增强（DA）策略提供的解决方案有限，因为它们不会增加数据集的方差，这可能导致训练数据的过拟合。虚拟缺陷方法以及生成对抗神经网络（GAN）最近在UT中的应用是旨在解决此问题的复杂DA方法。另一方面，在超声波传播建模方面已有的成熟研究使得合成UT训练数据的生成成为可能。在此背景下，我们进行了首次专题综述，以总结过去几十年在NDE中合成和增强UT训练数据方面取得的进展。此外，还概述了合成UT数据生成和增强的方法。在诸如有限元、有限差分和弹性动力学有限积分方法等数值方法中，介绍并讨论了诸如通用点源合成、高斯光束叠加和铅笔法等半解析方法以及其他UT建模软件。同样，介绍并讨论了用于一维和多维UT数据的现有DA方法、特征空间增强以及用于增强的GAN。本文最后详细讨论了现有方法在合成UT训练数据生成和UT数据DA方面的优缺点，以帮助读者在将其应用于特定测试案例时做出决策。
