Augmented Ultrasonic Data for Machine Learning
Augmented Ultrasonic Data for Machine Learning
复制标题
DOI：
10.1007/s10921-020-00739-5
复制
发表时间：
2021-03-01
影响因子：
2.8
通讯作者：
Rinta-aho, Jari
中科院分区：
文献类型：
--
作者：
Virkkunen, Iikka;Koskinen, Tuomas;Rinta-aho, Jari
到目前为止，无损检测中的缺陷检测，特别是像超声波数据这样的复杂信号，严重依赖训练有素的人类检查员的专业知识和判断力。虽然自动化系统已经使用了很长一段时间，但这些系统大多仅限于使用简单的决策自动化，如信号幅度阈值。各种机器学习算法的最新进展解决了许多类似的困难分类问题，这些问题以前被认为是棘手的。在无损检测方面，开放文献中已经报道了令人鼓舞的结果，但机器学习在无损检测领域的应用仍然非常有限。阻碍它们使用的关键问题是可用于培训的有代表性的有缺陷的数据集有限。在本文中，我们开发了现代的深卷积网络来检测相控阵超声数据中的缺陷。我们广泛使用数据增强来增强最初有限的原始数据，并帮助学习。数据增强利用了虚拟缺陷--这项技术已经成功地用于培训人类视察员，并很快将用于核检查资格。机器学习分类器的结果与人类的表现进行了比较。我们表明，使用复杂的数据增强，现代深度学习网络可以被训练成达到人类水平的性能。
Flaw detection in non-destructive testing, especially for complex signals like ultrasonic data, has thus far relied heavily on the expertise and judgement of trained human inspectors. While automated systems have been used for a long time, these have mostly been limited to using simple decision automation, such as signal amplitude threshold. The recent advances in various machine learning algorithms have solved many similarly difficult classification problems, that have previously been considered intractable. For non-destructive testing, encouraging results have already been reported in the open literature, but the use of machine learning is still very limited in NDT applications in the field. Key issue hindering their use, is the limited availability of representative flawed data-sets to be used for training. In the present paper, we develop modern, deep convolutional network to detect flaws from phased-array ultrasonic data. We make extensive use of data augmentation to enhance the initially limited raw data and to aid learning. The data augmentation utilizes virtual flaws-a technique, that has successfully been used in training human inspectors and is soon to be used in nuclear inspection qualification. The results from the machine learning classifier are compared to human performance. We show, that using sophisticated data augmentation, modern deep learning networks can be trained to achieve human-level performance.