Unsupervised Machine Learning for Ultrasonic Flaw Detection using Gaussian Mixture Modeling, K-Means Clustering and Mean Shift Clustering

• Published in: IEEE International Ultrasonics Symposium (Online) pp. 647 - 649
• Main Authors: Virupakshappa, Kushal, Oruklu, Erdal
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2019
• Subjects: Acoustics; Clustering algorithms; Discrete Wavelet Transform(DWT); Gaussian Mixture Modeling (GMM) and Mean Shift Clustering; K-means Clustering; Machine learning; Machine learning algorithms; Software algorithms; Training; Unified modeling language
• ISSN: 1948-5727
• DOI: 10.1109/ULTSYM.2019.8926078

Supervised Machine Learning (ML) algorithms such as Neural Networks, Support Vector Machines and Logistic Regression have been successfully utilized in Ultrasonic Non-Destructive Evaluation (NDE) applications. In supervised learning algorithms, data outputs are labeled and classified for training. In contrast, Unsupervised Machine Learning (UML) algorithms identify and exploit the commonalities in the data and no "ground truth" is necessary. In this work, we use three different UML algorithms based on K-means clustering, Gaussian Mixture Modeling and Mean Shift Clustering in order to detect and locate flaw echoes in ultrasonic A-Scan data. All three algorithms have been shown to perform flaw classification successfully. In particular, Gaussian Mixture Modeling achieves highest detection accuracy at 93%.