A comparative Study of Low-Rank-plus-Sparse Matrix Decomposition and Machine Learning for Non-Destructive Air-Ultrasound Defect Detection

Manar Al-Askary, Udaya Sampath K. Perera Miriya Thanthrige, Pierre Pfeffer, Luis Wachter, Giovanni Schober, Aydin Sezgin

Abstract: Defect detection plays an important role in product quality assurance in many industrial applications. Air-coupled ultrasound defect detection setups have the advantage that they are non-destructive and do not contaminate the investigated materials. However, this approach comes with some challenges due to the weak signaling response of the defects. Thus, sophisticated signal separation methods are required. To address this challenge, low-rank-plus-sparse recovery (LRPSR) is proposed and compared with state-of-the-art machine learning (ML) methods. The results obtained show that the LRPSR method achieves comparable results in terms of detection rate to those achieved by ML. Yet, for a small training data set, the LRPSR approach outperforms the ML algorithms. The small training data set is important for detecting defects of different production lines without having a time-consuming training process. In addition, a lower standard deviation of the detection rate of the LRPSR method is observed, which shows its suitability for real-time processing.