Auto-diagnosis of time-of-flight for ultrasonic signal based on defect peaks tracking model

Yang, F., Shi, D., Lo, L.-Y., Mao, Q., Zhang, J. and Lam, K.-H. (2023) Auto-diagnosis of time-of-flight for ultrasonic signal based on defect peaks tracking model. Remote Sensing, 15(3), 599. (doi: 10.3390/rs15030599)

Abstract

With the popularization of humans working in tandem with robots and artificial intelligence (AI) by Industry 5.0, ultrasonic non-destructive testing (NDT)) technology has been increasingly used in quality inspections in the industry. As a crucial part of handling ultrasonic testing results–signal processing, the current approach focuses on professional training to perform signal discrimination but automatic and intelligent signal optimization and estimation lack systematic research. Though the automated and intelligent framework for ultrasonic echo signal processing has already exhibited essential research significance for diagnosing defect locations, the real-time applicability of the algorithm for the time-of-flight (ToF) estimation is rarely considered, which is a very important indicator for intelligent detection. This paper conducts a systematic comparison among different ToF algorithms for the first time and presents the auto-diagnosis of the ToF approach based on the Defect Peaks Tracking Model (DPTM). The proposed DPTM is used for ultrasonic echo signal processing and recognition for the first time. The DPTM using the Hilbert transform was verified to locate the defect with the size of 2–10 mm, in which the wavelet denoising method was adopted. With the designed mechanical fixture through 3D printing technology on the pipeline to inspect defects, the difficulty of collecting sufficient data could be conquered. The maximum auto-diagnosis error could be reduced to 0.25% and 1.25% for steel plate and pipeline under constant pressure, respectively, which were much smaller than those with the DPTM adopting the cross-correlation. The real-time auto-diagnosis identification feature of DPTM has the potential to be combined with AI in future work, such as machine learning and deep learning, to achieve more intelligent approaches for industrial health inspection.

• Item Type: Articles
• Additional Information: This research was funded by the Hong Kong Polytechnic University and University of Glasgow, funder: Kwok-ho Lam.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Lam, Dr Koko

Creator Roles

Lam, K.-H.: Writing – review and editing, Supervision, Project administration, Funding acquisition

• Authors: Yang, F., Shi, D., Lo, L.-Y., Mao, Q., Zhang, J., and Lam, K.-H.
• College/School: College of Science and Engineering > School of Engineering > Systems Power and Energy
• Journal Name: Remote Sensing
• Publisher: MDPI
• ISSN: 2072-4292
• ISSN (Online): 2072-4292
• Published Online: 19 January 2023
• Copyright Holders: Copyright © 2023 The Authors
• First Published: First published in Remote Sensing 15(3): 599
• Publisher Policy: Reproduced under a Creative Commons License