Identification of welding defects from ultrasonic signals using an improved ACGAN and WOA-ShuffleNet V1

Export Citation

Chen, Y, Su, X, Shen, H, Zhang, G orcid iconORCID: 0000-0002-2351-2661, Ma, H, Dong, M and Liu, W (2026) Identification of welding defects from ultrasonic signals using an improved ACGAN and WOA-ShuffleNet V1. Nondestructive Testing and Evaluation. ISSN 1058-9759

[thumbnail of manuscript_R2.pdf]
Preview
 Text
manuscript_R2.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.
Download (1MB) | Preview

Abstract

In the ultrasonic detection of weld defects, addressing issues such as small-sample multi-class imbalanced distribution of echo signals and lightweight requirements for classification models, a welding defect ultrasonic signal recognition method based on Gramian angular summation field (GASF), improved auxiliary classifier generative adversarial network (ACGAN), and WOA-ShuffleNet V1 is proposed. First, ACGAN is enhanced by integrating a frequency-aware module, latent space optimisation, and optimised loss functions to improve generated sample quality. Then, through comparative analysis of expansion ratios and the impact of generative models on classification results, the effectiveness of the improved ACGAN in augmenting multi-class imbalanced small-sample data is validated. Finally, the whale optimisation algorithm (WOA) is employed to optimise hyperparameters of ShuffleNet V1. Experimental results show that on the expanded data, the method maintains 90.75% recognition accuracy while reducing FLOPs, model size and number of parameters, thus achieving a balance between lightweighting and classification performance.

Item Type: Article
Uncontrolled Keywords: Ultrasonic signal; welding defect identification; ACGAN; WOA; ShuffleNet V1; 40 Engineering; 4016 Materials Engineering; 0912 Materials Engineering; 0913 Mechanical Engineering; Acoustics; 4016 Materials engineering
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Engineering
Publisher: Taylor and Francis Group
Date of acceptance: 14 December 2025
Date of first compliant Open Access: 7 April 2026
Date Deposited: 07 Apr 2026 14:04
Last Modified: 07 Apr 2026 14:06
DOI or ID number: 10.1080/10589759.2025.2606206
URI: https://researchonline.ljmu.ac.uk/id/eprint/28332
View Item View Item
CORE (COnnecting REpositories)