The qualitative identification of weld defects is crucial for the safe use and life assessment of in-service welded components. Although intelligent defect recognition using machine learning has gained significant attention, existing approaches often suffer from limited defect types, small datasets, and reliance on single-feature sources. Consequently, the recognition accuracy remains insufficient for real-world industrial applications, especially when encountering new and complex defect patterns. To address these challenges, this study proposes a signal-image-joint machine learning fusion model (SIJ-MLF) that classifies weld defects using large-scale data collected from austenitic stainless steel weld samples. The method integrates multiple features extracted from both defect pulse signals and images, adaptive sliding window and feature selection techniques are introduced to further enhance recognition performance. Comparative analyses demonstrate that the proposed approach achieves a stable accuracy of up to 96% when tested on completely new practical samples. Moreover, an intelligent recognition software has been developed based on this work, illustrating its potential for reliable and efficient industrial inspection. • SIJ-MLF fuses ultrasonic signals and S-scan images for defect classification. • Adaptive sliding-window selects feature intervals, boosting accuracy to 96%. • Uses SHAP to quantify signal-feature contributions and confirm importance. • Ablation study shows SIJ-MLF’s superior performance and robustness across conditions. • SIJ-MLF-based software developed for industrial weld-defect detection.
Hu et al. (Sun,) studied this question.