Machine Learning-Based Ultrasonic Weld Characterization Using Hierarchical Wave Modeling and Diffusion-Driven Distribution Alignment

2025-10-14

AI Summary

To address critical challenges in industrial ultrasonic weld inspection—including severe scarcity of labeled training data, substantial simulation-to-reality gap, and strong in-situ noise interference—this paper proposes an end-to-end learning framework integrating physics-informed modeling with diffusion-based distribution alignment. Methodologically: (i) a reduced-order Helmholtz model grounded in Lamb wave theory is developed to efficiently generate high-fidelity synthetic training data; (ii) a diffusion-driven distribution alignment mechanism is introduced to mitigate domain shift and alleviate the small-sample problem; (iii) a U-Net architecture jointly performs acoustic field reconstruction and defect segmentation from noisy laser Doppler vibrometry signals. Experiments on real industrial scanning data demonstrate high-precision identification of weld heterogeneity and micro-cracks, significantly improving robustness and cross-domain generalization. To our knowledge, this work achieves the first industrial-grade deployment of fully automated ultrasonic weld inspection.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning with Manifolds

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Automated ultrasonic weld inspection remains a significant challenge in the nondestructive evaluation (NDE) community to factors such as limited training data (due to the complexity of curating experimental specimens or high-fidelity simulations) and environmental volatility of many industrial settings (resulting in the corruption of on-the-fly measurements). Thus, an end-to-end machine learning (ML) workflow for acoustic weld inspection in realistic (i.e., industrial) settings has remained an elusive goal. This work addresses the challenges of data curation and signal corruption by proposing workflow consisting of a reduced-order modeling scheme, diffusion based distribution alignment, and U-Net-based segmentation and inversion. A reduced-order Helmholtz model based on Lamb wave theory is used to generate a comprehensive dataset over varying weld heterogeneity and crack defects. The relatively inexpensive low-order solutions provide a robust training dateset for inversion models which are refined through a transfer learning stage using a limited set of full 3D elastodynamic simulations. To handle out-of-distribution (OOD) real-world measurements with varying and unpredictable noise distributions, i.e., Laser Doppler Vibrometry scans, guided diffusion produces in-distribution representations of OOD experimental LDV scans which are subsequently processed by the inversion models. This integrated framework provides an end-to-end solution for automated weld inspection on real data.

Problem

• Addresses limited training data for ultrasonic weld inspection using hierarchical modeling
• Handles signal corruption in industrial settings through diffusion-based distribution alignment
• Develops end-to-end ML workflow for automated weld defect characterization

Innovation

• Hierarchical wave modeling for dataset generation
• Diffusion-driven alignment for noise distribution handling
• U-Net-based segmentation and inversion workflow