A Study on Unsupervised Anomaly Detection and Defect Localization using Generative Model in Ultrasonic Non-Destructive Testing

TL;DR

This paper proposes an unsupervised anomaly detection method using a diffusion model for ultrasonic non-destructive testing, enabling defect detection and localization without requiring defect examples for training.

Contribution

It introduces a novel diffusion model-based approach for automated ultrasonic inspection that trains solely on defect-free data, addressing data scarcity issues.

Findings

Improved defect detection accuracy over traditional object detection methods.

Effective localization of defects in ultrasonic testing images.

Demonstrated robustness in automated inspection scenarios.

Abstract

In recent years, the deterioration of artificial materials used in structures has become a serious social issue, increasing the importance of inspections. Non-destructive testing is gaining increased demand due to its capability to inspect for defects and deterioration in structures while preserving their functionality. Among these, Laser Ultrasonic Visualization Testing (LUVT) stands out because it allows the visualization of ultrasonic propagation. This makes it visually straightforward to detect defects, thereby enhancing inspection efficiency. With the increasing number of the deterioration structures, challenges such as a shortage of inspectors and increased workload in non-destructive testing have become more apparent. Efforts to address these challenges include exploring automated inspection using machine learning. However, the lack of anomalous data with defects poses a barrier to improving the accuracy of automated inspection through machine learning. Therefore, in this study, we propose a method for automated LUVT inspection using an anomaly detection approach with a diffusion model that can be trained solely on negative examples (defect-free data). We experimentally confirmed that our proposed method improves defect detection and localization compared to general object detection algorithms used previously.