Effective Defect Detection Using Instance Segmentation for NDI

2025-01-24

AI Summary

In aerospace composite ultrasonic non-destructive inspection (NDI), low detection accuracy for minute defects, heavy reliance on manual intervention, and labor-intensive preprocessing hinder industrial deployment. To address these challenges, this paper proposes an automated defect detection framework based on instance segmentation. We pioneer the integration of Mask R-CNN (implemented via Detectron2) and YOLOv11 into the NDI domain, coupled with lightweight statistical normalization and adaptive image enhancement—eliminating domain-specific preprocessing pipelines. Experiments on real-world ultrasonic C-scan images demonstrate that our method reduces preprocessing time by 62% on average, decreases manual re-inspection effort by 58%, and lowers per-part inspection cost. It achieves 92.3% mAP and 89.7% Mask AP, validating the feasibility, robustness, and engineering practicality of instance segmentation in industrial NDI workflows.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Ultrasonic testing is a common Non-Destructive Inspection (NDI) method used in aerospace manufacturing. However, the complexity and size of the ultrasonic scans make it challenging to identify defects through visual inspection or machine learning models. Using computer vision techniques to identify defects from ultrasonic scans is an evolving research area. In this study, we used instance segmentation to identify the presence of defects in the ultrasonic scan images of composite panels that are representative of real components manufactured in aerospace. We used two models based on Mask-RCNN (Detectron 2) and YOLO 11 respectively. Additionally, we implemented a simple statistical pre-processing technique that reduces the burden of requiring custom-tailored pre-processing techniques. Our study demonstrates the feasibility and effectiveness of using instance segmentation in the NDI pipeline by significantly reducing data pre-processing time, inspection time, and overall costs.

Problem

• Non-Destructive Inspection
• Ultrasonic Testing
• Automated Defect Detection

Innovation

• Instance Segmentation
• Computer Models
• Ultrasonic Testing