Learning to Identify Drilling Defects in Turbine Blades with Single Stage Detectors

TL;DR

This paper presents a RetinaNet-based model for detecting small drilling defects in turbine blades' X-ray images, addressing challenges like large image sizes and limited datasets through innovative data handling and optimization techniques.

Contribution

It introduces a novel approach combining image tiling, data augmentation, and differential evolution optimization to improve defect detection in industrial settings.

Findings

High accuracy in defect identification using the proposed method

Effective handling of small defects in large images

Best practices for similar industrial defect detection tasks

Abstract

Nondestructive testing (NDT) is widely applied to defect identification of turbine components during manufacturing and operation. Operational efficiency is key for gas turbine OEM (Original Equipment Manufacturers). Automating the inspection process as much as possible, while minimizing the uncertainties involved, is thus crucial. We propose a model based on RetinaNet to identify drilling defects in X-ray images of turbine blades. The application is challenging due to the large image resolutions in which defects are very small and hardly captured by the commonly used anchor sizes, and also due to the small size of the available dataset. As a matter of fact, all these issues are pretty common in the application of Deep Learning-based object detection models to industrial defect data. We overcome such issues using open source models, splitting the input images into tiles and scaling them up, applying heavy data augmentation, and optimizing the anchor size and aspect ratios with a differential evolution solver. We validate the model with $3$-fold cross-validation, showing a very high accuracy in identifying images with defects. We also define a set of best practices which can help other practitioners overcome similar challenges.