Superpixel perception graph neural network for intelligent defect detection of aero-engine blade

TL;DR

This paper introduces a novel superpixel perception graph neural network (SPGNN) for intelligent defect detection in aero-engine blades, combining graph convolutional networks and superpixel perception for improved accuracy.

Contribution

The paper proposes a new SPGNN architecture that integrates multi-stage graph convolution and superpixel perception for enhanced defect detection in complex blade images.

Findings

SPGNN outperforms state-of-the-art methods in defect detection accuracy.

Constructed a simulated blade dataset with 3000 images for evaluation.

Validated effectiveness on a public aluminum dataset.

Abstract

Aero-engine is the core component of aircraft and other spacecraft. The high-speed rotating blades provide power by sucking in air and fully combusting, and various defects will inevitably occur, threatening the operation safety of aero-engine. Therefore, regular inspections are essential for such a complex system. However, existing traditional technology which is borescope inspection is labor-intensive, time-consuming, and experience-dependent. To endow this technology with intelligence, a novel superpixel perception graph neural network (SPGNN) is proposed by utilizing a multi-stage graph convolutional network (MSGCN) for feature extraction and superpixel perception region proposal network (SPRPN) for region proposal. First, to capture complex and irregular textures, the images are transformed into a series of patches, to obtain their graph representations. Then, MSGCN composed of several GCN blocks extracts graph structure features and performs graph information processing at graph level. Last but not least, the SPRPN is proposed to generate perceptual bounding boxes by fusing graph representation features and superpixel perception features. Therefore, the proposed SPGNN always implements feature extraction and information transmission at the graph level in the whole SPGNN pipeline, to alleviate the reduction of receptive field and information loss. To verify the effectiveness of SPGNN, we construct a simulated blade dataset with 3000 images. A public aluminum dataset is also used to validate the performances of different methods. The experimental results demonstrate that the proposed SPGNN has superior performance compared with the state-of-the-art methods.