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

arXiv: https://arxiv.org/abs/2210.07539 · HTML: https://mlsanity.com/paper/2210.07539/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 73 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Understanding Attention and Generalization in Graph Neural Networks](https://mlsanity.com/paper/1905.02850/) (2019)
- [Potential, Challenges and Future Directions for Deep Learning in Prognostics and Health Management Applications](https://mlsanity.com/paper/2005.02144/) (2020)
- [Cascade Graph Neural Networks for RGB-D Salient Object Detection](https://mlsanity.com/paper/2008.03087/) (2020)
- [Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling](https://mlsanity.com/paper/1910.11436/) (2019)
- [Graph Neural Network Encoding for Community Detection in Attribute Networks](https://mlsanity.com/paper/2006.03996/) (2020)
- [Reference-based Defect Detection Network](https://mlsanity.com/paper/2108.04456/) (2021)
- [Slow-varying Dynamics Assisted Temporal Capsule Network for Machinery Remaining Useful Life Estimation](https://mlsanity.com/paper/2203.16373/) (2022)
- [Graph neural network-based fault diagnosis: a review](https://mlsanity.com/paper/2111.08185/) (2021)
- [Automatic Borescope Damage Assessments for Gas Turbine Blades via Deep Learning](https://mlsanity.com/paper/2103.05430/) (2021)

## Built on by (most cited first, 1 of 1)

- [Robust Online Aero-Engine Blade Defect Detection via Dual-Alignment Test-Time Adaptation](https://mlsanity.com/paper/2610.00067/) (2026)

## Abstract (arXiv)

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.