# Automatic Borescope Damage Assessments for Gas Turbine Blades via Deep Learning

arXiv: https://arxiv.org/abs/2103.05430 · HTML: https://mlsanity.com/paper/2103.05430/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 15 of 15)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [Learning to Segment Object Candidates](https://mlsanity.com/paper/1506.06204/) (2015)
- [Blade Envelopes Part I: Concept and Methodology](https://mlsanity.com/paper/2011.11636/) (2020)
- [Blade Envelopes Part II: Multiple Objectives and Inverse Design](https://mlsanity.com/paper/2012.15579/) (2020)

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

- [Superpixel perception graph neural network for intelligent defect detection of aero-engine blade](https://mlsanity.com/paper/2210.07539/) (2022)

## Abstract (arXiv)

To maximise fuel economy, bladed components in aero-engines operate close to material limits. The severe operating environment leads to in-service damage on compressor and turbine blades, having a profound and immediate impact on the performance of the engine. Current methods of blade visual inspection are mainly based on borescope imaging. During these inspections, the sentencing of components under inspection requires significant manual effort, with a lack of systematic approaches to avoid human biases. To perform fast and accurate sentencing, we propose an automatic workflow based on deep learning for detecting damage present on rotor blades using borescope videos. Building upon state-of-the-art methods from computer vision, we show that damage statistics can be presented for each blade in a blade row separately, and demonstrate the workflow on two borescope videos.