Global Prior Transformer Network in Intelligent Borescope Inspection for Surface Damage Detection of Aeroengine Blade

Abstract

Surface damage detection is vital for diagnosis and monitoring of aero-engine blade. At present, borescope inspection is the dominant technology. Several inspectors hold borescope to inspect the blades one by one through naked eyes on the apron. The inspection of turbine blades even requires drilling into narrow aero-engine tail nozzle. The manual visual inspection is high cost and low efficiency. To improve detection efficiency and economic benefit, we propose an intelligent borescope inspection method in this paper. Facing the problem of weak damage information caused by background noise and unsatisfactory illumination, local window Transformer network efficiently models pixel-to-pixel relations with the help of global self-attention mechanism, shifted window strategy is used to conduct information exchange. The capacity of global modeling is benefit for capturing detail damage outline. Besides, to learn label relations as prior and embed it into model, semantic information of different damages is aggregated by a two-layer graph convolution network. The global label graph network provides global prior by modeling label dependencies based on the samples in dataset. Finally, the image features and label features are fused to provide rich feature representation for mode recognition and damage localization. We validate the effectiveness of the proposed method on three datasets, including simulated blade, aluminum, and real blade datasets. The results demonstrate that the proposed method has superior performance with 84.9 mAP on simulated blade dataset and satisfactory visualization results on real blade dataset.