A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal

Abstract

Artifacts are divergent strip artifacts or dark stripe artifacts in Industrial Computed Tomography (ICT) images due to large differences in density among the components of scanned objects, which can significantly distort the actual structure of scanned objects in ICT images. The presence of artifacts can seriously affect the practical application effectiveness of ICT in defect detection and dimensional measurement. In this paper, a series of convolution neural network models are designed and implemented based on preparing the ICT image artifact removal datasets. Our findings indicate that the RF (receptive field) and the spatial resolution of network can significantly impact the effectiveness of artifact removal. Therefore, we propose a dilated residual network for turbine blade ICT image artifact removal (DRAR), which enhances the RF of the network while maintaining spatial resolution with only a slight increase in computational load. Extensive experiments demonstrate that the DRAR achieves exceptional performance in artifact removal.

Correcting Hardening Artifacts of Aero-Engine Blades with an Iterative Linear Fitting Technique Framework

“…, y n ). If this function is used to represent the functional relationship of the correction model, the correction function g can be expressed as Equation (15).…”

“…Substituting y r,ML into Equation (15) to get the functional relationship g(Q, x r,0 , y r,ML ) of the data (Q, L t ) is satisfied. In the same way, y r can also be set to a fixed value y r,0 uniformly distributed in the vertical axis direction, so that Equation ( 16) can be converted into Equation (19).…”

“…Therefore, hardening artifact correction has always been a hot topic in the field of CT application research. There are many correction methods [ 11 , 12 , 13 , 14 , 15 ]. In terms of implementation methods, they can be divided into two categories, i.e., the hardware method and the software method.…”