Evaluation of Internal Cracks in Turbine Blade Thermal Barrier Coating Using Enhanced Multi-Scale Faster R-CNN Model

Abstract

Thermal Barrier Coatings (TBCs) have good performance in heat insulation during service on turbine blades. However, the accumulated residual stress will form cracks, which can easily lead to coating failure. To ensure safe operation, it is necessary to find a method that can evaluate the health of the coating. In this paper, a non-destructive evaluation technique based on Multi-Scale Enhanced-Faster R-CNN (MSE-Faster R-CNN) is proposed. Firstly, the Visual Geometry Group Network19 layer (VGG-19) was adopted as the baseline network to find the candidate crack Region of Interest (ROI). Considering the influence of the crack on the surroundings, the ROI was expanded to obtain the context information. Secondly, a multi-scale Faster R-CNN detector was used to refine the candidate regions, and provided a comprehensive feature for better crack detection. Finally, a fusion lifetime prediction model was proposed to estimate the remaining lifetime of the TBC. Extensive experiments were conducted to evaluate the performance of the proposed method. The results demonstrated that the proposed method can accurately locate (0.898) and detect (0.806) the cracks in different scales, and the lifetime estimation result reached the best level (Root Mean Square Error (RMSE) = 2.7); there wasas also an acceptable time cost (1.63 s), and all detection conditions of the error rates were below 15%, achieving the best results among the state-of-art methods.