Citation: Shi, L.; Long, Y.; Wang, Y.;
Chen, X.; Zhao, Q. Evaluation of
Internal Cracks in Turbine Blade
Thermal Barrier Coating Using
Enhanced Multi-Scale Faster R-CNN
Model. Appl. Sci. 2022, 12, 6446.
https://doi.org/10.3390/
app12136446
Academic Editors: Wenjun
(Chris) Zhang, Dhanjoo N. Ghista,
Kelvin K. L. Wong and Andrew W.
H. Ip
Received: 21 February 2022
Accepted: 22 June 2022
Published: 24 June 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Evaluation of Internal Cracks in Turbine Blade Thermal Barrier
Coating Using Enhanced Multi-Scale Faster R-CNN Model
Licheng Shi
1
, Yun Long
2
, Yuzhang Wang
2,
*, Xiaohu Chen
2
and Qunfei Zhao
1
1
Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China;
slc20081429@sjtu.edu.cn (L.S.); zhaoqf@sjtu.edu.cn (Q.Z.)
2
Key Laboratory for Power Machinery and Engineering of Ministry of Education, Shanghai Jiao Tong
University, Shanghai 200240, China; y.long@sjtu.edu.cn (Y.L.); chenxiaohu@sjtu.edu.cn (X.C.)
* Correspondence: yuzhangwang@sjtu.edu.cn; Tel.: +86-21-3420-6031
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.
Keywords:
thermal barrier coatings (TBCs); crack detection; infrared thermography; non-destructive
evaluation; Multi Scale Enhanced-Faster R-CNN (MSE-Faster R-CNN); lifetime estimation
1. Introduction
The working temperature of a gas turbine is rising continuously due to the continuous
pursuit of performance. A common way to deal with this situation is to spray Thermal
Barrier Coatings (TBCs) on the turbine blades, so that the components can bear a large
temperature gradient when exposed to heat flow [
1
,
2
]. During long term service, cracks are
one of the most common and serious defects in TBCs [
3
]. Since TBC is a multilayer structure
including top-coating layer, transition layer and the substrate, under high temperature
and harsh working conditions, the thermodynamic performance of different layers become
inconsistent, especially though a mismatch of thermal expansion coefficients. Such mis-
match between the layers will induce residual stress, which is considered to be the major
cause of the cracks [
4
]. The thermal insulation performance of the TBC will significantly
be reduced by a large sized crack or the penetration crack. When growing to a certain
extent, a crack will cause the coating to reach spallation, which makes TBC totally fail and
thus creates serious security problems. Therefore, implementing TBC crack detection is of
great importance.
The main crack detection methods include manual detection, ultrasonic detection, laser
scanning detection, infrared image-based detection, etc. [
5
]. Traditional manual detection
requires professional staff to shut down the gas turbine regularly and observe whether the
Appl. Sci. 2022, 12, 6446. https://doi.org/10.3390/app12136446 https://www.mdpi.com/journal/applsci
