scholarly journals Intelligent Life Prediction of Thermal Barrier Coating for Aero Engine Blades

Coatings ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 890
Author(s):  
Ruipeng Gao ◽  
Wei Mao ◽  
Yiran Wang ◽  
Shanshan Fan ◽  
Wei Shao

The existing methods for thermal barrier coating (TBC) life prediction rely mainly on experience and formula derivation and are inefficient and inaccurate. By introducing deep learning into TBC life analyses, a convolutional neural network (CNN) is used to extract the TBC interface morphology and analyze its life information, which can achieve a high-efficiency accurate judgment of the TBC life. In this thesis, an Adap–Alex algorithm is proposed to overcome the problems related to the large training time, over-fitting, and low accuracy in the existing CNN training of TBC images with complex tissue morphologies. The method adjusts the receptive field size, stride length, and other parameter settings and combines training epochs with a sigmoid function to realize adaptive pooling. TBC data are obtained by thermal vibration experiments, a TBC dataset is constructed, and then the Adap–Alex algorithm is used to analyze the generated TBC dataset. The average training time of the Adap–Alex method is significantly smaller than those of VGG-Net and Alex-Net by 125 and 685 s, respectively. For a fixed number of thermal vibrations, the test accuracy of the Adap–Alex algorithm is higher than those of Alex-Net and VGG-Net, which facilitates the TBC identification. When the number of thermal vibrations is 300, the accuracy reaches 93%, and the performance is highest.

1987 ◽  
Vol 32 (1-4) ◽  
pp. 305-306
Author(s):  
B. Pilsner ◽  
R. Hillery ◽  
R. McKnight ◽  
T. Cook ◽  
M. Hartle

1988 ◽  
Vol 110 (4) ◽  
pp. 610-616 ◽  
Author(s):  
T. A. Cruse ◽  
S. E. Stewart ◽  
M. Ortiz

Ceramic thermal barrier coating tests show that the coating fails by ceramic spallation. Analysis of life data indicates that cyclic thermal loading and thermal exposure play synergistic roles in controlling the spallation life of the coating. A life prediction algorithm has been developed, based on a damage accumulation algorithm that includes both cyclic and time-dependent damage. The cyclic damage is related to the calculated cyclic inelastic strain range in the ceramic coating; the time-dependent damage is related to the oxidation kinetics at the bond-ceramic interface. Cyclic inelastic strain range is calculated using a modified form of the Walker viscoplastic material model. Calculation of the oxidation kinetics is based on traditional oxidation algorithms using experimentally determined parameters. A relation between oxide growth and cycle parameters was derived from test data. The life prediction model was evaluated by predicting the lives of a set of thermal cyclic tests whose heating and cooling rates were significantly greater than those used to correlate the life parameters. Correlation between the actual and predicted spallation lives is within a factor of 3. This is judged to be satisfactory, relative to fatigue life prediction scatter in metals.


2007 ◽  
Vol 55 (5) ◽  
pp. 1491-1503 ◽  
Author(s):  
E BUSSO ◽  
L WRIGHT ◽  
H EVANS ◽  
L MCCARTNEY ◽  
S SAUNDERS ◽  
...  

Author(s):  
Hyunwoo Song ◽  
Yongseok Kim ◽  
Jeong-Min Lee ◽  
Junghan Yun ◽  
Dae-Jin Kim ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document