|
|
Research on Image Recognition for NiCrAlY Coating/N5 High-temperature Alloy System Based on Deep Learning Method |
WANG Minghao1, WANG Huan2, LIU Rui1, MENG Fandi1, LIU Li1(), WANG Fuhui1 |
1.Shenyang National Laboratory for Materials Science, Northeasten University, Shenyang 110819, China 2.College of Information Science and Engineering, Northeastern University, Shenyang 110169, China |
|
|
Abstract The evolution of micro-morphology for the couple of NiCrAlY coating/N5 high-temperature alloy system during service at high temperature, namely the precipitated TCP-phases within the substrate, the interface of coating/substrate, and the formed oxide scale etc., was studied by means of image processing technology, aiming to acquire the information related with their characteristics for the identification and retrieval of the relevant features of coating/alloy systems. Based on the acquired date-sets from 3600 frames of cross-sectional feature images of 64×64 pixels, a convolutional neural network (CNN) was established for classification and identification of the TCP phase, the interface of coating/substrate, and the oxide scale via a deep learning technique. The convolutional neural networks with two or three convolutional layers were respectively trained, so that the classification and identification of these three kinds of features, as well as the sliding window retrieval positioning are realized, thereby, the test set accuracy was 98% or 90.67%, respectively, for the neural network of two or three convolution layers coupled with the RMSProp optimizer. The test set accuracy for the convolutional neural network with three convolutional layers coupled with the Adam optimizer was 99.17%. This network performs best in retrieving the desired three features for images of 1024×943 pixel, correspondingly, the retrieval accuracy even can reach 100%.
|
Received: 05 September 2021
|
|
Fund: National Key R&D Program of China(2017YFB0702303) |
Corresponding Authors:
LIU Li
E-mail: liuli@mail.neu.edu.cn
|
About author: LIU Li, E-mail: liuli@mail.neu.edu.cn
|
1 |
Yang Z Z, Kuang N, Fan L, et al. Review of image classification algorithms based on convolutional neural networks [J]. J. Sign. Process., 2018, 34: 1474
|
|
杨真真, 匡楠, 范露 等. 基于卷积神经网络的图像分类算法综述 [J]. 信号处理, 2018, 34: 1474
|
2 |
Wang D K. Weld defect classification and recognition of the in-service pipeline based on BP neural network [J]. Comput. Tomogr. Theory Appl., 2012, 21: 43
|
|
王道阔. 基于BP神经网络的在役管线焊缝故障缺陷的分类识别 [J]. CT理论与应用研究, 2012, 21: 43
|
3 |
Zou L Y, Wu S Q, Fang H P, et al. Survey on material perception based on computer vision [J]. Appl. Res. Comput., 2019, 36: 2894
|
|
邹凌云, 伍世虔, 方红萍 等. 基于计算机视觉的材料感知技术综述 [J]. 计算机应用研究, 2019, 36: 2894
|
4 |
Yu C T, Yang Y F, Bao Z B, et al. Research progress in preparation and development of excellent bond coats for advanced thermal barrier coatings [J]. J. Chin. Soc. Corros. Prot., 2019, 39: 395
|
|
余春堂, 阳颖飞, 鲍泽斌 等. 先进高温热障涂层用高性能粘接层制备及研究进展 [J]. 中国腐蚀与防护学报, 2019, 39: 395
|
5 |
Wang X Y, Xin L, Wei H, et al. Progress of high-temperature protective coatings [J]. Corros. Sci. Prot. Technol., 2013, 25: 175
|
|
王心悦, 辛丽, 韦华 等. 高温防护涂层研究进展 [J]. 腐蚀科学与防护技术, 2013, 25: 175
|
6 |
Beele W, Czech N, Quadakkers W J, et al. Long-term oxidation tests on a re-containing MCrAlY coating [J]. Surf. Coat. Technol., 1997, 94/95: 41
|
7 |
Goward G W. Progress in coatings for gas turbine airfoils [J]. Surf. Coat. Technol., 1998, 108: 73
|
8 |
Jiang B C, Cao J D, Cao X Y, et al. Hot corrosion behavior of Gd2(Zr1- x Ce x )2O7 thermal barrier coating ceramics exposed to artificial particulates of CMAS [J]. J. Chin. Soc. Corros. Prot., 2021, 41: 263
|
|
姜伯晨, 曹将栋, 曹雪玉 等. Gd2(Zr1- x Ce x )2O7热障涂层陶瓷层材料的CMAS热腐蚀行为研究 [J]. 中国腐蚀与防护学报, 2021, 41: 263
|
9 |
Wen M, Jordan E H, Gell M. Remaining life prediction of thermal barrier coatings based on photoluminescence piezospectroscopy measurements [J]. J. Eng. Gas Turb. Power, 2005, 128: 610
doi: 10.1115/1.2135820
|
10 |
Huang Q Y, Li H K. High Temperature Alloys [M]. Beijing: Metallurgical Industry Press, 2000
|
|
黄乾尧, 李汉康. 高温合金 [M]. 北京: 冶金工业出版社, 2000
|
11 |
Wang B, Gong J, Wang A Y, et al. Oxidation behaviour of NiCrAlY coatings on Ni-based superalloy [J]. Surf. Coat. Technol., 2002, 149: 70
doi: 10.1016/S0257-8972(01)01427-X
|
12 |
Li W Z, Li Y Q, Yi D Q, et al. Microstructural evolution and failure mechanism of NiCrAlY coating systems during different cycled oxidation [J]. Chin. J. Nonferrrous Met., 2013, 23: 417
|
|
李伟洲, 李月巧, 易丹青 等. 不同冷热循环条件下NiCrAlY涂层体系的微观组织演变规律及失效机理 [J]. 中国有色金属学报, 2013, 23: 417
|
13 |
Chen Y, Zhao X F, Xiao P. Effect of microstructure on early oxidation of MCrAlY coatings [J]. Acta Mater., 2018, 159: 150
doi: 10.1016/j.actamat.2018.08.018
|
14 |
Chen W R, Wu R, Marple B R, et al. TGO growth behaviour in TBCs with APS and HVOF bond coats [J]. Surf. Coat. Technol., 2008, 202: 2677
doi: 10.1016/j.surfcoat.2007.09.042
|
15 |
Huang X W, Jiang X H, Li C C, et al. Research progress of coating life prediction and reliability evaluation [J]. Mater. Prot., 2018, 51(7): 110
|
|
黄烯望, 姜新华, 李长春 等. 涂层寿命预测与可靠性评价的研究进展 [J]. 材料保护, 2018, 51(7): 110
|
16 |
Chen H J, Li Q L, Cheng X D, et al. Influence of thermally grown oxide on failure of thermal barrier coating [J]. Mater. Prot., 2012, 45(3): 5
|
|
陈慧君, 李其连, 程旭东 等. TGO对热障涂层失效的作用分析 [J]. 材料保护, 2012, 45(3): 5
|
No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|