Thin thermally grown oxide thickness detection in thermal barrier coatings based on SWT-BP neural network algorithm and terahertz technology

Manting Luo; Manting Luo; Shuncong Zhong; Shuncong Zhong; Ligang Yao; Wanli Tu; Walter Nsengiyumva; Weiqiang Chen

doi:10.1364/AO.392748

Applied Optics
Vol. 59,
Issue 13,
pp. 4097-4104
(2020)
•https://doi.org/10.1364/AO.392748

Thin thermally grown oxide thickness detection in thermal barrier coatings based on SWT-BP neural network algorithm and terahertz technology

Manting Luo, Shuncong Zhong, Ligang Yao, Wanli Tu, Walter Nsengiyumva, and Weiqiang Chen

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Manting Luo, Shuncong Zhong, Ligang Yao, Wanli Tu, Walter Nsengiyumva, and Weiqiang Chen, "Thin thermally grown oxide thickness detection in thermal barrier coatings based on SWT-BP neural network algorithm and terahertz technology," Appl. Opt. 59, 4097-4104 (2020)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Check for updates

Related Topics
Table of Contents Category
- Instrumentation and Measurements
Optics & Photonics Topics
?

The topics in this list come from the Optics and Photonics Topics applied to this article.

About this Article
History
- Original Manuscript: March 13, 2020
- Revised Manuscript: March 31, 2020
- Manuscript Accepted: April 1, 2020
- Published: April 30, 2020

Abstract

Terahertz time-domain spectroscopy is a contactless and nondestructive testing technique that is often used to measure the thickness of layered materials. However, the technique presents limited thickness detection resolution, especially in the thin thermally grown oxide (TGO) of thermal barrier coatings whose thickness is below 30 µm. In this study, an SWT-BP algorithm combining a stationary wavelet transform (SWT) and a backpropagation (BP) neural network was proposed, and the regression coefficient of SWT-detailed results was 0.92. The prediction results were in good agreement with the real-time results; it demonstrated that the proposed algorithm was able to achieve a thickness prediction of up to 1–29 µm of the TGO. The proposed algorithm is suitable for thin thickness detection of the TGO.

Full Article | PDF Article

More Like This

In-situ evaluation of porosity in thermal barrier coatings based on the broadening of terahertz time-domain pulses: simulation and experimental investigations

Dongdong Ye, Weize Wang, Haiting Zhou, Jibo Huang, Wenchao Wu, Hanhong Gong, and Zhen Li
Opt. Express 27(20) 28150-28165 (2019)

Pulsed terahertz spectroscopy combined with hybrid machine learning approaches for structural health monitoring of multilayer thermal barrier coatings

Dongdong Ye, Weize Wang, Changdong Yin, Zhou Xu, Haiting Zhou, Huanjie Fang, Yuanjun Li, and Jibo Huang
Opt. Express 28(23) 34875-34893 (2020)

Detection method and instrument of interfacial debonding inside a thermal barrier coating based on fluorescence imaging

Zong Wang, Yanheng Zhang, Jinli Guo, Shijie Zhang, and Wei Qiu
Appl. Opt. 61(18) 5401-5408 (2022)

Previous Article Next Article

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (10)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (5)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (13)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

NDT Methods	Parameters Can Be Detected	Reference
UT	Density, elasticity modulus, thickness, bond quality	[4] and [6]
IRT	Coating thickness, coating crack, degumming	[7,8]
AE	Damage and crack	[9]
EC	Large internal pores of the coating, the thickness of the $β - {A l}_{2} O_{3}$ layer in the TGO layer, and the remaining thickness of the ceramic layer	[10]
THz-TDS	Nondestructive evaluation of microstructure of YSZ-TBCs, microstructure changes caused by sintering	[11–13], [19–21,23] [26,27]

Thickness of the Coating (µm)	Real Thickness (µm)	Solved by Original Signal (µm)	Solved by Deconvolved Signal (µm)	Solved by SWT Signal (µm)
Ceramic layer	180	169.15	177.12	175.53
Oxide layer	100	131.25	117.58	109.82

Parameters of Neural Network	Value
Number of network layers	3
Number of neurons in the input layer	600
Number of neurons in the hidden layer	29
Number of neurons in the output layer	1
Validate percent	0.1
Test percent	0.1
Train percent	0.8
Transfer function for the hidden layer	logsig
Transfer function for the output layer	tansig
Learning function	traingd
Learning rate	0.05
Momentum factor	0.9
Performance goal	1 E-5

	SWT Approximate Signals( ${\tilde{a}}_{1}$ )		SWT Detailed Signals( ${\tilde{d}}_{1}$ )
Real Thickness (µm)	Predicted Thickness (µm)	Thickness Deviation (µm)	Predicted Thickness (µm)	Thickness Deviation (µm)
1	18.71	17.71	4.70	3.70
3	5.48	2.48	4.65	1.65
5	1.49	−3.51	4.94	−0.06
7	1.65	−5.35	3.82	−3.18
9	1.86	−7.14	4.05	−4.95
11	2.89	−8.11	3.99	−7.01
13	8.30	−4.7	8.60	−4.4
15	14.83	−0.17	10.53	−4.47
17	15.46	−1.54	20.84	3.84
19	22.47	3.47	21.98	2.98
21	25.89	4.89	24.98	3.98
23	27.28	4.28	26.41	3.41
25	28.18	3.18	27.16	2.16
27	28.50	1.5	27.93	0.93
29	28.69	−0.31	24.08	−4.92

	RMSE	MAE	MAPE	$R$
Predicted results of ${\tilde{a}}_{1}$	6.1575	4.5560	1.5194	0.82
Predicted results of ${\tilde{d}}_{1}$	3.8327	3.4427	0.4934	0.92

Abstract

Cited By

Figures (10)

Tables (5)

Equations (13)

Applied Optics