Temperature interpretation method for temperature indicating paint based on spectrogram

被引：4

作者：

Ge, Junfeng ^{[1
,2
]}

Wang, Li ^{[1
]}

Gui, Kang ^{[1
,2
,3
]}

Ye, Lin ^{[1
,2
]}

机构：

[1] Huazhong Univ Sci & Technol, Sch Artificial Intelligence & Automation, Wuhan 430074, Hubei, Peoples R China

[2] Natl Key Lab Multispectral Informat Intelligent Pr, Wuhan 430074, Hubei, Peoples R China

[3] Huazhong Univ Sci & Technol, Sch Artificial Intelligence & Automation, Room 311,Bldg East 2,1037 Luoyu Rd, Wuhan 430074, Hubei, Peoples R China

来源：

MEASUREMENT | 2023年 / 219卷

关键词：

Temperature indicating paint; Reflectance spectrum; Spectrogram; Convolutional Neural Network;

D O I：

10.1016/j.measurement.2023.113317

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Accurate interpretation of temperature indicating paint (TIP) is of great importance in aviation and other industrial applications. This study presents a novel temperature interpretation approach based on the 2D spectrogram of TIP. A deep learning model called ESTNet(efficient spectrogram-temperature network) has been developed. The Gramian Angular Field (GAF) and the Continuous Wavelet Transform (CWT) are used to transform 1D reflectance spectrum into 2D spectrogram, GASF-Graph and scale2-Graph. The residual blocks and two composite coefficients are used to design RSTNet with an accuracy of 94% on KN3A samples when the input is GASF-Graph or scale2-Graph. Furthermore, RSTNet is optimized as ESTNet by the spectrogram information fusion strategy and channel attention mechanism. Using ESTNet, the interpretation accuracy of KN3A, KN6, and KN8 samples is 96%, 94%, and 96%, respectively, and RMSE is 1.5 & DEG;C, 2.1 & DEG;C, 1.8 & DEG;C, respectively. This research provides valuable insight and reference for other spectroscopic applications.

引用

页数：12

共 44 条

[11] Automated gender-Parkinson's disease detection at the same time via a hybrid deep model using human voice [J].

Kaya, Duygu .

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2022, 34 (26)

[12] The mRMR-CNN based influential support decision system approach to classify EEG signals [J].

Kaya, Duygu .

MEASUREMENT, 2020, 156

[13]

Keogh E. J., 2000, Proceedings. KDD-2000. Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, P285, DOI 10.1145/347090.347153

[14] Color recognition with a camera: A supervised algorithm for classification [J].

Lalanne, T ;

Lempereur, C .

1998 IEEE SOUTHWEST SYMPOSIUM ON IMAGE ANALYSIS AND INTERPRETATION, 1998, :198-204

[15] Surface temperature measurement on engine components by means of irreversible thermal coatings [J].

Lempereur, C. ;

Andral, R. ;

Prudhomme, J. Y. .

MEASUREMENT SCIENCE AND TECHNOLOGY, 2008, 19 (10)

[16] The Research of Temperature Indicating Paints and Its Application in Aero-engine Temperature Measurement [J].

Li Yang ;

Li Zhi-min .

2014 ASIA-PACIFIC INTERNATIONAL SYMPOSIUM ON AEROSPACE TECHNOLOGY, APISAT2014, 2015, 99 :1152-1157

[17]

Loshchilov I., 2016, arXiv, DOI DOI 10.48550/ARXIV.1608.03983

[18]

Maosong L, 2007, 2007 8 INT C EL MEAS, DOI [10.1109/ICEMI.2007.4350848, DOI 10.1109/ICEMI.2007.4350848]

[19] The influence of training sample size on the accuracy of deep learning models for the prediction of soil properties with near-infrared spectroscopy data [J].

Ng, Wartini ;

Minasny, Budiman ;

Mendes, Wanderson de Sousa ;

Melo Dematt, Jose Alexandre .

SOIL, 2020, 6 (02) :565-578

[20]

Nguyen RMH, 2014, LECT NOTES COMPUT SC, V8695, P186, DOI 10.1007/978-3-319-10584-0_13

← 1 2 3 4 5 →