Infrared Multispectral Radiation Temperature Measurement Based on PCA-ELM

doi:10.16183/j.cnki.jsjtu.2020.027

Abstract

Abstract:

In the case of unknown target emissivity, an infrared multispectral radiation temperature measurement method based on principal component analysis (PCA) and extreme learning machine (ELM) is established. The nonlinear mathematic model of target temperature and radiance spectrum is analyzed to find a set of initial input vectors, which include sufficient information to estimate temperature. The PCA method is used to extract the independent principle components in input vectors. This method can also reduce the input dimension for neural network. Based on ELM network, the sample data is sufficiently learned to build the target infrared temperature measurement model by PCA-ELM. The effectiveness of the proposed method is verified by using the blackbody and the coating material with unknown emissivity as test target sources.

Key words: principal component analysis (PCA), extreme learning machine (ELM), multispectral thermometry, radiance

CLC Number:

TB133
TN219

XI Jianhui, JIANG Han, CHEN Bo, FU Li. Infrared Multispectral Radiation Temperature Measurement Based on PCA-ELM[J]. Journal of Shanghai Jiao Tong University, 2021, 55(7): 891-898.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Tab.2

PCA results of spectral radiance of blackbody

特征值	特征向量
λ₁=138.7186	a₁=[ $0.0820 0.0821 … 0.0845$ ]^T
λ₂=2.2762	a₂=[ $0.1713 0.1694 … - 0.0621$ ]^T
λ₃=0.0051	a₃=[ $0.2696 0.2490 … 0.0834$ ]^T
?	?
λ₁₄₁=0	a₁₄₁=[ $0.0602 - 0.0630 … - 0.2857$ ]^T

Tab.2

Fig.5

Tab.3

Temperature measurement results of blackbody and its relative errors

T₁/℃	T₂/℃	$O (k) - T (k) O (k)$ /%	$ε -$	$0.98 - ε - 0.98$ /%
95	97.4762	2.61	0.9318	4.8
115	119.1212	3.58	0.9673	1.3
135	131.8413	2.34	1.0110	3.2
155	150.7401	2.75	1.0217	4.3
180	176.3031	2.05	1.0151	3.6
450	455.9431	1.32	0.9410	4.0
520	517.7082	0.44	0.9688	1.1
1000	1025.3000	2.53	0.9523	2.8

Tab.3

Fig.6

Fig.7

Tab.4

Tab.5

PCA results of spectral radiance of coating target

特征值	特征向量
λ₁=125.3228	a₁=[ $0.0475 0.0386 … 0.0796$ )^T
λ₂=12.0106	a₂=[ $0.1931 0.2276 … - 0.0362$ ]^T
λ₃=2.6217	a₃=[ $0.2838 0.2372 … - 0.2458$ ]^T
?	?
λ₁₄₁=0	a₁₄₁=[ $0.0007 - 0.0020 … 0.5271$ ]^T

Tab.5

Fig.8

Tab.6

Temperature measurement results and relative errors of coating target

T₁/℃	T₂/ ℃	$O (k) - T (k) O (k)$ /%	$ε -$
88	88.8148	0.93	0.8197
98	98.7474	0.71	0.8026
113	112.3211	0.60	0.7718
130	129.3978	0.46	0.6684
143	143.6489	0.45	0.5941
158	157.9227	0.04	0.5364
168	167.5493	0.27	0.5143

Tab.6

References 17

[1]	杨永军, 王中宇, 张术坤, 等. 基于多光谱测温优化的材料光谱发射率测量[J]. 北京航空航天大学学报, 2014, 40(8): 1022-1026.
	YANG Yongjun, WANG Zhongyu, ZHANG Shukun, et al. Material spectral emissivity measurement optimized by multi-spectral temperature measured[J]. Journal of Beijing University of Aeronautics and Astronautics, 2014, 40(8): 1022-1026.
[2]	MADURA H, KASTEK M, PIATKOWSKI T. Automatic compensation of emissivity in three-wavelength pyrometers[J]. Infrared Physics & Technology, 2007, 51(1): 1-8.
[3]	王新北, 萧鹏, 戴景民. 基于傅里叶红外光谱仪的光谱发射率测量装置的研制[J]. 红外与毫米波学报, 2007, 26(2): 149-152.
	WANG Xinbei, XIAO Peng, DAI Jingmin. Development of spectral emissivity measurement system based on Fourier transform infrared spectrometer(ftir)[J]. Journal of Infrared and Millimeter Waves, 2007, 26(2): 149-152.
[4]	曹立华, 杨词银, 万春明. 基于标校的双波段比色测温法[J]. 仪器仪表学报, 2012, 33(8): 1882-1888.
	CAO Lihua, YANG Ciyin, WAN Chunming. Correction-based dual-waveband color comparison thermometric method[J]. Chinese Journal of Scientific Instrument, 2012, 33(8): 1882-1888.
[5]	原遵东. 辐射测温的广义有效亮度温度[J]. 仪器仪表学报, 2012, 33(4): 721-726.
	YUAN Zundong. Generalized effective radiance temperature in radiation thermometry[J]. Chinese Journal of Scientific Instrument, 2012, 33(4): 721-726.
[6]	杨桢, 杨立, 张士成, 等. 基于双温双波段法的郎伯体红外测温技术[J]. 工程热物理学报, 2013, 34(11): 2132-2135.
	YANG Zhen, YANG Li, ZHANG Shicheng, et al. Infrared temperature measurement technology on lambertian based on the dual temperature and dual-band method[J]. Journal of Engineering Thermophysics, 2013, 34(11): 2132-2135.
[7]	孙元, 彭小奇. 基于彩色CCD的双色与三色比色测温法比较研究[J]. 传感技术学报, 2015, 28(8): 1184-1187.
	SUN Yuan, PENG Xiaoqi. Comparative study on two-color and three-color colorimetric temperature measurement based on colored CCD[J]. Chinese Journal of Sensors and Actuators, 2015, 28(8): 1184-1187.
[8]	SADE S, KATZIR A. Spectral emissivity and temperature measurements of selective bodies using multiband fiber-optic radiometry[J]. Journal of Applied Physics, 2004, 96(6): 3507-3513. doi: 10.1063/1.1784551 URL
[9]	FU T R, LIU J F, TANG J Q, et al. Temperature measurements of high-temperature semi-transparent infrared material using multi-wavelength pyrometry[J]. Infrared Physics & Technology, 2014, 66:49-55.
[10]	SVET D Y, MOSKALENKO N V. Radiative temperature-measurement in the presence of attenuation due to brown smoke[J]. High Temperature, 1989, 27(5): 783-787.
[11]	ZOU X B, ZHAO J W, POVEY M J W, et al. Variables selection methods in near-infrared spectroscopy[J]. Analytica Chimica Acta, 2010, 667(1/2): 14-32. doi: 10.1016/j.aca.2010.03.048 URL
[12]	孙晓刚, 原桂彬, 戴景民. 基于遗传神经网络的多光谱辐射测温法[J]. 光谱学与光谱分析, 2007, 27(2): 213-216. pmid: 17514938
	SUN Xiaogang, YUAN Guibin, DAI Jingmin. Multi-spectral thermometry based on GA-BP algorithm[J]. Spectroscopy and Spectral Analysis, 2007, 27(2): 213-216. pmid: 17514938
[13]	席剑辉, 徐振方, 傅莉, 等. 红外辐射亮度的RBF网络建模及其光谱发射率估计[J]. 红外与激光工程, 2016, 45(Sup.1): 1-6.
	XI Jianhui, XU Zhenfang, FU Li, et al. Modeling infrared radiance and calculating spectral emissivity based on RBF network[J]. Infrared and Laser Engineering, 2016, 45(Sup.1): 1-6.
[14]	YANG J Z, FENG Z, WANG X D, et al. Research on pipeline blocking state recognition algorithm based on mixed domain feature and KPCA-ELM[J]. International Journal of Computing Science and Mathematics, 2018, 9(5): 442-454. doi: 10.1504/IJCSM.2018.095498 URL
[15]	MAGALLON-BARO A, GRANTON P V, MILDER M T W, et al. A model-based patient selection tool to identify who may be at risk of exceeding dose tolerances during pancreatic SBRT[J]. Radiotherapy and Oncology, 2019, 141:116-122. doi: 10.1016/j.radonc.2019.09.016 URL
[16]	POTAPOV P, LUBK A. Optimal principal component analysis of STEM XEDS spectrum images[J]. Advanced Structural and Chemical Imaging, 2019, 5(1): 1-21. doi: 10.1186/s40679-019-0065-1 URL
[17]	刘嘉蔚, 李奇, 陈维荣, 等. 基于在线序列超限学习机和主成分分析的蒸汽冷却型燃料电池系统快速故障诊断方法[J]. 电工技术学报, 2019, 34(18): 3949-3960.
	LIU Jiawei, LI Qi, CHEN Weirong, et al. Fast fault diagnosis method of evaporatively cooled fuel cell system based on online sequential extreme learning machine and principal component analysis[J]. Transactions of China Electrotechnical Society, 2019, 34(18): 3949-3960.

T/℃	L₁/(W·m^-2· sr^-1·μm^-1)	L₂/(W·m^-2· sr^-1·μm^-1)	…	L₁₄₁/(W·m^-2· sr^-1·μm^-1)
80	0.629	0.671	…	17
85	0.755	0.781	…	17
?	?	?	…	?
1300	24158	23740	…	416

T/℃	L₁/(W·m^-2· sr^-1·mm^-1)	L₂/(W·m^-2· sr^-1·mm^-1)	…	L₁₄₁/(W·m^-2· sr^-1·mm^-1)
80	0.516	0.567	…	13.852
83	0.562	0.614	…	14.117
?	?	?	?	?
180	2.417	2.233	…	17.000