Modeling infrared radiance and calculating spectral emissivity based on RBF network

Xi Jianhui; Xu Zhenfang; Fu Li; Wang Qi

doi:10.3788/IRLA201645.S104004

A method of modeling infrared radiance based on RBF neural network was built, then the target spectral emissivity was estimated. When measuring the infrared radiation characteristics of the target surface in the 3-14 m band by FTIR spectrometer, the infrared radiance will be absorbed by carbon dioxide, water vapor, etc, and affected by some stray radiation. In this paper, the effective learning samples were firstly selected combined with the theory of infrared transmission. Then the samples based on the RBF network were fully learned, and a target infrared radiance model was built. And this model was used to estimate the radiance in the band of atmospheric absorption and stray radiation. A more complete target spectral emissivity curve was finally calculated. Compared the calculating results of blackbody with theoretical emissivity, the maximum relative error is 1.5%. The verification of temperature measurement also shows that the RBF neural networks can be built efficiently to estimate target spectral emissivity.

Modeling infrared radiance and calculating spectral emissivity based on RBF network

1. School of Automation,Shenyang Aerospace University,Shenyang 110136,China

Received Date: 2016-02-05

Rev Recd Date: 2016-03-03

Publish Date: 2016-05-25

Key words:

Abstract: A method of modeling infrared radiance based on RBF neural network was built, then the target spectral emissivity was estimated. When measuring the infrared radiation characteristics of the target surface in the 3-14 m band by FTIR spectrometer, the infrared radiance will be absorbed by carbon dioxide, water vapor, etc, and affected by some stray radiation. In this paper, the effective learning samples were firstly selected combined with the theory of infrared transmission. Then the samples based on the RBF network were fully learned, and a target infrared radiance model was built. And this model was used to estimate the radiance in the band of atmospheric absorption and stray radiation. A more complete target spectral emissivity curve was finally calculated. Compared the calculating results of blackbody with theoretical emissivity, the maximum relative error is 1.5%. The verification of temperature measurement also shows that the RBF neural networks can be built efficiently to estimate target spectral emissivity.

HTML

Reference (11)

[1]	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. (in Chinese)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.
[2]	Lv Jianwei, Wang Qiang. Effect of temperature and emissivity of aircraft skin on infrared radiation characteristics[J]. Opto-Electronic Engineering, 2009, 36(2):50-54. (in Chinese)吕建伟, 王强. 飞行器表面温度和发射率分布对红辐射特征的影响[J]. 光电工程, 2009, 36(2):50-54.
[3]	Luo Mingdong, Ji Honghu, Huang Wei, et al. Research on measurement method of mid-IR spectral radiant intensity of exhaust system with FTIR spectrometer[J]. Journal of Aerospace Power, 2007, 22(9):1423-1429. (in Chinese)罗明东, 吉洪湖, 黄伟, 等. 用FTIR光谱仪测量排气系统中红外光谱辐射强度的方法[J]. 航空动力学报, 2007, 22(9):1423-1429.
[4]	Dai Jingmin, Song Yang, Wang Zongwei. Review of spectral emissivity measurement[J]. Infrared and Laser Engineering, 2009, 38(4):710-715. (in Chinese)戴景民, 宋杨, 王宗伟. 光谱发射率测量技术[J]. 红外与激光工程, 2009, 38(4):710-715.
[5]	Wang Zongwei, Dai Jingmin, He Xiaowa, et al. The linearity analysis of ultrahigh temperature FTIR spectral emissivity measurement system[J]. Spectroscopy and Spectral Analysis, 2012, 32(2):313-316. (in Chinese)王宗伟, 戴景民, 何小瓦, 等. 超高温FTIR光谱发射率测量系统的线性度分析[J]. 光谱学与光谱分析, 2012, 32(2):313-316.
[6]	Yu Hai, Liang Lihui, Wang Shujie, et al. Error compensation for high precision reference encoder based on RBF neural networks[J]. Infrared and Laser Engineering, 2014, 43(12):4123-4127. (in Chinese)于海, 梁立辉, 王树洁, 等. 基于径向基函数神经网络的高精度基准编码器误差补偿[J]. 红外与激光工程, 2014, 43(12):4123-4127.
[7]	Liu Yanju, Kou Guohao, Song Jianhui. Target recognition based on RBF neural network[J]. Fire Control Command Control, 2015, 40(8):9-13. (in Chinese)刘砚菊, 寇国豪, 宋建辉. 基于RBF神经网络的空中目标识别技术[J]. 火力与指挥控制, 2015, 40(8):9-13.
[8]	Ishii J, Ono A. Uncertainty estimation for emissivity measurements near room temperature with a Fourier transform spectrometer[J]. Measurement Science and Technology, 2001, 12:2103-2112.
[9]	Luo Mingdong, Sang Jianhua, Huang Wei, et al. Investigation of calibration method and test application of FTIR spectrometer at 8-14m band[J]. Measurement Control Technology, 2013, 32:171-175. (in Chinese)罗明东, 桑建华, 黄伟, 等. FTIR光谱仪8~14m红外波段定标方法及测试应用[J]. 测控技术, 2013, 32:171-175.
[10]	Zhang Jianqi. Infrared Physics[M]. 2nd ed. Xi'an:Xidian University Press, 2013:128. (in Chinese)张建奇. 红外物理[M]. 第2版. 西安:西安电子科技大学出版社, 2013:128.
[11]	Chen S, Cowan C F N, Grant P M. Orthogonal least squares learning algorithm for radial basis function networks[J]. IEEE Trans Neural Networks, 1991, 2(2):302-309.

Modeling infrared radiance and calculating spectral emissivity based on RBF network

doi: 10.3788/IRLA201645.S104004

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views