A Fast Calculation Method of Gas Infrared Radiation Characteristics at High Temperature based on Radial Basis Function Neural Network

被引：0
|
作者：
Meng, Xiaying [1 ]
Du, Jun [1 ]
Wang, Biao [1 ]
Zhang, Yutao [1 ]
Gu, Dandan [1 ]
Qiu, Jian [2 ]
机构：
[1] Sci & Technol Electromagnet Scattering Lab, Shanghai, Peoples R China
[2] Aero Engine Corp China, Commercial Aircraft Engine, Shanghai, Peoples R China
来源：
2021 OPTOELECTRONICS GLOBAL CONFERENCE (OGC 2021) | 2021年
基金：
中国国家自然科学基金;
关键词：
gas infrared radiation; radial basis function neural network; fast algorithm; absorption coefficient;
D O I：
10.1109/OGC52961.2021.9654421
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
The radiation characteristics of high temperature gas are of great significance for infrared target detection. In this paper, a calculation method of high temperature gas radiation characteristics with high calculation efficiency is proposed. The calculation model of CO2 absorption coefficient at 2001-2450 cm(-1) band is established by using radial basis function neural network (RBFNN). In RBFNN model, the most accurate line by line (LBL) method is utilized to generate training samples. The input parameters are gas temperature, pressure and component concentration, and the output parameter is absorption coefficient. The results show that, compared with LBL method, RBFNN model has higher accuracy and is insensitive to input. After RBFNN training, RBFNN has higher computational efficiency while ensuring computational accuracy.
引用
收藏
页码：82 / 86
页数：5
相关论文
共 50 条
  • [1] Study on Infrared Radiation of Exhaust Gas Based on Nonlinear Calibration and Radial Basis Function Neural Network Correction
    Zhao, Yao
    Luo, Qing-Guo
    Qiu, Mian-Hao
    Liu, Hong-Bin
    JOURNAL OF NANOELECTRONICS AND OPTOELECTRONICS, 2020, 15 (09) : 1059 - 1068
  • [2] A Method for Fast Establishing Tropospheric Refractivity Profile Model Based on Radial Basis Function Neural Network
    Ma, Tao
    Liu, Heng
    Zhang, Yu
    PROGRESS IN ELECTROMAGNETICS RESEARCH M, 2019, 86 : 93 - 102
  • [3] A method for fast establishing tropospheric refractivity profile model based on radial basis function neural network
    Ma T.
    Liu H.
    Zhang Y.
    Progress In Electromagnetics Research M, 2019, 86 : 93 - 102
  • [4] Camera calibration method based on radial basis function neural network
    Liu Ding
    Yan Zhen-jie
    Liang Yan-ming
    Yang Yan-xi
    Proceedings of 2004 Chinese Control and Decision Conference, 2004, : 459 - 461
  • [5] Grating subdivision method based on radial basis function neural network
    Guo, Yu-Mei
    Guan, Rui
    Zhong, Yuan
    Shenyang Gongye Daxue Xuebao/Journal of Shenyang University of Technology, 2011, 33 (02): : 193 - 197
  • [6] An ultrafast and high accuracy calculation method for gas radiation characteristics using artificial neural network
    Cui, Juntao
    Zhang, Jianqi
    Dong, Cunquan
    Liu, Delian
    Huang, Xi
    INFRARED PHYSICS & TECHNOLOGY, 2020, 108
  • [7] The ridge method in a radial basis function neural network
    Praga-Alejo, Rolando J.
    Gonzalez-Gonzalez, David S.
    Cantu-Sifuentes, Mario
    Torres-Trevino, Luis M.
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2015, 79 (9-12): : 1787 - 1796
  • [8] The ridge method in a radial basis function neural network
    Rolando J. Praga-Alejo
    David S. González-González
    Mario Cantú-Sifuentes
    Luis M. Torres-Treviño
    The International Journal of Advanced Manufacturing Technology, 2015, 79 : 1787 - 1796
  • [9] The ridge method in a radial basis function neural network
    20151100633482
    Praga-Alejo, Rolando J. (rolandopraga@comimsa.com), 1787, Springer London (79): : 9 - 12
  • [10] Stable temperature calibration method of fiber Bragg grating based on radial basis function neural network
    An, Yang
    Wang, Xiaocen
    Qu, Zhigang
    Liao, Tao
    Wu, Liqun
    Nan, Zhongliang
    OPTICAL ENGINEERING, 2019, 58 (09)
12345