Inversion of Particle Size Distribution in Spectral Extinction Measurements Using PCA and BP Neural Network Algorithm
PING Li1, ZHAO Rong1, YANG Bin1*, YANG Yang1, CHEN Xiao-long2, WANG Ying1
1. School of Energy and Power Engineering/Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
2. Shanghai Space Propulsion Technology Research Institute, Shanghai 201109, China
Abstract：Spectral extinction method is widely used in the field of Particle Size Distribution (PSD) measurement. During the inversion process of particle size by spectral extinction method, the speed and accuracy of the whole inversion process are greatly affected due to the problems of complex theory, complicated calculation, slow convergence speed and unstable solution of particle extinction coefficient. Moreover, in the extinction data of many wavelengths, there is more repeated redundant information, which also greatly increases the time of the inversion algorithm. Aiming at the problems of complicated calculation and low inversion efficiency of spectral extinction PSD inversion algorithm, a spectral PSD analysis method based on Principal Component Analysis (PCA) and Back Propagation (BP) neural network was proposed. Based on Mie scattering theory, the spectral extinction values under different particle sizes and wavelengths were simulated and calculated. Through the PCA of the spectral extinction data set and the calculation of the comprehensive load coefficient of each wavelength, the optimal characteristic wavelength was selected. The PCA-BP neural network model was trained by using the reduced spectral extinction data, and the PSD was calculated by using the network model. Through simulation calculation, the prediction accuracy of PCA-BP neural network model was compared with the traditional BP neural network model, and the influence of wavelengths number on the prediction results of the two neural network models was analyzed. Based on the trained PCA-BP neural network model, the verification experiment of spectral extinction inversion algorithm of PSD was carried out, and an experimental system for PSD measurement by spectral extinction method is established. Six types of standard polystyrene particles with different particle size parameters ranging from 0.5 to 9.7 μm were measured. Simulation and experimental results show that the correlation between each wavelength vector can be determined based on the PCA method, and the extinction value corresponding to the optimal characteristic wavelength can be selected by using the comprehensive load coefficient, which has good representativeness of the overall spectral data and can realize the dimensionality reduction of spectral data. Compared with the traditional BP neural network model, the analysis method of PSD based on the PCA-BP neural network model has higher prediction accuracy and has more obvious advantages for predicting distribution parameters of more dispersed particle systems. Moreover, when the number of selected wavelengths is small, the PCA-BP neural network model still has high prediction accuracy. The trained PCA-BP neural network model is used to verify the particle size parameters experimentally. The PSD prediction results can be output instantaneously, and the error is within 5%, which verifies the algorithm’s feasibility.
基金资助: the National Natural Science Foundation of China (51806144), the Natural Science Foundation of Shanghai (20ZR1455200), Shanghai Rising-Star Program(19QC1400200)
通讯作者:
杨 斌
E-mail: yangbin@usst.edu.cn
作者简介: PING Li, (1993—), Ph D. candidate, University of Shanghai for Science and Technology e-mail:
usst_pl@163.com
引用本文:
平 力，赵 蓉，杨 斌，杨 杨，陈晓龙，王 莹. 基于PCA-BP神经网络的光谱消光法颗粒粒径反演算法研究[J]. 光谱学与光谱分析, 2021, 41(11): 3639-.
PING Li, ZHAO Rong, YANG Bin, YANG Yang, CHEN Xiao-long, WANG Ying. Inversion of Particle Size Distribution in Spectral Extinction Measurements Using PCA and BP Neural Network Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3639-.
[1] CAI Xiao-shu, SU Ming-xu, SHEN Jian-qi. Technology and Applications of Particle Size Measurement. Beijing: Chemical Industry Press, 2010.
[2] QI Hong, RUAN Liming, WANG Shenggang, et al. Chinese Optics Letters, 2008, 6(5): 346.
[3] Onofri F R A, Barbosa S, Touré O, et al. Journal of Quantitative Spectroscopy & Radiative Transfer, 2013, 126: 160.
[4] HUANG Xing. Doctoral Dissertation. Harbin Institute of Technology, 2019.
[5] LIU Hao, ZHOU Wu, CAI Xiao-shu, et al. Chinese Journal of Power Engineering, 2015, 35(10): 816.
[6] He Zhenzong, Qi Hong, Yao Yuchen, et al. Journal of Quantitative Spectroscopy and Radiative Transfer, 2014, 149: 117.
[7] WANG Chen, ZHANG Biao, CAO Li-xia, et al. Acta Optica Sinica, 2019, 39(2): 214.
[8] ZHAO Rong, PAN Ke-wei, YANG Bin, et al. Acta Optica Sinica, 2020, 40(7): 108.
[9] ZHOU Yi, CHEN Jun, YANG Huinan, et al. Results in Physics, 2018, 10: 22.
[10] Vargas-Ubera J, Aguilar F J, Gale M D. Applied Optics, 2007, 46(1): 124.
[11] Riefler N, Wriedt T. Particle & Particle Systems Characterization, 2008, 25(3): 216.
[12] XU Feng, CAI Xiaoshu, REN Kuanfang, et al. China Particuology, 2004, 2(6): 235.
[13] WANG Li, SUN Xiao-gang. Spectroscopy and Spectral Analysis, 2013, 33(3): 618.
[14] HE Zhenzong, QI Hong, Chen Qin, et al. Particuology, 2016, 28(5): 6.
[15] ZHANG Biao, LI Shu, XU Chuan-long, et al. Journal of Central South University·Science and Technology, 2016, 47(11): 3922.
[16] WANG Li. Doctoral Dissertation. Harbin Institute of Technology, 2013.
[17] Li M, Frette T, Wilkinson D. Industrial & Engineering Chemistry Research, 2001, 40(21): 4615.
