第34卷，第10期 2014年10月
光谱学与光谱分析 Spectroscopy and Spectral Analysis
Vol. 34,No. 10 -pp2792-2798
October.2014
Model Research of Electric Coal Calorific Value Based on Near Infrared Frequency Domain Self-Adaption AnalysisMethod
LI Zhi?, WANG Sheng-haol.2*, ZHAO Yong', WANG Xiang-feng", LI Yao-zheng 1. College of Information Science and Engineering , Northeastern University , Shenyang110819 , China
2. Key Laboratory of Liaoning Electrie Power Simulation & Control , Shenyang Institute of Engineering , Shenyang 110136 , China 3. Centre of Simulation , Shenyang Institute of Engineering , Shenyang110136, China
4. School of Power and Mechanical Engineering , Wuhan University of China , Wuhan430072, China
Abstract At present , because the blending coal was taken in some power stations as the major fuel which has too complex physical and chemical characters to build accurate normal near infrared quantitative models in some cases , which brought difficulties for on-line electric coal calorific value detection . For this reason , it was care-fully studied that the time domain and frequency domain properties of the power generation coal near infrared spectra , and w as proposed that a new quantitative near infrared method named frequency domain self -adaption analysis . The first step , time domain near infrared spectra are converted into frequency domain near infrared signal by Fast Fourier Transform ; The second step , the suitable frequency information range by means of valid spectra energy parameter ry was obtained by this method ; The third step , it was constructed that an informa-tion volume parameter which is formed by correlation coefficient , standard deviation spectra and coordinate of harmonic in frequency domain to initialize the regression model input parameters ' position ; Finally , the opti-mal model is established by way of discrete frequency domain scooping and synthesized performance function At the same time, compared with the principle component regression , partial least squares regression , back propagation artificial network , support vector regression and partial least squares regression optimized by ge-netic algorithm models , it is acquired that a more accurate method which can effectively avoid over fitting and virtual effective models and has a very useful application prospect by verifying the electric coal calorific value Additionally , this method can be used in other quantitative spectra analysis -
Keywords Near infrared spectra ; Fast Fourier transform ; Frequency domain self-adaption analysis method ; Calorific value of electric coal ; Quantitative analysis model
中图分类号：0657.3
Introduction
文献标识码：A
DOI : 10, 3964 /j. issn. 1000-0593 (2014)10-2792-07
er. At present , as the general method to obtain that parame-ter is X-ray fluorescence or neutron activation analysis which has radioactivity to human body , so they have not been ap-plied widelyl-a] , In this ease , near-infrared (NIR) technique
The calorific value of the power generation coal is an im -
portant data to optimize the combustion condition of the burn -Received : 2014-05-24 ; accepted; 2014-07-30
appears with so many advantages such as pollution-free , fast
Foundation item : National Natural Science Foundation of China (61371200)
Biography : LI Zhi , (1964—), professor level senior engineer , Ph .D ., master supervisor
W ANG Sheng-hao , (1981—), Ph .D . student of detection technology and automation equipment in Northeastern University , engi-neer in Key Laboratory of Liaoning Electric Power Simulation Control in Shenyang Institute of Engineering , researching on diree-
tion of NIR online power station coal quality detection
LI Zhi and WANG Sheng-hao : joint first authors
e-mail : wangyiwzzy@ 163 -com
Corresponding author