Model Research of Electric Coal Calorific Value Based on Near Infrared Frequency Domain Self-Adaption Analysis Method
LI Zhi2, WANG Sheng-hao1,2*, ZHAO Yong1, WANG Xiang-feng3, LI Yao-zheng4
1. College of Information Science and Engineering, Northeastern University, Shenyang 110819, China 2. Key Laboratory of Liaoning Electric Power Simulation & Control, Shenyang Institute of Engineering, Shenyang 110136, China 3. Centre of Simulation, Shenyang Institute of Engineering, Shenyang 110136, China 4. School of Power and Mechanical Engineering, Wuhan University of China, Wuhan 430072, 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 carefully studied that the time domain and frequency domain properties of the power generation coal near infrared spectra, and was 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 ηE was obtained by this method; The third step, it was constructed that an information 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 optimal 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 genetic 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.
Key words:Near infrared spectra;Fast Fourier transform;Frequency domain self-adaption analysis method;Calorific value of electric coal;Quantitative analysis model
李 智2,王圣毫1,2*,赵 勇1,王祥凤3,李耀铮4 . 基于近红外频域自适应分析法的电煤发热量模型研究 [J]. 光谱学与光谱分析, 2014, 34(10): 2792-2798.
LI Zhi2, WANG Sheng-hao1,2*, ZHAO Yong1, WANG Xiang-feng3, LI Yao-zheng4 . Model Research of Electric Coal Calorific Value Based on Near Infrared Frequency Domain Self-Adaption Analysis Method. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(10): 2792-2798.
[1] Liu X, Bansal R C. Energy Conversion and Management, 2012,56: 53. [2] Tillman D, Dao D. Fuel Process Technol., 2007, 88: 1094. [3] Lim C S, Abernethy D A. Applied Radiation and Isotopes, 2005,63(5): 697. [4] Damir Sorak, Lars Herberholz, Sylvia Iwascek, et al. Applied Spectroscopy Reviews, 2012,47(2): 83. [5] Andrés J M, Bona M T. Anal. Chim. Acta, 2005, 535(11): 123. [6] Andrés J M, Bona M T. Talanta, 2006, 70: 711. [7] Bona M T, Andrés J M. Talanta, 2007, 72: 1423. [8] Kim D W, Lee J M, Kim J S. Korean J. Chem. Eng., 2009, 26(2): 489. [9] Lei Meng, Li Ming. CIESC Journal, 2012,63(12): 3991. [10] Chu Xiao-li, Yuan Hong-fu, Lu Wan-zhen. Progress in Chemistry, 2004, 16(4):528. [11] Wu W, Walczak B, Penninckx W, et al. Anal. Chim. Acta, 1996, 331: 75. [12] Luisa Pasti, Delphine Jouan-Rimbaud, et al. Anal. Chim. Acta, 1998, 364: 253. [13] Li Z, Wang S H, Zheng W P, et al. J. Instrum. Anal., 2012, 31(3): 343. [14] Mitra S K. Digital Signal Processing: A Computer-Based Approach Four Edition. Translated by Yu X Y. Beijing: Electronics Industry Press, 2004. [15] GB/T 213—2008. Determination of Calorific Value of Coal. National Standards of the People’s Republic of China.