基于BP神经网络和激光诱导击穿光谱的燃煤热值快速测量方法研究

doi:10.3964/j.issn.1000-0593(2017)08-2575-05

Abstract
References
Related Citation (15)

Download: PDF (1129 KB)
Export: BibTeX | EndNote (RIS)

Abstract As a major indicator of coal property, the high accuracy and fast calorific value quantitative analysis plays a significant role in combustion efficiency and economic operation. Laser-induced breakdown spectroscopy (LIBS) was proposed to calibrate the calorific value of 35 coal samples combined with BP neural networks and cluster analysis. The calibration curve established on a certain type of coal samples can not be applied directly to the quantitative analysis for different types of coal considering the influence of matrix effect on the LIBS spectral data. Three different groups were classified with K-means clustering method according to the calorific value, ash content and volatile matter. The training set and the prediction set were optimized. Based on the correlation analysis of analytical line intensity and calorific value, taking into account the physical meaning of the analytical line, the peak intensity of 12 elements was taken as the input parameter of BP neural network model which was established for calorific value analysis of coal samples. The performance of the BP network and the comparison result of 3 different groups samples were studied. The result indicate that the R² value of calibration curve is 0.996, relative error (RE) and the relative standard deviation (RSD) of calorific value is less than 3.42% and 4.23%, respectively, performing good results of repeated measurement. The calibration curve has different prediction ability for three group coal samples. The influence of experimental parameter fluctuation and matrix effect was reduced in a certain degree using peak intensity as the input parameter. The repeatability and accuracy of quantitative analysis results can be further improved by establishing BP neutral network for various type of coal samples specifically. The analytical results of calorific value based on LIBS technology combined with BP neural network were well predicted, which was potentially proven as a promising technologyy for fast on-line analysis.

Key words：Slaser-induced breakdown spectroscopy; BP neural network; Cluster analysis; Calorific value; Quantitative analysis

Received: 2016-06-27 Accepted: 2016-10-19

ZTFLH:

O433.5

Corresponding Authors: YAO Shun-chun E-mail: epscyao@scut.edu.cn

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2017)08-2575-05 OR https://www.gpxygpfx.com/EN/Y2017/V37/I08/2575

[1] YAO Shun-chun, CHEN Jian-chao, LU Ji-dong, et al(姚顺春, 陈建超, 陆继东, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015, 35(6): 1719.
[2] Li X, Yin H, Wang Z, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2015, 111: 102.
[3] Zhang L, Hu Z Y, Yin W B, et al. Frontiers of Physics, 2012, 7: 690.
[4] Li X, Wang Z, Fu Y, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2014, 99(9): 82.
[5] Yuan T, Wang Z, Lui S L, et al. Journal of Analytical Atomic Spectrometry, 2013, 28(7): 1045.
[6] LIU Li-tuo, LIU Jian-guo, ZHAO Nan-jing, et al(刘立拓, 刘建国, 赵南京, 等). Chinese Journal of Lasers(中国激光), 2011, 38(s1).
[7] LI Zhong, LIU Ming-di, JI Shou-xiang(李仲, 刘明地, 吉守祥). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(3): 720.
[8] MENG De-shuo, ZHAO Nan-jing, MA Ming-jun, et al(孟德硕, 赵南京, 马明俊, 等). Journal of Optoelectronics·Laser(光电子·激光), 2015, 10: 1984.
[9] SANG Hai-feng, GU De-shan, WANG Fu-li, et al(桑海峰, 谷德山, 王福利, 等). Journal of Northeast Normal University·Natural Science Edition(东北师大学报·自然科学版), 2005, 37(1): 46.
[10] SUN Lan-xiang, YU Hai-bin, CONG Zhi-bo, et al(孙兰香, 于海斌, 丛智博, 等). Acta Optica Sinica(光学学报), 2010, 30(9): 2757.
[11] Romero C E, Saro R D, Craparo J, et al. Energy & Fuels, 2009, 24(1): 510.
[12] Samarasinghe, Sandhya. Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition(神经网络在应用科学和工程中的应用：从基本原理到复杂模式的识别). Translated by SHI Xiao-xia, CHEN Yi-min(史晓霞, 陈一民, 译). Beijing: China Machine Press(北京：机械工业出版社), 2010.
[13] Yao S, Lu J, Dong M, et al. Applied Spectroscopy, 2011, 65(10): 1197.
[14] DING Shi-fei, ZHAO Xiang-wei, et al(丁世飞, 赵相伟, 等). Modern Data Analysis and Information Pattern Recognition(现代数据分析与信息模式识别). Beijing: Science Press(北京：科学出版社), 2012.
[15] Zhang Y, Ruan G. Bernoulli Neural Network with Weights Directly Determined and with the Number of Hidden-Layer Neurons Automatically Determined. Springer Berlin Heidelberg, 2009. 36.