基于高光谱图像和卷积神经网络的燃煤热值估计算法

doi:10.11930/j.issn.1004-9649.201905023

中国电力 ›› 2019, Vol. 52 ›› Issue (9): 148-153.DOI: 10.11930/j.issn.1004-9649.201905023

基于高光谱图像和卷积神经网络的燃煤热值估计算法

杨明花¹, 张克涵²

1. 浙江浙能温州发电有限公司, 浙江温州 325602;
2. 西北工业大学, 陕西西安 710072

收稿日期:2019-05-06 修回日期:2019-08-14 出版日期:2019-09-05 发布日期:2019-09-19
通讯作者: 张克涵(1971-),男,通信作者,副教授,从事控制理论与控制工程研究,E-mail:zhangkehan210@163.com
作者简介:杨明花(1965-),女,高级工程师,从事热工自动化技术研究应用和计量管理工作,E-mail:yangmhwz@163.com
基金资助:
陕西省重点研发计划资助项目（2018GY-193）；浙江省能源集团有限公司科技项目（ZJNY-2014-010）。

Coal Calorific Value Estimation Algorithm Based on Hyperspectral Image and Convolutional Neural Network

YANG Minghua¹, ZHANG Kehan²

1. Zhejiang Zheneng Wenzhou Power Generation Co., Ltd., Wenzhou 325602, China;
2. Northwestern Polytechnical University, Xi'an 710072, China

Received:2019-05-06 Revised:2019-08-14 Online:2019-09-05 Published:2019-09-19
Supported by:
This work is supported by Shaanxi Province's Key Research and Development Program (No.2018GY-193) and Science and Technology Program of Zhejiang Energy Group Co., Ltd.(No. ZJNY-2014-010).

摘要/Abstract

摘要： 火力发电是中国主要的发电方式，煤质优劣直接决定着发电厂的安全生产、经济效益，而收到基低位发热量是煤质优劣的关键指标之一。针对目前煤炭发热量测量程序复杂、不易实时监测等问题，基于高光谱图像和卷积神经网络，提出一种方便、快速的热值估计算法。通过高光谱数据采集系统对煤样进行光谱成像，经过高斯低通滤波以及主成分分析，消除采集噪声以及光谱通道之间的数据冗余性；然后采用邻域均值化数据采集方法获得平滑的训练数据与测试数据，搭建7层的卷积神经网络；通过实验验证了所提方法的有效性，结果显示该方法具有较高的预测精度。

关键词: 火力发电, 收到基低位发热量, 高光谱图像, 主成分分析, 卷积神经网络

Abstract: Thermal power generation is still the major power generation mode in China. Since the quality of coal quality directly determines the safe production and economic benefits of power plants, net calorific value as received basis has become one of the key indicators of coal quality. Regarding the current problems such as complicated measurement procedures of coal calorific value and limitations of the general method in situations where real-time monitoring is required, this paper proposes a convenient and fast calorific value estimating algorithm based on hyperspectral image and convolutional neural network. Firstly, the image data of coal is collected by the hyperspectral data acquisition system. After Gaussian low-pass filtering and principal component analysis, the noise and data redundancy between spectral channels are eliminated. Then, the smooth training and test data are obtained by using the neighborhood average filtering and a 7-layer convolutional neural network is established. Finally, the effectiveness of the proposed method is verified by experiments. The results show that the method has high prediction accuracy.

Key words: thermal power generation, net calorific value as received basis, hyperspectral image, principal component analysis, convolutional neural network

中图分类号:

TP273

杨明花, 张克涵. 基于高光谱图像和卷积神经网络的燃煤热值估计算法[J]. 中国电力, 2019, 52(9): 148-153.

YANG Minghua, ZHANG Kehan. Coal Calorific Value Estimation Algorithm Based on Hyperspectral Image and Convolutional Neural Network[J]. Electric Power, 2019, 52(9): 148-153.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201905023

https://www.electricpower.com.cn/CN/Y2019/V52/I9/148

参考文献

[1] 李海永, 杨濮亦. 火电厂入炉煤低位热值实时测量的研究及其应用[J]. 电力建设, 2013, 34(10):60-64
LI Haiyong, YANG Puyi. Research and application of real-time measurement for lower calorific value of burning coal in coal-fired power plants[J]. Electric Power Construction, 2013, 34(10):60-64
[2] 刘伟平, 刘德俊. 基于SVR的在线热值仪校正算法[J]. 石油化工自动化, 2015, 51(6):50-54
LIU Weiping, LIU Dejun. Correction algorithm for SVR based online calorimeter[J]. Automation in Petro-Chemical Industry, 2015, 51(6):50-54
[3] 陈盛君. 煤的恒容低位热值的快速测量[J]. 化肥工业, 2005, 33(3):37-41
CHEN Shengjun. Rapid determination of constant volume low heating value of coal[J]. Chemical Fertilizer Industry, 2005, 33(3):37-41
[4] 陈勇. 煤炭热值测量不确定度的分析[J]. 煤化工, 2003, 105(2):13-19
CHEN Yong. Analysis of uncertainty in measurement of coal calorific value[J]. Coal Chemical Industry, 2003, 105(2):13-19
[5] 郭瑞君, 秦成果, 张澎涛, 等. 基于热值校正的适应煤质变化协调控制系统研究[J]. 内蒙古电力技术, 2010, 28(4):5-9
GUO Ruijun, QIN Chengguo, ZHANG Pengtao, et al. Research of coordinated control system adaptation to coal quality variation based on caloricity calibration[J]. Inner Mongolia Electric Power, 2010, 28(4):5-9
[6] 王帝, 陆继东, 董美蓉, 等. LIBS对煤中热值检测的新型校正模型[J]. 光谱学与光谱分析, 2016, 36(8):2607-2612
WANG Di, LU Jidong, DONG Meirong, et al. A new calibrated model of coal calorific value detection with LIBS[J]. Spectroscopy and Spectral Analysis, 2016, 36(8):2607-2612
[7] 高楠. 论近红外光谱技术在煤质检测分析中的应用[J]. 能源与节能, 2016(2):186-187
GAO Nan. On the application of near infrared spectral analysis technology in coal quality testing analysis[J]. Energy and Energy Conservation, 2016(2):186-187
[8] 陈民. 近红外光谱分析技术在煤质分析中的应用[J]. 科技创新导报, 2015, 12(34):99-101
CHEN Min. Application of near infrared spectroscopy in coal quality analysis[J]. Science and Technology Innovation Herald, 2015, 12(34):99-101
[9] 雷萌, 李明. 采用KPCA特征提取的近红外煤炭发热量预测模型[J]. 化工学报, 2012, 63(12):3991-3995
LEI Meng, LI Ming. NIRS prediction model of calorific value of coal with KPCA feature extract[J]. CIESC Journal, 2012, 63(12):3991-3995
[10] RUSSAKOVSKY O, DENG J, SU H, et al. Imagenet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015,115(3):211-252.
[11] HINTON G, DENG Li, YU Dong, et al. Deep neural networks for acoustic modeling in speech recognition[J]. IEEE Signal Processing Magazine, 2012(29):82-97.
[12] 王月兰, 马增益, 尤海辉, 等. 基于自适应神经模糊推理系统的煤粉锅炉飞灰含碳量建模[J]. 热力发电, 2018, 44(1):26-32
WANG Yuelan, MA Zengyi, YOU Haihui, et al. Modelling for unburned carbon content in fly ash from coal-fired boilers based on adaptive neuro-fuzzy inference system[J]. Thermal Power Generation, 2018, 44(1):26-32
[13] 杨国田, 张涛, 王英男, 等. 基于长短期记忆神经网络的火电厂NO_x排放预测模型[J]. 热力发电, 2018, 44(10):12-17
YANG Guotian, ZHANG Tao, WANG Yingnan, et al. Prediction model for NO_x emissions from thermal power plants based on long-short-term memory neural network[J]. Thermal Power Generation, 2018, 44(10):12-17
[14] 郭强, 刘伟平. 基于支持向量机的裂解炉燃料气热值软测量[J]. 石油化工自动化, 2014, 50(5):38-41
GUO Qiang, LIU Weiping. Soft measurement of calorific value for cracking furnace based on support vector machine[J]. Automation in Petro-Chemical Industry, 2014, 50(5):38-41
[15] 杨思远, 徐佩亮, 王振雷. 基于小波神经网络的热值软测量建模[J]. 石油化工自动化, 2011, 47(4):34-37
YANG Siyuan, XU Peiliang, WANG Zhenlei. Modeling of soft measurement for calorific values based on wavelet neural network[J]. Automation in Petro-Chemical Industry, 2011, 47(4):34-37
[16] 李越胜, 卢伟业, 赵静波, 等. 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[J]. 光谱学与光谱分析, 2017, 38(8):2575-2579
LI Yuesheng, LU Weiye, ZHAO Jingbo, et al. Detection of caloric value of coal using laser-induced breakdown spectroscopy combined with BP Neural networks[J]. Spectroscopy and Spectral Analysis, 2017, 38(8):2575-2579
[17] MANOLAKIS D, SHAW G. Detection algorithms for hyperspectral imaging applications[J]. IEEE Signal Processing Magazine, 2002, 19(1):29-43.
[18] ELMASRY G, SUN D W, ALLEN P. Near-infrared hyperspectral imaging for predicting colour, pH and tenderness of fresh beef[J]. Journal of Food Engineering, 2012, 110(1):127-140.
[19] KAMRUZZAMAN M, ELMASRY G, SUN D W, et al. Non-destructive prediction and visualization of chemical composition in lamb meat using NIR hyperspectral imaging and multivariate regression[J]. Innovative Food Science & Emerging Technologies, 2012, 16:218-226.
[20] GOWEN A A, O'DONNELL C P, CULLEN P J, et al. Hyperspectral imaging-an emerging process analytical tool for food quality and safety control[J]. Trend in Food Science & Technology, 2007, 18(12):590-598.
[21] 阮秋琦, 阮宇智.数字图像处理[M]. 北京:北京电子工业出版社, 2007:93.
[22] 李航. 统计学习方法[M]. 北京:清华大学出版社, 2012:79.

基于高光谱图像和卷积神经网络的燃煤热值估计算法

Coal Calorific Value Estimation Algorithm Based on Hyperspectral Image and Convolutional Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[2]	娄奇鹤, 李荣盛, 谭捷, 袁铁江. 基于卷积神经网络的暂稳极限功率计算[J]. 中国电力, 2024, 57(4): 211-219.
[3]	张兴平, 王腾, 张馨月, 张浩楠. 基于多智能体深度确定策略梯度算法的火力发电商竞价策略[J]. 中国电力, 2024, 57(11): 161-172.
[4]	周颖, 白雪峰, 王阳, 邱敏, 孙冲, 武亚杰, 李彬. 面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判[J]. 中国电力, 2024, 57(1): 9-17.
[5]	王大兴, 宁妍, 汪敬培, 徐洋, 毕峻, 周铭标, 王鹏. 构建新型电力系统背景下的微电网鲁棒简化建模[J]. 中国电力, 2024, 57(1): 148-157.
[6]	皮志勇, 朱益, 廖玄, 李振兴, 方豪, 吴沛. 基于深度学习的智能变电站通信链路故障定位方法[J]. 中国电力, 2023, 56(7): 136-145.
[7]	陆友文, 崔昊, 陈佳宁, 彭祥佳, 冯双, 刘栋. 基于RA-CNN和同步相量的风电场次/超同步振荡参数智能辨识方法[J]. 中国电力, 2023, 56(4): 46-55,67.
[8]	武小琳, 栾凌, 潘连武, 李海龙. 基于LM-CNN的输变电工程造价自动计算模型[J]. 中国电力, 2023, 56(2): 157-163.
[9]	陈子含, 滕伟, 胥学峰, 丁显, 柳亦兵. 基于图卷积网络和风速差分拟合的中长期风功率预测[J]. 中国电力, 2023, 56(10): 96-105.
[10]	陈正雄, 帕孜来·马合木提, 沈玮. 基于改进支持向量回归的IGBT老化预测[J]. 中国电力, 2022, 55(7): 1-10.
[11]	冯裕祺, 李辉, 李利娟, 周彦博, 谭貌, 彭寒梅. 基于CNN-GRU的光伏电站电压轨迹预测[J]. 中国电力, 2022, 55(7): 163-171.
[12]	艾欣, 胡寰宇, 任大鹏, 彭冬, 刘汇川, 薛雅玮, 张天琪. 电网发展诊断的改进模糊评价模型与评级[J]. 中国电力, 2022, 55(5): 66-75,165.
[13]	赵洪山, 李静璇. 基于PSR和改进灰色TOPSIS的园区客户能效评估模型[J]. 中国电力, 2022, 55(3): 203-212.
[14]	沙骏, 徐雨森, 刘冲冲, 冯定东, 胥峥, 臧海祥. 基于变分模态分解和分位数卷积-循环神经网络的短期风功率预测[J]. 中国电力, 2022, 55(12): 61-68.
[15]	刘金森, 罗宁, 王杰, 徐常, 曹毅, 刘志文. 基于海量场景降维的配电网源网荷储协同规划[J]. 中国电力, 2022, 55(12): 78-85.

模态框（Modal）标题

基于高光谱图像和卷积神经网络的燃煤热值估计算法

Coal Calorific Value Estimation Algorithm Based on Hyperspectral Image and Convolutional Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics