一种基于 Parzen 窗估计的鲁棒 ELM 烧结温度检测方法

陈华; 章兢; 张小刚; 胡义函

doi:10.3724/SP.J.1004.2012.00841

一种基于 Parzen 窗估计的鲁棒 ELM 烧结温度检测方法

doi: 10.3724/SP.J.1004.2012.00841

陈华^1,2,
章兢^1,2,
张小刚^2,,
胡义函²

1.
湖南大学信息科学与工程学院长沙 410082;
2.
湖南大学电气与信息工程学院长沙 410082

详细信息

通讯作者:
张小刚, 湖南大学电气与信息工程学院教授. 主要研究方向为工业窑炉过程控制与模式识别.

计量
- 文章访问数: 2109
- HTML全文浏览量: 37
- PDF下载量: 1083
- 被引次数: 0
出版历程
- 收稿日期: 2011-09-01
- 修回日期: 2011-12-11
- 刊出日期: 2012-05-20

A Robust-ELM Approach Based on Parzen Windiow's Estimation for Kiln Sintering Temperature Detection

1.
School of Information Science and Engineering, Hunan University, Changsha 410082;
2.
College of Electrical and Information Engineering, Hunan University, Changsha 410082

摘要

摘要: 在回转窑燃煤火焰视频模糊且干扰较大的情况下, 基于火焰辐射能量和燃烧稳定程度提取多帧煤粉燃烧图像的统计特征进行烧结温度判断. 为克服工业现场特征数据中的粗差干扰,将极限学习机(Extreme learning machine, ELM)与稳健估计理论相结合, 用训练误差分布的Parzen窗非参数估计构造ELM权矩阵,对其输出层权值进行稳健最小二乘估计. 基于上述火焰视频的统计特征,用该改进的鲁棒极限学习机(Robust-ELM)检测烧结带温度.实验结果表明, 在视频图像模糊、不能用常规静态图像处理方法软测量烧结带温度时,本文方法可快速有效地检测窑内烧结温度, 且检测系统不易受现场干扰,稳定性强.
- 煤粉燃烧 /
- 火焰图像 /
- 鲁棒极限学习机 /
- 烧结温度 /
- Parzen窗估计
Abstract: To eliminate the interference in the blurring pulverized coal flame image sequences of rotary kiln, a new kiln sintering temperature measurement method based on statistical features of pulverized coal flames and robust extreme learning machine (robust-ELM) is proposed in this paper. The degree of stability and quantity of radiant energy are computed from a blurry flames image sequences as statistical features, robust-ELM is presented to estimate the sintering temperature based on the above features of flames image. The distribution of training error of extreme learning machine (ELM) is estimated by Parzen windows to make up the weighted matrix to reduce the disturbance of gross errors in industrial field. Finally, a series of tests were undertaken on an industrial-scale flame videos, which showed the methods could measure sintering temperature more accurately, quickly, and robustly.
- Pulverized coal combustion /
- flame image /
- robust extreme learning machine (robust-ELM) /
- sintering tem- perature /
- Parzen windows estimation

HTML全文

参考文献(1)

[1]

Jiang Z W, Luo Z X, Zhou H C. A simple measurement method of temperature and emissivity of coal-fired flames from visible radiation image and its application in a CFB boiler furnace. Fuel, 2009, 88(6): 980-987[2] Luo Z X, Zhou H C. A combustion-monitoring system with 3-D temperature reconstruction based on flame-image processing technique. IEEE Transactions on Instrumentation and Measurement, 2007, 56(5): 1877-1882[3] Bae H, Kim S, Wang B H, Lee M H, Harashima F. Flame detection for the steam boiler using neural networks and image information in the Ulsan steam power generation plant. IEEE Transactions on Industrial Electronics, 2006, 53(1): 338-348[4] Liu He. Judging boiler combustion stability based on flame image and fuzzy neural network. Chinese Journal of Scientific Instrument, 2008, 29(6): 1280-1284 (刘禾. 基于火焰图像和模糊神经网络的锅炉燃烧稳定性判别. 仪器仪表学报, 2008, 29(6): 1280-1284)[5] Krabicka J, Lu G, Yan Y. Profiling and characterization of flame radicals by combining spectroscopic imaging and neural network techniques. IEEE Transactions on Instrumentation and Measurement, 2011, 60(5): 1854-1860[6] Smart J, Lu G, Yan Y, Riley G. Characterisation of an oxy-coal flame through digital imaging. Combustion and Flame, 2010, 157(6): 1132-1139[7] Zhang Xiao-Gang, Chen Hua, Zhang Jing, Liu Xiao-Yan. Intelligent predictive control strategy applied to sintering temperature in rotary kiln based on image feedback. Control Theory and Applications, 2007, 24(6): 995-998 (张小刚, 陈华, 章兢, 刘小燕. 基于图像反馈的回转窑烧结温度智能预测控制. 控制理论与应用, 2007, 24(6): 995-998)[8] Zhang Xiao-Gang, Chen Hua, Zhang Jing. Rotary kiln sintering temperature measurement and control based on fuzzy multisensor data fusion. Control and Decision, 2002, 17(6): 865-870 (张小刚, 陈华, 章兢. 基于多传感器数据融合的回转窑烧结温度检测和控制方法. 控制与决策, 2002, 17(6): 865-870)[9] Lin B, Jorgensen S B. Soft sensor design by multivariate fusion of image features and process measurements. Journal of Process Control, 2011, 21(4): 547-553[10] Jiang Hui-Yan, Wang Xiao-Dan, Zhou Xiao-Jie, Chai Tian-You. Study on soft sensor for temperature of burning zone based on SVR. Journal of System Simulation, 2008, 20(11): 2951-2955 (姜慧研, 王晓丹, 周晓杰, 柴天佑. 基于SVR的回转窑烧成带温度软测量方法的研究. 系统仿真学报, 2008, 20(11): 2951-2955)[11] Yi Zheng-Ming, Lv Zi-Jian, Liu Zhi-Ming. Flame image processing and its characteristic extraction for alumina rotary kiln. Chinese Journal of Scientific Instrument, 2006, 27(8): 969-972 (易正明, 吕子剑, 刘志明. 氧化铝回转窑火焰图像处理与特征提取. 仪器仪表学报, 2006, 27(8): 969-972)[12] Yi Zheng-Ming, Yan Ming, Chi Yun-Guang, Wang Li-You. Measurement technique of flame temperature in rotary kiln based on image processing. Acta Metrologica Sinica, 2008, 29(1): 43-46 (易正明, 鄢明, 迟云广, 王理猷. 基于图像处理的回转窑火焰温度测量技术研究. 计量学报, 2008, 29(1): 43-46)[13] Sun Peng, Zhou Xiao-Jie, Chai Tian-You. FCM segmentation for flame image of rotary kiln based on texture coarseness. Journal of System Simulation, 2008, 20(16): 4438-4445(孙鹏, 周晓杰, 柴天佑. 基于纹理粗糙度的回转窑火焰图像FCM分割方法. 系统仿真学报, 2008, 20(16): 4438-4445)[14] He Min, Zhang Jing, He Zhao-Hui, Jing Li-Wei. Measurement of filling percentage of clinker using rotary kiln image. Journal of Scientific Instrument, 2009, 30(12): 2586-2591 (何敏, 章兢, 何昭晖, 靖立伟. 基于回转窑图像的熟料填充率测量. 仪器仪表学报, 2009, 30(12): 2586-2591)[15] Li Shu-Tao, Wang Yao-Nan. The segmentation of kiln flame image based on neural networks. Journal of Scientific Instrument, 2001, 22(1): 10-13 (李树涛, 王耀南. 基于神经网络的回转窑火焰图像分割. 仪器仪表学报, 2001, 22(1): 10-13)[16] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications. Neurocomputing, 2006, 70(1-3): 489-501[17] Li Han-Zhou, Pan Quan, Zhang Hong-Cai, Zhao Chun-Hui, Feng Min. A study of algorithms of temperature measurement based on digital image processing. Proceedings of the Chinese Society for Electrical Engineering, 2003, 23(6): 195-200(李汉舟, 潘泉, 张洪才, 赵春晖, 冯旻. 基于数字图像处理的温度检测算法研究. 中国电机工程学报, 2003, 23(6): 195-200)[18] Lou Chun, Zhou Huai-Chun, Zhu Guo-Liang, Shao Yong. Analysis and measurement of radiative properties of particulate medium in a large-scale coal-fired boiler of power plant. Journal of Engineering Thermophysics, 2007, 28(S2): 217-220 (娄春, 周怀春, 朱国良, 邵勇. 煤粉炉内颗粒辐射特性的检测与分析. 工程热物理学报, 2007, 28(S2): 217-220)[19] Huang Ben-Yuan, Luo Zi-Xue, Zhou Huai-Chun. Diagnosis of combustion stability in furnace by using flame image method. Thermal Power Generation, 2007, 36(12): 19-22 (黄本元, 罗自学, 周怀春. 炉膛燃烧稳定性的火焰图像诊断方法. 热力发电, 2007, 36(12): 19-22)[20] Lamel L, Rabiner L, Rosenberg A, Wilpon J. An improved endpoint detector for isolated word recognition. IEEE Acoustics, Speech and Signal Processing Magazine, 1981, 29(4): 777-785[21] Huang G B, Chen L, Siew C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Transactions on Neural Networks, 2006, 17(4): 879-892[22] Huang G B, Wang D H, Lan Y. Extreme learning machines: a survey. International Journal of Machine Learning and Cybernetics, 2011, 2(2): 107-122[23] Suresh S, Babu R V, Kim H J. No-reference image quality assessment using modified extreme learning machine classifier. Applied Soft Computing, 2009, 9(2) 541-552[24] Saraswathi S, Sundaram S, Sundararajan N, Zimmermann M, Nilsen-Hamilton M. ICGA-PSO-ELM approach for accurate multiclass cancer classification resulting in reduced gene sets in which genes encoding secreted proteins are highly represented. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2011, 8(2): 452-463[25] Tian H X, Mao Z Z. An ensemble ELM based on modified AdaBoost.RT algorithm for predicting the temperature of molten steel in ladle furnace. IEEE Transactions on Automation Science and Engineering, 2010, 7(1): 73-80[26] Heeswijk M, Miche Y, Lindh-Knuutila T, Hilbers P A, Honkela T, Oja E, Lendasse A. Adaptive ensemble models of extreme learning machines for time series prediction. In: Proceedings of the 19th International Conference on Artificial Neural Networks: Part II. Berlin, Heidelberg: Springer-Verlag, 2009. 305-314[27] Soria-Olivas E, Gómez-Sanchis J, Martin J D, Vila-Francés J, Martínez M, Magdalena J R, Serrano A J. BELM: Bayesian extreme learning machine. IEEE Transactions on Neural Networks, 2011, 22(3): 505-509[28] Deng Wan-Yu, Zheng Qing-Hua, Chen Lin, Xu Xue-Bing. Research on extreme learning of neural networks. Chinese Journal of Computers, 2010, 33(2): 279-287 (邓万宇, 郑庆华, 陈琳, 许学斌. 神经网络极速学习方法研究. 计算机学报, 2010, 33(2): 279-287)[29] Bartlett P L. The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Transactions on Information Theory, 1998, 44(2): 525-536[30] Jiang Rui, Luo Gui-Ming. Optimal adaptive controller for stochastic systems based on weighted least-squares algorithm. Acta Automatica Sinica, 2006, 32(1): 140-147 (姜睿, 罗贵明. 基于加权最小二乘法的最优适应控制器. 自动化学报, 2006, 32(1): 140-147)[31] Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66

施引文献

资源附件(0)

访问统计