石灰回转窑煅烧带温度的软测量方法
|
摘要
作为石灰回转窑生产过程中的重要参数,煅烧带温度对于石灰生产质量有着极大的影响。由于回转窑结构的特殊性,且煅烧带温度极高,煅烧带温度很难利用传感器直接测量。针对石灰回转窑煅烧带温度的测量问题,将石灰回转窑煅烧带温度作为研究对象,提出了一种软测量方法。利用生产现场易测的数据建立回转窑煅烧带温度的软测量模型。首先引入核主成分分析对采集的可测数据进行主成分的提取,减少预测模型输入变量之间的耦合与相互干扰,同时减少了建模的复杂度。然后通过最小二乘支持向量机对石灰回转窑煅烧带温度建模。最小二乘支持向量机预测性能与模型参数有着很大的关系,为了提高预测精度,利用具有良好优化性能的和声搜索算法对最小二乘支持向量机预测模型中的参数进行优化。仿真实验结果表明,提出的回转窑煅烧带温度软测量方法具有较高的预测精度,减少了预测误差,预测值较好的反映了回转窑煅烧带温度的变化趋势。同时,减少了建模的复杂度。提出的石灰回转窑煅烧带温度软测量方法是有效的。
As an important parameter in the production process of lime rotary kiln,the burning zone temperature has a great influence on the quality of lime production. As a result of the special structure of the rotary kiln and the high temperature of the burning zone,it is difficult to measure the temperature of the burning zone directly by sensor. The burning zone temperature of lime rotary kiln is studied,and a soft-sensing method is proposed. This soft-sensing method of burning zone temperature in lime rotary kiln is established by using the data measured at the production field. Firstly,kernel principal component analysis is introduced and data of principal component is extracted. The coupling and mutual interference between the input variables of the prediction model,the complexity of the modeling are reduced. Then,the burning zone temperature prediction model is built by least squares support vector machine algorithm. The prediction performance of least squares support vector machine is closely related to the model parameters. In order to improve the prediction accuracy,the harmony search algorithm with good optimization performance is used to optimize the parameters of least squares support vector machine prediction model. The simulation results show that the soft-sensing method of burning zone temperature in the lime rotary kiln has a higher prediction accuracy and less prediction error. The prediction value reflects the trend of the burning zone temperature of the rotary kiln. At the same time,the complexity of modeling is reduced. The proposed soft-sensing method of burning zone temperature in lime rotary kiln is effective.
As an important parameter in the production process of lime rotary kiln,the burning zone temperature has a great influence on the quality of lime production. As a result of the special structure of the rotary kiln and the high temperature of the burning zone,it is difficult to measure the temperature of the burning zone directly by sensor. The burning zone temperature of lime rotary kiln is studied,and a soft-sensing method is proposed. This soft-sensing method of burning zone temperature in lime rotary kiln is established by using the data measured at the production field. Firstly,kernel principal component analysis is introduced and data of principal component is extracted. The coupling and mutual interference between the input variables of the prediction model,the complexity of the modeling are reduced. Then,the burning zone temperature prediction model is built by least squares support vector machine algorithm. The prediction performance of least squares support vector machine is closely related to the model parameters. In order to improve the prediction accuracy,the harmony search algorithm with good optimization performance is used to optimize the parameters of least squares support vector machine prediction model. The simulation results show that the soft-sensing method of burning zone temperature in the lime rotary kiln has a higher prediction accuracy and less prediction error. The prediction value reflects the trend of the burning zone temperature of the rotary kiln. At the same time,the complexity of modeling is reduced. The proposed soft-sensing method of burning zone temperature in lime rotary kiln is effective.
引文
[1]SHAHIN H,HASSANPOUR S,SABOONCHI A.Thermal energy analysis of a lime production process:Rotary kiln,preheater and cooler[J].Energy Conversion and Management,2016,114(4):110-121.
[2]LI K,GAO X W,ZHOU H B,et al.Fault diagnosis for down-hole conditions of sucker rod pumping systems based on the FBH-SC method[J].Petroleum Science,2015,12(1):135-147.
[3]李琨,韩莹,李申明,等.基于OS-ELM的游梁式抽油机系统电动机负载扭矩的在线混合建模[J].化工学报,2017,68(6):2465-2472.LI K,HAN Y,LI SH M,et al.OS-ELM-based hybrid online modeling for motor load torque of beam pumping units[J].CIESC Journal,2017,68(6):2465-2472.
[4]JIN H P,CHEN X G,YANG J W,et al.Multi-model adaptive soft sensor modeling method using local learning and online support vector regression for nonlinear timevariant batch processes[J].Chemical Engineering Science,2015,131(7):282-303.
[5]XU W,ZHANG L B,GU X S,et al.Soft sensor for ammonia concentration at the ammonia converter outlet based on an improved particle swarm optimization and BP neural network[J].Chemical Engineering Research and Design,2011,89(10):2102-2109.
[6]WANG G T,LI P,CAO J T.Variable activation function extreme learning machine based on residual prediction compensation[J].Soft Computing,2012,16(9):1477-1484.
[7]KANEKO H,FUNATSU K.Applicability domain of soft sensor models based on one-class support vector machine[J].AICh E Journal,2013,59(6):2046-2050.
[8]刘金鑫,朱云龙,沈喆,等.回转窑烧成带状态混合智能识别方法[J].自动化学报,2012,38(7):1153-1161.LIU J X,ZHU Y L,SHEN ZH,et al.Hybrid recognition method for burning zone condition of rotary kiln[J].Acta Automatica Sinica,2012,38(7):1153-1161.
[9]LIN B,JORGENSEN S B.Soft sensor design by multivariate fusion of image features and process measurements[J].Journal of Process Control,2011,21(4):547-553.
[10]张立,高宪文,王介生,等.基于模型迁移方法的回转窑煅烧带温度软测量[J].东北大学学报(自然科学版),2011,32(2):175-178.ZHANG L,GAO X W,WANG J SH,et al.Soft-sensing for calcining zone temperature in rotary kiln based on model migration[J].Journal of Northeastern University(Natural Science),2011,32(2):175-178.
[11]LIN B,RECKE B,SCHMIDT T M,et al.Data-driven soft sensor design with multiple-rate sampled data:a comparative study[J].Industrial&Engineering Chemistry Research,2009,48(11):5379-5387.
[12]KANEKO H,ARAKAWA M,FUNATSU K.Development of a new soft sensor method using in dependent component analysis and partial least squares[J].AICh E Journal,2009,55(1):87-98.
[13]HUANG J,YAN X F.Related and independent variable fault detection based on KPCA and SVDD[J].Journal of Process Control,2016,39(3):88-99.
[14]HEJAZI M,AL-HADDAD S A R,SINGH Y P,et al.ECG biometric authentication based on non-fiducial approach using kernel methods[J].Digital Signal Processing,2016,52(C):72-86.
[15]MARTINS M,SANTOS C,COSTA L,et al.Feature reduction with PCA/KPCA for gait classification with different assistive devices[J].International Journal of Intelligent Computing and Cybernetics,2015,8(4):363-382.
[16]JIN X Y,SUN Z H,GUAN X Y,et al.A sample-driven classification and identification method with KPCA and multi-SVM[J].Journal of Vibroengineering,2013,15(3):1186-1193.
[17]田中大,李树江,王艳红,等.基于KPCA优化ESN的网络流量预测方法[J].电机与控制学报,2015,19(12):114-120.TIAN ZH D,LI SH J,WANG Y H,et al.Network traffic prediction method based on KPCA optimized ESN[J].Electric Machines and Control,2015,19(12):114-120.
[18]殷贤华,王宁,陈晶溪.基于太赫兹时域光谱系统的橡胶分类识别[J].国外电子测量技术,2016,35(6):19-23.YIN X H,WANG N,CHEN J X.Rubber classification and recognition based on THz time-domain spectroscopy system[J].Foreign Electronic Measurement Technology,2016,35(6):19-23.
[19]XIAO Y C,W H G,XU W L,et al.L1 norm based KPCA for novelty detection[J].Pattern Recognition,2013,46(1):389-396.
[20]李怀俊,谢小鹏.基于核特征模糊聚类及模糊关联熵的齿轮故障模式识别[J].仪器仪表学报,2015,36(4):848-855.LI H J,XIE X P.Gear fault pattern recognition based on kernel feature fuzzy clustering and fuzzy association entropy[J].Chinese Journal of Scientific Instrument,2015,36(4):848-855.
[21]SUYKENS J A K,LUKAS L,VANDEWALLE J.Sparseapproximation using least squares support vector machines[C].IEEE International Symposium on Circuits and Systems,2002:757-760.
[22]高加琼,魏霖静.基于最小二乘及分类向量机的空气调节器故障检测[J].沈阳工业大学学报,2016,38(3):326-330.GAO J Q,WEI L J.Fault detection of air conditioner based on least squares and support vector machine classification[J].Journal of Shenyang University of Technology,2016,38(3):326-330.
[23]孙驷洲,付敬奇,朱峰.CGAQPSO优化LSSVM短期风电预测[J].电子测量与仪器学报,2016,30(11):1718-1725.SUN S ZH,FU J Q,ZHU F.Short-term wind power prediction based on LSSVM optimized by chaos Gauss attractor quantum-behaved particle swarm optimization[J].Journal of Electronic Measurement and Instrumentation,2016,30(11):1718-1725.
[24]GEEM Z W,KIM J H,LOGANATHAN G V.A new heuristic optimization algorithm:Harmony search[J].Simulations,2001,76(2):60-68.
[25]欧阳海滨,高立群,邹德旋,等.和声搜索算法探索能力研究及其修正[J].控制理论与应用,2014,31(1):57-65.OUYANG H B,GAO L Q,ZOU D X,et al.Exploration ability study of harmony search algorithm and its modification[J].Control Theory&Applications,2014,31(1):57-65.
[26]惠延波,李永超,王莉,等.基于电容式生物传感器的尿检仪设计[J].电子测量技术,2016,39(4):109-112.HUI Y B,LI Y CH,WANG L,et al.Design of urine test instrument based on capacitive biosensor[J].Electronic Measurement Technology,2016,39(4):109-112.
[27]李勇,施艳春.基于动态熵权的短期风速组合预测[J].沈阳工业大学学报,2016,38(3):247-251.LI Y,SHI Y CH.Short-term wind speed combination forecast based on dynamic entropy weight[J].Journal of Shenyang University of Technology,2016,38(3):247-251.
[2]LI K,GAO X W,ZHOU H B,et al.Fault diagnosis for down-hole conditions of sucker rod pumping systems based on the FBH-SC method[J].Petroleum Science,2015,12(1):135-147.
[3]李琨,韩莹,李申明,等.基于OS-ELM的游梁式抽油机系统电动机负载扭矩的在线混合建模[J].化工学报,2017,68(6):2465-2472.LI K,HAN Y,LI SH M,et al.OS-ELM-based hybrid online modeling for motor load torque of beam pumping units[J].CIESC Journal,2017,68(6):2465-2472.
[4]JIN H P,CHEN X G,YANG J W,et al.Multi-model adaptive soft sensor modeling method using local learning and online support vector regression for nonlinear timevariant batch processes[J].Chemical Engineering Science,2015,131(7):282-303.
[5]XU W,ZHANG L B,GU X S,et al.Soft sensor for ammonia concentration at the ammonia converter outlet based on an improved particle swarm optimization and BP neural network[J].Chemical Engineering Research and Design,2011,89(10):2102-2109.
[6]WANG G T,LI P,CAO J T.Variable activation function extreme learning machine based on residual prediction compensation[J].Soft Computing,2012,16(9):1477-1484.
[7]KANEKO H,FUNATSU K.Applicability domain of soft sensor models based on one-class support vector machine[J].AICh E Journal,2013,59(6):2046-2050.
[8]刘金鑫,朱云龙,沈喆,等.回转窑烧成带状态混合智能识别方法[J].自动化学报,2012,38(7):1153-1161.LIU J X,ZHU Y L,SHEN ZH,et al.Hybrid recognition method for burning zone condition of rotary kiln[J].Acta Automatica Sinica,2012,38(7):1153-1161.
[9]LIN B,JORGENSEN S B.Soft sensor design by multivariate fusion of image features and process measurements[J].Journal of Process Control,2011,21(4):547-553.
[10]张立,高宪文,王介生,等.基于模型迁移方法的回转窑煅烧带温度软测量[J].东北大学学报(自然科学版),2011,32(2):175-178.ZHANG L,GAO X W,WANG J SH,et al.Soft-sensing for calcining zone temperature in rotary kiln based on model migration[J].Journal of Northeastern University(Natural Science),2011,32(2):175-178.
[11]LIN B,RECKE B,SCHMIDT T M,et al.Data-driven soft sensor design with multiple-rate sampled data:a comparative study[J].Industrial&Engineering Chemistry Research,2009,48(11):5379-5387.
[12]KANEKO H,ARAKAWA M,FUNATSU K.Development of a new soft sensor method using in dependent component analysis and partial least squares[J].AICh E Journal,2009,55(1):87-98.
[13]HUANG J,YAN X F.Related and independent variable fault detection based on KPCA and SVDD[J].Journal of Process Control,2016,39(3):88-99.
[14]HEJAZI M,AL-HADDAD S A R,SINGH Y P,et al.ECG biometric authentication based on non-fiducial approach using kernel methods[J].Digital Signal Processing,2016,52(C):72-86.
[15]MARTINS M,SANTOS C,COSTA L,et al.Feature reduction with PCA/KPCA for gait classification with different assistive devices[J].International Journal of Intelligent Computing and Cybernetics,2015,8(4):363-382.
[16]JIN X Y,SUN Z H,GUAN X Y,et al.A sample-driven classification and identification method with KPCA and multi-SVM[J].Journal of Vibroengineering,2013,15(3):1186-1193.
[17]田中大,李树江,王艳红,等.基于KPCA优化ESN的网络流量预测方法[J].电机与控制学报,2015,19(12):114-120.TIAN ZH D,LI SH J,WANG Y H,et al.Network traffic prediction method based on KPCA optimized ESN[J].Electric Machines and Control,2015,19(12):114-120.
[18]殷贤华,王宁,陈晶溪.基于太赫兹时域光谱系统的橡胶分类识别[J].国外电子测量技术,2016,35(6):19-23.YIN X H,WANG N,CHEN J X.Rubber classification and recognition based on THz time-domain spectroscopy system[J].Foreign Electronic Measurement Technology,2016,35(6):19-23.
[19]XIAO Y C,W H G,XU W L,et al.L1 norm based KPCA for novelty detection[J].Pattern Recognition,2013,46(1):389-396.
[20]李怀俊,谢小鹏.基于核特征模糊聚类及模糊关联熵的齿轮故障模式识别[J].仪器仪表学报,2015,36(4):848-855.LI H J,XIE X P.Gear fault pattern recognition based on kernel feature fuzzy clustering and fuzzy association entropy[J].Chinese Journal of Scientific Instrument,2015,36(4):848-855.
[21]SUYKENS J A K,LUKAS L,VANDEWALLE J.Sparseapproximation using least squares support vector machines[C].IEEE International Symposium on Circuits and Systems,2002:757-760.
[22]高加琼,魏霖静.基于最小二乘及分类向量机的空气调节器故障检测[J].沈阳工业大学学报,2016,38(3):326-330.GAO J Q,WEI L J.Fault detection of air conditioner based on least squares and support vector machine classification[J].Journal of Shenyang University of Technology,2016,38(3):326-330.
[23]孙驷洲,付敬奇,朱峰.CGAQPSO优化LSSVM短期风电预测[J].电子测量与仪器学报,2016,30(11):1718-1725.SUN S ZH,FU J Q,ZHU F.Short-term wind power prediction based on LSSVM optimized by chaos Gauss attractor quantum-behaved particle swarm optimization[J].Journal of Electronic Measurement and Instrumentation,2016,30(11):1718-1725.
[24]GEEM Z W,KIM J H,LOGANATHAN G V.A new heuristic optimization algorithm:Harmony search[J].Simulations,2001,76(2):60-68.
[25]欧阳海滨,高立群,邹德旋,等.和声搜索算法探索能力研究及其修正[J].控制理论与应用,2014,31(1):57-65.OUYANG H B,GAO L Q,ZOU D X,et al.Exploration ability study of harmony search algorithm and its modification[J].Control Theory&Applications,2014,31(1):57-65.
[26]惠延波,李永超,王莉,等.基于电容式生物传感器的尿检仪设计[J].电子测量技术,2016,39(4):109-112.HUI Y B,LI Y CH,WANG L,et al.Design of urine test instrument based on capacitive biosensor[J].Electronic Measurement Technology,2016,39(4):109-112.
[27]李勇,施艳春.基于动态熵权的短期风速组合预测[J].沈阳工业大学学报,2016,38(3):247-251.LI Y,SHI Y CH.Short-term wind speed combination forecast based on dynamic entropy weight[J].Journal of Shenyang University of Technology,2016,38(3):247-251.