氧化铝输送中氧化铝粉流量的软测量方法研究
|
摘要
在铝电解生产过程中,氧化铝物料输送是一个极为重要的环节,其输送技术会直接影响铝电解生产的稳定和氧化铝单耗。随着超浓相输送技术的广泛应用和自动化水平的日益提高,通过优化控制确保产品质量,进而实现降耗增效已成为企业追求的目标。为了达到这一目标需对更多的工艺参数与变量进行在线精确测量,而铝电解中氧化铝粉流量即为其中主要参数之一。软测量作为一种解决产品质量等关键性生产参数在线测量问题的新技术,近年来已成为有效提高生产效益、保证产品质量的有力手段。
本文以电解铝厂氧化铝输送过程为背景,针对氧化铝粉流量或因进口仪表价格昂贵、或因现存国产仪表精度不高难以在线有效测量这一问题,提出了将软测量技术应用于氧化铝粉流量的在线估计。首先在对氧化铝输送过程工艺深入分析的基础上,结合自动化系统可提供的测量信息,确定了供料离心风机风流量和风压作为辅助变量;其次利用实际工业现场数据,分别以PLS、RBF和LS-SVM等单一模型,对氧化铝粉流量的软测量进行了仿真研究;进而考虑到模型参数选择对LS-SVM模型性能的影响,利用粒子群优化算法确定其参数,得到了精度更高、泛化能力更强的预测模型;再者针对单一模型难以全面描述复杂系统全局特性的问题,采用一种基于模糊C均值聚类的双层多模型软测量方法,对氧化铝粉流量的预测估计进行了仿真研究,该方法以模糊C均值聚类作为分类基础层,分别以多PLS、多RBF、多LS-SVM以及PLS+RBF+LSSVM作为各分类数据模型层,在线运行时将各模型的预测输出通过实际数据在各模型的隶属度上进行加权求和,从而获得被估计参数的软测量值。研究结果表明单一模型和多模型软测量建模方法,对于氧化铝粉流量的估计均具有一定的泛化能力和较好的预测精度,且异类多模型更优,LS-SVM更适宜模型的在线修正,从而验证了软测量技术用于氧化铝粉流量的在线估计是可行有效的,同时也为软测量技术在氧化铝粉流量预测的工业实现提供了依据。
Alumina conveying is one of the most important parts in the process of electrolytic aluminum plant for the production of alumina.The transportation technique is straight influence the stabilization of the production of alumina and the consumption per unit of alumina.Along with widely application of hyper dense phase conveying system and the improvement of automatic level day by day,through optimize and control to ensure the quality of product,and then realizing consumption reduction and Enlarging has already become the goal that enterprises have pursued.For the goal more craft parameters and variables are needed to be measured on-line,and alumina powder flow in electrolytic aluminum plant is one of the main parameters.The soft sensor technology have been presented itself as a new technology that settles the main parameter measured on-line, improving the productivity benefit and guarantee the quality of production in recent years.
On the background of the aluminium transport course in electrolytic aluminum plant,the soft sensor technology have been presented to measure the flow of alumina powder in electrolytic aluminum plant because of the difficult problem that alumina powder flow can not be precise measured on-line for import instruments cost expensive and the precision of domestic instrument is relatively low.At first on the basis of further investigate the craft of Alumina conveying and the measured information which the automation system can be offered the wind pressure and the wind flux of the centripetal fan are chosen as assistant variable to estimate the flow of alumina powder.Secondly on the basis of the actual industry's on-the-spot data PLS,RBF and LS-SVM simulation research has been carried out with the single model soft sensor of alumina powder flow. And then considering the impact of model parameter chosen on model performance Pso algorithm has been utilized to confirm its parameters and achieved higher precision and better generalization ability forecast model.It is difficult for single model to describe global properties of complex system,and multi-point of complex systems in work is taken into account,so a multi-modeling soft sensor based on double layers intelligent structure is proposed in this paper,in which fuzzy c-means clustering is classification layer,and many PLS,may RBF neural network,many LS-SVM and PLS+RBF+LS-SVM are modeling layers.The degrees of membership are used for combining the output of sub-models to obtain the finial result which is the measured value of estimated parameters,and then the model of alumina powder flow is founded. The result of simulation research proves that the single model and multi-modeling modeling technique all have better generalization ability and higher precision accuracy and different multi-models are superior.The soft sensor technique of LS-SVM is more suitable model that could be revision on-line and proved that this technique is feasible and effective,at the same time the soft sensor technology have offered the basis for the real-time monitoring of alumina powder flow in the field of the industry of aluminium.
本文以电解铝厂氧化铝输送过程为背景,针对氧化铝粉流量或因进口仪表价格昂贵、或因现存国产仪表精度不高难以在线有效测量这一问题,提出了将软测量技术应用于氧化铝粉流量的在线估计。首先在对氧化铝输送过程工艺深入分析的基础上,结合自动化系统可提供的测量信息,确定了供料离心风机风流量和风压作为辅助变量;其次利用实际工业现场数据,分别以PLS、RBF和LS-SVM等单一模型,对氧化铝粉流量的软测量进行了仿真研究;进而考虑到模型参数选择对LS-SVM模型性能的影响,利用粒子群优化算法确定其参数,得到了精度更高、泛化能力更强的预测模型;再者针对单一模型难以全面描述复杂系统全局特性的问题,采用一种基于模糊C均值聚类的双层多模型软测量方法,对氧化铝粉流量的预测估计进行了仿真研究,该方法以模糊C均值聚类作为分类基础层,分别以多PLS、多RBF、多LS-SVM以及PLS+RBF+LSSVM作为各分类数据模型层,在线运行时将各模型的预测输出通过实际数据在各模型的隶属度上进行加权求和,从而获得被估计参数的软测量值。研究结果表明单一模型和多模型软测量建模方法,对于氧化铝粉流量的估计均具有一定的泛化能力和较好的预测精度,且异类多模型更优,LS-SVM更适宜模型的在线修正,从而验证了软测量技术用于氧化铝粉流量的在线估计是可行有效的,同时也为软测量技术在氧化铝粉流量预测的工业实现提供了依据。
Alumina conveying is one of the most important parts in the process of electrolytic aluminum plant for the production of alumina.The transportation technique is straight influence the stabilization of the production of alumina and the consumption per unit of alumina.Along with widely application of hyper dense phase conveying system and the improvement of automatic level day by day,through optimize and control to ensure the quality of product,and then realizing consumption reduction and Enlarging has already become the goal that enterprises have pursued.For the goal more craft parameters and variables are needed to be measured on-line,and alumina powder flow in electrolytic aluminum plant is one of the main parameters.The soft sensor technology have been presented itself as a new technology that settles the main parameter measured on-line, improving the productivity benefit and guarantee the quality of production in recent years.
On the background of the aluminium transport course in electrolytic aluminum plant,the soft sensor technology have been presented to measure the flow of alumina powder in electrolytic aluminum plant because of the difficult problem that alumina powder flow can not be precise measured on-line for import instruments cost expensive and the precision of domestic instrument is relatively low.At first on the basis of further investigate the craft of Alumina conveying and the measured information which the automation system can be offered the wind pressure and the wind flux of the centripetal fan are chosen as assistant variable to estimate the flow of alumina powder.Secondly on the basis of the actual industry's on-the-spot data PLS,RBF and LS-SVM simulation research has been carried out with the single model soft sensor of alumina powder flow. And then considering the impact of model parameter chosen on model performance Pso algorithm has been utilized to confirm its parameters and achieved higher precision and better generalization ability forecast model.It is difficult for single model to describe global properties of complex system,and multi-point of complex systems in work is taken into account,so a multi-modeling soft sensor based on double layers intelligent structure is proposed in this paper,in which fuzzy c-means clustering is classification layer,and many PLS,may RBF neural network,many LS-SVM and PLS+RBF+LS-SVM are modeling layers.The degrees of membership are used for combining the output of sub-models to obtain the finial result which is the measured value of estimated parameters,and then the model of alumina powder flow is founded. The result of simulation research proves that the single model and multi-modeling modeling technique all have better generalization ability and higher precision accuracy and different multi-models are superior.The soft sensor technique of LS-SVM is more suitable model that could be revision on-line and proved that this technique is feasible and effective,at the same time the soft sensor technology have offered the basis for the real-time monitoring of alumina powder flow in the field of the industry of aluminium.
引文
[1]王树青.先进控制技术及应用[M].北京:化学工业出版社.2001,33-46
[2]Brosilow C B.Inferential Control of Process Control.AIChE Journal,1978,24(3):475-840
[3]Brosilow C B.The Structure and Dynamics of Inferential Control System.AIChE Journal,1978,24(3):485-499
[4]Babu Joseph,Coleman B.Brosilow.Inferential Control of Processes:Part Ⅰ.Steady State Analysis and Design[J].AIChE Journal,1978,24(3):485-492
[5]Coleman B.Brosilow,Martin Tong.Part Ⅱ.The Structure and Dynamics of Inferential Control Systems[J].AIChE Journal,1978,24(3):492-500
[6]Babu Joseph.Coleman B.Brosilow.Part Ⅲ.Construction of Optimal and Suboptimal Dynamic Estimators[J].AIChE Journal,1978,24(3):500-509
[7]俞金寿,刘爱伦,张克进.软测量技术及其在石油化工中的应用[M].化学工业出版社.2000
[8]徐敏,俞金寿.软测量技术[M].石油化工自动化.1998,1-3
[9]Gonzalez G D.Soft sensors for processing plants.Proceeding of the Second International Conference on Intelligent Processing and Manufacturing of Materials,1999,(1):59-69
[10]吴举,成庚,代启安.氧化铝超浓相输送系统计量新装置的研究开发[J].轻金属.2003,12:27-29
[11]朱波.氧化铝生产苛性比值软测量神经网络模型的在线修正方法研究[D].中南大学,2005
[12]李海青,黄志尧等.软测量技术原理及应用[M].化学工业出版社.2000,9
[13]刘瑞兰.软测量技术若干问题的研究及工业应用[D].浙江大学,2004
[14]俞金寿.软测量技术在石油化工中的应用[J].石油化工.2000,9(3):221-226
[15]石连生.基于双层智能结构的多模型软测量方法研究[D].兰州理工大学,2008
[16]于静江,周春晖.过程控制中的软测量技术[J].控制理论与应用,1996,Vol.13(2):137-144
[17]骆晨钟,邵惠鹤.软仪表技术及其工业应用[J].仪表技术与传感器,1999,Vol.1:32-39
[18]俞金寿.工业过程控制[M].北京:中国石化出版社,2002
[19]黄凤良.软测量思想与软测量技术[J].计量学报,2004,Vol.25(3):284-288
[20]杜锋,刘全,雷鸣.软测量技术及其在发酵过程中的应用[J].食品科学,2002,23(8):352-356
[21]Tham M T,Montagueand G A,Morris A J,Lant P A.Soft-sensors for process estimation and inferential control.Journal of Process Control,1991,1(1):3-14
[22]Macvoy T J.Contemplative Stance for Chemical Process Automatica.1992,28(2):441-442
[23]Weber R,Brosillow C B.The Use of Secondary Measurement to Improvement Control.AICHE J.1972
[24]Bhat N V,Minderman P A,Mcavoy T J etal.Modeling chemical process system via neural computation.
[25]Bates,J.M.,Granger,C.W.J.The combination of forecasts.Operations Research Quarterly,1969,20:319-325
[26]Wolpert D H.Stacked generalization.Neural Networks.1992,5(2):241-259
[27]Karakuzu C,Ozturk S,Turker M.Modeling,on-line state estimation and fuzzy control of production scale fed-batch baker's yeast fermentation.Control Engineering Practice,2006,(14):959-974
[28]王旭东,邵惠鹤.神经元网络建模技术与软测量技术[J].化工自动化及仪表,1996.23(2):28-31
[29]许勇刚,杨辉.基于RBF网络的稀土萃取过程组分含量软测量[J].稀土,2007,28(5):19-22
[30]杨旭华.神经网络及其在控制中的应用研究[D].浙江大学,2004
[31]董立忠,张荣祥.模糊信息处理及其应用[J].仪器仪表学报,1995,Vol.16(1):88-91
[32]L.Zhou,et al.,Modeling and control for nonlinear time-delay system via pattern RecognitionlEEE Trans.Neural Networks.1992,3(6):991-997.
[33]叶楠,吕勇哉.模式识别在状态估计中的应用[J].仪器仪表学报,1988.9(4):368-374
[34]Cortes C,Vapnik V N.Support vector machine.Machine Learning,1995,(20):273-297
[35]傅永峰.软测量建模方法研究及其工业应用[D].浙江大学,2007
[36]Qi H Y,Zhou X G,Liu L H,Yuan W K,A hybrid neural network-first principles model for fixed-bed reactor Chemical Engineering Science,1999,54(13-14):2521-2526
[37]李向阳,朱学峰,刘焕彬.间歇制浆蒸煮过程的混合建模方法研究[J].中国造纸学报,2001,16(2):24-28
[38]仲蔚,俞金寿.软测量技术及其在加氢裂化分馏塔中的应用[J].华东理工大学学报,1999 25(4):420-423
[39]Dai X,Wang W,Ding Y,Sun Z."Assumed inherent sensor" inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process,Computers and Chemical Engineering,2006,30(8):1203-1225
[40]杨辉,柴天佑.稀土萃取分离过程的优化设定控制[J].控制与决策,2005,20(4):398-402
[41]许光,俞欢军,陶少辉,陈德钊.与机理杂交的支持向量机为发酵过程建模[J].化工学报,2005,56(4):653-658
[42]Zhao Y.A soft sensor based on nonlinear principal component analysis,IEEE Proceedings of the Second International Conference on Machine Learning and Cybernetics,Xi'an,2-5 November 2003,707-710
[43]马朝阳,苏宏业,傅永峰,褚健.基于KPCA-SVR方法的复合肥养分含量建模[J].中国科学技术大学学报,2005,35(增刊):314-321
[44]吕立华,宋执环,李平.用于过程软测量的多小波网络[J].仪器仪表学报,2002,23(5):508-511
[45]常玉清,王小刚,王福利.基于多神经网络模型的软测量方法及应用[J].东北大学学报(自然科学版),2005,26(6):519-522
[46]桂卫华,李勇刚,阳春华,陈志盛.基于改进聚类算法的分布式SVM及其应用[J].控制与决策,2004,19(8):852-856
[47]罗荣富,邵惠鹤.软测量方法及其工业应用[M].上海交大出版社.1994:253-260
[48]徐敏.软测量方法和应用研究[D].华东理工大学,1999
[49]Alber.J.E.Online Data Reconciliation and Error Detection.H.P.1997.17(7):101-104
[50]李红军,秦永胜,徐用愚.化工过程中的数据协调及显著误差检测[J].化工自动化及仪表,1997,24(2):25-29
[51]荣冈,金晓明,王树青.软测量技术及其应用[J].化工自动化及仪表,1999,26(4):70-73
[52]Jizhen Liu,Zheng Zhao,Deliang Zeng,Yanqiao Chen.SOFT-SENSING MODEL OF OXYGEN CONTENT BASED ON DATA FUSION[J].Proceedings of the Fourth International Conference on Machine Learning and Cybernetics,2005:3991-3995
[53]Jianxu Luo,Huihe Shao.Soft sensing modeling using neurofuzzy system based on Rough Set Theory[J].Proceedings of the American Control Conference,2002:543-548
[54]Dibo Hou,Zekui Zhou,Guangxin Zhang.ON-LINE MEASUREMENT FOR THE BHE FOULING OF BREWERY WORT EVAPORATOR USING A SOFE SENSING APPROACH[J].IEEE,2003:95-98
[55]Wanliang Wang,Min Ren.Soft-sensing Method for Wastewater Treatment Based on BP Neural Network[J].Proceedings of the 4th World Congress on Intelligent Control and Autoination,2002::2330-2332
[56]Zaiwen Liu,Zhengxiang Wang,Fuxia Xue,Chaozhen Hou,Guoqiang Qi.Study on the Intelligent Soft Sensing Method for Sewage Disposal System[J].IEEE, 2003:181-183
[57] Peijin Wang. Design and Application of Soft Sensor Object in Water Treatment Plant[J].Machine Learning and Cybernetics, 2007 International Conference ,2007:2678 - 2682
[58] Wei Guo,Guochu Chen,Jinshou Yu.The Kalman Particle Swarm Optimization Algorithm and Its Application in Soft-sensor of Acrylonitrile Yield[J].IEEE,2005:124-127
[59] Yufa Xu , Guochu, Chen, Jinshou Yu, Particle Swarm Optimization Fuzzy Neural Network and its Application in Soft-Sensor Modeling of Acrylonitrile Yield[J].Machine Learning and Cybernetics, 2007 International Conference, 2007:1994 -1999
[60] Huajun Feng, Haoran Zhang, Soft Sensor Technique based on Robust SVM[J].The 2005 IEEE International Conference on Neural Networks and Brain, 2005:1704-1707.
[61] Haoran Zhang,Xiaodong Wang,Changjiang Zhang,Ganyun Lv.A New Soft Sensor Method Based on SVM[J].IEEE,2006:546-549.
[62] Rui Feng,Wei Shen,Huihe Shao.A Soft Sensor Modeling Approach Using Support Vector Machines[J].IEEE,2003:3702-3707.
[63] Mingguang Zhang,Zhanming Li,Wenhui Li.Study on Least Squares Support Vector Machines Algorithm and its Application[J].Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence,2005.
[64] Wensen An,Yanguang Sun.AN INFORMATION-GEOMETRICAL APPROACH TO KERNEL CONSTRUCTION IN SVM AND ITS APPLICATION IN SOFT-SENSOR MODELING[J].IEEE,2005:4356-4359
[65] Wang Jun,Peng Hong,Xiao Jian.Soft Sensor Model Based on Improved Fuzzy Neural Network[J].IEEE,2005:694-697.
[66] Tao Ye,Xuefeng Zhu,Xiangyang Li.A Soft Sensing Method Based on the Temporal Difference Learning Algorithm[J].Proceedings of the 6th World Congress on Intelligent Control,2006:4861-4865
[67] Yuqing Chang,Zhe Lv,Fuli Wang,Zhizhong Mao,Xiaogang Wang.Soft Sensing Modeling Based on Stacked Least Square-Support Vector Machine and Its Application[J].Proceedings of the 6th World Congress on Intelligent Control,2006:4846-4850
[68] Jun Wang, Hong Peng.Multi-scale Wavelet Support Vector Regression for Soft Sensor Modeling[J].IEEE,2005:284-287
[69]骆中华,刘瑞兰等.基于PLS快速剪枝法的RBF神经网络软测量建模方法和应用[J].化工自动化及仪表,2005,32(3):19-21
[70]王华忠,俞金寿.核函数方法及其在软测量建模中的应用研究[J].自动化仪表,2004,25(10):22-25
[71]张英,苏宏业,诸健.基于ISVM的软测量建模及其在PX生产中的应用研究[J].2005,20(10):1102-1106
[72]成忠,陈德钊.WBRPLSR方法及其在化工软测量中的应用[J].化工学报,2005,56(2):291-295
[73]邱书波,王化祥,刘雪真.RBF神经网络在卡伯值软测量中的应用研究[J].电子测量与仪器学报,2005,19(1):30-34.
[74]刘翠玲,孙晓荣等.RBF神经网络在超高压釜内油温软测量中的应用[J].仪表技术与传感器,2005,(4):11-13.
[75]谭超.基于支持向量机的软测量技术及其应用[J].传感器技术,2005,24(8):77-79.
[76]孙玉冲,陈明忠等.基于支持向量机的赖氨酸发酵生物参数软测量[J].仪器仪表学报,2008,29(10):2065-2070.
[77]李凡,吴强等.基于递推PLS的自适应钢温软测量模型[J].控制工程,2007,14(2):147-150
[78]段中兴,嵇启春.催化剂粉尘浓度软测量建模研究与应用[J].系统仿真学报,2008,20(14):3899-3902
[79]卢胜利,吴学军等.引黄灌渠斗口流量神经元网络软测量模型[J].计算机控制,2005,31(13):36-37
[80]陈国初,俞金寿.增强型微粒群优化算法及其在软测量中的应用[J].控制与决策,2005,20(4):377-381
[81]宫唤春.RBF神经网络软测量技术在汽油机CO排放中的应用[J].拖拉机与农用运输车,2007,34(5):48-50
[82]刘载文,王正祥,王小艺,杨斌,程志强.过程神经元网络学习算法及软测量方法的研究[J].系统仿真学报,2007,19(7):1456-1459.
[83]Wenjun Jia,Tianyou Chai,Hui Yang.A Hybrid Intelligent Soft-Sensor Method for the Rare Earth Cascade Extraction Process[J].Proceedings of the 6th World Congress on Intelligent Control,2006:4935-4939
[84]常玉清,王福利等.基于支持向量机的生物发酵过程的软测量建模[J].东北大学学报(自然科学版),2005,26(11):1025-1028
[85]郭辉,刘贺平,王玲.KPCA-LS-SVM建模方法及在钢材淬透性中的应用研究[J].控制与决策,2006,21(9):1073-1076
[86]刘瑞兰,牟盛静,苏宏业,褚健.基于支持向量机和粒子群算法的软测量建模 [J].控制理论与应用,2006,23(6):895-899
[87]陈爱军,宋执环,李平.基于矢量基学习的最小二乘支持向量机建模[J].控制理论与应用,2007,24(1):1-5
[88]姜万录,雷亚飞等.基RBFNN建模的动态流量软测量方法研究[J].仪器仪表学报,2008,29(9):1888-1892
[89]颜学峰.基于径基函数加权偏最小二乘回归的干点软测量[J].自动化学报,2007,33(2):193-195.
[90]王胜光.混合软测量方法在污水处理中的研究[D].上海交通大学,2008
[91]桑海峰,王福利等.基于最小二乘支持向量机的发酵过程混合建模[J].仪器仪表学报,2006,27(6):629-633
[92]王华忠,俞金寿.基于混合SVR-PLS方法的丙烯腈收率软测量建模[J].控制与决策,2005,20(5):549-552
[93]仲蔚,俞金寿.基于模糊C均值聚类的多模型软测量建模[J].华东理工大学学报,2000,26(1):83-87
[94]高林,顾幸生.基于模糊聚类分析的多模型软测量技术及其应用[J].自动化仪表,2003,24(08):10-13
[95]张笑天,颜学峰,钱锋.基于多神经网络模型的石脑油干点软测量[J].控制工程,2004,11(31):52-54
[96]张宇,李柠,黄道.基于多神经网络模型的酯化反应软测量[J].华东理工大学学报,2006,31(2):208-211
[97]阚晓旭,金晓明.RBF多模型神经网络软测量技术在湿法磷酸生产中的应用[J].化工自动化与仪表,2006,33(1):64-66
[98]张宇,李柠,黄道.基于多神经网络模型的酯化反应软测量[J].华东理工大学学报(自然科学版),2005,31(2):208-216
[99]李卫,杨煜普,王娜.基于核模糊聚类的多模型LSSVM回归建模[J].控制与决策,2008,23(5):164-166
[100]张宝业.氧化铝超浓相输送系统供料状态不稳定原因分析及对策[J].甘肃冶金,2005,27(2):38-39.
[101]World S etc al.Collinearity problem in linear regression;the partial least squares approach to generalized inverse[J].SIAMT,Sci.Stat.ComPut,1984(5):743-753
[102]Binchini M,Frasconi P,God M.Learning without Local Minima in Radial Basis Function Networks.IEEE Trans on Neural Networks.1995(3):749-755
[103]邱东强,涂亚庆.神经网络控制的现状与展望[J].自动化与仪器仪表,2001(5):1-7
[104]Burge.CJC.A Tutorial on Support Vector Machines for Pattern Recognition.Data Mining and Knowledge Discovery.1998(2):121-167
[105]Alex J.Smola,Bernhard Schoelkopf.A Tutorial on Support Vector Regression,Neuro COLT2 Technical Report Series NC2-TR-1998030,October,1998
[106]叶美盈,汪晓东,张浩然.基于在线最小二乘支持向量机回归的混沌时间序列预测[J].物理学报,Vol.54,No.6,June,2005
[107]蔡冬松,靖继鹏.基于最小二乘支持向量机的数据挖掘应用研究.情报科学,2005,12,Vol.23,No.12
[108]Kennedy J,Eberhart R.Particles warm optimization[A].Proc IEEE Int Conf on Neural Networks[C].Perth:IEEE,1995:1942-1948
[109]Shi Y H,Eberhart R C.Parameter Selection in Particle Swarm Optimization [C]//Annual Conference on Evolutionary Programming,San Diego,1998
[110]马文晓,白晓民,沐连顺.基于人工神经网络和模糊推理的短期负荷预测方法[J].电网技术.2003,27(5):29-32
[111]LIU Jian lin.On-line Soft Sensor for Polyethylene Process with Multiple Production Grades[J].Control Engineering Practice,2007,15:769-778
[112]Bezdek J C.Pattern Recognition with Fuzzy Objective Function Algorithms [M].New York:Plenum Press,1981
[113]李炜,石连生,李征宏.基于双层智能结构的多模型软测量方法研究[J].化工自动化及仪表,2007,34(6):58-61
[2]Brosilow C B.Inferential Control of Process Control.AIChE Journal,1978,24(3):475-840
[3]Brosilow C B.The Structure and Dynamics of Inferential Control System.AIChE Journal,1978,24(3):485-499
[4]Babu Joseph,Coleman B.Brosilow.Inferential Control of Processes:Part Ⅰ.Steady State Analysis and Design[J].AIChE Journal,1978,24(3):485-492
[5]Coleman B.Brosilow,Martin Tong.Part Ⅱ.The Structure and Dynamics of Inferential Control Systems[J].AIChE Journal,1978,24(3):492-500
[6]Babu Joseph.Coleman B.Brosilow.Part Ⅲ.Construction of Optimal and Suboptimal Dynamic Estimators[J].AIChE Journal,1978,24(3):500-509
[7]俞金寿,刘爱伦,张克进.软测量技术及其在石油化工中的应用[M].化学工业出版社.2000
[8]徐敏,俞金寿.软测量技术[M].石油化工自动化.1998,1-3
[9]Gonzalez G D.Soft sensors for processing plants.Proceeding of the Second International Conference on Intelligent Processing and Manufacturing of Materials,1999,(1):59-69
[10]吴举,成庚,代启安.氧化铝超浓相输送系统计量新装置的研究开发[J].轻金属.2003,12:27-29
[11]朱波.氧化铝生产苛性比值软测量神经网络模型的在线修正方法研究[D].中南大学,2005
[12]李海青,黄志尧等.软测量技术原理及应用[M].化学工业出版社.2000,9
[13]刘瑞兰.软测量技术若干问题的研究及工业应用[D].浙江大学,2004
[14]俞金寿.软测量技术在石油化工中的应用[J].石油化工.2000,9(3):221-226
[15]石连生.基于双层智能结构的多模型软测量方法研究[D].兰州理工大学,2008
[16]于静江,周春晖.过程控制中的软测量技术[J].控制理论与应用,1996,Vol.13(2):137-144
[17]骆晨钟,邵惠鹤.软仪表技术及其工业应用[J].仪表技术与传感器,1999,Vol.1:32-39
[18]俞金寿.工业过程控制[M].北京:中国石化出版社,2002
[19]黄凤良.软测量思想与软测量技术[J].计量学报,2004,Vol.25(3):284-288
[20]杜锋,刘全,雷鸣.软测量技术及其在发酵过程中的应用[J].食品科学,2002,23(8):352-356
[21]Tham M T,Montagueand G A,Morris A J,Lant P A.Soft-sensors for process estimation and inferential control.Journal of Process Control,1991,1(1):3-14
[22]Macvoy T J.Contemplative Stance for Chemical Process Automatica.1992,28(2):441-442
[23]Weber R,Brosillow C B.The Use of Secondary Measurement to Improvement Control.AICHE J.1972
[24]Bhat N V,Minderman P A,Mcavoy T J etal.Modeling chemical process system via neural computation.
[25]Bates,J.M.,Granger,C.W.J.The combination of forecasts.Operations Research Quarterly,1969,20:319-325
[26]Wolpert D H.Stacked generalization.Neural Networks.1992,5(2):241-259
[27]Karakuzu C,Ozturk S,Turker M.Modeling,on-line state estimation and fuzzy control of production scale fed-batch baker's yeast fermentation.Control Engineering Practice,2006,(14):959-974
[28]王旭东,邵惠鹤.神经元网络建模技术与软测量技术[J].化工自动化及仪表,1996.23(2):28-31
[29]许勇刚,杨辉.基于RBF网络的稀土萃取过程组分含量软测量[J].稀土,2007,28(5):19-22
[30]杨旭华.神经网络及其在控制中的应用研究[D].浙江大学,2004
[31]董立忠,张荣祥.模糊信息处理及其应用[J].仪器仪表学报,1995,Vol.16(1):88-91
[32]L.Zhou,et al.,Modeling and control for nonlinear time-delay system via pattern RecognitionlEEE Trans.Neural Networks.1992,3(6):991-997.
[33]叶楠,吕勇哉.模式识别在状态估计中的应用[J].仪器仪表学报,1988.9(4):368-374
[34]Cortes C,Vapnik V N.Support vector machine.Machine Learning,1995,(20):273-297
[35]傅永峰.软测量建模方法研究及其工业应用[D].浙江大学,2007
[36]Qi H Y,Zhou X G,Liu L H,Yuan W K,A hybrid neural network-first principles model for fixed-bed reactor Chemical Engineering Science,1999,54(13-14):2521-2526
[37]李向阳,朱学峰,刘焕彬.间歇制浆蒸煮过程的混合建模方法研究[J].中国造纸学报,2001,16(2):24-28
[38]仲蔚,俞金寿.软测量技术及其在加氢裂化分馏塔中的应用[J].华东理工大学学报,1999 25(4):420-423
[39]Dai X,Wang W,Ding Y,Sun Z."Assumed inherent sensor" inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process,Computers and Chemical Engineering,2006,30(8):1203-1225
[40]杨辉,柴天佑.稀土萃取分离过程的优化设定控制[J].控制与决策,2005,20(4):398-402
[41]许光,俞欢军,陶少辉,陈德钊.与机理杂交的支持向量机为发酵过程建模[J].化工学报,2005,56(4):653-658
[42]Zhao Y.A soft sensor based on nonlinear principal component analysis,IEEE Proceedings of the Second International Conference on Machine Learning and Cybernetics,Xi'an,2-5 November 2003,707-710
[43]马朝阳,苏宏业,傅永峰,褚健.基于KPCA-SVR方法的复合肥养分含量建模[J].中国科学技术大学学报,2005,35(增刊):314-321
[44]吕立华,宋执环,李平.用于过程软测量的多小波网络[J].仪器仪表学报,2002,23(5):508-511
[45]常玉清,王小刚,王福利.基于多神经网络模型的软测量方法及应用[J].东北大学学报(自然科学版),2005,26(6):519-522
[46]桂卫华,李勇刚,阳春华,陈志盛.基于改进聚类算法的分布式SVM及其应用[J].控制与决策,2004,19(8):852-856
[47]罗荣富,邵惠鹤.软测量方法及其工业应用[M].上海交大出版社.1994:253-260
[48]徐敏.软测量方法和应用研究[D].华东理工大学,1999
[49]Alber.J.E.Online Data Reconciliation and Error Detection.H.P.1997.17(7):101-104
[50]李红军,秦永胜,徐用愚.化工过程中的数据协调及显著误差检测[J].化工自动化及仪表,1997,24(2):25-29
[51]荣冈,金晓明,王树青.软测量技术及其应用[J].化工自动化及仪表,1999,26(4):70-73
[52]Jizhen Liu,Zheng Zhao,Deliang Zeng,Yanqiao Chen.SOFT-SENSING MODEL OF OXYGEN CONTENT BASED ON DATA FUSION[J].Proceedings of the Fourth International Conference on Machine Learning and Cybernetics,2005:3991-3995
[53]Jianxu Luo,Huihe Shao.Soft sensing modeling using neurofuzzy system based on Rough Set Theory[J].Proceedings of the American Control Conference,2002:543-548
[54]Dibo Hou,Zekui Zhou,Guangxin Zhang.ON-LINE MEASUREMENT FOR THE BHE FOULING OF BREWERY WORT EVAPORATOR USING A SOFE SENSING APPROACH[J].IEEE,2003:95-98
[55]Wanliang Wang,Min Ren.Soft-sensing Method for Wastewater Treatment Based on BP Neural Network[J].Proceedings of the 4th World Congress on Intelligent Control and Autoination,2002::2330-2332
[56]Zaiwen Liu,Zhengxiang Wang,Fuxia Xue,Chaozhen Hou,Guoqiang Qi.Study on the Intelligent Soft Sensing Method for Sewage Disposal System[J].IEEE, 2003:181-183
[57] Peijin Wang. Design and Application of Soft Sensor Object in Water Treatment Plant[J].Machine Learning and Cybernetics, 2007 International Conference ,2007:2678 - 2682
[58] Wei Guo,Guochu Chen,Jinshou Yu.The Kalman Particle Swarm Optimization Algorithm and Its Application in Soft-sensor of Acrylonitrile Yield[J].IEEE,2005:124-127
[59] Yufa Xu , Guochu, Chen, Jinshou Yu, Particle Swarm Optimization Fuzzy Neural Network and its Application in Soft-Sensor Modeling of Acrylonitrile Yield[J].Machine Learning and Cybernetics, 2007 International Conference, 2007:1994 -1999
[60] Huajun Feng, Haoran Zhang, Soft Sensor Technique based on Robust SVM[J].The 2005 IEEE International Conference on Neural Networks and Brain, 2005:1704-1707.
[61] Haoran Zhang,Xiaodong Wang,Changjiang Zhang,Ganyun Lv.A New Soft Sensor Method Based on SVM[J].IEEE,2006:546-549.
[62] Rui Feng,Wei Shen,Huihe Shao.A Soft Sensor Modeling Approach Using Support Vector Machines[J].IEEE,2003:3702-3707.
[63] Mingguang Zhang,Zhanming Li,Wenhui Li.Study on Least Squares Support Vector Machines Algorithm and its Application[J].Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence,2005.
[64] Wensen An,Yanguang Sun.AN INFORMATION-GEOMETRICAL APPROACH TO KERNEL CONSTRUCTION IN SVM AND ITS APPLICATION IN SOFT-SENSOR MODELING[J].IEEE,2005:4356-4359
[65] Wang Jun,Peng Hong,Xiao Jian.Soft Sensor Model Based on Improved Fuzzy Neural Network[J].IEEE,2005:694-697.
[66] Tao Ye,Xuefeng Zhu,Xiangyang Li.A Soft Sensing Method Based on the Temporal Difference Learning Algorithm[J].Proceedings of the 6th World Congress on Intelligent Control,2006:4861-4865
[67] Yuqing Chang,Zhe Lv,Fuli Wang,Zhizhong Mao,Xiaogang Wang.Soft Sensing Modeling Based on Stacked Least Square-Support Vector Machine and Its Application[J].Proceedings of the 6th World Congress on Intelligent Control,2006:4846-4850
[68] Jun Wang, Hong Peng.Multi-scale Wavelet Support Vector Regression for Soft Sensor Modeling[J].IEEE,2005:284-287
[69]骆中华,刘瑞兰等.基于PLS快速剪枝法的RBF神经网络软测量建模方法和应用[J].化工自动化及仪表,2005,32(3):19-21
[70]王华忠,俞金寿.核函数方法及其在软测量建模中的应用研究[J].自动化仪表,2004,25(10):22-25
[71]张英,苏宏业,诸健.基于ISVM的软测量建模及其在PX生产中的应用研究[J].2005,20(10):1102-1106
[72]成忠,陈德钊.WBRPLSR方法及其在化工软测量中的应用[J].化工学报,2005,56(2):291-295
[73]邱书波,王化祥,刘雪真.RBF神经网络在卡伯值软测量中的应用研究[J].电子测量与仪器学报,2005,19(1):30-34.
[74]刘翠玲,孙晓荣等.RBF神经网络在超高压釜内油温软测量中的应用[J].仪表技术与传感器,2005,(4):11-13.
[75]谭超.基于支持向量机的软测量技术及其应用[J].传感器技术,2005,24(8):77-79.
[76]孙玉冲,陈明忠等.基于支持向量机的赖氨酸发酵生物参数软测量[J].仪器仪表学报,2008,29(10):2065-2070.
[77]李凡,吴强等.基于递推PLS的自适应钢温软测量模型[J].控制工程,2007,14(2):147-150
[78]段中兴,嵇启春.催化剂粉尘浓度软测量建模研究与应用[J].系统仿真学报,2008,20(14):3899-3902
[79]卢胜利,吴学军等.引黄灌渠斗口流量神经元网络软测量模型[J].计算机控制,2005,31(13):36-37
[80]陈国初,俞金寿.增强型微粒群优化算法及其在软测量中的应用[J].控制与决策,2005,20(4):377-381
[81]宫唤春.RBF神经网络软测量技术在汽油机CO排放中的应用[J].拖拉机与农用运输车,2007,34(5):48-50
[82]刘载文,王正祥,王小艺,杨斌,程志强.过程神经元网络学习算法及软测量方法的研究[J].系统仿真学报,2007,19(7):1456-1459.
[83]Wenjun Jia,Tianyou Chai,Hui Yang.A Hybrid Intelligent Soft-Sensor Method for the Rare Earth Cascade Extraction Process[J].Proceedings of the 6th World Congress on Intelligent Control,2006:4935-4939
[84]常玉清,王福利等.基于支持向量机的生物发酵过程的软测量建模[J].东北大学学报(自然科学版),2005,26(11):1025-1028
[85]郭辉,刘贺平,王玲.KPCA-LS-SVM建模方法及在钢材淬透性中的应用研究[J].控制与决策,2006,21(9):1073-1076
[86]刘瑞兰,牟盛静,苏宏业,褚健.基于支持向量机和粒子群算法的软测量建模 [J].控制理论与应用,2006,23(6):895-899
[87]陈爱军,宋执环,李平.基于矢量基学习的最小二乘支持向量机建模[J].控制理论与应用,2007,24(1):1-5
[88]姜万录,雷亚飞等.基RBFNN建模的动态流量软测量方法研究[J].仪器仪表学报,2008,29(9):1888-1892
[89]颜学峰.基于径基函数加权偏最小二乘回归的干点软测量[J].自动化学报,2007,33(2):193-195.
[90]王胜光.混合软测量方法在污水处理中的研究[D].上海交通大学,2008
[91]桑海峰,王福利等.基于最小二乘支持向量机的发酵过程混合建模[J].仪器仪表学报,2006,27(6):629-633
[92]王华忠,俞金寿.基于混合SVR-PLS方法的丙烯腈收率软测量建模[J].控制与决策,2005,20(5):549-552
[93]仲蔚,俞金寿.基于模糊C均值聚类的多模型软测量建模[J].华东理工大学学报,2000,26(1):83-87
[94]高林,顾幸生.基于模糊聚类分析的多模型软测量技术及其应用[J].自动化仪表,2003,24(08):10-13
[95]张笑天,颜学峰,钱锋.基于多神经网络模型的石脑油干点软测量[J].控制工程,2004,11(31):52-54
[96]张宇,李柠,黄道.基于多神经网络模型的酯化反应软测量[J].华东理工大学学报,2006,31(2):208-211
[97]阚晓旭,金晓明.RBF多模型神经网络软测量技术在湿法磷酸生产中的应用[J].化工自动化与仪表,2006,33(1):64-66
[98]张宇,李柠,黄道.基于多神经网络模型的酯化反应软测量[J].华东理工大学学报(自然科学版),2005,31(2):208-216
[99]李卫,杨煜普,王娜.基于核模糊聚类的多模型LSSVM回归建模[J].控制与决策,2008,23(5):164-166
[100]张宝业.氧化铝超浓相输送系统供料状态不稳定原因分析及对策[J].甘肃冶金,2005,27(2):38-39.
[101]World S etc al.Collinearity problem in linear regression;the partial least squares approach to generalized inverse[J].SIAMT,Sci.Stat.ComPut,1984(5):743-753
[102]Binchini M,Frasconi P,God M.Learning without Local Minima in Radial Basis Function Networks.IEEE Trans on Neural Networks.1995(3):749-755
[103]邱东强,涂亚庆.神经网络控制的现状与展望[J].自动化与仪器仪表,2001(5):1-7
[104]Burge.CJC.A Tutorial on Support Vector Machines for Pattern Recognition.Data Mining and Knowledge Discovery.1998(2):121-167
[105]Alex J.Smola,Bernhard Schoelkopf.A Tutorial on Support Vector Regression,Neuro COLT2 Technical Report Series NC2-TR-1998030,October,1998
[106]叶美盈,汪晓东,张浩然.基于在线最小二乘支持向量机回归的混沌时间序列预测[J].物理学报,Vol.54,No.6,June,2005
[107]蔡冬松,靖继鹏.基于最小二乘支持向量机的数据挖掘应用研究.情报科学,2005,12,Vol.23,No.12
[108]Kennedy J,Eberhart R.Particles warm optimization[A].Proc IEEE Int Conf on Neural Networks[C].Perth:IEEE,1995:1942-1948
[109]Shi Y H,Eberhart R C.Parameter Selection in Particle Swarm Optimization [C]//Annual Conference on Evolutionary Programming,San Diego,1998
[110]马文晓,白晓民,沐连顺.基于人工神经网络和模糊推理的短期负荷预测方法[J].电网技术.2003,27(5):29-32
[111]LIU Jian lin.On-line Soft Sensor for Polyethylene Process with Multiple Production Grades[J].Control Engineering Practice,2007,15:769-778
[112]Bezdek J C.Pattern Recognition with Fuzzy Objective Function Algorithms [M].New York:Plenum Press,1981
[113]李炜,石连生,李征宏.基于双层智能结构的多模型软测量方法研究[J].化工自动化及仪表,2007,34(6):58-61