基于“内含传感器”的粗糙模糊神经网络逆方法的软测量研究与应用
|
摘要
软测量技术为解决工业控制系统在线检测过程中,一些控制参数无法通过检测仪表进行直接检测或由于检测仪表价格昂贵难以应用等实际难题提供了有效的技术手段。
神经网络逆理论将神经网络对非线性系统的逼近能力、自学习能力以及容错能力的特点与逆系统方法有机的结合起来,借助于神经网络逼近原系统的逆系统。用以进行动态测量,则将会对逆系统方法的理论研究和传感器动态特性的工程应用等方面都将产生积极深远的意义。
粗糙集理论是一种研究不完整、不确定知识和数据的表达、学习、归纳的理论方法。其在不需额外的先验知识的情况下,通过描绘知识表达中不同属性的重要性,进行知识表达空间约减,去掉冗余信息,简化信息的表达空间维数。
本文沿着“软测量技术——神经网络逆理论——粗糙集理论—粗糙模糊神经网络逆理论方法的提出——将粗糙模糊神经网络逆方法应用到实际软测量中”的思路对作者在课题研究所做的工作进行了详细的介绍。其中运用粗糙集理论的属性约减和规则提取方法来构建糊神经网络逆是本论文的研究重点。
本文主要以红霉素发酵过程中的实测数据为例,对粗糙模糊神经网络逆的输入样本数据的处理首先进行了描述。文章分别对样本数据的误差处理,归一化进行了详细的说明,并通过Matlab等仿真软件对处理后的结果进行了仿真,以说明该方法的有效性。
最后,通过粗糙集理论对经过模糊化后的模糊数据集进行属性约减和规则提取构建相应的粗糙模糊神经网络来逼近“内含传感器”的逆,以达到对红霉素发酵过程中的重要参数菌丝浓度、总糖浓度、产物浓度等难以在线测量的数据的软测量。将获得的预测结果与用相同数据进行软测量的神经网络逆预测的结果进行了比较。通过仿真结果发现粗糙神经网络在预测精度和泛化能力上都有一定的提高,基本满足了对发酵过程进一步进行优化控制的要求。
研究结果表明,该建模方法在预测精度和泛化能力上都具有一定的优越性。
Soft Sensor Technique is an effective approach which is used to solve some actual puzzles,caused by the unavailability of measures in the controlling process variables measuring or the high price of measures,in industrial process control systems.
Neural network inverse theory integrates neural network approximation ability,self-learning ability and fault tolerance characteristics of nonlinear systems with inverse system method. Through the use of neural network approximation of the inverse system with original system,used for dynamic measurements,inverse system method will be on the theoretical study and the dynamic characteristics of the sensor project application will have a positive far-reaching significant.
Rough set theory is a theoretical method which is applied to study the expression,learning and inducing of incomplete and uncertain data. It can reduce the knowledge-expression space;cancel the redundant information via describing the importance of different attribute in knowledge expression without prior knowledge.
In this paper down,"Soft-sensing technology——Neural Network inverse theory——Rough Set Theory——The theory of rough fuzzy neural network inverse method proposed will be rough fuzzy neural network inverse method is applied to soft sensor in" line of thinking on the subject of the author at the Institute to do the work a detailed introduction.The use of rough set theory in which the attribute reduction and rule extraction methods to build neural network inverse paste is the focus of this thesis research
In this paper,as an example of the measured data of erythromycin fermentation process.The input sample data are processed firstly of the rough fuzzy neural network inverse.Article separately detailed description of carried out the error data on the sample treatment, normalized,and through Matlab simulation software,such as treatment results after the simulation,to illustrate the effectiveness of the method.
Finally,after a rough set theory to fuzzy after the fuzzy data set attribute reduction and rule extraction to construction of the rough fuzzy neural network approximation "includes sensors Inverse",so as to achieve on difficult-line measurement data soft sensor of the important parameters of mycelium concentration,total sugar concentration,and the product of the concentration in the erythromycin fermentation process. Receive the prediction results with the same soft-sensing data of ANN inverse prediction results were compared.The simulation results showed that rough neural network in prediction accuracy and generalization ability is on the more improvement,basically meet the needs of a further optimize the fermentation process control.
The results show that the modeling method in the prediction accuracy and generalization ability on must have superiority.
神经网络逆理论将神经网络对非线性系统的逼近能力、自学习能力以及容错能力的特点与逆系统方法有机的结合起来,借助于神经网络逼近原系统的逆系统。用以进行动态测量,则将会对逆系统方法的理论研究和传感器动态特性的工程应用等方面都将产生积极深远的意义。
粗糙集理论是一种研究不完整、不确定知识和数据的表达、学习、归纳的理论方法。其在不需额外的先验知识的情况下,通过描绘知识表达中不同属性的重要性,进行知识表达空间约减,去掉冗余信息,简化信息的表达空间维数。
本文沿着“软测量技术——神经网络逆理论——粗糙集理论—粗糙模糊神经网络逆理论方法的提出——将粗糙模糊神经网络逆方法应用到实际软测量中”的思路对作者在课题研究所做的工作进行了详细的介绍。其中运用粗糙集理论的属性约减和规则提取方法来构建糊神经网络逆是本论文的研究重点。
本文主要以红霉素发酵过程中的实测数据为例,对粗糙模糊神经网络逆的输入样本数据的处理首先进行了描述。文章分别对样本数据的误差处理,归一化进行了详细的说明,并通过Matlab等仿真软件对处理后的结果进行了仿真,以说明该方法的有效性。
最后,通过粗糙集理论对经过模糊化后的模糊数据集进行属性约减和规则提取构建相应的粗糙模糊神经网络来逼近“内含传感器”的逆,以达到对红霉素发酵过程中的重要参数菌丝浓度、总糖浓度、产物浓度等难以在线测量的数据的软测量。将获得的预测结果与用相同数据进行软测量的神经网络逆预测的结果进行了比较。通过仿真结果发现粗糙神经网络在预测精度和泛化能力上都有一定的提高,基本满足了对发酵过程进一步进行优化控制的要求。
研究结果表明,该建模方法在预测精度和泛化能力上都具有一定的优越性。
Soft Sensor Technique is an effective approach which is used to solve some actual puzzles,caused by the unavailability of measures in the controlling process variables measuring or the high price of measures,in industrial process control systems.
Neural network inverse theory integrates neural network approximation ability,self-learning ability and fault tolerance characteristics of nonlinear systems with inverse system method. Through the use of neural network approximation of the inverse system with original system,used for dynamic measurements,inverse system method will be on the theoretical study and the dynamic characteristics of the sensor project application will have a positive far-reaching significant.
Rough set theory is a theoretical method which is applied to study the expression,learning and inducing of incomplete and uncertain data. It can reduce the knowledge-expression space;cancel the redundant information via describing the importance of different attribute in knowledge expression without prior knowledge.
In this paper down,"Soft-sensing technology——Neural Network inverse theory——Rough Set Theory——The theory of rough fuzzy neural network inverse method proposed will be rough fuzzy neural network inverse method is applied to soft sensor in" line of thinking on the subject of the author at the Institute to do the work a detailed introduction.The use of rough set theory in which the attribute reduction and rule extraction methods to build neural network inverse paste is the focus of this thesis research
In this paper,as an example of the measured data of erythromycin fermentation process.The input sample data are processed firstly of the rough fuzzy neural network inverse.Article separately detailed description of carried out the error data on the sample treatment, normalized,and through Matlab simulation software,such as treatment results after the simulation,to illustrate the effectiveness of the method.
Finally,after a rough set theory to fuzzy after the fuzzy data set attribute reduction and rule extraction to construction of the rough fuzzy neural network approximation "includes sensors Inverse",so as to achieve on difficult-line measurement data soft sensor of the important parameters of mycelium concentration,total sugar concentration,and the product of the concentration in the erythromycin fermentation process. Receive the prediction results with the same soft-sensing data of ANN inverse prediction results were compared.The simulation results showed that rough neural network in prediction accuracy and generalization ability is on the more improvement,basically meet the needs of a further optimize the fermentation process control.
The results show that the modeling method in the prediction accuracy and generalization ability on must have superiority.
引文
[1]荣冈,金晓明,王树青.先进控制技术应用.第三讲.软测量技术及其应用,化工自动化仪表1999.26(4):70-74.
[2]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
[3]骆晨钟,邵慧鹤.软仪表技术极其应用[J].仪表技术与传感器1999(1):32-39.
[4]孙欣,王金春,何声亮.过程观测两[J].自动化仪表1995.16(8):1-5
[5]王士同.神经模糊系统极其应用[M].北京:北京航空航天大学出版社.1998:45-46
[6]周鸣争.基于神经网络的软测量模型应用[J].仪器仪表学报.1999.20(6):654-656
[7]子静江,周春晖.过程控制中的软测量技术[J].控制理论与应用.1996.13(4):137-144
[8]俞金寿,刘爱伦.软测量技术极其应用[J].世界仪表和自动化.1997.1(12):18-20
[9]徐敏,俞金寿.软测量技术[J].石油化工自动化.1998.(2):1-3
[10]朱学峰.软测量技术极其应用[J].华南理工大学学报(自然科学版).2002.30(11):61-67
[11]骆晨钟,邵惠鹤,吴俊生.基于机理分析的方法分析实现催化裂化反应预测转化率.产品产率软测量[J].化工自动化仪表.1999.26(2):29-33
[12]Adilson Jose de Assis.Rusbens Maciel Filho.Soft Sensors development for on-line bioreactor state estimation[J].Computer and chemical Engineering.2000.24:1009-1103
[13]Pawlak Z.Rough Set approach to knowledge-based decision support[J]European Journal of Op- creational Research.1997
[14]何丹.非线性控制系统的神经网络逆系统方法.东南大学博士学位论文.1999
[15]戴先中.多变量非线性系统的神经网络逆控制方法[M]北京:科学出版社.2005
[16]欧阳平凯.发酵工程关键技术极其应用.北京:化学工业出版社,2005
[17]罗荣福,邵惠鹤.模糊神经网络方法及其在推断控制中的应用[C]第一届全球华人智能控制与智能自动化大会论文集.北京:科学出版社.1993:763-769
[18]Mei.Jywan Syu.Neural network modeling of fed.Bath cell growth pattern[J]Biotechnology and Bioengineering.1993(42):376-380
[19]L.F.M.Zorzetto.Process modeling development through artificial-neural network and hybrid models[J].Computers and Chemical Engineering.24(2000):1335.1360
[20]吴晓汉.基于神经网络的软测量技术及应用[J].自动化与仪器仪表.1998.12-17
[21]Liang Tan.State estimation for optimal control of a non-linear System[J].IEEE,1991(9):2235-2239
[22]Parrish.J.R.and Brosilow.C.B.No-linear inferential control[J]AICHEJ.24(1998):364-644
[23]叶楠,吕勇哉.模式识别在状态估计中的应用--类软测量技术[J].仪器仪表学报.1998:633-644
[24]Zhou.L.teal.Modeling and control for nonlinear time-delay system via pattern recognition approach[C].Preprints of 2~(nd) IFAC Workshop on Artificial Intelligence in real time control.1989(7):12
[25]张泉灵,王树青.基于神经网络的非线性预测函数控制[J].浙江大学学报.2001:9(5)
[26]张增科.青霉素发酵过程专家系统[J].药物进展.1997(2):27-97
[27]Wills.M.J.et.al.Artificial network in process estimation and control[J].Automatic.1992:1183-1187
[28]王国胤.Rough集理论与知识获取[M].西安交通大学出版社
[29]Skpwron A the discernibility matrices and functions in Information system R Slowmski Intelligent decision support.Handbook of Applications and Advances of the rough set theory [J]kluwer Academe publishers.1992.331-363
[30]张文修等.粗糙集理论与方法[M].北京:科学出版社.2001
[31]Tengfei Zhang.Jianmei Xiao.Dynamic System Modeling based on Rough Set and RBF Neural Networks Proceedings of the 5~(th) World Congress on Intelligent Control and Automation[J].June 15-19.2004 Hangzhou.PR China.PP 185-189
[32]王东锴,梁樑.含冲突的决策表中的决策规则发现[J].系统工程.2003 Vol.21 No.1
[33]李春文,冯元琨.多变量非线性控制的逆系统方法.清华大学出版社.1991
[34]余建平.基于改进神经网络的污水处理参数软测量模型研究[D]重庆:重庆大学城市建设与环境工程学院.2005
[35]卿晓霞,余建平,王波.基于粗糙集--神经网络的污水参数软测量技术研究[J].2005.3
[36]孟军,刘永超,莫海波.基于粗糙集理论的不完备数据填补方法.计算机工程与应用.2008.44(6):174-177
[37]候利娟,王国胤,聂能,吴渝.粗糙集理论中的离散化问题.计算机科学2000 Vol.27 No.12
[38]周献中,黄兵.基于粗集的不完备信息系统属性约减 南京理工大学学报Vol.27.No.5
[39]H.劳格尔特,K.弗里切著(黄沙,李生训译).多变复数[M].北京:科学出版社,1988
[40]赵怀林.微机测量与数据误差处理方法 电测与仪表.2002.Vol.39.No.437
[41]邢杰 减免啤酒生产过程检测数据误差的认识.啤酒科技2005.5
[42]韩力群.人工神经网络理论.设计与应用[M]北京:化学工业出版社.2002.53-55
[43]白厚义.回归设计及多元统计分析[M].南宁:广西科学技术出版社.2003.178-205
[44]梅长林,周家良.实用统计方法[M].北京:科学出版社.2002,53-65
[45]陈元青,陈琦,王树青.多元统计分析方法在链霉素发酵中的应用[J]生物工程学报.1993.3(15):368-372
[46]杜艳丽,张芳,姜长洪.神经元网络在谷氨酸发酵过程中的应用[J]沈阳化工学院学报.2005.19(3):228-230
[47]何明,冯博琴,马兆丰,傅向华.一种基于粗糙集的神经网络构造方法.西安交通大学学报.2004 Vol.38 No.12
[48]叶楠,吕勇哉.模式识别在状态估计中的应用--一类软测量技术[J].仪器仪表学报.1988,9(4):368-374
[49]Zhou,L.et al.Modeling and control for Nonlinear Time-Delay System via Pattern Recognition Approach[C].Preprints of 2~(nd) TFAC Workshop on Artificial Intelligence in Real Time Control,1989,7-12
[50]穆罕默德·阿塔,蒋慰孙.精馏塔板效率的在线模式识别[J].信息与控制.1993,22(1):47-49
[51]Fu Chunsheng.Et al.Application of Fuzzy Set Theory to Biochemical Process-A new model for problem diagnosis.Chinese J.of Biotechnology,1989,5(2)
[52]于静江,周春晖.原油塔控制中的只能方法[C].第一届全球华人智能控制与智能控制自动化大会论文集.北京:科学出版社.1993:471-475
[53]陈双叶,易继铠.基于粗糙集理论的模糊神经网络及其在化纤生产过程中的应用[J].中国工程科学,2001,3(12):42-46.
[54]於志军,王士同.基于粗糙集的模糊神经网络建模研究.[J].华东船舶工业学院学报,2000,14(3):1-6.
[55]许志兴,丁运亮.一种基于粗糙集理论的粗糙神经网络构造方法[J].南京航空航天大学学报.2001,33(4):355-358
[56]WuZhaocong,LiDeren.Neural Network Based on Rough Sets and Its Application to Remote Sensing lmage Classification[J].Geo-spatial Information Science.2002,5(2):17-21.
[57]Pabitra Mitra,Sushmita Mitra,Sanka K.Pal.Modal Rough Fuzzy MLP;Evolutionary Design [C].Tokyo:Ning zhong,Andrzej skowron,setsuo ohsuga(Eds),New Direction in Rough Sets,Data Mining,and Granular-Soft Computing.7~(th) international workshop;proceeding/RSFDG RC'99,Nov.9-11,Yamaguchi,Japan,Notes in Artificial Intelligence,springer,1999,128-136.
[58]Buckley J.J,Hayashi Yoichi.Fuzzy neural networks:a Survey[J].Fuzzy Sets and Systems,66:1-13,1994.
[59]Jang J.R.Self-learning fuzzy logic control based on temporal back-propagation[C].IEEE Ttrans.Neural Networks,3(5):714-723,1992.
[60]Wang Li,J.M.Mendel.Generating fuzzy rules by learning from examples[C].IEEET Trans,Neural Networks,40(12):1320-1336,1991.
[61]Jang J.R.ANFIS,Adaptive NetworkBased Fuzzy Inference System[J].IEEE Transactions on Systems,Man and Cyemetics,23(3):665-684,1993.
[62]Numberger.A,D.Nauck,R.Kruse.Neural-fuzzy control based on the NEFCON-model:recent developments[J].Soft Computing,2:168-182,1999.
[63]Tran.L.Haoi,S.Osowski.Neural-fuzzy TSK network for approximation of static and dynamic functions[J].Control and Cybernetics,31(2):309-326,2002.
[64]Nauck.D,Kruse.R.Neural-fuzzy systems for function approximation[J].Fuzzy Sets and Systems,10:261-27 i,1999.
[65]Sanchez.E.Genetic algorithms,Neural networks and fuzzy logic systems[C].In Proc.Second International Conference on Fuzzy Logic and Neural Networks.lizuka.17-19,1992.
[66]Machado.R.J,A.F.Rocha.Evaluative Fuzzy Neural networks[C].In Proc.First.IEEE.International Conference on Fuzzy Systems(RJZZ-IEEE 92),San Diego,493-500,1992.
[67]Buckley J.J,K.D.Reily,Penmetcha.K.V.Back propagation and genetic algorithms for training Fuzzy Neural Nets q.Genetic Algorithms and Soft Computing,505-532,1996.
[68]王树青,元英进.生化过程自动化技术[M].北京:化学工业出版社,1999.
[69]蒋慰孙.首届全国生化过程模型化与控制学术讨论会论文集[C].上海:华东化工学院出版社,1989.
[70]王树青.中国第二届生化过程模型化与控制技术讨论会论文集[C].杭州:浙江大学出版社,1990
[71]Xianzhong Dai,Dongchuan Yu,Yuhan Ding et al,ANN Inversion Based Soft-Sensing of Biochemical Parameters in Erythromycin Fermentation[C],Prdceeding of 2004 International Coference on Infornation Acquisition,2004,262-266.
[2]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
[3]骆晨钟,邵慧鹤.软仪表技术极其应用[J].仪表技术与传感器1999(1):32-39.
[4]孙欣,王金春,何声亮.过程观测两[J].自动化仪表1995.16(8):1-5
[5]王士同.神经模糊系统极其应用[M].北京:北京航空航天大学出版社.1998:45-46
[6]周鸣争.基于神经网络的软测量模型应用[J].仪器仪表学报.1999.20(6):654-656
[7]子静江,周春晖.过程控制中的软测量技术[J].控制理论与应用.1996.13(4):137-144
[8]俞金寿,刘爱伦.软测量技术极其应用[J].世界仪表和自动化.1997.1(12):18-20
[9]徐敏,俞金寿.软测量技术[J].石油化工自动化.1998.(2):1-3
[10]朱学峰.软测量技术极其应用[J].华南理工大学学报(自然科学版).2002.30(11):61-67
[11]骆晨钟,邵惠鹤,吴俊生.基于机理分析的方法分析实现催化裂化反应预测转化率.产品产率软测量[J].化工自动化仪表.1999.26(2):29-33
[12]Adilson Jose de Assis.Rusbens Maciel Filho.Soft Sensors development for on-line bioreactor state estimation[J].Computer and chemical Engineering.2000.24:1009-1103
[13]Pawlak Z.Rough Set approach to knowledge-based decision support[J]European Journal of Op- creational Research.1997
[14]何丹.非线性控制系统的神经网络逆系统方法.东南大学博士学位论文.1999
[15]戴先中.多变量非线性系统的神经网络逆控制方法[M]北京:科学出版社.2005
[16]欧阳平凯.发酵工程关键技术极其应用.北京:化学工业出版社,2005
[17]罗荣福,邵惠鹤.模糊神经网络方法及其在推断控制中的应用[C]第一届全球华人智能控制与智能自动化大会论文集.北京:科学出版社.1993:763-769
[18]Mei.Jywan Syu.Neural network modeling of fed.Bath cell growth pattern[J]Biotechnology and Bioengineering.1993(42):376-380
[19]L.F.M.Zorzetto.Process modeling development through artificial-neural network and hybrid models[J].Computers and Chemical Engineering.24(2000):1335.1360
[20]吴晓汉.基于神经网络的软测量技术及应用[J].自动化与仪器仪表.1998.12-17
[21]Liang Tan.State estimation for optimal control of a non-linear System[J].IEEE,1991(9):2235-2239
[22]Parrish.J.R.and Brosilow.C.B.No-linear inferential control[J]AICHEJ.24(1998):364-644
[23]叶楠,吕勇哉.模式识别在状态估计中的应用--类软测量技术[J].仪器仪表学报.1998:633-644
[24]Zhou.L.teal.Modeling and control for nonlinear time-delay system via pattern recognition approach[C].Preprints of 2~(nd) IFAC Workshop on Artificial Intelligence in real time control.1989(7):12
[25]张泉灵,王树青.基于神经网络的非线性预测函数控制[J].浙江大学学报.2001:9(5)
[26]张增科.青霉素发酵过程专家系统[J].药物进展.1997(2):27-97
[27]Wills.M.J.et.al.Artificial network in process estimation and control[J].Automatic.1992:1183-1187
[28]王国胤.Rough集理论与知识获取[M].西安交通大学出版社
[29]Skpwron A the discernibility matrices and functions in Information system R Slowmski Intelligent decision support.Handbook of Applications and Advances of the rough set theory [J]kluwer Academe publishers.1992.331-363
[30]张文修等.粗糙集理论与方法[M].北京:科学出版社.2001
[31]Tengfei Zhang.Jianmei Xiao.Dynamic System Modeling based on Rough Set and RBF Neural Networks Proceedings of the 5~(th) World Congress on Intelligent Control and Automation[J].June 15-19.2004 Hangzhou.PR China.PP 185-189
[32]王东锴,梁樑.含冲突的决策表中的决策规则发现[J].系统工程.2003 Vol.21 No.1
[33]李春文,冯元琨.多变量非线性控制的逆系统方法.清华大学出版社.1991
[34]余建平.基于改进神经网络的污水处理参数软测量模型研究[D]重庆:重庆大学城市建设与环境工程学院.2005
[35]卿晓霞,余建平,王波.基于粗糙集--神经网络的污水参数软测量技术研究[J].2005.3
[36]孟军,刘永超,莫海波.基于粗糙集理论的不完备数据填补方法.计算机工程与应用.2008.44(6):174-177
[37]候利娟,王国胤,聂能,吴渝.粗糙集理论中的离散化问题.计算机科学2000 Vol.27 No.12
[38]周献中,黄兵.基于粗集的不完备信息系统属性约减 南京理工大学学报Vol.27.No.5
[39]H.劳格尔特,K.弗里切著(黄沙,李生训译).多变复数[M].北京:科学出版社,1988
[40]赵怀林.微机测量与数据误差处理方法 电测与仪表.2002.Vol.39.No.437
[41]邢杰 减免啤酒生产过程检测数据误差的认识.啤酒科技2005.5
[42]韩力群.人工神经网络理论.设计与应用[M]北京:化学工业出版社.2002.53-55
[43]白厚义.回归设计及多元统计分析[M].南宁:广西科学技术出版社.2003.178-205
[44]梅长林,周家良.实用统计方法[M].北京:科学出版社.2002,53-65
[45]陈元青,陈琦,王树青.多元统计分析方法在链霉素发酵中的应用[J]生物工程学报.1993.3(15):368-372
[46]杜艳丽,张芳,姜长洪.神经元网络在谷氨酸发酵过程中的应用[J]沈阳化工学院学报.2005.19(3):228-230
[47]何明,冯博琴,马兆丰,傅向华.一种基于粗糙集的神经网络构造方法.西安交通大学学报.2004 Vol.38 No.12
[48]叶楠,吕勇哉.模式识别在状态估计中的应用--一类软测量技术[J].仪器仪表学报.1988,9(4):368-374
[49]Zhou,L.et al.Modeling and control for Nonlinear Time-Delay System via Pattern Recognition Approach[C].Preprints of 2~(nd) TFAC Workshop on Artificial Intelligence in Real Time Control,1989,7-12
[50]穆罕默德·阿塔,蒋慰孙.精馏塔板效率的在线模式识别[J].信息与控制.1993,22(1):47-49
[51]Fu Chunsheng.Et al.Application of Fuzzy Set Theory to Biochemical Process-A new model for problem diagnosis.Chinese J.of Biotechnology,1989,5(2)
[52]于静江,周春晖.原油塔控制中的只能方法[C].第一届全球华人智能控制与智能控制自动化大会论文集.北京:科学出版社.1993:471-475
[53]陈双叶,易继铠.基于粗糙集理论的模糊神经网络及其在化纤生产过程中的应用[J].中国工程科学,2001,3(12):42-46.
[54]於志军,王士同.基于粗糙集的模糊神经网络建模研究.[J].华东船舶工业学院学报,2000,14(3):1-6.
[55]许志兴,丁运亮.一种基于粗糙集理论的粗糙神经网络构造方法[J].南京航空航天大学学报.2001,33(4):355-358
[56]WuZhaocong,LiDeren.Neural Network Based on Rough Sets and Its Application to Remote Sensing lmage Classification[J].Geo-spatial Information Science.2002,5(2):17-21.
[57]Pabitra Mitra,Sushmita Mitra,Sanka K.Pal.Modal Rough Fuzzy MLP;Evolutionary Design [C].Tokyo:Ning zhong,Andrzej skowron,setsuo ohsuga(Eds),New Direction in Rough Sets,Data Mining,and Granular-Soft Computing.7~(th) international workshop;proceeding/RSFDG RC'99,Nov.9-11,Yamaguchi,Japan,Notes in Artificial Intelligence,springer,1999,128-136.
[58]Buckley J.J,Hayashi Yoichi.Fuzzy neural networks:a Survey[J].Fuzzy Sets and Systems,66:1-13,1994.
[59]Jang J.R.Self-learning fuzzy logic control based on temporal back-propagation[C].IEEE Ttrans.Neural Networks,3(5):714-723,1992.
[60]Wang Li,J.M.Mendel.Generating fuzzy rules by learning from examples[C].IEEET Trans,Neural Networks,40(12):1320-1336,1991.
[61]Jang J.R.ANFIS,Adaptive NetworkBased Fuzzy Inference System[J].IEEE Transactions on Systems,Man and Cyemetics,23(3):665-684,1993.
[62]Numberger.A,D.Nauck,R.Kruse.Neural-fuzzy control based on the NEFCON-model:recent developments[J].Soft Computing,2:168-182,1999.
[63]Tran.L.Haoi,S.Osowski.Neural-fuzzy TSK network for approximation of static and dynamic functions[J].Control and Cybernetics,31(2):309-326,2002.
[64]Nauck.D,Kruse.R.Neural-fuzzy systems for function approximation[J].Fuzzy Sets and Systems,10:261-27 i,1999.
[65]Sanchez.E.Genetic algorithms,Neural networks and fuzzy logic systems[C].In Proc.Second International Conference on Fuzzy Logic and Neural Networks.lizuka.17-19,1992.
[66]Machado.R.J,A.F.Rocha.Evaluative Fuzzy Neural networks[C].In Proc.First.IEEE.International Conference on Fuzzy Systems(RJZZ-IEEE 92),San Diego,493-500,1992.
[67]Buckley J.J,K.D.Reily,Penmetcha.K.V.Back propagation and genetic algorithms for training Fuzzy Neural Nets q.Genetic Algorithms and Soft Computing,505-532,1996.
[68]王树青,元英进.生化过程自动化技术[M].北京:化学工业出版社,1999.
[69]蒋慰孙.首届全国生化过程模型化与控制学术讨论会论文集[C].上海:华东化工学院出版社,1989.
[70]王树青.中国第二届生化过程模型化与控制技术讨论会论文集[C].杭州:浙江大学出版社,1990
[71]Xianzhong Dai,Dongchuan Yu,Yuhan Ding et al,ANN Inversion Based Soft-Sensing of Biochemical Parameters in Erythromycin Fermentation[C],Prdceeding of 2004 International Coference on Infornation Acquisition,2004,262-266.