反馈神经网络在热工系统建模中的应用
|
摘要
传统的辨识方法多针对线性系统,对复杂非线性系统的辨识显示出诸多的不足。神经网络的非线性、并行分布处理和自学习等特性为解决这些问题提供了新的出路。
本文着重对ELMAN神经网络的结构和动态记忆特性进行了研究,并验证了通过增加连接承接层和输出层之间的权值可以加快网络的学习速度。将改进的ELMAN网络应用于再热汽温的动态系统建模中,可见Elman网络在辨识线性系统方面与最小二乘都有良好效果;同时由于Elman网络具有自学习和映射任意非线性系统的能力,因而其在非线性系统辨识中也有较好的逼近能力。
Most traditional system identification methods were applied to linear system,and it is still too difficult to solve the problems of non-linear system.Neural network has Characteristics such as non-linear,parallel distributed processing and self-learning which give us a new way on system identification.
This paper research on the structure and dynamic memory characteristics of Elman neural network and increased the learning speed by adding new weights connecting the context nodes to the output nodes.Using this approach to identify reheat steam temperature system,we can see that the Elman neural network can identify linear system as good as least square method.Because neural network have the abilities of self-learning and mapping arbitrary non-linear system,the simulation result of non-linear system identification use Elman neural network is nice too.
本文着重对ELMAN神经网络的结构和动态记忆特性进行了研究,并验证了通过增加连接承接层和输出层之间的权值可以加快网络的学习速度。将改进的ELMAN网络应用于再热汽温的动态系统建模中,可见Elman网络在辨识线性系统方面与最小二乘都有良好效果;同时由于Elman网络具有自学习和映射任意非线性系统的能力,因而其在非线性系统辨识中也有较好的逼近能力。
Most traditional system identification methods were applied to linear system,and it is still too difficult to solve the problems of non-linear system.Neural network has Characteristics such as non-linear,parallel distributed processing and self-learning which give us a new way on system identification.
This paper research on the structure and dynamic memory characteristics of Elman neural network and increased the learning speed by adding new weights connecting the context nodes to the output nodes.Using this approach to identify reheat steam temperature system,we can see that the Elman neural network can identify linear system as good as least square method.Because neural network have the abilities of self-learning and mapping arbitrary non-linear system,the simulation result of non-linear system identification use Elman neural network is nice too.
引文
[1]史维祥,尤昌德.系统辨识基础[M].上海:上海科学技术出版社,1988:107-120
[2]许南荣,宋文忠,夏安邦.系统辨识[M].南京:东南大学出版社,1991:17-70
[3]Zadeh L A.From Circuit Theory to System Theory[J].Proc.IRE,1962,50(5):856-865
[4]方崇智,萧德云.过程辨识[M].北京:清华大学出版社,1988:15-20
[5]刘豹,王正欧.系统辨识[M].北京:机械工业出版社,1993:46-58
[6]Eykhoff P.System Identification-Parameter and State Estimation[M].John Wiley & Sons,1974:3-45
[7]Ljung L.Convergence Analysis of Parametric Identification Methods[J].IEEE Trans.on Automatic Control,1978,AC-23(5):770-783.
[8]徐小平,王峰,胡钢.系统辨识研究的现状[J].自动化技术,2007,15(39):112-115
[9]朱明星,龚蓬.在线学习 RBF 神经网络的模型参考自适应控制器[M].微机发展,2001,2(5):5-7
[10]Fogel E,Huang Y F.On the Value of Information in System Identification Bounded Noise Case[J].IEEE Trans.Automatic Control,1982,18(2):229-238
[11]舒迪前.预测控制系统及其应用[M].北京:机械工业出版社,1996:30-42
[12]傅学芳.现代优化计算方法--遗传算法简介[J].昌雄师专学报,2001,20(2):42-46
[13]李红星.基于遗传算法的闭环系统辨识方法[J].电气传动,2000,31(3):57-60
[14]Maclay D,Dorey R.Applying Genetic Search Techniques to Driver Train Modeling[J].IEEE Control Systems,1993,20(6):50-55
[15]Kristinsson K.System Identification and Control Using Genetic Algorithms[J].IEEE Trans.on Systems,Man and Cybernetics,1992,22(5):1033-1046
[16]谢克明,南建峰.基于模糊神经网络的辨识与控制技术的现状及展望[J],太原理工大学学报,1998,29(1):8-12
[17]李霞,模糊模型辨识的研究[C].兰州:兰州理工大学硕士毕业论文,2004.5(1),24-27
[18]T.Takagi.M.Sugeno,Fuzzy identification of systems and Applications to modeling and control.IEEE Transactions on System,Man and Cybernetics, No.1,1985:116-132
[19]Lee Yingchin.A combined approach to fuzzy model identification[J].IEEE Transactions on Systems,Man and Cybernetics,1994,24(5):450-455
[20]张广莹,邓正隆.小波分析在系统辨识中的应用[J].电机与控制学报,2002,(1):64-67
[21]王静,毋茂盛,孙玉强.小波变换及其应用[J].河南师范大学学报(自然科学版),2002,30(2):86-89
[22]高隽,人工神经网络原理及仿真实例[M].北京:机械工业出版社.2003:1-19
[23]丁士圻,郭丽华.人工神经网络基础[M].哈尔滨:哈尔滨工程大学出版社,2008:5-53
[24]周妮娜,王永彬.基于神经网络的非线性系统辨识[J].宝鸡文理学院学报(自然科学版),2006,26(1),257-258
[25]谢承泮.神经网络发展综述[J].科技情报开发与经济,2006,16(12):148-149
[26]刘永红.神经网络理论的发展与前沿问题[J].信息与控制,1999,28(1):31-44
[27]石幸利.人工神经网络的发展及其应用[J].重庆科技学院学报(自然科学版),2006,8(2):99-101
[28]匡胤.基于人工神经网络的系统建模及 MATLAB 实现[J].四川理工学院学报(自然科学版),2007,20(5):6-9
[29]赵春涛,赵克定,邵鸿德,张业建.基于 Elman 网络的液压系统辨识[J].机床与液压,2003,4(1):129-130
[30]史天运,贾利民,蔡秀生.一种新型的动态递归神经网络及其全自动设计算法[J].信息与控制,2000,29(6):512-515
[31]杨璐,高自友.一种可用于时序预测的自反馈神经网络[J].预测,1998,6(11):41-43
[32]PHAM D.A recurrent back-propagation neural network for dynamic system identification[J].Journal of Systems Engineering,1992:2(4):213-223.
[33]赵奇,刘开第,庞彦军.JORDAN 神经网络在系统辨识中应用研究[J].制造业自动化.2005,27(3):16-18
[34]王攀,苏智,冯珊.局部回归 Elman 网络学习算法的注记[J].武汉理工大学学报,2002,24(2):14-15
[35]SHI X H,LIANG Y C,LEE H P.et al.Improved Elman networks and applications for controlling ultrasonic motors[J].Applied Artificial Intelligence,2004,18:603-629
[36]李明,韩旭明,王丽敏.一种改进的 Elman 神经网络及其在股市中的应用[J].计 算机工程与应用,2006,34(67),218-220
[37]D.R.Hush and B.G.Horne,Progress in supervised neural networks[J].IEEE Signal Processing Magazine.1993,10(2):8-39
[38]X.Z.Gao,X.M.Gao,and S.J.Ovaska.A Modified Elman Neural Network Model with Application to Dynamical Systems Identification[J].IEEE International Conference on Systems,Man and Cybernetics.1996,2(14):1376-1381
[39]李丽荣,沈春林,韩璞.基于 BP 网络的热工过程模型辨识方法[J].南京航空航天大学学报.2001,33(5):499-502
[40]代悦.神经网络在火电厂建模中的应用[M].河北:华北电力大学硕士论文,2003:26-27
[41]周光明,马永光.神经网络在火电厂过热蒸汽温度控制系统中的应用[J].仪器仪表用户.2005,12(5):67-68
[42]王颖.基于扰动分析的再热汽温模糊 PID 控制方法研究[M].北京:华北电力大学硕士论文,2006:18-27
[43]李界家,吴成东,朱栋华.阎焕忠最小二乘辨识算法在故障检测中的应用研究[J].自动化仪表,2003,24(4):19-21
[44]葛哲学,孙志强.飞思科技研发中心.神经网络理论与 MATLAB R2007实现[M].北京:电子工业出版社,2007,133-160
[2]许南荣,宋文忠,夏安邦.系统辨识[M].南京:东南大学出版社,1991:17-70
[3]Zadeh L A.From Circuit Theory to System Theory[J].Proc.IRE,1962,50(5):856-865
[4]方崇智,萧德云.过程辨识[M].北京:清华大学出版社,1988:15-20
[5]刘豹,王正欧.系统辨识[M].北京:机械工业出版社,1993:46-58
[6]Eykhoff P.System Identification-Parameter and State Estimation[M].John Wiley & Sons,1974:3-45
[7]Ljung L.Convergence Analysis of Parametric Identification Methods[J].IEEE Trans.on Automatic Control,1978,AC-23(5):770-783.
[8]徐小平,王峰,胡钢.系统辨识研究的现状[J].自动化技术,2007,15(39):112-115
[9]朱明星,龚蓬.在线学习 RBF 神经网络的模型参考自适应控制器[M].微机发展,2001,2(5):5-7
[10]Fogel E,Huang Y F.On the Value of Information in System Identification Bounded Noise Case[J].IEEE Trans.Automatic Control,1982,18(2):229-238
[11]舒迪前.预测控制系统及其应用[M].北京:机械工业出版社,1996:30-42
[12]傅学芳.现代优化计算方法--遗传算法简介[J].昌雄师专学报,2001,20(2):42-46
[13]李红星.基于遗传算法的闭环系统辨识方法[J].电气传动,2000,31(3):57-60
[14]Maclay D,Dorey R.Applying Genetic Search Techniques to Driver Train Modeling[J].IEEE Control Systems,1993,20(6):50-55
[15]Kristinsson K.System Identification and Control Using Genetic Algorithms[J].IEEE Trans.on Systems,Man and Cybernetics,1992,22(5):1033-1046
[16]谢克明,南建峰.基于模糊神经网络的辨识与控制技术的现状及展望[J],太原理工大学学报,1998,29(1):8-12
[17]李霞,模糊模型辨识的研究[C].兰州:兰州理工大学硕士毕业论文,2004.5(1),24-27
[18]T.Takagi.M.Sugeno,Fuzzy identification of systems and Applications to modeling and control.IEEE Transactions on System,Man and Cybernetics, No.1,1985:116-132
[19]Lee Yingchin.A combined approach to fuzzy model identification[J].IEEE Transactions on Systems,Man and Cybernetics,1994,24(5):450-455
[20]张广莹,邓正隆.小波分析在系统辨识中的应用[J].电机与控制学报,2002,(1):64-67
[21]王静,毋茂盛,孙玉强.小波变换及其应用[J].河南师范大学学报(自然科学版),2002,30(2):86-89
[22]高隽,人工神经网络原理及仿真实例[M].北京:机械工业出版社.2003:1-19
[23]丁士圻,郭丽华.人工神经网络基础[M].哈尔滨:哈尔滨工程大学出版社,2008:5-53
[24]周妮娜,王永彬.基于神经网络的非线性系统辨识[J].宝鸡文理学院学报(自然科学版),2006,26(1),257-258
[25]谢承泮.神经网络发展综述[J].科技情报开发与经济,2006,16(12):148-149
[26]刘永红.神经网络理论的发展与前沿问题[J].信息与控制,1999,28(1):31-44
[27]石幸利.人工神经网络的发展及其应用[J].重庆科技学院学报(自然科学版),2006,8(2):99-101
[28]匡胤.基于人工神经网络的系统建模及 MATLAB 实现[J].四川理工学院学报(自然科学版),2007,20(5):6-9
[29]赵春涛,赵克定,邵鸿德,张业建.基于 Elman 网络的液压系统辨识[J].机床与液压,2003,4(1):129-130
[30]史天运,贾利民,蔡秀生.一种新型的动态递归神经网络及其全自动设计算法[J].信息与控制,2000,29(6):512-515
[31]杨璐,高自友.一种可用于时序预测的自反馈神经网络[J].预测,1998,6(11):41-43
[32]PHAM D.A recurrent back-propagation neural network for dynamic system identification[J].Journal of Systems Engineering,1992:2(4):213-223.
[33]赵奇,刘开第,庞彦军.JORDAN 神经网络在系统辨识中应用研究[J].制造业自动化.2005,27(3):16-18
[34]王攀,苏智,冯珊.局部回归 Elman 网络学习算法的注记[J].武汉理工大学学报,2002,24(2):14-15
[35]SHI X H,LIANG Y C,LEE H P.et al.Improved Elman networks and applications for controlling ultrasonic motors[J].Applied Artificial Intelligence,2004,18:603-629
[36]李明,韩旭明,王丽敏.一种改进的 Elman 神经网络及其在股市中的应用[J].计 算机工程与应用,2006,34(67),218-220
[37]D.R.Hush and B.G.Horne,Progress in supervised neural networks[J].IEEE Signal Processing Magazine.1993,10(2):8-39
[38]X.Z.Gao,X.M.Gao,and S.J.Ovaska.A Modified Elman Neural Network Model with Application to Dynamical Systems Identification[J].IEEE International Conference on Systems,Man and Cybernetics.1996,2(14):1376-1381
[39]李丽荣,沈春林,韩璞.基于 BP 网络的热工过程模型辨识方法[J].南京航空航天大学学报.2001,33(5):499-502
[40]代悦.神经网络在火电厂建模中的应用[M].河北:华北电力大学硕士论文,2003:26-27
[41]周光明,马永光.神经网络在火电厂过热蒸汽温度控制系统中的应用[J].仪器仪表用户.2005,12(5):67-68
[42]王颖.基于扰动分析的再热汽温模糊 PID 控制方法研究[M].北京:华北电力大学硕士论文,2006:18-27
[43]李界家,吴成东,朱栋华.阎焕忠最小二乘辨识算法在故障检测中的应用研究[J].自动化仪表,2003,24(4):19-21
[44]葛哲学,孙志强.飞思科技研发中心.神经网络理论与 MATLAB R2007实现[M].北京:电子工业出版社,2007,133-160