神经网络辨识及自适应逆控制研究
|
摘要
自适应逆控制作为一种新颖的控制器和调节器的设计方法,引起国内外学者越来越广泛的研究兴趣。现代神经网络技术的发展为非线性自适应逆控制的研究和实现创造了条件,探索和设计合理的动态神经网络结构和算法,构建更加有效的系统结构等已成为非线性自适应逆控制研究的重点。本文研究了神经网络的结构和算法,及基于神经网络逆模型的非线性自适应逆控制系统,主要研究内容如下:
首先,系统分析了RBF网络中现有的几种确定聚类中心的算法:K-均值聚类法、梯度下降法、正交最小二乘法和动态聚类法。针对动态聚类法中距离门限值是固定不变的这一缺点,提出了一种改进的动态聚类法,根据样本密度对距离门限值进行调整,通过对煤气炉数据辨识的仿真研究,验证了该算法的有效性及快速性。
其次,将RBF和BP这两种神经网络应用到自适应逆控制系统中,经一阶惯性环节的仿真结果表明RBF网络的泛化能力较低,影响了系统的控制精度。将基于BP网络的自适应逆噪声消除方法应用到轧辊偏心厚度控制中,仿真结果表明,该方法能很好地消除带钢的厚度偏差,各项指标均优于PID控制,为轧辊偏心厚度控制提供了一个新的解决方案。
最后,将基于BP网络的自适应逆噪声消除方法应用到一个非线性系统控制中,系统的控制误差和均方差均小于其它方法,验证了该算法对非线性系统控制的有效性。
As a new novel controller and adjustor design method, adaptive inverse control has caught overseas and domestic scholars’more and more study interest. The development of present neural network creates condition for the nonlinear adaptive inverse study and actualization. Exploring and designing rational dynamic neural network structure and arithmetic, building more effectual system structure have become the emphasis of nonlinear adaptive inverse study. This paper has study the structure and arithmetic of neural network, and the adaptive inverse control system based on neural network. The main study content states as follow:
Firstly, we study the main clustering methods of RBF network, K-mean clustering method, gradient descent method, orthogonal least squares method and dynamic clustering method. Focus on dynamic clustering method, the most defect is its threshold space is fixed. We raise an improved dynamic cluster method, which adjust the threshold according sample density. The emulation results show the method’s validity and quickness.
Secondly, apply RBFNN and BPNN to adaptive inverse control system. The first-order system emulation results show that the generalization of RBFNN is lower, and reduces the system control precision. Then we apply the adaptive inverse noise elimination method based on BPNN to the roller eccentricity gauge control system. The emulation results show that the criterions of this method all overmatch PID control scheme. It offers a new resolve scheme for roller eccentricity.
Finally, we apply adaptive inverse noise elimination method, based on BPNN, to nonlinear system. The control error and MSE all less than other methods, which shows the adaptive inverse control method’s valid to nonlinear system.
首先,系统分析了RBF网络中现有的几种确定聚类中心的算法:K-均值聚类法、梯度下降法、正交最小二乘法和动态聚类法。针对动态聚类法中距离门限值是固定不变的这一缺点,提出了一种改进的动态聚类法,根据样本密度对距离门限值进行调整,通过对煤气炉数据辨识的仿真研究,验证了该算法的有效性及快速性。
其次,将RBF和BP这两种神经网络应用到自适应逆控制系统中,经一阶惯性环节的仿真结果表明RBF网络的泛化能力较低,影响了系统的控制精度。将基于BP网络的自适应逆噪声消除方法应用到轧辊偏心厚度控制中,仿真结果表明,该方法能很好地消除带钢的厚度偏差,各项指标均优于PID控制,为轧辊偏心厚度控制提供了一个新的解决方案。
最后,将基于BP网络的自适应逆噪声消除方法应用到一个非线性系统控制中,系统的控制误差和均方差均小于其它方法,验证了该算法对非线性系统控制的有效性。
As a new novel controller and adjustor design method, adaptive inverse control has caught overseas and domestic scholars’more and more study interest. The development of present neural network creates condition for the nonlinear adaptive inverse study and actualization. Exploring and designing rational dynamic neural network structure and arithmetic, building more effectual system structure have become the emphasis of nonlinear adaptive inverse study. This paper has study the structure and arithmetic of neural network, and the adaptive inverse control system based on neural network. The main study content states as follow:
Firstly, we study the main clustering methods of RBF network, K-mean clustering method, gradient descent method, orthogonal least squares method and dynamic clustering method. Focus on dynamic clustering method, the most defect is its threshold space is fixed. We raise an improved dynamic cluster method, which adjust the threshold according sample density. The emulation results show the method’s validity and quickness.
Secondly, apply RBFNN and BPNN to adaptive inverse control system. The first-order system emulation results show that the generalization of RBFNN is lower, and reduces the system control precision. Then we apply the adaptive inverse noise elimination method based on BPNN to the roller eccentricity gauge control system. The emulation results show that the criterions of this method all overmatch PID control scheme. It offers a new resolve scheme for roller eccentricity.
Finally, we apply adaptive inverse noise elimination method, based on BPNN, to nonlinear system. The control error and MSE all less than other methods, which shows the adaptive inverse control method’s valid to nonlinear system.
引文
1 E.Walach, B.Widrow. Adaptive Signal Processing for Adaptive Control. IFAC Workshop on Adaptive Systems in Control and Signal Processing, Sweden,1986:15-18
2 E.Walach, B.Widrow. Adaptive Signal Processing for Adaptive Control. IFAC Workshop on Adaptive Systems in Control and Signal Processing, Sweden,1986:15-18
3 B.Widrow, M.Bilello. Adaptive Inverse Control. Proceeding of the 1993 International Symposium on Intelligent Control. Chicago, Llinois, USA, 1993:1-5
4 B.Widrow, G.L.Plett. Nonlinear Adaptive Inverse Control. Proc of the 36th IEEE CDC San Diego, CA, 1997:1032-1037
5 B.威德罗, E.瓦莱斯.自适应逆控制.刘树棠,韩崇昭译.西安:西安交通大学出版社,2000
6何振亚.自适应信号处理.北京:科学出版社,2004:166-170
7于灵慧,房建成.一种非线性自适应逆噪声控制器设计及其仿真.系统仿真学报, 2006,18(1):165-168
8高大远,沈辉,胡德文.非线性系统的自组织多模型自适应逆控制.控制理论与应用, 2008,25(4):677-682
9韩永成,方一鸣,赵琳琳.电液伺服系统自适应逆向递推控制器设计.自动化仪表,2008, 29(11):54-57
10蔡勇,战兴群,张炎华.船舶自适应逆控制操舵.中国造船,2004,45(4):71-76
11胡立坤,王庆超.基于线性网络的一类带扰动线性对象的逆控制研究.控制系统, 2006,10(22):33-36
12卢志刚,李伟,冀尔康,等.微粒群算法优化设计自适应滤波器.仪器仪表学报,2005, 26(8):594-595
13邹阿金,沈洪远.Chebyshev神经网络辨识器.煤炭自动化,1998,4:10-11
14曾喆昭,扶蔚朋.基于模糊Chebyshev基函数神经网络的快速学习算法.系统仿真学报, 2001,13(3):321-322
15叶军.基于复合正交神经网络的自适应逆控制系统.计算机仿真,2004,21(2):92-94
16 A.M. Karshenas, M.W. Duunigan, Williams. Adaptive Inverse Control Algorithm forShock Testing. IEEE Proc.-control Theory Appl., 2000,147(3):267-276
17 S. Wu, S. Cetinkunt. Model Reference Adaptive Inverse Control of a Single Link Flexible Robot. Computers & Structures, 1993,47(2):213-223
18 Du Gang, Zhan Xingqun, Zhang Weiming. Improved Filtered-εAdaptive Inverse Control and Its Application on Nonlinear Ship Maneuvering. Journal of Systems Engineering and Electronics, 2006,17(4):788-792
19党映农,韩崇昭.基于Volterra基函数网络的自适应逆控制方法.西安交通大学学报, 2000,34(9):8-12
20王宝华,杨成语,张强.自适应逆推励磁控制器设计.电工技术学报,2005,20(12):91-94
21杨立永,李华德,王久和.基于逆系统理论的感应电动机控制策略.辽宁工程技术大学学报,2005,24(5):706-708
22卢志刚,易之光,赵翠俭,等.一种新型的自适应逆扰动消除器.仪器仪表学报, 2004,25(4):858-859
23郭建国.基于自适应动态逆的自主飞艇速度控制系统设计.宇航学报,2008,29(5): 1505-1509
24周涌,陈庆伟,胡维礼.内模控制研究的新发展.控制理论与应用,2004,21(3):475-482
25朱家强,朱纪洪,郭锁凤.基于神经网络的鲁棒自适应逆飞行控制.控制理论与应用, 2005,22(2):182-188
26王金林,陈明,王芳.基于神经网络的非线性系统自适应逆控制.弹箭与制导学报, 2004,S4:288-291
27彭疆,周国荣.基于神经网络的机器人逆运动学算法.智能控制技术,2005,23(4):30- 32
28黎科峰,田源,任章.升力式再入飞行器的神经网络自适应逆控制系统设计.导弹与航天运载技术,2006,4:20-24
29徐丽娜.神经网络控制.北京:电子工业出版社,2003
30 Simon Haykin,叶世伟,史忠植译.神经网络原理.北京:机械工业出版社,2004
31王永骥,涂健.神经元网络控制.北京:机械工业出版社,1998.
32 H.J.Cochofel, Wooten D, Principe J. A Neural Network Development Environment for Adaptive Inverse Control. IEEE Intelligence Conference on Neural Networks,1998:963-967
33 C.L.M. Harnold, K.Y.Lee. Free-model Based Adaptive Inverse Neuro controller for Dynamic Systems. The 37th IEEE Conference on Decision and Control, Tampa, Florida, 1998:507-512
34 C.L.M.Harnold. Free-model Based Adaptive Inverse Controller for Nonlinear Dynamic Systems, Ph. D. Dissertation, Pennsylvania State University, 2000:100-125
35 C.L.M.Harnold, K.Y.Lee. Application of the Free–model Based Neural Networks in Model Reference Adaptive Inverse Control.The American Control Conference, Chicago, Illinois, 2000:1664-1668
36宫林,姜长生,吴庆宪.基于自适应逆的无人机着陆控制.航空兵器,2009,4:3-7
37赵新龙,谭永红,董建萍.基于迟滞算子的非平滑三明治系统自适应控制.控制理论与应用,2008,25(6):1121-1127
38韩华,罗安.一种基于DTFE的非线性自适应逆控制.控制与决策,2008,23(11):1315 -1320
39高大远,沈辉,胡德文.非线性系统的自组织多模型自适应逆控制.控制理论与应用,2008,25(4):677-682
40陈洁,潘长鹏,顾文锦.基于自适应小波网络的反舰导弹非线性控制算法研究.宇航学报,2008,29(3):652-956
41廖忠,孙叶青.小波神经网络的水电机组自适应逆控制.中国计量学院学报,2007,18(2):151-154
42阚洪亮,阚凤龙,韩中华,等.神经网络自适应逆控制在铝电解过程控制中的应用.科技广场,2007,9:186-187
43周辉,董正宏,朱仁峰.基于神经网络的反馈式自适应逆控制系统.控制工程,2006,13(3):244-247
44李士勇.模糊控制·神经网络和智能控制论,哈尔滨:哈尔滨工业大学,1998
45 Li J.,Yu J.S. Nonlinear Hybrid Adaptive Inverse Control Using Neural Fuzzy System and its Application to CSTR Systems. The 4th World Congress on Intelligent Control and Automation, Shanghai,2002:1896-1900
46丁海山,毛剑琴,林岩.基于模糊树模型的自适应直接逆控制.自动化学报,2008,34(5):574-580
47毛剑琴,丁海山.率相关迟滞非线性系统的智能化建模与控制.中国科学,2009,29(3): 289-304
48王广军,朱丽娜,沈曙光.一种基于逆动力学模糊规则的自适应控制方法.系统仿真学报,2008,20(15):3907-3910
49 Zhao Jia, Chen Shenggong, Shen Gongzhang. Study on Fuzzy Immune Adaptive Model InversionControl System for Helicopter Flight. Journal of System Simulation, 2009,21(13):3997-4002
50高道祥,孙增圻,罗熊,等.基于Backstepping的高超声速飞行器模糊自适应控制.控制理论与应用,2008,25(5):805-810
51孙富春,刘华平,孙增圻.非线性系统神经模糊自适应控制的问题与策略.清华大学学报,2003,43(4):470-474
52欧阳军,闫桂荣,王腾.LS-SVM在随机振动在线自适应逆控制中的应用.应用力学学报,2007,24(4):530-536
53张浩,叶梧,冯穗力,等.一种新型的基于自适应逆控制的预失真器设计.信号处理, 2006,22(4):486-491
54贺昱曜,徐德民,万建.基于预测的模型参考自适应逆控制.长安大学学报,2004, 24(1):100-103
55王宏楠,李书臣,林丽君,等.基于单步预测的模型参考自适应逆控制.河北工业大学学报,2007,36(3):54-58
56王宏楠,李书臣,林丽君.基于曲线拟合预测模型的自适应逆控制研究.微计算机信息,2008,24(1):28-30
57李元杰,戴再平.一种对象扰动预测控制器的设计.自动化仪表,2003,24(3):18-20
58王丹民,李擎,李华德.金属力学性能质量预测及其控制.控制理论与应用.2007, 24(4):669-673
59焦李成.神经网络计算.西安:西安电子科技大学出版社,1993
60 D.Carbonell Oliver. Neural Networks Based Nonlinear Adaptive Inverse Conirol Algorithjtns. Thesis for the Engineer degree, Stanford University, Stanford, CA, September 1996
61王永骥,涂健.神经元网络控制.北京:机械工业出版社,1998.
62 L.Gregory, Plett. Adaptive Inverse Control of Plants with Disturbances.PhD thesis, Stanford University,Stanford,CA,May1998
63李士勇.模糊控制神经网络控制和智能控制.哈尔滨:哈尔滨工业大学出版社,1996
64 Guo Wenqiang, Qiu Tianshuang, Tang Hong. Performance of RBF Neural Networks for Array Processing in Impulsive Noise Environment. Digital Signal Processing, 2008, 2(18):168-178.
65 J. Moody, C.Darken. Fast Learning in Networks of Locally-tuned Processing Units. Neural Computation, 1989,1:281-294.
66 Yoshinori Abe, Youji Iiguni. Fast computation of RBF coefficients using FFT. Signal Processing, 2006,11(86): 3264-3274.
67贾明兴,赵春晖,王福利.基于RBF神经网络的非线性主元分析方法.仪器仪表学报, 2008,29(3):453-457.
68魏海坤,李奇,宋文忠.梯度算法下RBF网的参数变化动态.控制理论与应用.2007, 24(3):356-361.
69 J.G. Wilpon, L.R.Rabiner. Modified K-Means Clustering Algorithms for Use in Isolated Word Recognition. IEEE Transactions on Acoustics, Speech, Signal Proc, 1985, 33(3):587-594.
70 S.Chen Orthogonal Least Square Learning Algorithm for Radial Basis Function Networks. IEEE Trans. on NN. 1992,2(2):302-309.
71张军峰,胡寿松.基于一种新型聚类算法的RBF神经网络混沌时间序列预测.物理学报,2007,56(2): 713-719.
72黄国宏,邵惠鹤.一种新的基于构造型RBF神经元网络分类算法.控制与决策,2005, 20(12):1411-1415.
73 Box GEP, Jenkins GM. Time Series Analysis, Forecasting and Control(S0016-0032). San Francisco, CA: Holden Day,1970.
74 J D.Farmer Chaotic attract ors of infinite2 dimensi onal dynamical systems. Physica D, 1982; 4: 366-393
75刘福才,关新平,裴润.基于一种新模糊模型的非线性系统模糊辨识.控制理论与应用,2003,20(1): 113-116.
76刘福才,关新平,裴润.一种基于模糊规则的非线性系统快速模糊辨识方法.系统仿真学报,2002,14(5): 547- 550.
77谭文,王耀南,周少武,等.混沌时间序列的模糊神经网络预测.物理学报,2003,52(4): 795-791
78陶宝壮,李炜,张义超.RBF与BP网络实时性分析.皖西学院.2008.24(5):31-33
79智会强,牛坤,田亮等.RBF网络和BP网络在函数副近领域内的比较研究.科技通报, 2005,21(2):193-197
80许健勇.薄板冷轧厚度与板形高精度控制技术.钢铁,2002,37(1).46-51.
81边海涛,杨荃,钟恬,等.基于RBF神经网络的轧辊偏心补偿控制.钢铁,2007,42(11): 33-36
82王哲英,王君,马明旭,等.提高轧辊偏心信号频谱分析精度的方法.钢铁,2005,40(8): 56-60
83刘建昌,王立平,武玉新,等.一种能补偿轧辊偏心的AGC系统.电气传动,1994,6:18-22
84李勇,王君,胡贤磊,等.新型液压轧机控制方案的研究.钢铁,2007,42(6):42-47
85郑大钟.线性系统理论.北京:清华大学出版社,2002
86李桂芳,杨成梧,张玉珍,等.一类非线性系统的自适应反馈无源化问题.南京理工大学学报,2005,29(4):384-388
87杨青,李树荣.基于Backstepping设计的不确定非线性系统的预测控制.控制理论与应用,2007,24(4):525-529
88 Sun Limin, Yan Tingxin, Bi Yanzhong. A Practical Topology Control and Data Forwarding Mechanism for Wireless Sensor Networks. Acta Automatica Sinica,2006, 32(6):867-874
2 E.Walach, B.Widrow. Adaptive Signal Processing for Adaptive Control. IFAC Workshop on Adaptive Systems in Control and Signal Processing, Sweden,1986:15-18
3 B.Widrow, M.Bilello. Adaptive Inverse Control. Proceeding of the 1993 International Symposium on Intelligent Control. Chicago, Llinois, USA, 1993:1-5
4 B.Widrow, G.L.Plett. Nonlinear Adaptive Inverse Control. Proc of the 36th IEEE CDC San Diego, CA, 1997:1032-1037
5 B.威德罗, E.瓦莱斯.自适应逆控制.刘树棠,韩崇昭译.西安:西安交通大学出版社,2000
6何振亚.自适应信号处理.北京:科学出版社,2004:166-170
7于灵慧,房建成.一种非线性自适应逆噪声控制器设计及其仿真.系统仿真学报, 2006,18(1):165-168
8高大远,沈辉,胡德文.非线性系统的自组织多模型自适应逆控制.控制理论与应用, 2008,25(4):677-682
9韩永成,方一鸣,赵琳琳.电液伺服系统自适应逆向递推控制器设计.自动化仪表,2008, 29(11):54-57
10蔡勇,战兴群,张炎华.船舶自适应逆控制操舵.中国造船,2004,45(4):71-76
11胡立坤,王庆超.基于线性网络的一类带扰动线性对象的逆控制研究.控制系统, 2006,10(22):33-36
12卢志刚,李伟,冀尔康,等.微粒群算法优化设计自适应滤波器.仪器仪表学报,2005, 26(8):594-595
13邹阿金,沈洪远.Chebyshev神经网络辨识器.煤炭自动化,1998,4:10-11
14曾喆昭,扶蔚朋.基于模糊Chebyshev基函数神经网络的快速学习算法.系统仿真学报, 2001,13(3):321-322
15叶军.基于复合正交神经网络的自适应逆控制系统.计算机仿真,2004,21(2):92-94
16 A.M. Karshenas, M.W. Duunigan, Williams. Adaptive Inverse Control Algorithm forShock Testing. IEEE Proc.-control Theory Appl., 2000,147(3):267-276
17 S. Wu, S. Cetinkunt. Model Reference Adaptive Inverse Control of a Single Link Flexible Robot. Computers & Structures, 1993,47(2):213-223
18 Du Gang, Zhan Xingqun, Zhang Weiming. Improved Filtered-εAdaptive Inverse Control and Its Application on Nonlinear Ship Maneuvering. Journal of Systems Engineering and Electronics, 2006,17(4):788-792
19党映农,韩崇昭.基于Volterra基函数网络的自适应逆控制方法.西安交通大学学报, 2000,34(9):8-12
20王宝华,杨成语,张强.自适应逆推励磁控制器设计.电工技术学报,2005,20(12):91-94
21杨立永,李华德,王久和.基于逆系统理论的感应电动机控制策略.辽宁工程技术大学学报,2005,24(5):706-708
22卢志刚,易之光,赵翠俭,等.一种新型的自适应逆扰动消除器.仪器仪表学报, 2004,25(4):858-859
23郭建国.基于自适应动态逆的自主飞艇速度控制系统设计.宇航学报,2008,29(5): 1505-1509
24周涌,陈庆伟,胡维礼.内模控制研究的新发展.控制理论与应用,2004,21(3):475-482
25朱家强,朱纪洪,郭锁凤.基于神经网络的鲁棒自适应逆飞行控制.控制理论与应用, 2005,22(2):182-188
26王金林,陈明,王芳.基于神经网络的非线性系统自适应逆控制.弹箭与制导学报, 2004,S4:288-291
27彭疆,周国荣.基于神经网络的机器人逆运动学算法.智能控制技术,2005,23(4):30- 32
28黎科峰,田源,任章.升力式再入飞行器的神经网络自适应逆控制系统设计.导弹与航天运载技术,2006,4:20-24
29徐丽娜.神经网络控制.北京:电子工业出版社,2003
30 Simon Haykin,叶世伟,史忠植译.神经网络原理.北京:机械工业出版社,2004
31王永骥,涂健.神经元网络控制.北京:机械工业出版社,1998.
32 H.J.Cochofel, Wooten D, Principe J. A Neural Network Development Environment for Adaptive Inverse Control. IEEE Intelligence Conference on Neural Networks,1998:963-967
33 C.L.M. Harnold, K.Y.Lee. Free-model Based Adaptive Inverse Neuro controller for Dynamic Systems. The 37th IEEE Conference on Decision and Control, Tampa, Florida, 1998:507-512
34 C.L.M.Harnold. Free-model Based Adaptive Inverse Controller for Nonlinear Dynamic Systems, Ph. D. Dissertation, Pennsylvania State University, 2000:100-125
35 C.L.M.Harnold, K.Y.Lee. Application of the Free–model Based Neural Networks in Model Reference Adaptive Inverse Control.The American Control Conference, Chicago, Illinois, 2000:1664-1668
36宫林,姜长生,吴庆宪.基于自适应逆的无人机着陆控制.航空兵器,2009,4:3-7
37赵新龙,谭永红,董建萍.基于迟滞算子的非平滑三明治系统自适应控制.控制理论与应用,2008,25(6):1121-1127
38韩华,罗安.一种基于DTFE的非线性自适应逆控制.控制与决策,2008,23(11):1315 -1320
39高大远,沈辉,胡德文.非线性系统的自组织多模型自适应逆控制.控制理论与应用,2008,25(4):677-682
40陈洁,潘长鹏,顾文锦.基于自适应小波网络的反舰导弹非线性控制算法研究.宇航学报,2008,29(3):652-956
41廖忠,孙叶青.小波神经网络的水电机组自适应逆控制.中国计量学院学报,2007,18(2):151-154
42阚洪亮,阚凤龙,韩中华,等.神经网络自适应逆控制在铝电解过程控制中的应用.科技广场,2007,9:186-187
43周辉,董正宏,朱仁峰.基于神经网络的反馈式自适应逆控制系统.控制工程,2006,13(3):244-247
44李士勇.模糊控制·神经网络和智能控制论,哈尔滨:哈尔滨工业大学,1998
45 Li J.,Yu J.S. Nonlinear Hybrid Adaptive Inverse Control Using Neural Fuzzy System and its Application to CSTR Systems. The 4th World Congress on Intelligent Control and Automation, Shanghai,2002:1896-1900
46丁海山,毛剑琴,林岩.基于模糊树模型的自适应直接逆控制.自动化学报,2008,34(5):574-580
47毛剑琴,丁海山.率相关迟滞非线性系统的智能化建模与控制.中国科学,2009,29(3): 289-304
48王广军,朱丽娜,沈曙光.一种基于逆动力学模糊规则的自适应控制方法.系统仿真学报,2008,20(15):3907-3910
49 Zhao Jia, Chen Shenggong, Shen Gongzhang. Study on Fuzzy Immune Adaptive Model InversionControl System for Helicopter Flight. Journal of System Simulation, 2009,21(13):3997-4002
50高道祥,孙增圻,罗熊,等.基于Backstepping的高超声速飞行器模糊自适应控制.控制理论与应用,2008,25(5):805-810
51孙富春,刘华平,孙增圻.非线性系统神经模糊自适应控制的问题与策略.清华大学学报,2003,43(4):470-474
52欧阳军,闫桂荣,王腾.LS-SVM在随机振动在线自适应逆控制中的应用.应用力学学报,2007,24(4):530-536
53张浩,叶梧,冯穗力,等.一种新型的基于自适应逆控制的预失真器设计.信号处理, 2006,22(4):486-491
54贺昱曜,徐德民,万建.基于预测的模型参考自适应逆控制.长安大学学报,2004, 24(1):100-103
55王宏楠,李书臣,林丽君,等.基于单步预测的模型参考自适应逆控制.河北工业大学学报,2007,36(3):54-58
56王宏楠,李书臣,林丽君.基于曲线拟合预测模型的自适应逆控制研究.微计算机信息,2008,24(1):28-30
57李元杰,戴再平.一种对象扰动预测控制器的设计.自动化仪表,2003,24(3):18-20
58王丹民,李擎,李华德.金属力学性能质量预测及其控制.控制理论与应用.2007, 24(4):669-673
59焦李成.神经网络计算.西安:西安电子科技大学出版社,1993
60 D.Carbonell Oliver. Neural Networks Based Nonlinear Adaptive Inverse Conirol Algorithjtns. Thesis for the Engineer degree, Stanford University, Stanford, CA, September 1996
61王永骥,涂健.神经元网络控制.北京:机械工业出版社,1998.
62 L.Gregory, Plett. Adaptive Inverse Control of Plants with Disturbances.PhD thesis, Stanford University,Stanford,CA,May1998
63李士勇.模糊控制神经网络控制和智能控制.哈尔滨:哈尔滨工业大学出版社,1996
64 Guo Wenqiang, Qiu Tianshuang, Tang Hong. Performance of RBF Neural Networks for Array Processing in Impulsive Noise Environment. Digital Signal Processing, 2008, 2(18):168-178.
65 J. Moody, C.Darken. Fast Learning in Networks of Locally-tuned Processing Units. Neural Computation, 1989,1:281-294.
66 Yoshinori Abe, Youji Iiguni. Fast computation of RBF coefficients using FFT. Signal Processing, 2006,11(86): 3264-3274.
67贾明兴,赵春晖,王福利.基于RBF神经网络的非线性主元分析方法.仪器仪表学报, 2008,29(3):453-457.
68魏海坤,李奇,宋文忠.梯度算法下RBF网的参数变化动态.控制理论与应用.2007, 24(3):356-361.
69 J.G. Wilpon, L.R.Rabiner. Modified K-Means Clustering Algorithms for Use in Isolated Word Recognition. IEEE Transactions on Acoustics, Speech, Signal Proc, 1985, 33(3):587-594.
70 S.Chen Orthogonal Least Square Learning Algorithm for Radial Basis Function Networks. IEEE Trans. on NN. 1992,2(2):302-309.
71张军峰,胡寿松.基于一种新型聚类算法的RBF神经网络混沌时间序列预测.物理学报,2007,56(2): 713-719.
72黄国宏,邵惠鹤.一种新的基于构造型RBF神经元网络分类算法.控制与决策,2005, 20(12):1411-1415.
73 Box GEP, Jenkins GM. Time Series Analysis, Forecasting and Control(S0016-0032). San Francisco, CA: Holden Day,1970.
74 J D.Farmer Chaotic attract ors of infinite2 dimensi onal dynamical systems. Physica D, 1982; 4: 366-393
75刘福才,关新平,裴润.基于一种新模糊模型的非线性系统模糊辨识.控制理论与应用,2003,20(1): 113-116.
76刘福才,关新平,裴润.一种基于模糊规则的非线性系统快速模糊辨识方法.系统仿真学报,2002,14(5): 547- 550.
77谭文,王耀南,周少武,等.混沌时间序列的模糊神经网络预测.物理学报,2003,52(4): 795-791
78陶宝壮,李炜,张义超.RBF与BP网络实时性分析.皖西学院.2008.24(5):31-33
79智会强,牛坤,田亮等.RBF网络和BP网络在函数副近领域内的比较研究.科技通报, 2005,21(2):193-197
80许健勇.薄板冷轧厚度与板形高精度控制技术.钢铁,2002,37(1).46-51.
81边海涛,杨荃,钟恬,等.基于RBF神经网络的轧辊偏心补偿控制.钢铁,2007,42(11): 33-36
82王哲英,王君,马明旭,等.提高轧辊偏心信号频谱分析精度的方法.钢铁,2005,40(8): 56-60
83刘建昌,王立平,武玉新,等.一种能补偿轧辊偏心的AGC系统.电气传动,1994,6:18-22
84李勇,王君,胡贤磊,等.新型液压轧机控制方案的研究.钢铁,2007,42(6):42-47
85郑大钟.线性系统理论.北京:清华大学出版社,2002
86李桂芳,杨成梧,张玉珍,等.一类非线性系统的自适应反馈无源化问题.南京理工大学学报,2005,29(4):384-388
87杨青,李树荣.基于Backstepping设计的不确定非线性系统的预测控制.控制理论与应用,2007,24(4):525-529
88 Sun Limin, Yan Tingxin, Bi Yanzhong. A Practical Topology Control and Data Forwarding Mechanism for Wireless Sensor Networks. Acta Automatica Sinica,2006, 32(6):867-874