基于FPGA的多变量模糊神经网络控制的研究
|
摘要
模糊控制、神经网络控制都是先进控制技术的控制方法,在工业过程控制中获得广泛的应用。实际工业过程往往具有非线性、不确定性、难以建立精确的数学模型等特点,使得单一的一种控制方法难以达到理想的控制效果。如果能够结合两种控制方法,各取所长,优势互补,设计一个通用的模糊神经网络控制芯片对工业生产过程进行合理、有效地控制,就可以缩短系统开发周期,降低成本。
模糊神经网络的研究主要包括模糊神经网络理论的研究、模糊神经网络应用的研究和模糊神经网络实现技术的研究。本文主要侧重的是模糊神经网络实现技术方面的研究,利用FPGA嵌入式系统的应用开发技术实现模糊神经网络控制器的研究与设计,并将其封装成为一个专用的IP核,供其他的控制系统使用。
首先对模糊神经网络的控制原理和设计中使用的算法进行了深入地研究与分析;其次,利用MATLAB设计多变量模糊神经网络控制器,针对特定的被控对象进行仿真实验,并获得比较理想的控制效果;然后,研究基于FPGA的多变量模糊神经网络控制算法的实现,对控制器进行分层设计。系统的设计模块主要包括模糊化模块、控制规则模块、权值-参数计算模块、去模糊化模块和耦合处理模块等。在设计过程中遵循自顶向下的设计原则,使用Altera公司的软件QuartusII 8.1对各个模块设计进行优化处理,最后进行整个系统的设计综合。两个仿真实验结果表明,基于FPGA的模糊神经网络控制器比MATLAB设计的模糊神经网络控制器性能优良,在利用较少硬件资源的前提下,不仅可以提高控制器的运行速度,还可以改善传统控制器的控制性能。
Fuzzy control and neural network control, which are the control method of advanced control technology, access to a wide application in the industrial process control. The actual industrial process often has many characteristics involving nonlinear, uncertain and difficult to establish accurate mathematical model, which can not achieve desired control effect by using a single control method. If we can combine the two control methods with each other in their respective merits. It is designed the general control chip of fuzzy neural network and carried out the effective and reasonable control in the process of industrial production.The control method can cut down the developing period of system and reduce the developing cost of system.
The research of fuzzy neural network mainly includes the theoretical study of fuzzy neural network, the application research of fuzzy neural network and the achievement technology research of fuzzy neural network. It is emphasized on the implementation technical research of fuzzy neural network, innovatively used of the application and development technology of FPGA-based embedded system to accomplish the research and design of fuzzy neural network controller, and packaged the controller into a dedicated IP core for the other control system.
First and foremost, the paper introduced the prorouthly research and analysis of control theory and design algorithms of fuzzy neural network. In addition, it is designed the multivariable fuzzy neural network controller in MATLAB, whose simulation experiment of the particular charged object is carried out, and it is obtained to the ideal control effect. Last but not least, it is investigated the implementation of the algorithm of multivariable fuzzy neural network control based on FPGA, and it is carried out the hierarchal design of the controller, then it is carried on the simulation experiment with the software of Altera's QuartusII 8.1. The results of the two simulation experiments show that the performance of the FPGA-based fuzzy neural network controller is more excellent than that of the fuzzy neural network controller designed in MATLAB. The design module of the system includes fuzzification module, control rule module, defuzzification module, coupling treatment module and weight parameter module.It is followed with the principle of top-down design in the design process, and has been optimized the each module design, then it is carried out the whole system design and synthesis. The design can not only raise the speed of the controller, under the premise of the use of fewer hardware resources, but also improve the control performance of the traditional controller.
模糊神经网络的研究主要包括模糊神经网络理论的研究、模糊神经网络应用的研究和模糊神经网络实现技术的研究。本文主要侧重的是模糊神经网络实现技术方面的研究,利用FPGA嵌入式系统的应用开发技术实现模糊神经网络控制器的研究与设计,并将其封装成为一个专用的IP核,供其他的控制系统使用。
首先对模糊神经网络的控制原理和设计中使用的算法进行了深入地研究与分析;其次,利用MATLAB设计多变量模糊神经网络控制器,针对特定的被控对象进行仿真实验,并获得比较理想的控制效果;然后,研究基于FPGA的多变量模糊神经网络控制算法的实现,对控制器进行分层设计。系统的设计模块主要包括模糊化模块、控制规则模块、权值-参数计算模块、去模糊化模块和耦合处理模块等。在设计过程中遵循自顶向下的设计原则,使用Altera公司的软件QuartusII 8.1对各个模块设计进行优化处理,最后进行整个系统的设计综合。两个仿真实验结果表明,基于FPGA的模糊神经网络控制器比MATLAB设计的模糊神经网络控制器性能优良,在利用较少硬件资源的前提下,不仅可以提高控制器的运行速度,还可以改善传统控制器的控制性能。
Fuzzy control and neural network control, which are the control method of advanced control technology, access to a wide application in the industrial process control. The actual industrial process often has many characteristics involving nonlinear, uncertain and difficult to establish accurate mathematical model, which can not achieve desired control effect by using a single control method. If we can combine the two control methods with each other in their respective merits. It is designed the general control chip of fuzzy neural network and carried out the effective and reasonable control in the process of industrial production.The control method can cut down the developing period of system and reduce the developing cost of system.
The research of fuzzy neural network mainly includes the theoretical study of fuzzy neural network, the application research of fuzzy neural network and the achievement technology research of fuzzy neural network. It is emphasized on the implementation technical research of fuzzy neural network, innovatively used of the application and development technology of FPGA-based embedded system to accomplish the research and design of fuzzy neural network controller, and packaged the controller into a dedicated IP core for the other control system.
First and foremost, the paper introduced the prorouthly research and analysis of control theory and design algorithms of fuzzy neural network. In addition, it is designed the multivariable fuzzy neural network controller in MATLAB, whose simulation experiment of the particular charged object is carried out, and it is obtained to the ideal control effect. Last but not least, it is investigated the implementation of the algorithm of multivariable fuzzy neural network control based on FPGA, and it is carried out the hierarchal design of the controller, then it is carried on the simulation experiment with the software of Altera's QuartusII 8.1. The results of the two simulation experiments show that the performance of the FPGA-based fuzzy neural network controller is more excellent than that of the fuzzy neural network controller designed in MATLAB. The design module of the system includes fuzzification module, control rule module, defuzzification module, coupling treatment module and weight parameter module.It is followed with the principle of top-down design in the design process, and has been optimized the each module design, then it is carried out the whole system design and synthesis. The design can not only raise the speed of the controller, under the premise of the use of fewer hardware resources, but also improve the control performance of the traditional controller.
引文
[1]蔚东晓,贾霞彦.模糊控制的现状与发展[J].自动化与仪器仪表,2006,(6):4-7.
[2]张慧平,戴波,杨薇.现代控制理论在过程工业中的应用和发展[J].北京石油化工学院学报,2006,14(3):57-61.
[3]华清远见嵌入式培训中心.FPGA应用开发与典型实例[M].北京:人民邮电出版社,2008:7-9.
[4]刘佳,焦斌亮.FPGA的发展趋势及其新应用[J].电子技术,2008,(4):43-44.
[5]潘松.CPLD/FPGA在电子设计中的应用前景[J].电子技术应用,1997,12(7):6-8.
[6]张科.基于FPGA的智能控制器的研究[D].哈尔滨理工大学硕士学位论文,2009,3:2.
[7]刘福奇,刘波.Verilog HDL应用程序设计[M].北京:电子工业出版社,2009,10:1-21.
[8]夏宇闻.Verilog数字系统设计教程[M].北京:北京航空航天大学出版社,2004,7:1-9.
[9]王金明.数字系统设计与Verilog HDL[M].北京:电子工业出版社,2002,1:12-13.
[10]潘松,黄继业.EDA实用教程(第2版)[M].北京:科学出版社,2005,5:1-27.
[11]潘松,王国栋.基于EDA技术的CPLD/FPGA应用前景[J].电子与自动化,1999,9(3):3-6.
[12] KEVIN M.PASSINO , STEPHEN YURKOVICH . Fuzzy control[M].Beijing:Tsinghua University Press,2001,1:27-29.
[13]刘一笑.先进控制技术应用综述[J].控制工程,2003,7(10):20-23.
[14]王艳秋.先进控制技术的集成与应用研究[D].东北大学博士学位论文,2006,1:1-7.
[15]赵俊.基于若干智能方法的先进控制系统综合设计研究[D].西安电子科技大学博士学位论文,2008,12:3-8.
[16] RIVALS I , PERSONNAZ L . Nonlinear internal modle using neuralnetworks[J].IEEE Transactions on Neural Networks Control,2000,11(1):80-90.
[17] LINGJI CHEN,KUMPATI S.NARENDRA.Nonlinear adaptive control using neural networks and multiple models[J].Automatica,2001,13(37):1245-1255.
[18] Y F CHAN ,M MOALLEM ,W WANG .Efficient implementation of advanced control altorithm using FPGA technology[C] . The 43rd IEEE Conference on Decision and Control, Bahamas,2004,11:4885-4890.
[19]崔涛,杨全胜.基于FPGA技术的通用模糊控制器设计[J].计算机技术与发展,2009,19(3):15-18.
[20]郭敏,秦刚,刘洋.基于FPGA的温度模糊自适应PID控制器的设计[J].电子设计工程,2009,17(l0):85-87.
[21]包明,张睿,余成波.基于模糊控制的移动机器人FPGA实现[J].电子技术应用,2008,34(7):29-31.
[22]万丽雯.基于FPGA的直接转矩模糊控制技术研究[J].电子测试,2009,12(8):43-46.
[23] LUND T.The architecture of an FPGA-style programmable fuzzy logic controller chip[C].The 5th Australasian Computer Architecture Conference,2000,6:206-208.
[24] TZUU-HSENG S.L, SHI-JIE CHANG,YI-XIANG CHEN. Fuzzy bahavior control on an FPGA-based car-like mobile robot[J]. IEEE Implementation of Human-Like Driving Skills by Autonomous,2003,15(3):867-880.
[25] CHIA-FENG JUANG , CHAO-HSIN HSU.Temperature control by chip implemented adaptive recurrent fuzzy controller designed by evolutionary algorithm[J]. IEEE Transactions on Automatic Control ,2004,40(5),31-34.
[26]焦素敏,阎有运.基于FPGA的模糊控制器的设计[J].华北水利水电学院学报, 2006,27(2):69-72.
[27] F.J.LIN,D.H.WANG and P.K.HUANG.FPGA-based fuzzy sliding-mode control for a linear induction motor drive[J].IEEE Proc.on Electric Power, 2005,152(5):1137-1148.
[28]夏欣,贾永刚,王素珍.RBF神经网络中指数函数ex的FPGA实现[J].微计算机信息(嵌入式与SOC),2005,21(7-2):145-146.
[29]李利歌,阎保定,侯忠.基于FPGA的神经网络硬件可重构实现[J].河南科技大学学报(自然科学版),2009,30(1):37-40.
[30]朱清智,阎保定,栗素娟.一种新型交流伺服控制系统试验研究[J].微电机,2009,42(6):86-88.
[31]白瑞林,沈宪明,章智慧.模糊CMAC网络的FPGA实现[J].计算机测量与控制,2007,15(4):527-530.
[32]白瑞林,王建,沈宪明.基于FPGA的CMAC-PID控制器的研究[J].计算机工程,2007,33(7):240-242.
[33]白瑞林,沈宪明,章智慧.基于FPGA的2-D模糊CMAC网络的硬件实现[J].计算机工程与设计,2007,28(2):430-435.
[34]冯智贵,吴明赞,陈晓宁,等.基于ARM和FPGA的雷达伺服控制器设计[J].世界科技研究与发展,2008,30(6):746-750.
[35]孔超,李占才,王沁,等.一种基于FPGA的SOM神经网络算法的并行实现[J].计算机工程,2007,33(19):236-237,240.
[36]吴军,吁少峰,来昂. FPGA乘法器在电能集中采集系统中的应用[J].江西理工大学学报,2009,30(6):34-37.
[37] FAIEDH H,GAFSI Z,TORKI KETAL.Digital hardware implementation of a neural network used for classification[C].Proceedings of the 16th International Conference on Microelectronics,Tunis,2004,5:551.
[38]熊光泽,詹瑾瑜.嵌入式系统软/硬件协同设计技术综述[J].计算机应用,2006,26(4):757-760,764.
[39]于宗光,魏敬和,王国章.SoC和FPGA技术未来的发展趋势[J] .电子与封装,2006,6(3):l-5.
[40]姚琳.在嵌入式系统中用FPGA进行开发的几个发展方向[J] .今日电子,2007,(6):125-127.
[41]赵曙光,郭万有,杨颂华,等.可编程逻辑器件原理、开发与应用[M].西安:西安电子科技大学出版社,2006:1-88,187-217.
[42]徐光辉,程东旭,黄如,等.基于FPGA的嵌入式系统开发与应用[M].北京:电子工业出版社,2007,5:10-48.
[43]史先龙.基于FPGA的可重构计算技术的研究应用[D].北京化工大学硕士学位论文,2006,12:2-7.
[44]李士勇.工程模糊数学及应用[M].哈尔滨:哈尔滨工业大学出版社,2004,8:159-166.
[45]路永坤.参数自调整模糊控制器研究及基于FPGA实现设计[J].自动化博览,2008,2:74-76.
[46] TONG SHAOCHENG,LI CHANGYING,LI YONGMING.Fuzzy adaptive observer backstepping control for MIMO nonlinear systems [J]. Fuzzy Sets and Systems,2009,8(19):2755-2775.
[47]李士勇.模糊控制·神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,1998,9:268-270.
[48]张智星,孙春在,水谷英二.神经-模糊和软件算[M].西安:西安交通大学出版社,2000,6:33-49.
[49]何克忠,李伟.计算机控制系统[M].北京:清华大学出版社.1998,4:187-192.
[50] L LI,G SONG,J OU.Nonlinear structural vibration suppression using dynamic neural network observer and adaptive fuzzy sliding mode control [J].Journal of Vibration and Control,2009,19(6):1503 - 1526.
[51] YU-YI FU,CHIA-JU Wu,JIN-TSONG JENG.Annealing robust radial basis function networks with support vector regression for nonlinear inverse system identification with outliers [J].Journal of Vibration and Control,2010,5(16):1915 - 1940.
[52] LASZLO BAKO.Real-time classification of datasets with hardware embedded neuromorphic neural networks [J].Brief Bioinform,2010,7(11): 348 - 353.
[53]闻新,周露,李翔,等.MATLAB神经网络仿真与应用[M].北京:科学出版社.2003,7:291-293.
[54]刘金琨.机器人控制系统的设计与MATLAB仿真[M].北京:清华大学出版社.2008,6:86-90,547.
[55] STELIOS TIMOTHEOU.The random neural network: a survey[J].The Computer Journal,2010,11(53): 251 - 267.
[56] STEVE FURBER,STEVE TEMPLE.Neural systems engineering[J]. J R Soc Interface,2007,6(4):193 -206.
[57] ALEXANDER SPROEWITZ , RICO MOECKEL , AUKE JAN IJSPEERT.Learning to move in modular robots using central pattern generators and online optimization[J].The International Journal of Robotics Research,2008,8(27):423 - 443.
[2]张慧平,戴波,杨薇.现代控制理论在过程工业中的应用和发展[J].北京石油化工学院学报,2006,14(3):57-61.
[3]华清远见嵌入式培训中心.FPGA应用开发与典型实例[M].北京:人民邮电出版社,2008:7-9.
[4]刘佳,焦斌亮.FPGA的发展趋势及其新应用[J].电子技术,2008,(4):43-44.
[5]潘松.CPLD/FPGA在电子设计中的应用前景[J].电子技术应用,1997,12(7):6-8.
[6]张科.基于FPGA的智能控制器的研究[D].哈尔滨理工大学硕士学位论文,2009,3:2.
[7]刘福奇,刘波.Verilog HDL应用程序设计[M].北京:电子工业出版社,2009,10:1-21.
[8]夏宇闻.Verilog数字系统设计教程[M].北京:北京航空航天大学出版社,2004,7:1-9.
[9]王金明.数字系统设计与Verilog HDL[M].北京:电子工业出版社,2002,1:12-13.
[10]潘松,黄继业.EDA实用教程(第2版)[M].北京:科学出版社,2005,5:1-27.
[11]潘松,王国栋.基于EDA技术的CPLD/FPGA应用前景[J].电子与自动化,1999,9(3):3-6.
[12] KEVIN M.PASSINO , STEPHEN YURKOVICH . Fuzzy control[M].Beijing:Tsinghua University Press,2001,1:27-29.
[13]刘一笑.先进控制技术应用综述[J].控制工程,2003,7(10):20-23.
[14]王艳秋.先进控制技术的集成与应用研究[D].东北大学博士学位论文,2006,1:1-7.
[15]赵俊.基于若干智能方法的先进控制系统综合设计研究[D].西安电子科技大学博士学位论文,2008,12:3-8.
[16] RIVALS I , PERSONNAZ L . Nonlinear internal modle using neuralnetworks[J].IEEE Transactions on Neural Networks Control,2000,11(1):80-90.
[17] LINGJI CHEN,KUMPATI S.NARENDRA.Nonlinear adaptive control using neural networks and multiple models[J].Automatica,2001,13(37):1245-1255.
[18] Y F CHAN ,M MOALLEM ,W WANG .Efficient implementation of advanced control altorithm using FPGA technology[C] . The 43rd IEEE Conference on Decision and Control, Bahamas,2004,11:4885-4890.
[19]崔涛,杨全胜.基于FPGA技术的通用模糊控制器设计[J].计算机技术与发展,2009,19(3):15-18.
[20]郭敏,秦刚,刘洋.基于FPGA的温度模糊自适应PID控制器的设计[J].电子设计工程,2009,17(l0):85-87.
[21]包明,张睿,余成波.基于模糊控制的移动机器人FPGA实现[J].电子技术应用,2008,34(7):29-31.
[22]万丽雯.基于FPGA的直接转矩模糊控制技术研究[J].电子测试,2009,12(8):43-46.
[23] LUND T.The architecture of an FPGA-style programmable fuzzy logic controller chip[C].The 5th Australasian Computer Architecture Conference,2000,6:206-208.
[24] TZUU-HSENG S.L, SHI-JIE CHANG,YI-XIANG CHEN. Fuzzy bahavior control on an FPGA-based car-like mobile robot[J]. IEEE Implementation of Human-Like Driving Skills by Autonomous,2003,15(3):867-880.
[25] CHIA-FENG JUANG , CHAO-HSIN HSU.Temperature control by chip implemented adaptive recurrent fuzzy controller designed by evolutionary algorithm[J]. IEEE Transactions on Automatic Control ,2004,40(5),31-34.
[26]焦素敏,阎有运.基于FPGA的模糊控制器的设计[J].华北水利水电学院学报, 2006,27(2):69-72.
[27] F.J.LIN,D.H.WANG and P.K.HUANG.FPGA-based fuzzy sliding-mode control for a linear induction motor drive[J].IEEE Proc.on Electric Power, 2005,152(5):1137-1148.
[28]夏欣,贾永刚,王素珍.RBF神经网络中指数函数ex的FPGA实现[J].微计算机信息(嵌入式与SOC),2005,21(7-2):145-146.
[29]李利歌,阎保定,侯忠.基于FPGA的神经网络硬件可重构实现[J].河南科技大学学报(自然科学版),2009,30(1):37-40.
[30]朱清智,阎保定,栗素娟.一种新型交流伺服控制系统试验研究[J].微电机,2009,42(6):86-88.
[31]白瑞林,沈宪明,章智慧.模糊CMAC网络的FPGA实现[J].计算机测量与控制,2007,15(4):527-530.
[32]白瑞林,王建,沈宪明.基于FPGA的CMAC-PID控制器的研究[J].计算机工程,2007,33(7):240-242.
[33]白瑞林,沈宪明,章智慧.基于FPGA的2-D模糊CMAC网络的硬件实现[J].计算机工程与设计,2007,28(2):430-435.
[34]冯智贵,吴明赞,陈晓宁,等.基于ARM和FPGA的雷达伺服控制器设计[J].世界科技研究与发展,2008,30(6):746-750.
[35]孔超,李占才,王沁,等.一种基于FPGA的SOM神经网络算法的并行实现[J].计算机工程,2007,33(19):236-237,240.
[36]吴军,吁少峰,来昂. FPGA乘法器在电能集中采集系统中的应用[J].江西理工大学学报,2009,30(6):34-37.
[37] FAIEDH H,GAFSI Z,TORKI KETAL.Digital hardware implementation of a neural network used for classification[C].Proceedings of the 16th International Conference on Microelectronics,Tunis,2004,5:551.
[38]熊光泽,詹瑾瑜.嵌入式系统软/硬件协同设计技术综述[J].计算机应用,2006,26(4):757-760,764.
[39]于宗光,魏敬和,王国章.SoC和FPGA技术未来的发展趋势[J] .电子与封装,2006,6(3):l-5.
[40]姚琳.在嵌入式系统中用FPGA进行开发的几个发展方向[J] .今日电子,2007,(6):125-127.
[41]赵曙光,郭万有,杨颂华,等.可编程逻辑器件原理、开发与应用[M].西安:西安电子科技大学出版社,2006:1-88,187-217.
[42]徐光辉,程东旭,黄如,等.基于FPGA的嵌入式系统开发与应用[M].北京:电子工业出版社,2007,5:10-48.
[43]史先龙.基于FPGA的可重构计算技术的研究应用[D].北京化工大学硕士学位论文,2006,12:2-7.
[44]李士勇.工程模糊数学及应用[M].哈尔滨:哈尔滨工业大学出版社,2004,8:159-166.
[45]路永坤.参数自调整模糊控制器研究及基于FPGA实现设计[J].自动化博览,2008,2:74-76.
[46] TONG SHAOCHENG,LI CHANGYING,LI YONGMING.Fuzzy adaptive observer backstepping control for MIMO nonlinear systems [J]. Fuzzy Sets and Systems,2009,8(19):2755-2775.
[47]李士勇.模糊控制·神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,1998,9:268-270.
[48]张智星,孙春在,水谷英二.神经-模糊和软件算[M].西安:西安交通大学出版社,2000,6:33-49.
[49]何克忠,李伟.计算机控制系统[M].北京:清华大学出版社.1998,4:187-192.
[50] L LI,G SONG,J OU.Nonlinear structural vibration suppression using dynamic neural network observer and adaptive fuzzy sliding mode control [J].Journal of Vibration and Control,2009,19(6):1503 - 1526.
[51] YU-YI FU,CHIA-JU Wu,JIN-TSONG JENG.Annealing robust radial basis function networks with support vector regression for nonlinear inverse system identification with outliers [J].Journal of Vibration and Control,2010,5(16):1915 - 1940.
[52] LASZLO BAKO.Real-time classification of datasets with hardware embedded neuromorphic neural networks [J].Brief Bioinform,2010,7(11): 348 - 353.
[53]闻新,周露,李翔,等.MATLAB神经网络仿真与应用[M].北京:科学出版社.2003,7:291-293.
[54]刘金琨.机器人控制系统的设计与MATLAB仿真[M].北京:清华大学出版社.2008,6:86-90,547.
[55] STELIOS TIMOTHEOU.The random neural network: a survey[J].The Computer Journal,2010,11(53): 251 - 267.
[56] STEVE FURBER,STEVE TEMPLE.Neural systems engineering[J]. J R Soc Interface,2007,6(4):193 -206.
[57] ALEXANDER SPROEWITZ , RICO MOECKEL , AUKE JAN IJSPEERT.Learning to move in modular robots using central pattern generators and online optimization[J].The International Journal of Robotics Research,2008,8(27):423 - 443.