基于GA的游梁抽油机变频驱动模糊神经网络最优控制
|
摘要
交流变频驱动抽油机是近年来在游梁式抽油机的基础上应用变频调速技术发展起来的新技术,对其各部分及总体的适用控制方法正在形成。在工程实际中,需控制的系统常常存在着不确定性、高度非线性、时变、时滞等特性,要建立精确的数学模型往往较为困难。因此本文首次将基于遗传算法的模糊神经网络控制应用于交流变频驱动抽油机系统,以求获得良好的计算机实时控制效果。
本文的硬件系统是由原有的游梁式抽油机模拟实验装置改造成的交流变频驱动抽油机控制系统实验装置。本文使用的控制算法是:模糊逻辑控制与神经网络控制相结合,利用遗传退火算法对模糊神经网络控制器参数进行综合设计、优化,通过控制器性能指标离线寻找最优的控制器结构和参数。目的是将该算法应用于交流变频驱动的抽油机控制系统中,同时与一般模糊控制进行对比研究,以验证该控制算法的可行性和优越性。通过实验得出:一般模糊控制稳态误差为3%,基于遗传算法的模糊神经网络最优控制的稳态误差1.8%。通过不同控制算法的实验结果得出,基于遗传算法的模糊神经网络最优控制在系统中控制效果更好,表明应用于交流变频驱动抽油机控制系统是可行的。
本文通过理论分析与实验研究,将基于遗传算法的模糊神经网络最优控制应用于交流变频驱动抽油机系统是非常有意义的,为该课题的进一步深入研究奠定了基础。
The beam pumping unit driven by AC frequency conversion is newly developed technology based on the conventional beam pumping unit. Owing to the existence of undetermined, nonlinear, time-varied and time-lag factor in Engineering contol system, it is difficult to build the precise mathematic model. In this paper, a fuzzy-neural network besed genetic algorithm is applied to the well pumping unit driven AC frequency conversion in order to obtain the better real time effect.
The hardware system that is experiment installment of AC control system in well pumping unit is refitted based on the simulating experiment installment of well pumping unit. The control algorithm is described as follows: With a controller of fuzzy logic combined with neural network, parameters of the controller are optimized by genetic algorithm. Then optimal structure and parameters of the controller are obtained by offline. The main purpose is that the control algorithm can be applied to the pumping unit driven AC frequency conversion. In addition, the feasibility and advantage of this algorithm had been verified by compared with the general fuzzy controller. The results of experiment show that stable error of general fuzzy controller is 3% and the stable error of optimal controller of fuzzy-neural network based on the genial algorithm is 1.8%.The experiment results of different control algorithm show that the control effect is better in the system with the optimal control of fuzzy-neural network based on the genetic algorithm. So the control system of AC frequency conversion driven of well pumping unit is feasible.
Through theoretical analysis and experiments, it is significant that the optimal control of fuzzy-neural network based on the generic algorithm, the proposed scheme established a basis of advanced study.
本文的硬件系统是由原有的游梁式抽油机模拟实验装置改造成的交流变频驱动抽油机控制系统实验装置。本文使用的控制算法是:模糊逻辑控制与神经网络控制相结合,利用遗传退火算法对模糊神经网络控制器参数进行综合设计、优化,通过控制器性能指标离线寻找最优的控制器结构和参数。目的是将该算法应用于交流变频驱动的抽油机控制系统中,同时与一般模糊控制进行对比研究,以验证该控制算法的可行性和优越性。通过实验得出:一般模糊控制稳态误差为3%,基于遗传算法的模糊神经网络最优控制的稳态误差1.8%。通过不同控制算法的实验结果得出,基于遗传算法的模糊神经网络最优控制在系统中控制效果更好,表明应用于交流变频驱动抽油机控制系统是可行的。
本文通过理论分析与实验研究,将基于遗传算法的模糊神经网络最优控制应用于交流变频驱动抽油机系统是非常有意义的,为该课题的进一步深入研究奠定了基础。
The beam pumping unit driven by AC frequency conversion is newly developed technology based on the conventional beam pumping unit. Owing to the existence of undetermined, nonlinear, time-varied and time-lag factor in Engineering contol system, it is difficult to build the precise mathematic model. In this paper, a fuzzy-neural network besed genetic algorithm is applied to the well pumping unit driven AC frequency conversion in order to obtain the better real time effect.
The hardware system that is experiment installment of AC control system in well pumping unit is refitted based on the simulating experiment installment of well pumping unit. The control algorithm is described as follows: With a controller of fuzzy logic combined with neural network, parameters of the controller are optimized by genetic algorithm. Then optimal structure and parameters of the controller are obtained by offline. The main purpose is that the control algorithm can be applied to the pumping unit driven AC frequency conversion. In addition, the feasibility and advantage of this algorithm had been verified by compared with the general fuzzy controller. The results of experiment show that stable error of general fuzzy controller is 3% and the stable error of optimal controller of fuzzy-neural network based on the genial algorithm is 1.8%.The experiment results of different control algorithm show that the control effect is better in the system with the optimal control of fuzzy-neural network based on the genetic algorithm. So the control system of AC frequency conversion driven of well pumping unit is feasible.
Through theoretical analysis and experiments, it is significant that the optimal control of fuzzy-neural network based on the generic algorithm, the proposed scheme established a basis of advanced study.
引文
[1]张志檩.变频技术在石化行业的节能应用及进展[J].变频器世界,2006,(10)77-80.
[2]周维.游梁式抽油机节能技术的现状与展望[J].石油矿场机械,2002,16(5):28-32.
[3]徐甫荣.变频器在抽油机上应用的若干问题探讨[J].电气传动自动化,2004,26(2):4-8.
[4]胡新.抽油机数控系统[J].石油机械,1991,19(1):45-49.
[5]崔振华,余国安.有杆抽油系统[M].北京:石油工业出版社,1994.23-48.
[6]张连山.国外抽油机的技术发展[J].石油机械,1999,27(4):54-56.
[7]张连山.国外AC顶驱钻机变频驱动的应用与发展[J].石油机械,1998,26(5):50-53.
[8]张连山.国外顶部驱动钻井系统的最新发展[J].钻采工艺,1999,22(6):50-54.
[9]赵来军,倪振文,余国安等.抽油机变频控制技术[J].钻采工艺,1999,22(6):61-63.
[10]张连山.我国抽油机的发展趋势[J].钻采工艺,1996,19(6):41-46.
[11]余小清.数控抽油机井的诊断数据处理[J].西安石油学院学报,1994,9(2):52-54.
[12]赵来军,倪振文,余国安等.游梁抽油机智能控制装置的研制[J].石油矿场机械,1998,27(6):1-5.
[13]曲刚,孙永兴.抽油机智能化变频控制系统的应用现状[J].变频器世界,2005,(5):87-91.
[14]秦力顼.基于GA的模糊神经网络智能控制研究及其在非线性系统中的应用[D].重庆:重庆大学,2004.2-3.
[15]蔡自兴.智能控制[M].第二版.北京:电子工业出版社,2004.2-5.
[16]H Pomares,I Rojas,J Gonzalez.A Two-Stage Approach to Self-Learning Direct Fuzzy Controllers[J].International Journal of Approximate Reasoning,2002,29(3):267-289.
[17]M Munir-ul,M Chowdhury,Yun Li.Messy Genetic Algorithm Based New Leaning Method for Structurally Optimised Neurofuzzy Controllers[C].The IEEE International Conference On Industrial Technology.1996,(4):274-278.
[18]李旭明,康赐荣.基于遗传算法的最优模糊控制器设计[N].华侨大学学报(自然科学版),1999(1):95-99.
[19]Sung Hoe Kim,Chongkug Park.A Self-Organized Fuzzy Controller for Wheeed Mobile Robot Using an Evolutionary Algorithm[J].IEEE Transactions on Industrial Electronics,2001,48(2):467-474.
[20]Wei-Yen Wang,Yi-Hsum Li.Networks.Evolutionary Learning of BMF Fuzzy-Neural Using A Reduced-Form Genetic Algorithm[N].IEEE Transactions On Systems,Man and Cybernetics-Part B:Cybernetics,2003-12-6(33).
[21]张燕宾.SPWM变频调速应用技术[M].第二版.北京:机械工业出版社,2002.21-22,102-121.
[22]张选正,张金远.变频器应用经验[M],北京:中国电力出版社,2006.4-12.
[23]周洲深.交直流调速系统与MATLAB仿真[M].北京:中国电力出版社,2004.196-245.
[24]张选正,张金远.变频器应用经验[M],北京:中国电力出版社,2006.58-59.
[25]马志源.电力拖动控制系统[M].北京:科学出版社,2004.5-17,220-229.
[26]范正翘.电力传动与自动控制系统[M].北京:北京航空航天大学出版社,2003.228-236.
[27]张立明.人工神经网络模型及其应用[M].上海:复旦大学出版社,1993.193-199.
[28]Michalewicz,Z,Janikow,C,and Krawczyk,J.A Modified Genetic Algorithm for Optimal Control Problems[J],Computers & Mathematics with Applications,1992,23(12):83-94.
[29]孙增圻.智能控制理论与技术[M].北京:清华大学出版社,2004.52-75.
[30]易继锴,侯媛彬.智能控制技术[M],北京:北京工业大学出版社,2003.139-216.
[31]恽为民,席裕庚.遗传算法的全局收敛性和计算效率分析[J].控制理论与应用.1996,13(4):455-460.
[32]王士同.神经模糊系统及其应用[M].第一版.北京:北京航空航天大学出版社.1998.2-3.
[33]周志坚,毛宗源.模糊神经网络的交叉研究[J].电路与系统学报,1998,3(3):81-85.
[34]王隆杰,毛宗源.利用神经网络进行推理的模糊控制器[J].控制理论与应用,1994,11(4):508-512.
[35]张良杰,李衍达.模糊神经网络技术的新近发展[J].信息与控制.1995,24(1):39-45.
[36]杨煜普,许晓鸣,张钟俊.基于模糊神经网络的控制规则获取及置信度估计问题[J].模式识别与人工智能,1994,7(1):53-59.
[37]杨煜普,许晓鸣,张钟俊.基于模糊神经网络的控制规则获取及置信度估计问题[J].模式识别与人工智能,1994,7(1):53-59.
[38]陈尹萍.基于遗传算法的模糊神经网络控制器研究[D].武汉:武汉理工大学,2006.18-21.
[39]胡波,张斌,林锦国.基于遗传算法的模糊神经网络控制器的仿真[J].南京化工大学学报,2001,23(5):53-56.
[40]李孝安,张晓绩等.基于遗传算法的PID控制器参数寻优方法及应用[C].中国启动化学会第十届青年学术年会论文集,西安:1994,304-307.
[41]张晓绩,戴冠中,徐乃平.遗传算法在抽取和过滤模糊控制规则中的应用研究[J].控制理论和应用.1998,15(3):379-384.
[42]《采油技术于册编写组》.采油技术手册[M].北京:石油化学工业出版社,1977.139,142,144,147-150,939.
[43]重晓阳.实时控制系统中的中断技术[J].现代计算机,1995,(11):41-43.
[44]刘宝林,桂暖银.地质钻机交流调速系统驱动性能的实验研究[J].探矿工程,1996,(1):49-52.
[2]周维.游梁式抽油机节能技术的现状与展望[J].石油矿场机械,2002,16(5):28-32.
[3]徐甫荣.变频器在抽油机上应用的若干问题探讨[J].电气传动自动化,2004,26(2):4-8.
[4]胡新.抽油机数控系统[J].石油机械,1991,19(1):45-49.
[5]崔振华,余国安.有杆抽油系统[M].北京:石油工业出版社,1994.23-48.
[6]张连山.国外抽油机的技术发展[J].石油机械,1999,27(4):54-56.
[7]张连山.国外AC顶驱钻机变频驱动的应用与发展[J].石油机械,1998,26(5):50-53.
[8]张连山.国外顶部驱动钻井系统的最新发展[J].钻采工艺,1999,22(6):50-54.
[9]赵来军,倪振文,余国安等.抽油机变频控制技术[J].钻采工艺,1999,22(6):61-63.
[10]张连山.我国抽油机的发展趋势[J].钻采工艺,1996,19(6):41-46.
[11]余小清.数控抽油机井的诊断数据处理[J].西安石油学院学报,1994,9(2):52-54.
[12]赵来军,倪振文,余国安等.游梁抽油机智能控制装置的研制[J].石油矿场机械,1998,27(6):1-5.
[13]曲刚,孙永兴.抽油机智能化变频控制系统的应用现状[J].变频器世界,2005,(5):87-91.
[14]秦力顼.基于GA的模糊神经网络智能控制研究及其在非线性系统中的应用[D].重庆:重庆大学,2004.2-3.
[15]蔡自兴.智能控制[M].第二版.北京:电子工业出版社,2004.2-5.
[16]H Pomares,I Rojas,J Gonzalez.A Two-Stage Approach to Self-Learning Direct Fuzzy Controllers[J].International Journal of Approximate Reasoning,2002,29(3):267-289.
[17]M Munir-ul,M Chowdhury,Yun Li.Messy Genetic Algorithm Based New Leaning Method for Structurally Optimised Neurofuzzy Controllers[C].The IEEE International Conference On Industrial Technology.1996,(4):274-278.
[18]李旭明,康赐荣.基于遗传算法的最优模糊控制器设计[N].华侨大学学报(自然科学版),1999(1):95-99.
[19]Sung Hoe Kim,Chongkug Park.A Self-Organized Fuzzy Controller for Wheeed Mobile Robot Using an Evolutionary Algorithm[J].IEEE Transactions on Industrial Electronics,2001,48(2):467-474.
[20]Wei-Yen Wang,Yi-Hsum Li.Networks.Evolutionary Learning of BMF Fuzzy-Neural Using A Reduced-Form Genetic Algorithm[N].IEEE Transactions On Systems,Man and Cybernetics-Part B:Cybernetics,2003-12-6(33).
[21]张燕宾.SPWM变频调速应用技术[M].第二版.北京:机械工业出版社,2002.21-22,102-121.
[22]张选正,张金远.变频器应用经验[M],北京:中国电力出版社,2006.4-12.
[23]周洲深.交直流调速系统与MATLAB仿真[M].北京:中国电力出版社,2004.196-245.
[24]张选正,张金远.变频器应用经验[M],北京:中国电力出版社,2006.58-59.
[25]马志源.电力拖动控制系统[M].北京:科学出版社,2004.5-17,220-229.
[26]范正翘.电力传动与自动控制系统[M].北京:北京航空航天大学出版社,2003.228-236.
[27]张立明.人工神经网络模型及其应用[M].上海:复旦大学出版社,1993.193-199.
[28]Michalewicz,Z,Janikow,C,and Krawczyk,J.A Modified Genetic Algorithm for Optimal Control Problems[J],Computers & Mathematics with Applications,1992,23(12):83-94.
[29]孙增圻.智能控制理论与技术[M].北京:清华大学出版社,2004.52-75.
[30]易继锴,侯媛彬.智能控制技术[M],北京:北京工业大学出版社,2003.139-216.
[31]恽为民,席裕庚.遗传算法的全局收敛性和计算效率分析[J].控制理论与应用.1996,13(4):455-460.
[32]王士同.神经模糊系统及其应用[M].第一版.北京:北京航空航天大学出版社.1998.2-3.
[33]周志坚,毛宗源.模糊神经网络的交叉研究[J].电路与系统学报,1998,3(3):81-85.
[34]王隆杰,毛宗源.利用神经网络进行推理的模糊控制器[J].控制理论与应用,1994,11(4):508-512.
[35]张良杰,李衍达.模糊神经网络技术的新近发展[J].信息与控制.1995,24(1):39-45.
[36]杨煜普,许晓鸣,张钟俊.基于模糊神经网络的控制规则获取及置信度估计问题[J].模式识别与人工智能,1994,7(1):53-59.
[37]杨煜普,许晓鸣,张钟俊.基于模糊神经网络的控制规则获取及置信度估计问题[J].模式识别与人工智能,1994,7(1):53-59.
[38]陈尹萍.基于遗传算法的模糊神经网络控制器研究[D].武汉:武汉理工大学,2006.18-21.
[39]胡波,张斌,林锦国.基于遗传算法的模糊神经网络控制器的仿真[J].南京化工大学学报,2001,23(5):53-56.
[40]李孝安,张晓绩等.基于遗传算法的PID控制器参数寻优方法及应用[C].中国启动化学会第十届青年学术年会论文集,西安:1994,304-307.
[41]张晓绩,戴冠中,徐乃平.遗传算法在抽取和过滤模糊控制规则中的应用研究[J].控制理论和应用.1998,15(3):379-384.
[42]《采油技术于册编写组》.采油技术手册[M].北京:石油化学工业出版社,1977.139,142,144,147-150,939.
[43]重晓阳.实时控制系统中的中断技术[J].现代计算机,1995,(11):41-43.
[44]刘宝林,桂暖银.地质钻机交流调速系统驱动性能的实验研究[J].探矿工程,1996,(1):49-52.