智能自适应解耦控制及其在板形板厚综合控制中的应用
|
摘要
板形和板厚是现代板带生产中两个非常重要的质量控制指标,板形、板厚质量控制水平的高低直接关系到板带钢制成品质量的优劣和板带钢市场销售的好坏,因此,板厚和板形控制功能是板带轧机自动控制系统中两个最主要的功能。
板形、板厚两者之间相互关联、相互交叉、耦合程度严重。因此,两者构成了一个多变量、强耦合复杂控制系统。本文通过分析这一系统各变量之间耦合关系和各个变量的变化规律,研究了影响板形板厚两个重要质量指标的主要因素,建立了板形板厚综合控制系统控制模型,并针对山东莱钢1500mm热连轧带钢精轧六机架板形板厚控制要求,研究、设计了三种控制方法。
根据板形板厚综合控制系统的特点:难以进行精确计算、难以建立精确数学模型、控制变量多、强耦合等,本文将基于遗传算法和神经网络的智能控制方法应用于板形板厚综合控制系统中,提高了板形板厚控制精度,主要所作的研究工作有:
(1)通过对多变量神经网络控制器结构研究,在不变性原理的基础上提出了多变量串联补偿神经网络解耦控制方法。通过采用神经网络解耦补偿控制,在不影响系统控制功能和性能的前提下,实现了多变量之间的解耦,优化了控制系统的性能指标。
(2)通过对标准遗传算法(Standard Genetic Algorithm简称SGA)的原理、控制参数的选择、遗传操作、编码方式等方面的分析、研究,针对SGA存在的易陷入局部最优、早熟以及多值参数优化中存在的二进制编码串过长等影响遗传算法的计算精度和运行效率的缺陷,对遗传算法进行改进,提出了基于实数编码的自适应竞争遗传算法(Adaptive Compete Genetic Algorithm简称ACGA)。采用ACGA、自适应遗传算法(Adaptive Genetic Algorithm简称AGA)和SGA对几个标准测试函数作了优化仿真,结果表明ACGA的性能要优于SGA和AGA的性能。同时,采用ACGA优化所设计的几种控制器的仿真和实际应用也表明ACGA能够较好地消除SGA所存在的缺陷,其学习效率、收敛速度等明显优于SGA和AGA。
(3)针对广义预测控制的特点及实际应用情况,在总结原参考轨线的基础上,根据原参考轨线柔化系数不易精确确定、轨线参考性因人而异、准确度有待提高等不足,提出了一种新的参考轨线算法—自适应参考轨线,使得参考轨线跟踪系统输入输出的差值,提高了参考轨线精度。同时进一步研究了基于神经网络的预测控制算法,将神经网络与预测控制的融合,设计了一种神经网络预测控制器,改进了对多变量、非线性控制系统的预测控制性能,提高了1500mm热连轧精轧六机架板形板厚控制的实时性精度,增强了系统稳定性。
(4)针对常规PID控制算法易于实现,但对系统参数变化适应性差的特点,将ACGA应用到PID控制器的参数在线优化中。通过仿真验证表明,本文所研究的智能控制方法对PID控制性能改进效果明显,不仅实现了PID参数的在线自整定,而且提高了系统的控制精度和响应速度。通过在精轧机上实际应用,表明基于ACGA的PID控制方法的性能明显优于传统PID控制效果。
最后,将所研究的智能控制方法应用于山东莱钢集团1500mm热连轧带钢项目精轧六机架板形板厚综合控制系统中,通过对板形板厚实际控制效果比较情况看,基于ACGA多变量神经网络自适应解耦预测控制方法实时性和控制精度更好,而且控制系统设计不依赖于对象精确的数学模型,控制方法简单易行,易于实现,能够很好地满足当今板形板厚质量综合控制目标的要求。
Strip Flatness and Gauge are two very important quality control indices in the modern strip production line. The quality control level will directly influence the quality of finished products as well as the sale markets. Therefore, the most important function of automatic control system of strip rolling mill consists of the control of the flatness and the gauge.
The flatness and the gauge control, with the interlocking, intercrossing and strong coupling relation, constitute a complex multivariable strong coupling control system. By analyzing coupling relationship and variation law among all the variations in the system, the main factors of affecting the flatness and the gauge are analyzed, then the control model for strip quality integrated control system is established, and finally the three control methods are designed according to the flatness and the gauge control requirements of finishing mill 6 stand for Shan Dong Laiwu Steel 1500mm hot strip.
The strip quality integrated control system has several features such as difficult to calculate exactly and to establish the accurate mathematical model, many control variations and strong coupling, etc. According to all these features, the neural network adaptive decoupling control theory is employed to the quality integrated control system, and several neural network decoupling controllers are designed as follows:
(1) Through studying on the structural of the multivariable neural network controller, this paper presents a new multivariable tandem connection compensation neural network decoupling control method based on the invariance principle. Through adapting the neural network decoupling compensation control, the couple among the multivariations can be decoupled successfully and the performance indices are optimized under the conditions of maintaining the system intrinsic control function and intrinsic performance.
(2) Special analysis and study is made on the standard genetic algorithm (SGA) for its principle, control parameters setting, genetic operation and coding method. Due to the standard GA with some deficiencies such as tendency to get into local optimization, prematurity, low calculation precision and operation efficiency owing to the existence of the too long binary character string in multi-valued parameter optimization process, etc, an improved real-code GA, namely Adaptive Competitive Genetic Algorithm (ACGA), is proposed. Comparing with the standard GA and the adaptive genetic algorithm (AGA), the simulation results demonstrate that ACGA have better performance. The several developed controllers are optimized by ACGA, the simulation results further show that ACGA not only overcomes the deficiencies of standard GA but also have better convergence rate and learning efficiency than standard GA and and AGA.
(3) Due to difficult to determine softness factor and the poor adaptability of reference trajectory in prediction control, a new reference trajectory, namely adaptive reference trajectory algorithm, is presented. The prediction control algorithm based on neural network is described, which can be employed to the multivariable nonlinear objects due to the integration between neural network and prediction control. By adjusting the step, optimizing the weight and improving reference trajectory algorithm of Prediction control, the real time and control precision of the control system are improved, and the stability of the system is enhanced.
(4) Although the conventional PID control algorithm is easy to achieve and good control performance, the adaptability for the variation of system parameters is weak. Therefore, the ACGA is applied to the online optimization for the parameters of the PID controller, and the simulation results show that the proposed algorithm not only achieves the online self-tune of PID parameters, but also improves the control precision and response speed. Moreover, the validity of proposed algorithm is further demonstrated by the application to the real finishing mill.
Finally, the proposed intelligent control methods have been applied to the flatness and the gauge integrated control system of finishing mill 6 stand for Shan Dong Laiwu Steel 1500mm hot strip project, and the results show that the multivariable neural network adaptive decoupling predictive controller has the advantages of better adaptability for parameter variety, stronger interference rejection, better tracing input, and higher calculation and control precision. Furthermore, the controller can be easily design due to not relying on precise mathematic model and simple control algorithm, and can also fulfill strip quality integrated control requirements very well.
板形、板厚两者之间相互关联、相互交叉、耦合程度严重。因此,两者构成了一个多变量、强耦合复杂控制系统。本文通过分析这一系统各变量之间耦合关系和各个变量的变化规律,研究了影响板形板厚两个重要质量指标的主要因素,建立了板形板厚综合控制系统控制模型,并针对山东莱钢1500mm热连轧带钢精轧六机架板形板厚控制要求,研究、设计了三种控制方法。
根据板形板厚综合控制系统的特点:难以进行精确计算、难以建立精确数学模型、控制变量多、强耦合等,本文将基于遗传算法和神经网络的智能控制方法应用于板形板厚综合控制系统中,提高了板形板厚控制精度,主要所作的研究工作有:
(1)通过对多变量神经网络控制器结构研究,在不变性原理的基础上提出了多变量串联补偿神经网络解耦控制方法。通过采用神经网络解耦补偿控制,在不影响系统控制功能和性能的前提下,实现了多变量之间的解耦,优化了控制系统的性能指标。
(2)通过对标准遗传算法(Standard Genetic Algorithm简称SGA)的原理、控制参数的选择、遗传操作、编码方式等方面的分析、研究,针对SGA存在的易陷入局部最优、早熟以及多值参数优化中存在的二进制编码串过长等影响遗传算法的计算精度和运行效率的缺陷,对遗传算法进行改进,提出了基于实数编码的自适应竞争遗传算法(Adaptive Compete Genetic Algorithm简称ACGA)。采用ACGA、自适应遗传算法(Adaptive Genetic Algorithm简称AGA)和SGA对几个标准测试函数作了优化仿真,结果表明ACGA的性能要优于SGA和AGA的性能。同时,采用ACGA优化所设计的几种控制器的仿真和实际应用也表明ACGA能够较好地消除SGA所存在的缺陷,其学习效率、收敛速度等明显优于SGA和AGA。
(3)针对广义预测控制的特点及实际应用情况,在总结原参考轨线的基础上,根据原参考轨线柔化系数不易精确确定、轨线参考性因人而异、准确度有待提高等不足,提出了一种新的参考轨线算法—自适应参考轨线,使得参考轨线跟踪系统输入输出的差值,提高了参考轨线精度。同时进一步研究了基于神经网络的预测控制算法,将神经网络与预测控制的融合,设计了一种神经网络预测控制器,改进了对多变量、非线性控制系统的预测控制性能,提高了1500mm热连轧精轧六机架板形板厚控制的实时性精度,增强了系统稳定性。
(4)针对常规PID控制算法易于实现,但对系统参数变化适应性差的特点,将ACGA应用到PID控制器的参数在线优化中。通过仿真验证表明,本文所研究的智能控制方法对PID控制性能改进效果明显,不仅实现了PID参数的在线自整定,而且提高了系统的控制精度和响应速度。通过在精轧机上实际应用,表明基于ACGA的PID控制方法的性能明显优于传统PID控制效果。
最后,将所研究的智能控制方法应用于山东莱钢集团1500mm热连轧带钢项目精轧六机架板形板厚综合控制系统中,通过对板形板厚实际控制效果比较情况看,基于ACGA多变量神经网络自适应解耦预测控制方法实时性和控制精度更好,而且控制系统设计不依赖于对象精确的数学模型,控制方法简单易行,易于实现,能够很好地满足当今板形板厚质量综合控制目标的要求。
Strip Flatness and Gauge are two very important quality control indices in the modern strip production line. The quality control level will directly influence the quality of finished products as well as the sale markets. Therefore, the most important function of automatic control system of strip rolling mill consists of the control of the flatness and the gauge.
The flatness and the gauge control, with the interlocking, intercrossing and strong coupling relation, constitute a complex multivariable strong coupling control system. By analyzing coupling relationship and variation law among all the variations in the system, the main factors of affecting the flatness and the gauge are analyzed, then the control model for strip quality integrated control system is established, and finally the three control methods are designed according to the flatness and the gauge control requirements of finishing mill 6 stand for Shan Dong Laiwu Steel 1500mm hot strip.
The strip quality integrated control system has several features such as difficult to calculate exactly and to establish the accurate mathematical model, many control variations and strong coupling, etc. According to all these features, the neural network adaptive decoupling control theory is employed to the quality integrated control system, and several neural network decoupling controllers are designed as follows:
(1) Through studying on the structural of the multivariable neural network controller, this paper presents a new multivariable tandem connection compensation neural network decoupling control method based on the invariance principle. Through adapting the neural network decoupling compensation control, the couple among the multivariations can be decoupled successfully and the performance indices are optimized under the conditions of maintaining the system intrinsic control function and intrinsic performance.
(2) Special analysis and study is made on the standard genetic algorithm (SGA) for its principle, control parameters setting, genetic operation and coding method. Due to the standard GA with some deficiencies such as tendency to get into local optimization, prematurity, low calculation precision and operation efficiency owing to the existence of the too long binary character string in multi-valued parameter optimization process, etc, an improved real-code GA, namely Adaptive Competitive Genetic Algorithm (ACGA), is proposed. Comparing with the standard GA and the adaptive genetic algorithm (AGA), the simulation results demonstrate that ACGA have better performance. The several developed controllers are optimized by ACGA, the simulation results further show that ACGA not only overcomes the deficiencies of standard GA but also have better convergence rate and learning efficiency than standard GA and and AGA.
(3) Due to difficult to determine softness factor and the poor adaptability of reference trajectory in prediction control, a new reference trajectory, namely adaptive reference trajectory algorithm, is presented. The prediction control algorithm based on neural network is described, which can be employed to the multivariable nonlinear objects due to the integration between neural network and prediction control. By adjusting the step, optimizing the weight and improving reference trajectory algorithm of Prediction control, the real time and control precision of the control system are improved, and the stability of the system is enhanced.
(4) Although the conventional PID control algorithm is easy to achieve and good control performance, the adaptability for the variation of system parameters is weak. Therefore, the ACGA is applied to the online optimization for the parameters of the PID controller, and the simulation results show that the proposed algorithm not only achieves the online self-tune of PID parameters, but also improves the control precision and response speed. Moreover, the validity of proposed algorithm is further demonstrated by the application to the real finishing mill.
Finally, the proposed intelligent control methods have been applied to the flatness and the gauge integrated control system of finishing mill 6 stand for Shan Dong Laiwu Steel 1500mm hot strip project, and the results show that the multivariable neural network adaptive decoupling predictive controller has the advantages of better adaptability for parameter variety, stronger interference rejection, better tracing input, and higher calculation and control precision. Furthermore, the controller can be easily design due to not relying on precise mathematic model and simple control algorithm, and can also fulfill strip quality integrated control requirements very well.
引文
[1]孙一康 带钢热连轧的模型与控制 冶金工业出版社2002.5 p124-p186
[3]孙一康 杨金标 马正午 热连轧厚度自动控制系统的仿真研究 1980年 第四期P86-101
[4]孙一康 带钢热连轧计算机控制系统的发展 北京科技大学学报 轧钢自动化专刊 vol.21 增刊P1-9
[5]刘价,孙一康 主编 带钢热连轧计算机控制 机械工业出版社 1996
[6]吕程,赵启林,刘立忠等.热轧精轧机组负荷分配的优化算法.钢铁研究学报,2001,13(1):26-29
[7]贾春玉.热带轧极高精度负荷预测模型的开发.钢铁研究,2000,(6):40-42
[8]白埃民等.综合等负荷汉书法栽种板生产中的应用.钢铁,1993,28(4):35-39
[9]余四清等.多种负荷均衡分配法.钢铁,1996,31(7):48-51
[10]刘靖等.多种负荷均衡分配法优化冷轧板带生产规程.北京科技大学学报,1993增刊92-95
[11]梁国平.关于轧机的最佳负荷分配问题.钢铁,1980,15(1):42-48
[12]张进之等.连轧优化规程计算机设定计算方法.钢铁研究学报,1987,7(3):99-104
[13]F.Wagner 热带钢轧机的轧制力前馈厚度控制 国外钢铁 1997年第6期
[14]祝东奎等.兼顾板形的带钢冷连轧机最优负荷分配.北京科技大学学报,2000,22(1):246--252
[15]#12
[16]赵红雁等.人工神经网络推理的模糊控制其应用于热轧带钢厚度控制.上海金属,2001,23(1):28-31
[17]张进之.压力AGC参数方程及变刚度轧机分析.冶金自动化,1984,8(1):24-31
[18]郝付国等.动态设定型AGC在中厚板轧机上的应用.钢铁,1995,30(7):32-36
[19]王立平等.本钢1700mm热连轧机变刚度分析与实现.冶金自动化.1995,10(6):14-16
[20]张进之.动态设定形变刚度厚控方法的效果分析.重型机械,1998,(1):30-34
[21]陈先霖,张杰等.宽带钢热连轧机板形控制系统的开发.钢铁,2000,35(7):28-32
[22]李虎兴等.1700mm冷连轧机板形的优化和控制.武汉钢铁学院学报,1990,13(3):246-252
[23]许良等.HC轧机板形优化模型的研究.钢铁,1997,32(6):33-36
[24]#12
[25]#12
[26]#12
[27]#12
[28]王立平等.热连轧机厚度设定与控制系统分析.控制与决策,1994,9(2):15-20
[29]华建新.宝钢2030冷连轧机的自学习.冶金自动化,1991,15(4):35-38
[30]D.A.Shaw,Control Strategies for High Production and Quality:U.S.Steel Gary 84-in.Hot Strip Mill,Iron and Steel Engineer,june.1998,31-39
[31]D.A.Shaw,Strip Profile Control Technology and Economic Impact of Target Profiles,Iron and Steel Engineer,March 1998,31-39
[32]V.B.Ginzburg,et al,Selection of Optimum Strip Profiles and Flatness Technology for Rolling Mills,Iron and Steel Engineer,July 1997.7,30-38
[33]张清洞等.CVC四辊冷轧机板形与设定研究.钢铁,1997.10,29-33
[34]刘玉礼等.400HC轧机板形设定控制数学模型.钢铁,1998.7,28-32
[35]Sean J.Egan,et al,Flatness modeling and control for a continuous tandem cold mill,Iron and Steel Engineer,1996.3,38-41
[36]C.Nnappez,et al,Control of Strip flatness in cold rolling,Iron and Steel Engineer,1997.4,42-45
[37]H.Wolters,Strips profile and flatness control in hot strip mills with particular reference to CVC technology,Proceedings of 4~(th) international Steel Rolling conference,A.20-A.20.7
[38]N.F.Portmann,et al,Application of neural networks in rolling mill automation,Iron and Steel Engineer,1995.2,33-36
[39]Y.Z.LU,Meeeting challenge of intelligent system technologies in the iron and steel industry,Iron and Steel Engineer,1996.9,139-149
[40]王国栋,刘相华.金属轧制过程人工智能优化.北京:冶金工业出版社,2000.3
[41]张大志等.基于遗传算法的冷连轧机组参数优化设定系统.上海金属,2000,22(6):25-30
[42]张大志等.基于遗传算法的冷连轧机辊形配置优化系统的开发及应用.冶金自动化,2001,(1):17-20
[43]#12
[44]#12
[45]#12
[46]Yasunori Katayama,Masaki NakajimaHiroshi Koyama.A neural fuzzy control system for rolling mills.Steel Technology International,1992,189-196
[47]#12
[48]#12
[49]小西正躬.塑性加工の知能化技术.塑性と加工,1993,34(387):337-344
[50]孙登月,杜凤山,朱泉封等.五机架冷连轧机轧制压力人工神经网络与报.钢铁,2002,37(2):28-30,34
[51]周旭东,李连诗.人工神经网络板形板厚综合控制.轧钢,1995,(4):16-19
[52]乔俊飞等.一种基于神经网络的内模控制方法及其应用.天津大学学报,2000,33(1):25-28
[53]贾春玉等.基于模糊神经网络进行冷轧板形智能控制的研究.重型机械,2000(5):11-14
[54 刘建昌.基于神经网络的自适应厚度控制.钢铁,1999,34(11):33-36
[55]刘晓星.冷连轧机轧制规程的多目标模糊优化设计.钢铁,2000,35(8):34-36
[56]马虹蔚.五机架轧制规范优化与自适应的研究.武钢技术,2000,38(5):36-38
[57]童朝南等.模糊控制器在热连轧微张力控制中的应用.钢铁,1998,33(5):36-38
[58]张宏伟.多变量自适应解耦控制理论在单机架轧机系统中的应用.北京科技大 学博士论文,1995
[59]喻宗权.模糊神经系统研究综述.自动化与仪表,1998,13(6):3-5
[60]闻新,周露等.MATLAB神经网络应用设计.北京:科学出版社,2000.9
[61]张良杰等.模糊神经网络技术的新近发展.信息与控制,1995,24(1):39-44
[62]高卫华,谢勇英.RBF神经网络与自适应模糊系统.电气自动化,2000(3):4-5
[63]申东日,冯少回等.BP网络改进方法概述.化工自动化及仪表,2000,27(1):28-30
[64]李少元,席裕庚.智能控制的新进展(Ⅱ).控制与决策,2000,15(2):136-140
[65]何述东等.多层前向神经网络结构的研究进展.控制理论与应用,1998,15(3):313-318
[66]戴连奎等.多层前向神经网络的随机学习新算法及其工业应用.自动化学报,1998,24(1):33-35
[67]费敏锐等.智能控制方法的交叉综合及其应用.《控制理论与应用》,第13卷,第3期,1996
[68]周旭东等 自适应神经网络板形板厚综合控制论 北京科技大学学报 No.41994
[69]石中锁 板形板厚神经网络预测控制与H_∞控制系统的研究 北京科技大学博士论文 1997
[70]戴晓龙 神经网络板形板厚综合控制系统的研究 北京科技大学博士论文1995
[71]Holland J.H.Adaptation in natural and Artificial System.The University of Michigan press,1975
[72]Kenneth D J.An Analysis of the Behavior of a Class of Genetic Adaptive System.Ann Arbor:University of Michigan Press,1975
[73]周明,孙树栋.遗传算法原理及应用.国防工业出版社,北京:1999,6然科学版),2000,No.1:33-38
[74]文绍纯,罗飞,付连续等.基于遗传算法的人工神经网络的应用综述.自动化与仪器仪表,2001,1(6)
[75]李智勇,童调生.基于多物种进化遗传算法的神经网络进化设计方法.系统仿真学报,2003,15(6)
[76]杨国君,崔平远,李琳琳.遗传算法在神经网络控制中的应用与实现.系统仿真学报,2001,13(5)
[77]薛福珍,唐琰.基于GA的模糊神经网络控制器的设计与仿真.系统仿真学 报,2001,13(5)
[78]王永初,解耦控制系统,四川科学技术出版社,1983
[79]R.J.Kavangh,Noninteracting Controls in Linear Multivariable Systems,AIEE.Trans.Appl.Ind.Vol.76.Pt Ⅱ.95-99.May.1957.
[80]Falb,P.L.and Wolovich,W.A,Decoupling in the Design and Synthesis of Multivariable Control Systems,IEEE Trans.on Automatic Control.Vol 12,651-659,1967
[81]F.G.Shinskey,Process Control Systems,McGraw-Hill Book Company,Second Edition,1979
[82]P.E.McDermott and D.A.Mellichamp,A decoupling pole-placement self-tuning controller for a class of multivariable process,Optimal Control Applications and Methods,Vol 7,862-867,1985
[83]Lang S.J,Gu X,Y and Chai T.Y.,A Multivariablized self-tuning feedforward controller with decoupling design,IEEE Trans.AC,vol 5,474-477,1986
[84]Chai T.Y,Lang S.J and Gu X.Y,A Generalized self-tunning feedforward controller and multivariable application,Proceedings of the 24~(th) IEEE Conference on Decision and Control,862-867,1985
[85]B.Wittemmark,R.Middleton and G.Goodwin,Adaptive Decoupling of Multivariable Systems.Int.J.Control,Vol 46,1993-2009,1987
[86]白焰,神经解耦控制在钢球磨煤机中间仓储式制粉系统中的应用,东北大学博士论文,1998
[87]岳恒、柴天佑,一类多变量非线性系统的神经网络自适应解耦控制,信息与控制,Vol 28,607-612,1999
[88]吴黎明、柴天佑,一类非线性离散时间系统的神经网络解耦策略,自动化学报,Vol23,207-212,1997
[89]柴天佑、张振山等,棒材连轧机立式活套的多变量自适应解耦控制,自动化学报,Vol
[90]Wittenmark B,Middleton R H,Goodwin G C.Adaptive decoupling of multivariable systems,International Journal of Control,1987,46(6):1993-2009.
[91]Wahba A M,Sheirah M A.Adaptive decoupler for multivariable systems,International Journal of System Science,1993,24(1):97-109.
[92]T.Y.Chai.Direct adaptive decoupling control for general stochastic multivariable system.Int.J.Control,1990,51(4)
[93]AJCarlton,etc:Automation of the LTV Steel Hennepin tandem cold mill.Iron and Steel Engineer,June 1992
[94]Yoshiro Washikita,etc:Renewal of Automatic Gage Control System for a Cold Tandem Mill with Electic Screwdowns.ISIJ International,38,1998
[95]曹建国.宽带钢热连轧机板形板厚解耦控制研究,北京科技大学博士学位论文,1999
[96]奚志敏.宽带钢热连轧机凸度自动控制系统数学模型的研究与应用,北京科技大学硕士学位论文,2004
[97]孙克文.宽带钢热连轧平坦度闭环控制系统研究,北京科技大学硕士学位论文,2005
[98]罗永军.宽带钢热连轧机板形与板厚解耦控制仿真研究,北京科技大学博士学位论文,2004
[99]张清东.宽带钢冷轧机板形自动控制系统的研究.[博士学位论文].北京:北京科技大学,1994
[100]中国金属协会热轧板带学术委员会编著.中国热轧宽带钢轧机及生产技术.北京:冶金工业出版社,2002
[101]忻为民等.提高热带轧机精轧AGC控制精度初探.轧钢,1998,3:17-19
[102]曹建国等.热轧带钢板形板厚综合控制系统的耦合关系.北京科技大学学报,2000,22(6):551-553
[103]曹建国等.宽带钢热连轧机板形设定的解耦与应用.钢铁,2001,36(4):42-46
[104]曹建国等.热轧带钢板形板厚耦合特性变化机理与参数求解.北京科技大学学报,2001,23(5):452-455
[105]丁修堃.轧制过程自动化.北京:冶金工业出版社,1986
[106]杨固川.国产热带钢连轧机主要设备技术分析.冶金设备,2003,8(4):26-31
[107]武其俭.热轧板带生产设备的发展.钢铁,2000,35(8):67-70
[108]张树堂,周积智等.热轧超薄带钢生产的新发展.北京:中国金属学会论文集,2004
[109]Gunter Kneppe,Dieter Rosenthal.Hot strip rolling technology:Tasks for the new century.MPT International,1998,22(3):56-68
[110]Goldberg,D.E Messy Genetic Algorrithms:Motivation,Analysis and First Results.Complex System.1989,3;493-530
[111]Schaffer,J.D.A Study of Gentic Parameters Affecting Online Performance of Genetic Algorithms for Function Optimization Process.3rd conf Genetic Algorithms 1989,51-60
[112]Grefenstette,J.J Optimization of Control Parameters for Genetic Algorithms IEEE Trans on Systems Man and Cybernetics 1986,SNC 16(1)122-128
[113]Davis,L.Adapting Operater Probabilities in Genetic Algorithms Proc.3~(rd) Genetic Algorithms,1989 61-69
[114]Fogarty,t.c.Varying the probability of mutation in Genetic Algorithms.Proc.3~(rd)Conf Genetic Algorithm,1989 104-109
[115]Whitley,D.Gentor:A distributed Genetic Algorithms.J.Expt.Ther Intell.1990,2,189-214
[116]何星等.一类基于适时启发式搜索的优化控制算法.中国控制与决策学术年会论文集,1995
[117]Goldberg,D.E.E,Segrest,P.Finite Markov Chain analysis of Genetic Algorithm.Proc of the second Int Conf.on Genetic Algorithms 1987
[118]Rudolph,G..Convergence properties of canonical Genetic Algorithms IEEE Trans.On Neural Networks 1994,5(1)
[119]Qi.X.Palmeri,F..Theoretical Analysis of Evolutionary algorithms with an infinite population size in continuous space part Ⅰ:Base properties of selection and mutation,IEEE Trans on Neural Network 1994
[120]蒋宗礼.人工神经网络导论.高等教育出版社,2001.8
[121]梁建辉.基于遗传算法的神经网络预测控制及应用,西北工业大学硕士学位论文,44-52
[122]李国勇.智能控制及其MATLAB实现.北京:电子工业出版社,2005.
[123]Eiben,A.E,Aarts,E.H,etc.Glbal Convergence of Genetic Algorithm:An Infinite Markov Chain Analysis.Parallel Problem Solving frome Nature Schwefel,H.P,and Marmer,R.Eds.Heidelberg Berlin:Springer-verlag.
[124]Kohonen T.Self-Organized Formation of Topologically Correct Feature Maps,Biio,Cybern.,1982,43,56-69
[125]Hopfield JJ.Neural Networks and physical Systems with Emergent Collective Computational Abilities,Proc.Natl.A-cad.Sci.,USA,1982,(79):2254-2258
[126]Hinton GE,Sejuowski TJ,AckleyDH.Boltzmann Machines:Cotraint Satisfaction Networks that Learn,Carnegie-Mellon University,Tech,Report CMU-CS-84-119,1984
[127]Hinton GE,Sejuowski TJ,Learning and Relearning in Boltzmann Machines,In Parallel Distributed Processing:Explorations in the Microstructure of Cognition,MIT Press,MA,1986,1:282-317
[128]Werbos P.Backpropagation:Past and future,the proceeding of the IEEE Interenational Conferenceon Nature Networkes,1988,343-353
[129]Parker D.Learning Logic Invention Report S81-64,Filel,Office of Technology Licensing,Stanford Univer,1982
[130]廖晓昕.细胞神经网络的数学理论(Ⅰ)(Ⅱ).中国科学(A辑),1994,24(9):902-910:24(10):1037-1046
[131]史忠植.神经计算.北京:电子工业出版社,1993
[132]靳蕃.神经计算智能基础——原理、方法.成都:西南交大出版社,2000
[133]刘金琨.智能控制.北京:电子工业出版社,2005.5
[134]王小平 曹立明.遗传算法——理论、应用于软件实现.西安:西安交通大学出版社,2002.1
[135]李敏强 寇纪淞 林丹 李书全.遗传算法的基本理论与应用.北京:科学出版社,2002.3
[136]王焱.智能化热连轧模型优化及参数自学习方法研究.北京科技大学博士论文,2002
[137]孙增圻,邓志东.智能控制理论与技术.北京:清华大学出版社,1997
[138]刘国平,符强,张华.BP神经网络在带钢宽展预测控制中的应用.南昌大学学报,2003.9,25(3)
[139]符强,张进之.基于人工神经网络的热连轧参数预测模型.钢铁研究学报,2003,15(4)
[140]谢利群,王国栋等.基于BP神经网络的热连轧粗轧宽度预测模型.轧钢,2001.8,18(4)
[141]姚有领,费敏锐.神经元PID控制器的研究及应用.电网技术,第31卷,第20期,2007
[142]姚有领,费敏锐.基于神经网络的板形板厚解耦控制的研究与应用.《冶金设备》,特刊,2007
[3]孙一康 杨金标 马正午 热连轧厚度自动控制系统的仿真研究 1980年 第四期P86-101
[4]孙一康 带钢热连轧计算机控制系统的发展 北京科技大学学报 轧钢自动化专刊 vol.21 增刊P1-9
[5]刘价,孙一康 主编 带钢热连轧计算机控制 机械工业出版社 1996
[6]吕程,赵启林,刘立忠等.热轧精轧机组负荷分配的优化算法.钢铁研究学报,2001,13(1):26-29
[7]贾春玉.热带轧极高精度负荷预测模型的开发.钢铁研究,2000,(6):40-42
[8]白埃民等.综合等负荷汉书法栽种板生产中的应用.钢铁,1993,28(4):35-39
[9]余四清等.多种负荷均衡分配法.钢铁,1996,31(7):48-51
[10]刘靖等.多种负荷均衡分配法优化冷轧板带生产规程.北京科技大学学报,1993增刊92-95
[11]梁国平.关于轧机的最佳负荷分配问题.钢铁,1980,15(1):42-48
[12]张进之等.连轧优化规程计算机设定计算方法.钢铁研究学报,1987,7(3):99-104
[13]F.Wagner 热带钢轧机的轧制力前馈厚度控制 国外钢铁 1997年第6期
[14]祝东奎等.兼顾板形的带钢冷连轧机最优负荷分配.北京科技大学学报,2000,22(1):246--252
[15]#12
[16]赵红雁等.人工神经网络推理的模糊控制其应用于热轧带钢厚度控制.上海金属,2001,23(1):28-31
[17]张进之.压力AGC参数方程及变刚度轧机分析.冶金自动化,1984,8(1):24-31
[18]郝付国等.动态设定型AGC在中厚板轧机上的应用.钢铁,1995,30(7):32-36
[19]王立平等.本钢1700mm热连轧机变刚度分析与实现.冶金自动化.1995,10(6):14-16
[20]张进之.动态设定形变刚度厚控方法的效果分析.重型机械,1998,(1):30-34
[21]陈先霖,张杰等.宽带钢热连轧机板形控制系统的开发.钢铁,2000,35(7):28-32
[22]李虎兴等.1700mm冷连轧机板形的优化和控制.武汉钢铁学院学报,1990,13(3):246-252
[23]许良等.HC轧机板形优化模型的研究.钢铁,1997,32(6):33-36
[24]#12
[25]#12
[26]#12
[27]#12
[28]王立平等.热连轧机厚度设定与控制系统分析.控制与决策,1994,9(2):15-20
[29]华建新.宝钢2030冷连轧机的自学习.冶金自动化,1991,15(4):35-38
[30]D.A.Shaw,Control Strategies for High Production and Quality:U.S.Steel Gary 84-in.Hot Strip Mill,Iron and Steel Engineer,june.1998,31-39
[31]D.A.Shaw,Strip Profile Control Technology and Economic Impact of Target Profiles,Iron and Steel Engineer,March 1998,31-39
[32]V.B.Ginzburg,et al,Selection of Optimum Strip Profiles and Flatness Technology for Rolling Mills,Iron and Steel Engineer,July 1997.7,30-38
[33]张清洞等.CVC四辊冷轧机板形与设定研究.钢铁,1997.10,29-33
[34]刘玉礼等.400HC轧机板形设定控制数学模型.钢铁,1998.7,28-32
[35]Sean J.Egan,et al,Flatness modeling and control for a continuous tandem cold mill,Iron and Steel Engineer,1996.3,38-41
[36]C.Nnappez,et al,Control of Strip flatness in cold rolling,Iron and Steel Engineer,1997.4,42-45
[37]H.Wolters,Strips profile and flatness control in hot strip mills with particular reference to CVC technology,Proceedings of 4~(th) international Steel Rolling conference,A.20-A.20.7
[38]N.F.Portmann,et al,Application of neural networks in rolling mill automation,Iron and Steel Engineer,1995.2,33-36
[39]Y.Z.LU,Meeeting challenge of intelligent system technologies in the iron and steel industry,Iron and Steel Engineer,1996.9,139-149
[40]王国栋,刘相华.金属轧制过程人工智能优化.北京:冶金工业出版社,2000.3
[41]张大志等.基于遗传算法的冷连轧机组参数优化设定系统.上海金属,2000,22(6):25-30
[42]张大志等.基于遗传算法的冷连轧机辊形配置优化系统的开发及应用.冶金自动化,2001,(1):17-20
[43]#12
[44]#12
[45]#12
[46]Yasunori Katayama,Masaki NakajimaHiroshi Koyama.A neural fuzzy control system for rolling mills.Steel Technology International,1992,189-196
[47]#12
[48]#12
[49]小西正躬.塑性加工の知能化技术.塑性と加工,1993,34(387):337-344
[50]孙登月,杜凤山,朱泉封等.五机架冷连轧机轧制压力人工神经网络与报.钢铁,2002,37(2):28-30,34
[51]周旭东,李连诗.人工神经网络板形板厚综合控制.轧钢,1995,(4):16-19
[52]乔俊飞等.一种基于神经网络的内模控制方法及其应用.天津大学学报,2000,33(1):25-28
[53]贾春玉等.基于模糊神经网络进行冷轧板形智能控制的研究.重型机械,2000(5):11-14
[54 刘建昌.基于神经网络的自适应厚度控制.钢铁,1999,34(11):33-36
[55]刘晓星.冷连轧机轧制规程的多目标模糊优化设计.钢铁,2000,35(8):34-36
[56]马虹蔚.五机架轧制规范优化与自适应的研究.武钢技术,2000,38(5):36-38
[57]童朝南等.模糊控制器在热连轧微张力控制中的应用.钢铁,1998,33(5):36-38
[58]张宏伟.多变量自适应解耦控制理论在单机架轧机系统中的应用.北京科技大 学博士论文,1995
[59]喻宗权.模糊神经系统研究综述.自动化与仪表,1998,13(6):3-5
[60]闻新,周露等.MATLAB神经网络应用设计.北京:科学出版社,2000.9
[61]张良杰等.模糊神经网络技术的新近发展.信息与控制,1995,24(1):39-44
[62]高卫华,谢勇英.RBF神经网络与自适应模糊系统.电气自动化,2000(3):4-5
[63]申东日,冯少回等.BP网络改进方法概述.化工自动化及仪表,2000,27(1):28-30
[64]李少元,席裕庚.智能控制的新进展(Ⅱ).控制与决策,2000,15(2):136-140
[65]何述东等.多层前向神经网络结构的研究进展.控制理论与应用,1998,15(3):313-318
[66]戴连奎等.多层前向神经网络的随机学习新算法及其工业应用.自动化学报,1998,24(1):33-35
[67]费敏锐等.智能控制方法的交叉综合及其应用.《控制理论与应用》,第13卷,第3期,1996
[68]周旭东等 自适应神经网络板形板厚综合控制论 北京科技大学学报 No.41994
[69]石中锁 板形板厚神经网络预测控制与H_∞控制系统的研究 北京科技大学博士论文 1997
[70]戴晓龙 神经网络板形板厚综合控制系统的研究 北京科技大学博士论文1995
[71]Holland J.H.Adaptation in natural and Artificial System.The University of Michigan press,1975
[72]Kenneth D J.An Analysis of the Behavior of a Class of Genetic Adaptive System.Ann Arbor:University of Michigan Press,1975
[73]周明,孙树栋.遗传算法原理及应用.国防工业出版社,北京:1999,6然科学版),2000,No.1:33-38
[74]文绍纯,罗飞,付连续等.基于遗传算法的人工神经网络的应用综述.自动化与仪器仪表,2001,1(6)
[75]李智勇,童调生.基于多物种进化遗传算法的神经网络进化设计方法.系统仿真学报,2003,15(6)
[76]杨国君,崔平远,李琳琳.遗传算法在神经网络控制中的应用与实现.系统仿真学报,2001,13(5)
[77]薛福珍,唐琰.基于GA的模糊神经网络控制器的设计与仿真.系统仿真学 报,2001,13(5)
[78]王永初,解耦控制系统,四川科学技术出版社,1983
[79]R.J.Kavangh,Noninteracting Controls in Linear Multivariable Systems,AIEE.Trans.Appl.Ind.Vol.76.Pt Ⅱ.95-99.May.1957.
[80]Falb,P.L.and Wolovich,W.A,Decoupling in the Design and Synthesis of Multivariable Control Systems,IEEE Trans.on Automatic Control.Vol 12,651-659,1967
[81]F.G.Shinskey,Process Control Systems,McGraw-Hill Book Company,Second Edition,1979
[82]P.E.McDermott and D.A.Mellichamp,A decoupling pole-placement self-tuning controller for a class of multivariable process,Optimal Control Applications and Methods,Vol 7,862-867,1985
[83]Lang S.J,Gu X,Y and Chai T.Y.,A Multivariablized self-tuning feedforward controller with decoupling design,IEEE Trans.AC,vol 5,474-477,1986
[84]Chai T.Y,Lang S.J and Gu X.Y,A Generalized self-tunning feedforward controller and multivariable application,Proceedings of the 24~(th) IEEE Conference on Decision and Control,862-867,1985
[85]B.Wittemmark,R.Middleton and G.Goodwin,Adaptive Decoupling of Multivariable Systems.Int.J.Control,Vol 46,1993-2009,1987
[86]白焰,神经解耦控制在钢球磨煤机中间仓储式制粉系统中的应用,东北大学博士论文,1998
[87]岳恒、柴天佑,一类多变量非线性系统的神经网络自适应解耦控制,信息与控制,Vol 28,607-612,1999
[88]吴黎明、柴天佑,一类非线性离散时间系统的神经网络解耦策略,自动化学报,Vol23,207-212,1997
[89]柴天佑、张振山等,棒材连轧机立式活套的多变量自适应解耦控制,自动化学报,Vol
[90]Wittenmark B,Middleton R H,Goodwin G C.Adaptive decoupling of multivariable systems,International Journal of Control,1987,46(6):1993-2009.
[91]Wahba A M,Sheirah M A.Adaptive decoupler for multivariable systems,International Journal of System Science,1993,24(1):97-109.
[92]T.Y.Chai.Direct adaptive decoupling control for general stochastic multivariable system.Int.J.Control,1990,51(4)
[93]AJCarlton,etc:Automation of the LTV Steel Hennepin tandem cold mill.Iron and Steel Engineer,June 1992
[94]Yoshiro Washikita,etc:Renewal of Automatic Gage Control System for a Cold Tandem Mill with Electic Screwdowns.ISIJ International,38,1998
[95]曹建国.宽带钢热连轧机板形板厚解耦控制研究,北京科技大学博士学位论文,1999
[96]奚志敏.宽带钢热连轧机凸度自动控制系统数学模型的研究与应用,北京科技大学硕士学位论文,2004
[97]孙克文.宽带钢热连轧平坦度闭环控制系统研究,北京科技大学硕士学位论文,2005
[98]罗永军.宽带钢热连轧机板形与板厚解耦控制仿真研究,北京科技大学博士学位论文,2004
[99]张清东.宽带钢冷轧机板形自动控制系统的研究.[博士学位论文].北京:北京科技大学,1994
[100]中国金属协会热轧板带学术委员会编著.中国热轧宽带钢轧机及生产技术.北京:冶金工业出版社,2002
[101]忻为民等.提高热带轧机精轧AGC控制精度初探.轧钢,1998,3:17-19
[102]曹建国等.热轧带钢板形板厚综合控制系统的耦合关系.北京科技大学学报,2000,22(6):551-553
[103]曹建国等.宽带钢热连轧机板形设定的解耦与应用.钢铁,2001,36(4):42-46
[104]曹建国等.热轧带钢板形板厚耦合特性变化机理与参数求解.北京科技大学学报,2001,23(5):452-455
[105]丁修堃.轧制过程自动化.北京:冶金工业出版社,1986
[106]杨固川.国产热带钢连轧机主要设备技术分析.冶金设备,2003,8(4):26-31
[107]武其俭.热轧板带生产设备的发展.钢铁,2000,35(8):67-70
[108]张树堂,周积智等.热轧超薄带钢生产的新发展.北京:中国金属学会论文集,2004
[109]Gunter Kneppe,Dieter Rosenthal.Hot strip rolling technology:Tasks for the new century.MPT International,1998,22(3):56-68
[110]Goldberg,D.E Messy Genetic Algorrithms:Motivation,Analysis and First Results.Complex System.1989,3;493-530
[111]Schaffer,J.D.A Study of Gentic Parameters Affecting Online Performance of Genetic Algorithms for Function Optimization Process.3rd conf Genetic Algorithms 1989,51-60
[112]Grefenstette,J.J Optimization of Control Parameters for Genetic Algorithms IEEE Trans on Systems Man and Cybernetics 1986,SNC 16(1)122-128
[113]Davis,L.Adapting Operater Probabilities in Genetic Algorithms Proc.3~(rd) Genetic Algorithms,1989 61-69
[114]Fogarty,t.c.Varying the probability of mutation in Genetic Algorithms.Proc.3~(rd)Conf Genetic Algorithm,1989 104-109
[115]Whitley,D.Gentor:A distributed Genetic Algorithms.J.Expt.Ther Intell.1990,2,189-214
[116]何星等.一类基于适时启发式搜索的优化控制算法.中国控制与决策学术年会论文集,1995
[117]Goldberg,D.E.E,Segrest,P.Finite Markov Chain analysis of Genetic Algorithm.Proc of the second Int Conf.on Genetic Algorithms 1987
[118]Rudolph,G..Convergence properties of canonical Genetic Algorithms IEEE Trans.On Neural Networks 1994,5(1)
[119]Qi.X.Palmeri,F..Theoretical Analysis of Evolutionary algorithms with an infinite population size in continuous space part Ⅰ:Base properties of selection and mutation,IEEE Trans on Neural Network 1994
[120]蒋宗礼.人工神经网络导论.高等教育出版社,2001.8
[121]梁建辉.基于遗传算法的神经网络预测控制及应用,西北工业大学硕士学位论文,44-52
[122]李国勇.智能控制及其MATLAB实现.北京:电子工业出版社,2005.
[123]Eiben,A.E,Aarts,E.H,etc.Glbal Convergence of Genetic Algorithm:An Infinite Markov Chain Analysis.Parallel Problem Solving frome Nature Schwefel,H.P,and Marmer,R.Eds.Heidelberg Berlin:Springer-verlag.
[124]Kohonen T.Self-Organized Formation of Topologically Correct Feature Maps,Biio,Cybern.,1982,43,56-69
[125]Hopfield JJ.Neural Networks and physical Systems with Emergent Collective Computational Abilities,Proc.Natl.A-cad.Sci.,USA,1982,(79):2254-2258
[126]Hinton GE,Sejuowski TJ,AckleyDH.Boltzmann Machines:Cotraint Satisfaction Networks that Learn,Carnegie-Mellon University,Tech,Report CMU-CS-84-119,1984
[127]Hinton GE,Sejuowski TJ,Learning and Relearning in Boltzmann Machines,In Parallel Distributed Processing:Explorations in the Microstructure of Cognition,MIT Press,MA,1986,1:282-317
[128]Werbos P.Backpropagation:Past and future,the proceeding of the IEEE Interenational Conferenceon Nature Networkes,1988,343-353
[129]Parker D.Learning Logic Invention Report S81-64,Filel,Office of Technology Licensing,Stanford Univer,1982
[130]廖晓昕.细胞神经网络的数学理论(Ⅰ)(Ⅱ).中国科学(A辑),1994,24(9):902-910:24(10):1037-1046
[131]史忠植.神经计算.北京:电子工业出版社,1993
[132]靳蕃.神经计算智能基础——原理、方法.成都:西南交大出版社,2000
[133]刘金琨.智能控制.北京:电子工业出版社,2005.5
[134]王小平 曹立明.遗传算法——理论、应用于软件实现.西安:西安交通大学出版社,2002.1
[135]李敏强 寇纪淞 林丹 李书全.遗传算法的基本理论与应用.北京:科学出版社,2002.3
[136]王焱.智能化热连轧模型优化及参数自学习方法研究.北京科技大学博士论文,2002
[137]孙增圻,邓志东.智能控制理论与技术.北京:清华大学出版社,1997
[138]刘国平,符强,张华.BP神经网络在带钢宽展预测控制中的应用.南昌大学学报,2003.9,25(3)
[139]符强,张进之.基于人工神经网络的热连轧参数预测模型.钢铁研究学报,2003,15(4)
[140]谢利群,王国栋等.基于BP神经网络的热连轧粗轧宽度预测模型.轧钢,2001.8,18(4)
[141]姚有领,费敏锐.神经元PID控制器的研究及应用.电网技术,第31卷,第20期,2007
[142]姚有领,费敏锐.基于神经网络的板形板厚解耦控制的研究与应用.《冶金设备》,特刊,2007