基于二次逼近神经网络的反应釜预测控制
|
摘要
针对在化工生产过程中使用连续搅拌反应釜(Continuous Stirred Tank Reactor,CSTR)时存在的控制方式不便,调节的精确度不高等问题;在对实际问题进行分析建模的基础上,提出了一种基于二次逼近神经网络模型的预测控制方法;该方法首先利用多层前馈神经网络模型去逼近连续搅拌反应釜系统的多步预测值,其次在已创建的预测模型的基础上优化并求解预测控制的二次目标函数,以得到最优的控制参数,最后由通过泰勒展开式的二次逼近得到非线性预测控制器的最优解;通过对控制模型的模拟以及带入相关参数进行仿真实验,对连续搅拌反应釜控制系统的仿真结果进行分析表明:该方法控制精确度较高,并且是可行有效的,能够使生产效率得到显著提高且保证了产品的质量,具有较高的实用价值。
A predictive control method based on neural network is presented for the problem of production inconvenience and low precision in a continuous stirred tank reactor(CSTR)which is widely used in chemical process.Firstly,using a multi-layer feed forward neural network to approximate the CSTR system's multi-step predictive value,secondly based on the forecast model for solving quadratic objective function optimization predictive control by the Taylor expansion approximation quadratic nonlinear predictive control law controller.The simulation results of CSTR show that:that essay's method has high accuracy and that method is feasible and effective.The utility model has the advantages of high production efficiency,high product quality and high practical value.
A predictive control method based on neural network is presented for the problem of production inconvenience and low precision in a continuous stirred tank reactor(CSTR)which is widely used in chemical process.Firstly,using a multi-layer feed forward neural network to approximate the CSTR system's multi-step predictive value,secondly based on the forecast model for solving quadratic objective function optimization predictive control by the Taylor expansion approximation quadratic nonlinear predictive control law controller.The simulation results of CSTR show that:that essay's method has high accuracy and that method is feasible and effective.The utility model has the advantages of high production efficiency,high product quality and high practical value.
引文
[1]杨军民.反应釜温度控制的研究现状及化工自动化发展现状[J].广东化工,2010,37(5):288-290.
[2]于海英.化学反应釜温度模糊控制器[D].阜新:辽宁工程技术大学,2002.
[3]马海军,王文中,翟素兰,等.基于卷积神经网络的监控视频人,数统计算法[J].安徽大学学报(自然科学版)2016,40(3)22-28.
[4]王华强,石亚娟,王健波.神经网络模糊PID在水轮机调速中的应用[J].合肥工业大学学报(自然科学版),2012,35(9):1187-1191.
[5]谭元飞.基于神经网络预测控制的锅炉过热汽温控制研究[D].西安:西安科技大学,2012.
[6]张兴,戴莹,李争.一种时变非线性对象神经网络PID控制的仿真[J].合肥工业大学学报(自然科学版),2006,29(11):1375-1379.
[7]Neshasteriz A R,Khaki S A,Sadjadian H.Generalized predictive control and tuning of industrial processes with second order plus dead time models[J].Journal of Process Control,2010(20).
[8]程辉,秦廷,陈宗海.液位对象的一种非线性广义预测控制策略研究[J].计算机仿真,2006,23(9):333-335.
[9]满红,邵诚.基于Hammerstein-Wiener模型的连续搅拌反应釜神经网络预测控制[J].化工学报,2011,62(8):2275-2276.
[10]曾谊晖,龚金科,李金梅,杨贤平.数控切削加工表面粗糙度RBF神经网络预测模型[J].煤矿机械,2011,32(3):117-119.
[11]李奇安,褚健.对角CARIMA模型多变量广义预测控制改进算法[J].控制理论与运用,2007,24(3):423-427
[12]陈薇.非线性预测控制算法的研究与应用[D].合肥:中国科学技术大学,2007.
[2]于海英.化学反应釜温度模糊控制器[D].阜新:辽宁工程技术大学,2002.
[3]马海军,王文中,翟素兰,等.基于卷积神经网络的监控视频人,数统计算法[J].安徽大学学报(自然科学版)2016,40(3)22-28.
[4]王华强,石亚娟,王健波.神经网络模糊PID在水轮机调速中的应用[J].合肥工业大学学报(自然科学版),2012,35(9):1187-1191.
[5]谭元飞.基于神经网络预测控制的锅炉过热汽温控制研究[D].西安:西安科技大学,2012.
[6]张兴,戴莹,李争.一种时变非线性对象神经网络PID控制的仿真[J].合肥工业大学学报(自然科学版),2006,29(11):1375-1379.
[7]Neshasteriz A R,Khaki S A,Sadjadian H.Generalized predictive control and tuning of industrial processes with second order plus dead time models[J].Journal of Process Control,2010(20).
[8]程辉,秦廷,陈宗海.液位对象的一种非线性广义预测控制策略研究[J].计算机仿真,2006,23(9):333-335.
[9]满红,邵诚.基于Hammerstein-Wiener模型的连续搅拌反应釜神经网络预测控制[J].化工学报,2011,62(8):2275-2276.
[10]曾谊晖,龚金科,李金梅,杨贤平.数控切削加工表面粗糙度RBF神经网络预测模型[J].煤矿机械,2011,32(3):117-119.
[11]李奇安,褚健.对角CARIMA模型多变量广义预测控制改进算法[J].控制理论与运用,2007,24(3):423-427
[12]陈薇.非线性预测控制算法的研究与应用[D].合肥:中国科学技术大学,2007.