基于递归模糊神经网络的污水处理控制方法

针对污水处理过程具有非线性、大时变等问题,提出了一种基于递归模糊神经网络的多变量控制方法。该方法通过递归模糊神经网络控制器自适应地获得对操作变量的控制精度,控制器在常规BP学习算法的基础上采用学习率自适应学习算法且引入了动量项来训练网络参数,避免网络陷入局部最优,提高了网络对系统的控制精度。最后,基于仿真基准模型(BSM1)平台对第五分区中的溶解氧和第二分区中的硝态氮控制进行动态仿真实验,结果表明,与PID、前馈神经网络和常规递归神经网络相比,该方法能有效提高系统的自适应控制精度。     

基于自适应粒子群优化算法的预测控制算法及其在加热炉支管平衡中的应用

多变量和输出受限系统的预测控制问题一般表现为一个不易直接求解的多变量且多约束的非线性动态规划问题.传统优化方法在解决此优化问题时,存在易收敛到非法解或局部极小、计算时间长以及对模型参数与初值依赖性强的缺点.提出了一种基于自适应粒子群优化的预测控制算法(APSO-DMC),采用自适应粒子群优化算法(APSO)作为模型预测控制的优化方法,在线实时求解最优控制律,从而有效地克服了传统优化方法的不足.将此算法应用于常减压装置加热炉支管温度平衡控制中,仿真试验结果显示了该方法的有效性.     

基于智能融合策略的冰铜品位预测模型

针对铜闪速熔炼过程中冰铜品位检测的重要性,根据多相多组分数学模型建立冰铜品位的机理模型;同时该过程具有大滞后、非线性等复杂特性,利用现场的大量生产数据建立模糊神经网络模型,并提出一种新的网络参数学习的受约束梯度下降算法,提高其参数学习效率.基于模糊逻辑的智能协调器根据实际生产条件融合两种模型的输出作为预测结果.工业数据验证表明,智能融合模型比单一模型更能有效地实现冰铜品位的准确预测,为铜闪速熔炼过程的优化控制提供有力的指导.     

基于多目标的模糊神经网络及在pH控制过程中的应用

设计了一种基于多目标的动态模糊递归神经网络（FRNN）建模方法,用于pH中和过程的广义预测控制。所设计的多目标优化算法以提高拟合精度和简化网络结构为原则,同时优化模糊神经网络中的模糊规则数、隶属度函数中心点及其宽度,由此得到的FRNN模型可以高精度拟合pH中和过程。依据该动态模型,在控制过程的每一个控制周期得到其局部线性模型,将广义预测控制中复杂的非线性优化问题转化为简单的二次线性规划问题。仿真对比结果验证了所提方法的有效性。     

基于自适应模糊推理的非线性系统辨识器设计

针对传统模糊建模方法中模型参数都是根据经验选取的局限性,提出一种类高斯隶属函数,推导了基于类高斯隶属函数的自适应模糊推理模型,利用Stone-Weierstrass定理证明了该模型能以任意精度逼近非线性系统.将自适应模糊推理模型应用于非线性动态系统辨识中,设计了非线性系统辨识器,采用梯度下降算法学习模型中参数,通过仿真得到了较好的辨识效果.     

基于混合评价指标的自组织模糊神经网络设计研究

针对在无增长和修剪阈值时模糊神经网络结构难以自适应问题,提出一种基于混合评价指标(hybrid evaluation index, HEI)的结构设计方法。首先,通过模糊C均值聚类算法(fuzzy C-means clustering, FCM)确定初始规则层神经元数目及其中心与宽度。其次,基于戴维森堡丁指数(Davies bouldin index, DBI)和邓恩指数(Dunn index, DI)提出一种新的相关性评价指标(relevance evaluation index, REI)来计算规则层各神经元输出之间的相关性,同时根据训练过程中网络输出均方根误差(root mean square error, RMSE)的变化情况来确定网络的学习能力,然后基于REI和RMSE提出了HEI。通过HEI来调整模糊神经网络的拓扑结构,有效解决了在无增长和修剪阈值时网络结构难以动态自调整的问题且避免了网络结构冗余。最后,通过对Mackey-Glass时间序列预测、非线性系统辨识和大气中PM_2.5浓度预测,证明了该结构设计方法的可行性和有效性。     

自适应模糊滑模控制在化工过程中的应用

为有效处理多变量、非线性及非最小相位系统的复杂化工过程,提出了一种新型的自适应模糊滑模控制,该方法针对滑模控制鲁棒性好但存在抖振的问题,采用模糊控制柔化控制信号,而与滑模控制的结合可以充分利用系统信息,简化模糊控制;在此基础上提出一种新的自适应调整比例因子来进行模糊变论域,柔化了控制信号并减小了滑模控制器输出的抖振。并给出模糊滑模控制的算法和稳定性分析,得到简化后的通用模糊规则库,可通过比例因子在线调节输入量的论域,使构成的控制系统具有很强的鲁棒性、较好的自适应能力和较高的控制精度。最后对于非线性单输入单输出(SISO)和多输入多输出(MIMO)化工模型进行仿真研究,结果表明即使工况点发生大的变化或受到较大干扰时,仍具有良好的抗扰动能力和很强的鲁棒性。     

基于混合评价指标的自组织模糊神经网络设计研究

针对在无增长和修剪阈值时模糊神经网络结构难以自适应问题,提出一种基于混合评价指标(hybrid evaluation index, HEI)的结构设计方法。首先,通过模糊C均值聚类算法(fuzzy C-means clustering, FCM)确定初始规则层神经元数目及其中心与宽度。其次,基于戴维森堡丁指数(Davies bouldin index, DBI)和邓恩指数(Dunn index, DI)提出一种新的相关性评价指标(relevance evaluation index, REI)来计算规则层各神经元输出之间的相关性,同时根据训练过程中网络输出均方根误差(root mean square error, RMSE)的变化情况来确定网络的学习能力,然后基于REI和RMSE提出了HEI。通过HEI来调整模糊神经网络的拓扑结构,有效解决了在无增长和修剪阈值时网络结构难以动态自调整的问题且避免了网络结构冗余。最后,通过对Mackey-Glass时间序列预测、非线性系统辨识和大气中PM_(2.5)浓度预测,证明了该结构设计方法的可行性和有效性。     

一种多参数模糊神经网络控制系统调度算法

针对多回路网络控制系统的数据传输问题,提出了一种多参数模糊神经网络调度算法。首先,运用模糊神经网络的自学习能力对回路误差及误差变化率参数进行训练,并记忆模糊控制规则,确定各控制回路的网络需求度。其次,结合网络需求度参数和网络紧急度参数,采用动态权重算法确定各回路优先级,实现各回路优先级的在线调整。最后,建立了模糊神经网络调度优先级动态权重可调的多回路控制系统的仿真模型。仿真结果表明:在相同的网络带宽占用率下,该调度算法具有良好的动态控制性能,并保证了系统的稳定性。     

基于自组织模糊神经网络的污水处理过程溶解氧控制

针对活性污泥污水处理过程溶解氧浓度控制问题，提出一种基于自组织模糊神经网络（SOFNN）的控制方法。该神经网络控制器依据激活强度和互信息理论在线动态增长和修剪规则层神经元，以满足实际工况的动态变化。同时，采用梯度下降算法在线优化隶属函数层中心、宽度和输出权值，以保证SOFNN的收敛性。进一步通过Lyapunov稳定性理论对SOFNN学习率进行分析，给出控制系统稳定性证明。最后在国际基准仿真平台BSM1上进行实验验证。实验结果显示，与PID、模糊逻辑控制（FLC）和固定结构FNN等控制策略相比，SOFNN在跟踪精度、控制平稳性和自适应能力上更具有优势。     

Controlling of Proton Exchange Membrane Fuel Cell by Model Predictive Controller Based on ANFIS Model

Proton exchange fuel cell is one of the most promising new technologies in electrical energy production. Due to slow dynamic, nonlinearity and dependency of time changing variables of proton exchange membrane fuel cell (PEMFC), its control issue is a challenging problem. In this paper, model predictive controller (MPC) based on the adaptive neuro‐fuzzy interface model of the PEMFC is proposed to control the output voltage. First the adaptive neuro‐fuzzy interference system (ANFIS) model is identified to approximate the dynamic behavior of the PEMFC system with a set of data which are taken from a physical model of a 5 kW PEMFC setup plant. Then the branch‐and‐bound method and the greedy algorithm are used to solve the constrained optimization function of the predictive control problem. The results reveal that the ANFIS model can effectively approximate the dynamic behavior of the PEMFC and the predictive controller based on this model can successfully control the output and satisfy the constraints.     

基于D-FNN的聚合过程转化速率软测量建模及重构

引言以氯乙烯单体(VCM)为原料,采用悬浮法聚合工艺生产聚氯乙烯(PVC)树脂是一种典型的间歇式化工生产过程。VCM的转化率对PVC树脂产品质量有很大影响,不同转化率时对PVC     

Some manifold learning considerations toward explicit model predictive control

Model predictive control (MPC) is a de facto standard control algorithm across the process industries. There remain, however, applications where MPC is impractical because an optimization problem is solved at each time step. We present a link between explicit MPC formulations and manifold learning to enable facilitated prediction of the MPC policy. Our method uses a similarity measure informed by control policies and system state variables, to “learn” an intrinsic parametrization of the MPC controller using a diffusion maps algorithm, which will also discover a low-dimensional control law when it exists as a smooth, nonlinear combination of the state variables. We use function approximation algorithms to project points from state space to the intrinsic space, and from the intrinsic space to policy space. The approach is illustrated first by “learning” the intrinsic variables for MPC control of constrained linear systems, and then by designing controllers for an unstable nonlinear reactor.     

模糊非线性内模控制算法及其在pH值控制中的应用

pH值控制过程具有较强的非线性,历来是过程控制研究的一大热点,本文针对pH值控制系统提出了一种基于模糊推理网的非线性内模控制算法（FNIMC）。模糊推理网用于辨识对象的模糊模型;FNIMC由一个逆模控制器和具有一个可调参数的鲁棒滤波器组成。仿真结果表明该算法优于非线性PID调节器,且计算效率高。     

Dynamic recurrent radial basis function network model predictive control of unstable nonlinear processes

A multistep model predictive control (MPC) strategy based on dynamically recurrent radial basis function networks (RBFNs) is proposed for single-input single-output (SISO) control of uncertain nonlinear processes. The control system consists of two automatically configured RBFNs, a trained network representing the plant model and a network with on-line learning to function as controller. The automatic configuration and learning of the networks is carried out by using a hierarchically self-organizing learning algorithm. This control strategy is structurally simple and computationally efficient since a single output node of each RBFN is configured to provide multistep predictions for plant output and controller. The performance of the proposed RBFNMPC strategy is evaluated by applying to two unstable nonlinear chemical processes, a chemical reactor and a biochemical reactor, and also a stable polymerization reactor. Further, the results of the RBFNMPC is compared with similar RBFN model based control strategies and also with well tuned PID/PI controller. The results show the better performance of the proposed RBFNMPC for the control of open-loop unstable nonlinear processes that exhibit multiple steady-state behavior.     

MODEL PREDICTIVE CONTROL (MPC) AND ITS CURRENT ISSUES IN CHEMICAL ENGINEERING

Model predictive control (MPC) is one of the main process control techniques explored in the recent past; it is the amalgamation of different technologies used to predict future control action and future control trajectories knowing the current input and output variables and the future control signals. It can be said that the MPC scheme is based on the explicit use of a process model and process measurements to generate values for process input as a solution of an on-line (real-time) optimization problem to predict future process behavior. There have been a number of contributions in the field of nonlinear model–based predictive control dealing with issues like stability, efficient computation, optimization, constraints, and others. New developments in nonlinear MPC (NMPC) approaches come from resolving various issues, from faster optimization methods to different process models. This article specifically deals with chemical engineering systems ranging from reactors to distillation columns where MPC plays a role in the enhancement of the systems’ performance.     

稳态目标优化的稳定MIMO约束预测控制

A two-stage multi-objective optimization model-predictive control algorithms(MPC) strategy is presented. A domain MPC controller with input constraints is used to increase freedom for steady-state objective and enhance stabilization of the controller. A steady-state objective optimization algorithm oriented to transient process is adopted to realize optimization of objectives else than dynamic control. It is proved that .the stabilization for both dynamic control and steady-state objective optimization can be guaranteed. The theoretical results are demonstrated and discussed using a distillation tower as the model. Theoretical analysis and simulation results show that this control stratek--v is efl$cient and provides a good strategic solution to uractical urocess control.