基于多核支持向量机的非线性模型预测控制

Multi-kernel-based support vector machine （SVM） model structure of nonlinear systems and its specific identification method is proposed, which is composed of a SVM with linear kernel function followed in series by a SVM with spline kernel function. With the help of this model, nonlinear model predictive control can be transformed to linear model predictive control, and consequently a unified analytical solution of optimal input of multi-step-ahead predictive control is possible to derive. This algorithm does not require online iterative optimization in order to be suitable for real-time control with less calculation. The simulation results of pH neutralization process and CSTR reactor show the effectiveness and advantages of the presented algorithm.     

PI型预测函数控制算法的研究及在重油焦化装置的应用

By extending the system＇s state variables, a novel predictive functional controller has been developed. The structure of this controller is similar to that of classical proportional integral （PI） optimal controller and includes a control block that can perform a feed-forward control of future P-step set points. It considers both the state variables and the output errors in its cost function, which results in enhanced control performance compared with traditional state space predictive functional control （TSSPFC） methods that consider only the predictive output errors. The predictive functional controller （PFC） has been compared with TSSPFC in terms of tracking ability, disturbance rejection, and also based on its application to heavy oil coking equipment. The results obtained show the effectiveness of the controller.     

混杂系统基于参数规划的状态反馈预测控制

In this article, state feedback predictive controller for hybrid system via parametric programming is proposed. First, mixed logic dynamic （MLD） modeling mechanism for hybrid system is analyzed, which has a distinguished advantage to deal with the logic rules and constraints of a plant. Model predictive control algorithm with moving horizon state estimator （MHE） is presented. The estimator is adopted to estimate the current state of the plant with process disturbance and measurement noise, and the state estimated are utilized in the predictive controller for both regulation and tracking problems of the hybrid system based on MLD model. Off-line parametric programming is adopted and then on-line mixed integer programming problem can be treated as the parameter programming with estimated state as the parameters. A three tank system is used for computer simulation, results show that the proposed MHE based predictive control via parametric programming is effective for hybrid system with model/olant mismatch, and has a potential for the engineering applications.     

基于改进DOB的矿物研磨过程最优运行先进反馈控制(英文)

Advanced feedback control for optimal operation of mineral grinding process is usually based on the model predictive control (MPC) dynamic optimization. Since the MPC does not handle disturbances directly by controller design, it cannot achieve satisfactory effects in controlling complex grinding processes in the presence of strong disturbances and large uncertainties. In this paper, an improved disturbance observer (DOB) based MPC advanced feedback control is proposed to control the multivariable grinding operation. The improved DOB is based on the optimal achievable H 2 performance and can deal with disturbance observation for the nonminimum-phase delay systems. In this DOB-MPC advanced feedback control, the higher-level optimizer computes the optimal operation points by maximize the profit function and passes them to the MPC level. The MPC acts as a presetting controller and is employed to generate proper pre-setpoint for the lower-level basic feedback control system. The DOB acts as a compensator and improves the operation performance by dynamically compensating the setpoints for the basic control system according to the observed various disturbances and plant uncertainties. Several simulations are performed to demonstrate the proposed control method for grinding process operation.     

Multivariable Nonlinear Proportional-Integral-Derivative Decoupling Control Based on Recurrent Neural Networks

A nonlinear proportional-integral-derivative (PID) controller is constructed based on recurrent neural networks. In the control process of nonlinear multivariable systems, several nonlinear PID controllers have been adopted in parallel. Under the decoupling cost function, a decoupling control strategy is proposed. Then the stability condition of the controller is presented based on the Lyapunov theory. Simulation examples are given to show effectiveness of the proposed decoupling control.     

基于递归神经网络的多变量非线性PID解耦控制

A nonlinear proportional-integral-derivative (PID) controller is constructed based on recurrent neural networks. In the control process of nonlinear multivariable systems, several nonlinear PID controllers have been adopted in parallel. Under the decoupling cost function, a decoupling control strategy is proposed. Then the stability condition of the controller is presented based on the Lyapunov theory. Simulation examples are given to show effectiveness of the proposed decoupling control.     

Nonlinear Model Algorithmic Control of a pH Neutralization Process

Control of pH neutralization processes is challenging in the chemical process industry because of their inherent strong nonlinearity. In this paper, the model algorithmic control （MAC） strategy is extended to nonlinear processes using Hammerstein model that consists of a static nonlinear polynomial function followed in series by a linear impulse response dynamic element. A new nonlinear Hammerstein MAC algorithm （named NLH-MAC） is presented in detail. The simulation control results of a pH neutralization process show that NLH-MAC gives better control performance than linear MAC and the commonly used industrial nonlinear propotional plus integral plus derivative （PID） controller. Further simulation experiment demonstrates that NLH-MAC not only gives good control response, but also possesses good stability and robustness even with large modeling errors.     

一种对预测控制系统经济性能评估的实用方法及其工业应用

In this article, an approach for economic performance assessment of model predictive control (MPC) system is presented. The method builds on steady-state economic optimization techniques and uses the linear quadratic Gaussian (LQG) benchmark other than conventional minimum variance control (MVC) to estimate the potential of reduction in variance. The LQG control is a more practical performance benchmark compared to MVC for performance assessment since it considers input variance and output variance, and it thus provides a desired basis for determining the theoretical maximum economic benefit potential arising from variability reduction. Combining the LQG benchmark directly with benefit potential of MPC control system, both the economic benefit and the op-timal operation condition can be obtained by solving the economic optimization problem. The proposed algorithm is illustrated by simulated example as well as application to economic performance assessment of an industrial model predictive control system.     

An integrated approach for machine-learning-based system identification of dynamical systems under control: application towards the model predictive control of a highly nonlinear reactor system

Advanced model-based control strategies,e.g.,model predictive control,can offer superior control of key process variables for multiple-input multiple-output systems.The quality of the system model is critical to controller performance and should adequately describe the process dynamics across its operating range while remaining amenable to fast optimization.This work articulates an integrated system identification procedure for deriving black-box nonlinear continuous-time multiple-input multiple-output system models for nonlinear model predictive control.To showcase this approach,five candidate models for polynomial and interaction features of both output and manipulated variables were trained on simulated data and integrated into a nonlinear model predictive controller for a highly nonlinear continuous stirred tank reactor system.This procedure successfully identified system models that enabled effective control in both servo and regulator problems across wider operating ranges.These controllers also had reasonable per-iteration times of ca.0.1 s.This demonstration of how such system models could be identified for nonlinear model predictive control without prior knowledge of system dynamics opens further possibilities for direct data-driven methodologies for model-based control which,in the face of process uncertainties or modelling limitations,allow rapid and stable control over wider operating ranges.     

改进的模糊预测控制算法及其在CSTR过程中的应用

A finite horizon predictive control algorithm,which applies a saturated feedback control law as its local control law,is presented for nonlinear systems with time-delay subject to input constraints.In the algorithm,N free control moves,a saturated local control law and the terminal weighting matrices are solved by a minimization problem based on linear matrix inequality(LMI) constraints online.Compared with the algorithm with a nonsaturated local law,the presented algorithm improves the performances of the closed-loop systems such as feasibility and optimality.This model predictive control(MPC) algorithm is applied to an industrial continuous stirred tank reactor(CSTR) with explicit input constraint.The simulation results demonstrate that the presented algorithm is effective.     

基于多项式核的稀疏核学习单步预测控制算法及其应用

提出一种基于稀疏核学习辨识模型的单步预测控制（sparse kernel learning one-step-ahead predictive control,SKL-OPC）框架,并推导了该框架下采用多项式核的一种控制算法。该算法在求取最优控制律时可将调节变量从目标函数分离出来,并最终转化为求解一奇数次代数方程根的问题。因此无需复杂的非线性优化技术,且克服了基于二次多项式核辨识模型不准确造成控制算法失效的缺点。在一非线性连续搅拌反应釜的控制研究表明了该方法的有效性和优越性。     

非线性Hammerstein模型预测控制策略及其在pH中和过程中的应用

所有实际工业过程都包含一定程度的非线性,如pH中和过程由于其本身的强非线性是工业过程控制中具有挑战性的难题,但至今为止仍缺乏有效的非线性控制方法。将基于差分方程模型的模型预测控制策略(model predictive control,MPC)推广到包含一个静态非线性多项式函数和一个线性差分方程动态环节的非线性Hammerstein系统,详细描述了基于静态非线性多项式函数的最优控制作用求解方法,提出了一套新的非线性Hammerstein MPC 控制策略(nonlinear Hammerstein predictive control,NLHPC)。pH中和过程控制仿真和控制实验表明,NLHPC的控制结果好于工业上常用的非线性 PID(nonlinear PID,NL-PID)控制器。     

An experimental study for property control in a continuous styrene polymerization reactor using a polynomial ARMA model

By using a multivariable nonlinear model predictive controller (NLMPC), the control experiments for the monomer conversion and the weight-average molecular weight are conducted in a continuous styrene polymerization reactor. Instead of a complex first-principles model, a polynomial auto-regressive moving average model (ARMA) is used to describe the nonlinear behavior of the polymerization reactor. The pseudorandom multilevel input signals mounted on the jacket inlet temperature and the feed flow rate are applied to the polymerization reaction system to identify a polynomial ARMA model. In the experiments of identification and control, the monomer conversion and the weight-average molecular weight are measured by on-line densitometer and viscometer with appropriate correlations. The on-line measurements are found to be in good agreement with the off-line analysis by the gravimetry and the gel permeation chromatography. Since a polynomial ARMA model is expected to give a higher order objective function of input variables, we employ the extended Kalman filter based NLMPC scheme to reduce the computational requirement in the control experiments. The NLMPC based on the polynomial ARMA model is found to perform satisfactorily for the control of the polymer properties during a grade-transition period as well as under the steady-state operation.     

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.     

基于T-S模糊模型与粒子群优化的非线性预测控制

引言模型预测控制属于一种基于模型的多变量的控制算法,发展至今已在化工过程控制方面得到了广泛的应用[1-5]。状态反馈预测控制[6-8]是模型预测控制技术的一种,基于状态空间模型,采用实测状态     

Economic model predictive control of stochastic nonlinear systems

This work focuses on the design of stochastic Lyapunov‐based economic model predictive control (SLEMPC) systems for a broad class of stochastic nonlinear systems with input constraints. Under the assumption of stabilizability of the origin of the stochastic nonlinear system via a stochastic Lyapunov‐based control law, an economic model predictive controller is proposed that utilizes suitable constraints based on the stochastic Lyapunov‐based controller to ensure economic optimality, feasibility and stability in probability in a well‐characterized region of the state‐space surrounding the origin. A chemical process example is used to illustrate the application of the approach and demonstrate its economic benefits with respect to an EMPC scheme that treats the disturbances in a deterministic, bounded manner. © 2018 American Institute of Chemical Engineers AIChE J, 64: 3312–3322, 2018     

NEURAL NETWORK-BASED PREDICTIVE CONTROL FOR MULTIVARIABLE PROCESSES

In this paper, the systematic derivations of setting up a nonlinear model predictive control based on the neural network are presented. This extends our previous work (Chen, 1998) into a multivariable system to explore the characteristics of the design. There are two stages for the development of nonlinear neural network predictive control: a neural network model and a control design. In the neural network model design, a parallel multiple-input, single-output neural network autoregressive with a model of exogenous inputs (NNARX) is proposed for multistep ahead predictions. In control design, the controller with extended control horizon is developed. The Levenberg-Marquardt algorithm is applied to training the NNARX model. Also, the sequential quadratic programming is used to search for the optimal manipulated inputs. The gradient of the objective function and constraints that require computation of Jacobian matrices are completely derived for optimization calculation. To demonstrate the control ability of MIMO cases, the proposed method is applied through two nonlinear simulation problems.     

Neural network-based predictive control for multivariable processes

In this paper, the systematic derivations of setting up a nonlinear model predictive control based on the neural network are presented. This extends our previous work (Chen, 1998) into a multivariable system to explore the characteristics of the design. There are two stages for the development of nonlinear neural network predictive control: a neural network model and a control design. In the neural network model design, a parallel multiple-input, single-output neural network autoregressive with a model of exogenous inputs (NNARX) is proposed for multistep ahead predictions. In control design, the controller with extended control horizon is developed. The Levenberg-Marquardt algorithm is applied to training the NNARX model. Also, the sequential quadratic programming is used to search for the optimal manipulated inputs. The gradient of the objective function and constraints that require computation of Jacobian matrices are completely derived for optimization calculation. To demonstrate the control ability of MIMO cases, the proposed method is applied through two nonlinear simulation problems.