Machine learning-based predictive control of nonlinear processes. Part I: Theory

This article focuses on the design of model predictive control (MPC) systems for nonlinear processes that utilize an ensemble of recurrent neural network (RNN) models to predict nonlinear dynamics. Specifically, RNN models are initially developed based on a data set generated from extensive open-loop simulations within a desired process operation region to capture process dynamics with a sufficiently small modeling error between the RNN model and the actual nonlinear process model. Subsequently, Lyapunov-based MPC (LMPC) that utilizes RNN models as the prediction model is developed to achieve closed-loop state boundedness and convergence to the origin. Additionally, machine learning ensemble regression modeling tools are employed in the formulation of LMPC to improve prediction accuracy of RNN models and overall closed-loop performance while parallel computing is utilized to reduce computation time. Computational implementation of the method and application to a chemical reactor example is discussed in the second article of this series.     

Distributed model predictive control of switched nonlinear systems with scheduled mode transitions

A method for the design of distributed model predictive control (DMPC) systems for a class of switched nonlinear systems for which the mode transitions take place according to a prescribed switching schedule is presented. Under appropriate stabilizability assumptions on the existence of a set of feedback controllers that can stabilize the closed‐loop switched, nonlinear system, a cooperative DMPC architecture using Lyapunov‐based model predictive control (MPC) in which the distributed controllers carry out their calculations in parallel and communicate in an iterative fashion to compute their control actions is designed. The proposed DMPC design is applied to a nonlinear chemical process network with scheduled mode transitions and its performance and computational efficiency properties in comparison to a centralized MPC architecture are evaluated through simulations. © 2013 American Institute of Chemical Engineers AIChE J, 59:860‐871, 2013     

Machine-learning-based construction of barrier functions and models for safe model predictive control

In this paper, we propose a control Lyapunov-barrier function-based model predictive control method utilizing a feed-forward neural network specified control barrier function (CBF) and a recurrent neural network (RNN) predictive model to stabilize nonlinear processes with input constraints, and to guarantee that safety requirements are met for all times. The nonlinear system is first modeled using RNN techniques, and a CBF is characterized by constructing a feed-forward neural network (FNN) model with unique structures and properties. The FNN model for the CBF is trained based on data samples collected from safe and unsafe operating regions, and the resulting FNN model is verified to demonstrate that the safety properties of the CBF are satisfied. Given sufficiently small bounded modeling errors for both the FNN and the RNN models, the proposed control system is able to guarantee closed-loop stability while preventing the closed-loop states from entering unsafe regions in state-space under sample-and-hold control action implementation. We provide the theoretical analysis for bounded unsafe sets in state-space, and demonstrate the effectiveness of the proposed control strategy using a nonlinear chemical process example with a bounded unsafe region.     

Machine learning-based model predictive control of hybrid dynamical systems

This article presents a machine learning-based model predictive control (MPC) scheme for stabilization of hybrid dynamical systems, for which the evolution of states exhibits both continuous and discrete dynamics described by differential and difference equations, respectively. We first present the development of two recurrent neural networks (RNNs) for approximating continuous- and discrete-time dynamics of hybrid dynamical systems, respectively, and then construct a unified hybrid RNN by integrating the two RNN models to capture both continuous and discrete dynamics. The hybrid RNN is used as the prediction model in Lyapunov-based MPC (RNN-LMPC), under which closed-loop stability of hybrid dynamical systems is established. Finally, two case studies including a bouncing ball example and a chemical process are utilized to illustrate the open- and closed-loop performance of the proposed RNN-LMPC scheme.     

Machine learning-based distributed model predictive control of nonlinear processes

This work explores the design of distributed model predictive control (DMPC) systems for nonlinear processes using machine learning models to predict nonlinear dynamic behavior. Specifically, sequential and iterative DMPC systems are designed and analyzed with respect to closed-loop stability and performance properties. Extensive open-loop data within a desired operating region are used to develop long short-term memory (LSTM) recurrent neural network models with a sufficiently small modeling error from the actual nonlinear process model. Subsequently, these LSTM models are utilized in Lyapunov-based DMPC to achieve efficient real-time computation time while ensuring closed-loop state boundedness and convergence to the origin. Using a nonlinear chemical process network example, the simulation results demonstrate the improved computational efficiency when the process is operated under sequential and iterative DMPCs while the closed-loop performance is very close to the one of a centralized MPC system.     

Statistical machine-learning–based predictive control of uncertain nonlinear processes

In this study, we present machine-learning–based predictive control schemes for nonlinear processes subject to disturbances, and establish closed-loop system stability properties using statistical machine learning theory. Specifically, we derive a generalization error bound via Rademacher complexity method for the recurrent neural networks (RNN) that are developed to capture the dynamics of the nominal system. Then, the RNN models are incorporated in Lyapunov-based model predictive controllers, under which we study closed-loop stability properties for the nonlinear systems subject to two types of disturbances: bounded disturbances and stochastic disturbances with unbounded variation. A chemical reactor example is used to demonstrate the implementation and evaluate the performance of the proposed approach.     

A nested online scheduling and nonlinear model predictive control framework for multi-product continuous systems

In the pursuit of integrated scheduling and control frameworks for chemical processes, it is important to develop accurate integrated models and computational strategies such that optimal decisions can be made in a dynamic environment. In this study, a recently developed switched system formulation that integrates scheduling and control decisions is extended to closed-loop operation embedded with nonlinear model predictive control (NMPC). The resulting framework is a nested online scheduling and control loop that allows to obtain fast and accurate solutions as no model reduction is needed and no integer variables are involved in the formulations. In the outer loop, the integrated model is solved to calculate an optimal product switching sequence such that the process economics is optimized, whereas in the inner loop, an NMPC implements the scheduling decisions. The proposed scheme was tested on two multi-product continuous systems. Unexpected large disturbances and rush orders were handled effectively.     

Multi-objective nonlinear model predictive control through switching cost functions and its applications to chemical processes

This paper proposes a switching multi-objective model predictive control (MOMPC) algorithm for constrained nonlinear continuous-time process systems. Different cost functions to be minimized inMPC are switched to satisfy different performance criteria imposed at different sampling times. In order to ensure recursive feasibility of the switching MOMPC and stability of the resulted closed-loop system, the dual-mode control method is used to design the switching MOMPC controller. In this method, a local control law with some free-parameters is constructed using the control Lyapunov function technique to enlarge the terminal state set of MOMPC. The correction termis computed if the states are out of the terminal set and the free-parameters of the local control laware computed if the states are in the terminal set. The recursive feasibility of the MOMPC and stability of the resulted closed-loop system are established in the presence of constraints and arbitrary switches between cost functions. Finally, implementation of the switching MOMPC controller is demonstrated with a chemical process example for the continuous stirred tank reactor.     

Bounded robust control of constrained multivariable nonlinear processes

This work focuses on control of multi-input multi-output (MIMO) nonlinear processes with uncertain dynamics and actuator constraints. A Lyapunov-based nonlinear controller design approach that accounts explicitly and simultaneously for process nonlinearities, plant-model mismatch, and input constraints, is proposed. Under the assumption that all process states are accessible for measurement, the approach leads to the explicit synthesis of bounded robust multivariable nonlinear state feedback controllers with well-characterized stability and performance properties. The controllers enforce stability and robust asymptotic reference-input tracking in the constrained uncertain closed-loop system and provide, at the same time, an explicit characterization of the region of guaranteed closed-loop stability. When full state measurements are not available, a combination of the state feedback controllers with high-gain state observes and appropriate saturation filters, is employed to synthesize bounded robust multivariable output feedback controllers that require only measurements of the outputs for practical implementation. The resulting output feedback design is shown to inherit the same closed-loop stability and performance properties of the state feedback controllers and, in addition, recover the closed-loop stability region obtained under state feedback, provided that the observer gain is sufficiently large. The developed state and output feedback controllers are applied successfully to non-isothermal chemical reactor examples with uncertainty, input constraints, and incomplete state measurements. Finally, we conclude the paper with a discussion that attempts to put in perspective the proposed Lyapunov-based control approach with respect to the nonlinear model predictive control (MPC) approach and discuss the implications of our results for the practical implementation of MPC, in control of uncertain nonlinear processes with input constraints.     

Extended moving horizon estimation for chemical processes under non-Gaussian noises

Studies on moving horizon estimation (MHE) for applications featuring process uncertainties and measurement noises that follow time-dependent non-Gaussian distributions are absent from the literature. An extended version of MHE (EMHE) is proposed here to improve the estimation for a general class of non-Gaussian process uncertainties and measurement noises at no significant additional computational costs. Gaussian mixture models are introduced to the proposed EMHE to approximate offline the non-Gaussian densities of these random variables. Moreover, the proposed EMHE-based estimation scheme can be updated online by re-approximating the corresponding Gaussian mixture models when the distributions of noises/uncertainties change due to sudden or seasonal changes in the operating conditions. These updates are not expected to increase the central processing unit times considerably. Illustrative case studies featuring open-loop operation and closed-loop control using nonlinear model predictive control have shown that the practical features offered by EMHE resulted in significant improvements in state estimation and online control.     

Closed-loop dynamic real-time optimization with stabilizing model predictive control

Dynamic real-time optimization (DRTO) is a supervisory strategy at the upper level of the industrial process automation architecture that computes economically optimal set-point trajectories that are in turn passed on to the lower-level model predictive control (MPC) for tracking. The economically optimal solution, in several process industries, could lead to operating the plant at or around an unstable steady state. The present article accounts for this by developing a closed-loop DRTO (CL-DRTO) formulation that enables handling unstable operating points via an underlying MPC with stability constraints. To this end, a stabilizing MPC that handles trajectory tracking for unstable systems is embedded within the upper-level DRTO. The resulting CL-DRTO problem is reformulated by applying a simultaneous solution approach. The economic benefits realized by the proposed strategy are illustrated through applications to both linearized and nonlinear dynamic models for single-input single-output and multi-input multi-output continuous stirred tank reactor case studies.     

On improving accuracy of computationally efficient nonlinear predictive control based on neural models

For nonlinear processes the classical model predictive control (MPC) algorithm, in which a linear model is used, usually does not give satisfactory closed-loop performance. In such nonlinear cases a suboptimal MPC strategy is typically used in which the nonlinear model is successively linearised on-line for the current operating point and, thanks to linearisation, the control policy is calculated from a quadratic programming problem. Although the suboptimal MPC algorithm frequently gives good results, for some nonlinear processes it would be beneficial to further improve control accuracy. This paper details a computationally efficient nonlinear MPC algorithm in which a neural model is linearised on-line along the predicted trajectory in an iterative way. The algorithm needs solving on-line only a series of quadratic programming problems. Advantages of the discussed algorithm are demonstrated in the control system of a high-purity ethylene–ethane distillation column for which the classical linear MPC algorithm does not work and the classical suboptimal MPC algorithm is slow. It is shown that the discussed algorithm can give practically the same control accuracy as the algorithm with on-line nonlinear optimisation and, at the same time, the algorithm is significantly less computationally demanding.     

Modeling and predictive control of nonlinear processes using transfer learning method

This work develops a transfer learning (TL) framework for modeling and predictive control of nonlinear systems using recurrent neural networks (RNNs) with the knowledge obtained in modeling one process transferred to another. Specifically, transfer learning uses a pretrained model developed based on a source domain as the starting point, and adapts the model to a target process with similar configurations. The generalization error for TL-based RNN (TL-RNN) is first derived to demonstrate the generalization capability on the target process. The theoretical error bound that depends on model capacity and the discrepancy between source and target domains is then utilized to guide the development of pretrained models for improved model transferability. Subsequently, the TL-RNN model is utilized as the prediction model in model predictive controller (MPC) for the target process. Finally, the simulation study of chemical reactors via Aspen Plus Dynamics is used to demonstrate the benefits of transfer learning.     

多层次结构模型预测控制系统的层次间模型切换方法

引言实际的工业过程对象,大部分都呈现出很强的非线性特性,其控制过程十分复杂。虽然近年来,对非线性技术的研究已经取得了很多的成果。但是非线性系统精确建模困难[1]、非线性微分方程求解     

基于MLD模型的CSTR建模和控制

A novel control strategy for a continuous stirred tank reactor （CSTR） system, which has the typical characteristic of strongly pronounced nonlinearity, multiple operating points, and a wide operating range, is initiated from the point of hybrid systems. The proposed scheme makes full use of the modeling power of mixed logical dynamical （MLD） systems to describe the highly nonlinear dynamics and multiple operating points in a unified framework as a hybrid system, and takes advantage of the good control quality of model predictive control （MPC） to design a controller. Thus, this approach avoids oscillation during switching between sub-systems, helps to relieve shaking in transition, and augments the stability robustness of the whole system, and finally achieves optimal （i.e. fast and smooth） transition between operating points. The simulation results demonstrate that the presented approach has a satisfactory performance.     

基于加权偏离度统计方法的预测控制性能评估算法

针对带区域约束条件的预测控制系统性能评估问题,在考虑过程输出变量约束类型的基础上,提出了基于加权偏离度统计方法的控制性能评估算法。该方法依据控制要求的不同,将输出变量分为质量变量和约束变量,并结合工程经验合理选择变量的权重。基于系统闭环运行数据和约束设置,通过计算变量的加权偏离度得到控制系统的性能评估指标,从而为预测控制器的参数调整和性能提升提供了决策依据。系统仿真实例和工程应用证明了该评估算法对区域预测控制系统性能评估的有效性。     

Encrypted model predictive control design for security to cyberattacks

In recent years, cyber-security of networked control systems has become crucial, as these systems are vulnerable to targeted cyberattacks that compromise the stability, integrity, and safety of these systems. In this work, secure and private communication links are established between sensor–controller and controller–actuator elements using semi-homomorphic encryption to ensure cyber-security in model predictive control (MPC) of nonlinear systems. Specifically, Paillier cryptosystem is implemented for encryption-decryption operations in the communication links. Cryptosystems, in general, work on a subset of integers. As a direct consequence of this nature of encryption algorithms, quantization errors arise in the closed-loop MPC of nonlinear systems. Thus, the closed-loop encrypted MPC is designed with a certain degree of robustness to the quantization errors. Furthermore, the trade-off between the accuracy of the encrypted MPC and the computational cost is discussed. Finally, two chemical process examples are employed to demonstrate the implementation of the proposed encrypted MPC design.     

基于神经网络和多模型的非线性自适应PID控制及应用

针对一类未知的单输入单输出离散非线性系统,提出了基于神经网络和多模型的非线性自适应PID控制方法。该方法由线性自适应PID控制器、神经网络非线性自适应PID控制器以及切换机构组成。采用线性自适应PID控制器可保证闭环系统所有信号有界;采用神经网络非线性自适应PID控制器可改善系统性能;通过引入合理的切换机制,能够在保证闭环系统稳定的同时,提高系统性能。理论分析表明,该方法能够保证闭环系统所有信号有界,如果适当地选择神经网络的结构和参数,系统的跟踪误差将收敛于任意给定的紧集。将所提出的方法应用于连续搅拌反应釜,仿真结果验证了所提出方法的有效性。由于该方法基于增量式数字PID控制器,在工业过程中有着广阔的应用前景。