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.     

Multistage nonlinear model predictive control for pumping treatment in hydraulic fracturing

Hydraulic fracturing has gained increasing attention as it allows the constrained natural gas and crude oil to flow out of low-permeability shale formations and significantly increase production. Perilous operating states of extremely high pressure also raise some safety concerns, requiring us to formulate an appropriate dynamic model, and provide a careful engineering control to ensure safe operating conditions. Moreover, uncertainties due to spatially varying rock properties increase the difficulties in control of the fracturing process. In this work, we formulate a first-principles model by considering the fracture evolution, mass transport of substances in the slurry, changing fluid properties, and the monitored operating pressure on the ground level. Next, we implement nonlinear model predictive control (NMPC) to control the process under a set of final requirements and process constraints. Our results show that the performance of standard NMPC degrades when the rock uncertainty causes the parameter mismatch between the process and the predictive model in the controller. With standard NMPC, designed with a nominal model, the process fails to meet the terminal requirements of fracture geometry, and pressure is violated in one of the parameter mismatch cases. Therefore, we resort to multistage NMPC, which considers uncertainty evolution in a scenario tree with separate control sequences to address constraint violations. We demonstrate that multistage NMPC presents good performance by showing constraint satisfaction whether the uncertain rock parameter realization is time-invariant or time-variant. We also simulate the process with multistage NMPC including different numbers of scenarios and compare their control performance. Our investigation demonstrates that multistage NMPC effectively manages parametric uncertainties attributed to non-homogeneous rock formation, and provides a promising control strategy for the hydraulic fracturing process.     

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 economic model predictive control for operational safety of nonlinear processes

Achieving operational safety of chemical processes while operating them in an economically‐optimal manner is a matter of great importance. Our recent work integrated process safety with process control by incorporating safety‐based constraints within model predictive control (MPC) design; however, the safety‐based MPC was developed with a centralized architecture, with the result that computation time limitations within a sampling period may reduce the effectiveness of such a controller design for promoting process safety. To address this potential practical limitation of the safety‐based control design, in this work, we propose the integration of a distributed model predictive control architecture with Lyapunov‐based economic model predictive control (LEMPC) formulated with safety‐based constraints. We consider both iterative and sequential distributed control architectures, and the partitioning of inputs between the various optimization problems in the distributed structure based on their impact on process operational safety. Moreover, sufficient conditions that ensure feasibility and closed‐loop stability of the iterative and sequential safety distributed LEMPC designs are given. A comparison between the proposed safety distributed EMPC controllers and the safety centralized EMPC is demonstrated via a chemical process example. © 2017 American Institute of Chemical Engineers AIChE J, 63: 3404–3418, 2017     

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.     

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。     

Economic model predictive control of nonlinear process systems using empirical models

Economic model predictive control (EMPC) is a feedback control technique that attempts to tightly integrate economic optimization and feedback control since it is a predictive control scheme that is formulated with an objective function representing the process economics. As its name implies, EMPC requires the availability of a dynamic model to compute its control actions and such a model may be obtained either through application of first principles or through system identification techniques. In industrial practice, it may be difficult in general to obtain an accurate first‐principles model of the process. Motivated by this, in the present work, Lyapunov‐based EMPC (LEMPC) is designed with a linear empirical model that allows for closed‐loop stability guarantees in the context of nonlinear chemical processes. Specifically, when the linear model provides a sufficient degree of accuracy in the region where time varying economically optimal operation is considered, conditions for closed‐loop stability under the LEMPC scheme based on the empirical model are derived. The LEMPC scheme is applied to a chemical process example to demonstrate its closed‐loop stability and performance properties as well as significant computational advantages. © 2014 American Institute of Chemical Engineers AIChE J, 61: 816–830, 2015     

一类化工过程多变量系统的自适应非线性预测控制

针对化工过程的一类多变量非线性系统,提出了一种自适应非线性预测控制(ANMPC)算法。在采用递归最小二乘法进行预测模型参数在线辨识的基础上,将系统的静态非线性关系用一个反向传播(BP)神经网络稳态模型来表示,通过稳态模型求得的动态增益来进一步校正预测模型的参数。详述了ANMPC控制器设计步骤,通过在一个多变量pH中和过程中的仿真验证了本算法的可行性和有效性。     

Nonlinear model predictive control for dividing wall columns

Dividing wall columns (DWCs) are practical, effective, and promising among distillation process intensification technologies. Nonlinear model predictive control (NMPC) schemes are developed in this study to control the three-product DWCs. As these systems are intensely interactive and highly nonlinear, NMPC may be more suitable than the traditional PI control. The model is established based on Python and Pyomo platforms. As the original mathematical model of the column section is ill-posed, index reduction is used to avoid a high-index differential-algebraic equation (DAE) system. The well-posed index-1 system after index reduction is employed for the steady-state simulation and dynamic control in this study. Case studies with three DWC configurations to separate the mixture of ethanol (A), n-propanol (B), and n-butanol (C) show that the NMPC performs very well with small maximum deviations and short settling times. This demonstrates that the NMPC is a feasible and very effective scheme to control three-product DWCs.     

Proactive fault‐tolerant model predictive control

Fault‐tolerant control methods have been extensively researched over the last 10 years in the context of chemical process control applications, and provide a natural framework for integrating process monitoring and control aspects in a way that not only fault detection and isolation but also control system reconfiguration is achieved in the event of a process or actuator fault. But almost all the efforts are focused on the reactive fault‐tolerant control. As another way for fault‐tolerant control, proactive fault‐tolerant control has been a popular topic in the communication systems and aerospace control systems communities for the last 10 years. At this point, no work has been done on proactive fault‐tolerant control within the context of chemical process control. Motivated by this, a proactive fault‐tolerant Lyapunov‐based model predictive controller (LMPC) that can effectively deal with an incipient control actuator fault is proposed. This approach to proactive fault‐tolerant control combines the unique stability and robustness properties of LMPC as well as explicitly accounting for incipient control actuator faults in the formulation of the MPC. Our theoretical results are applied to a chemical process example, and different scenaria were simulated to demonstrate that the proposed proactive fault‐tolerant model predictive control method can achieve practical stability and efficiently deal with a control actuator fault. © 2013 American Institute of Chemical Engineers AIChE J, 59: 2810–2820, 2013     

Integrated cyberattack detection and resilient control strategies using Lyapunov-based economic model predictive control

The use of an integrated system framework, characterized by numerous cyber/physical components (sensor measurements, signals to actuators) connected through wired/wireless networks, has not only increased the ability to control industrial systems but also the vulnerabilities to cyberattacks. State measurement cyberattacks could pose threats to process control systems since feedback control may be lost if the attack policy is not thwarted. Motivated by this, we propose three detection concepts based on Lyapunov-based economic model predictive control (LEMPC) for nonlinear systems. The first approach utilizes randomized modifications to an LEMPC formulation online to potentially detect cyberattacks. The second method detects attacks when a threshold on the difference between state measurements and state predictions is exceeded. Finally, the third strategy utilizes redundant state estimators to flag deviations from “normal” process behavior as cyberattacks.     

Distributed dissipative model predictive control for process networks with imperfect communication

Results are developed to ensure stability of a dissipative distributed model predictive controller in the case of structured or arbitrary failure of the controller communication network; bounded errors in the communication may similarly be handled. Stability and minimum performance of the process network is ensured by placing a dissipative trajectory constraint on each controller. This allows for the interaction effects between units to be captured in the dissipativity properties of each process, and thus, accounted for by choosing suitable dissipativity constraints for each controller. This approach is enabled by the use of quadratic difference forms as supply rates, which capture detailed dynamic system information. A case study is presented to illustrate the results. © 2014 American Institute of Chemical Engineers AIChE J, 60: 1682–1699, 2014     

A feedback control framework for safe and economically‐optimal operation of nonlinear processes

Maintaining safe operation of chemical processes and meeting environmental constraints are issues of paramount importance in the area of process systems and control engineering, and are ideally achieved while maximizing economic profit. It has long been argued that process safety is fundamentally a process control problem, yet few research efforts have been directed toward integrating the rather disparate domains of process safety and process control. Economic model predictive control (EMPC) has attracted significant attention recently due to its ability to optimize process operation accounting directly for process economics considerations. However, there is very limited work on the problem of integrating safety considerations in EMPC to ensure simultaneous safe operation and maximization of process profit. Motivated by the above considerations, this work develops three EMPC schemes that adjust in real‐time the size of the safety sets in which the process state should reside to ensure safe process operation and feedback control of the process state while optimizing economics via time‐varying process operation. Recursive feasibility and closed‐loop stability are established for a sufficiently small EMPC sampling period. The proposed schemes, which effectively integrate feedback control, process economics, and safety considerations, are demonstrated with a chemical process example. © 2016 American Institute of Chemical Engineers AIChE J, 62: 2391–2409, 2016     

Selection of control configurations for economic model predictive control systems

Economic model predictive control (EMPC) is a feedback control method that dictates a potentially dynamic (time‐varying) operating policy to optimize the process economics. The objective function used in the EMPC system may be a general nonlinear function that describes the process/system economics. As this function is not derived on the sole basis of classical control considerations (stabilization, tracking, and optimal control action calculation) but rather on the basis of economics, selecting the appropriate control configuration, and quantifying the influence of a given input on an economic cost is an important task for the proper design and computational efficiency of an EMPC scheme. Owing to these considerations, an input selection methodology for EMPC is proposed which utilizes the relative degree and the sensitivity of the economic cost with respect to an input to identify and select stabilizing manipulated inputs with the most dynamic and steady‐state influence on the economic cost function to be assigned to EMPC. Other considerations for input selection for EMPC are also discussed and integrated into a proposed input selection methodology for EMPC. The control configuration selection method for EMPC is demonstrated using a chemical process example. © 2014 American Institute of Chemical Engineers AIChE J, 60: 3230–3242, 2014     

Real‐time economic model predictive control of nonlinear process systems

Closed‐loop stability of nonlinear systems under real‐time Lyapunov‐based economic model predictive control (LEMPC) with potentially unknown and time‐varying computational delay is considered. To address guaranteed closed‐loop stability (in the sense of boundedness of the closed‐loop state in a compact state‐space set), an implementation strategy is proposed which features a triggered evaluation of the LEMPC optimization problem to compute an input trajectory over a finite‐time prediction horizon in advance. At each sampling period, stability conditions must be satisfied for the precomputed LEMPC control action to be applied to the closed‐loop system. If the stability conditions are not satisfied, a backup explicit stabilizing controller is applied over the sampling period. Closed‐loop stability under the real‐time LEMPC strategy is analyzed and specific stability conditions are derived. The real‐time LEMPC scheme is applied to a chemical process network example to demonstrate closed‐loop stability and closed‐loop economic performance improvement over that achieved for operation at the economically optimal steady state. © 2014 American Institute of Chemical Engineers AIChE J, 61: 555–571, 2015     

基于最小二乘支持向量机的MIMO线性参数变化模型辨识及预测控制

将现有的面向单输入单输出系统的基于最小二乘支持向量机的参数变化模型辨识算法(SISO-LSSVM-LPV), 推广到多输入多输出系统, 实现了面向多输入多输出系统的基于最小二乘支持向量机的参数变化模型辨识算法(MIMO-LSSVM-LPV), 进一步结合基于遗传算法的预测控制算法(GA-MPC), 提出并实现了MIMO-LSSVM-LPV+ GA-MPC的建模控制一体化新架构。仿真结果表明, 该辨识算法可逼近复杂非线性MIMO系统, 辨识精度高, 并且保留了线性回归低计算量的优点, 结合了GA的MPC可实现最优控制量的在线实时寻优, 并取得了良好控制效果。     

Actuator stiction compensation via model predictive control for nonlinear processes

The problem of valve stiction is addressed, which is a nonlinear friction phenomenon that causes poor performance of control loops in the process industries. A model predictive control (MPC) stiction compensation formulation is developed including detailed dynamics for a sticky valve and additional constraints on the input rate of change and actuation magnitude to reduce control loop performance degradation and to prevent the MPC from requesting physically unrealistic control actions due to stiction. Although developed with a focus on stiction, the MPC‐based compensation method presented is general and has potential to compensate for other nonlinear valve dynamics which have some similarities to those caused by stiction. Feasibility and closed‐loop stability of the proposed MPC formulation are proven for a sufficiently small sampling period when Lyapunov‐based constraints are incorporated. Using a chemical process example with an economic model predictive controller (EMPC), the selection of appropriate constraints for the proposed method is demonstrated. The example verified the incorporation of the stiction dynamics and actuation magnitude constraints in the EMPC causes it to select set‐points that the valve output can reach and causes the operating constraints to be met. © 2016 American Institute of Chemical Engineers AIChE J, 62: 2004–2023, 2016     

An integrated framework for scheduling and control using fast model predictive control

Integration of scheduling and control involves extensive information exchange and simultaneous decision making in industrial practice (Engell and Harjunkoski, Comput Chem Eng. 2012;47:121–133; Baldea and Harjunkoski I, Comput Chem Eng. 2014;71:377–390). Modeling the integration of scheduling and dynamic optimization (DO) at control level using mathematical programming results in a Mixed Integer Dynamic Optimization which is computationally expensive (Flores‐Tlacuahuac and Grossmann, Ind Eng Chem Res. 2006;45(20):6698–6712). In this study, we propose a framework for the integration of scheduling and control to reduce the model complexity and computation time. We identify a piece‐wise affine model from the first principle model and integrate it with the scheduling level leading to a new integration. At the control level, we use fast Model Predictive Control (fast MPC) to track a dynamic reference. Fast MPC also overcomes the increasing dimensionality of multiparametric MPC in our previous study (Zhuge and Ierapetritou, AIChE J. 2014;60(9):3169–3183). Results of CSTR case studies prove that the proposed approach reduces the computing time by at least two orders of magnitude compared to the integrated solution using mp‐MPC. © 2015 American Institute of Chemical Engineers AIChE J, 61: 3304–3319, 2015     

An economic model predictive control approach to integrated production management and process operation

Managing production schedules and tracking time‐varying demand of certain products while optimizing process economics are subjects of central importance in industrial applications. We investigate the use of economic model predictive control (EMPC) in tracking a production schedule. Specifically, given that only a small subset of the total process state vector is typically required to track certain scheduled values, we design a novel EMPC scheme, through proper construction of the objective function and constraints, that forces specific process states to meet the production schedule and varies the rest of the process states in a way that optimizes process economic performance. Conditions under which feasibility and closed‐loop stability of a nonlinear process under such an EMPC for schedule management can be guaranteed are developed. The proposed EMPC scheme is demonstrated through a chemical process example in which the product concentration is requested to follow a certain production schedule. © 2016 American Institute of Chemical Engineers AIChE J, 63: 1892–1906, 2017     

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.