基于证据网络的多变量MPC经济性能评估

MPC控制系统作为先进控制策略,已经被广泛地应用于工业生产中。但在实际工业中,MPC控制系统的变量的软约束往往设定得比较保守,使系统无法达到最优经济性能。针对有约束的MPC控制系统,采用二次型经济性能指标函数来评价系统的经济性能,将最优工作点的求解问题转化为一个典型的有约束的线性规划问题。进而根据历史数据和二次型经济性能指标函数所得最优运行结果建立多变量MPC的证据网络模型,通过证据网络的反向推理和决策,得到造成MPC控制系统性能下降的可能原因,并提出改善控制系统性能的策略。最后通过仿真实验,验证了基于证据网络的经济性能评估的有效性。     

模型预测控制在水泥生产线自动化的应用

介绍模型预测控制（MPC）在某5?000 t/d水泥生产线的应用,MPC系统用于分解炉、回转窑和篦冷机的控制。生产线动态模型由多变量系统辨识（动态数据建模）获得。该MPC系统的实施时间为3周,2018年7月投运后一直稳定运行。相对手动控制,MPC控制系统大大降低了分解炉出口温度等关键参数的波动性。与手动控制比较,可节煤15%。最新运行数据表明,分解炉出口温度波动进一步降低,熟料游离氧化钙合格率接近100%,而另一条手动控制生产线熟料游离氧化钙合格率约为80%。本文还提出一个MPC项目经济效益的简单估算公式。     

模型预测控制技术在水泥回转窑的成功应用

针对水泥回转窑内关键变量:如给煤量、喂料量、窑温度、窑头负压、篦床压力等多变量强耦合严重,运行工况变化大且波动频繁而导致水泥熟料质量不稳定和产能低等问题,提出了一种模型预测控制(MPC)策略。该策略采用多目标层优化方法,利用陕西榆林某水泥厂获得的实际生产数据进行模型辨识,将辨识出的优质模型导入MPC控制器中对回转窑的关键变量进行控制。最后导出投运先进控制前后的数据进行分析对比,结果表明该策略可以明显降低相关工艺参数的波动幅度,产生节煤效益并且提高水泥成品的质量。     

快速增量约束预测控制及在GLCC液位控制中的应用

针对气-液柱状旋流式(GLCC)多相流量计的液位控制问题,提出一种增量多变量模型预测控制(MPC)算法。采用控制增量状态空间模型和阶梯式控制策略,建立约束多变量MPC优化控制问题。为在线计算约束优化问题,引入坐标轮换法和黄金分割法,在线计算控制变量增量值,进而得到预测控制量。最后,以GLCC多相流量计的两输入单输出液位控制模型为例,仿真验证本文算法的有效性。     

模型预测控制在钠氨合成工艺上的应用研究

基于钠氨合成连续化生产工艺,从化学反应机理出发,建立钠氨塔式反应器动态机理模型。并对模型进行动态分析,对多变量非线性模型进行集总化、线性化处理。推广单变量模型预测控制到多变量模型预测控制,对反应器温度进行控制。通过仿真比较,验证了MPC控制算法比PID控制具有更好的控制效果。     

多变量控制方式在液氮洗工艺中的应用

针对液氮洗装置的工艺特点,通过对合成氨装置生产工艺和过程控制以及历史数据的采集分析,对被控变量进行预测控制与精准控制,保证被控变量在最优区间运行,成功将多变量控制方式应用于合成氨装置。不仅解决了装置多变量耦合性问题,也解决了氢氮比控制滞后问题,减小工艺参数波动,提高装置运行的稳定性。     

新一代的自适应模型预测控制器

提出了新一代的自适应模型预测控制器,自适应MPC控制器由MPC控制模块、在线辨识模块、性能监控模块3个模块组成,相互协调配和来实现自适应MPC控制。除了控制器功能设计以外,其余过程均可自动进行。对于新建MPC应用,首先进行多变量测试与辨识,在模型符合控制要求时,自动进入控制器投运。通过控制器性能监视发现模型不满足控制要求精度时,触发一次多变量模型测试与辨识过程,替换原有模型进行控制,保证控制器性能始终处于最佳状态。自适应MPC控制器在PTA装置上的应用表明了算法的有效性。     

基于迁移变分自编码器-标签映射的湿式球磨机负荷参数软测量

在工况改变时,湿式球磨机的实时数据和建模数据分布不一致,不满足传统软测量建模方法要求的数据同分布假设,导致模型失准和性能恶化。为此,引入迁移学习思想,提出一种基于迁移变分自编码器-标签映射的软测量模型,实现多工况下湿式球磨机负荷参数的准确测量。首先,迁移目标域数据编码得到的隐变量分布参数,对源域数据对应隐变量进行拟合,再解码得到迁移数据;然后采用相似性度量选取相似样本构建标签映射模型,并得到映射标签;最后使用迁移数据和映射标签构建出最终的软测量模型。实验结果表明,该软测量方法显著优于现有方法,适用于多工况下的软测量建模。     

基于迁移变分自编码器-标签映射的湿式球磨机负荷参数软测量

在工况改变时，湿式球磨机的实时数据和建模数据分布不一致，不满足传统软测量建模方法要求的数据同分布假设，导致模型失准和性能恶化。为此，引入迁移学习思想，提出一种基于迁移变分自编码器-标签映射的软测量模型，实现多工况下湿式球磨机负荷参数的准确测量。首先，迁移目标域数据编码得到的隐变量分布参数，对源域数据对应隐变量进行拟合，再解码得到迁移数据；然后采用相似性度量选取相似样本构建标签映射模型，并得到映射标签；最后使用迁移数据和映射标签构建出最终的软测量模型。实验结果表明，该软测量方法显著优于现有方法，适用于多工况下的软测量建模。     

多变量预测控制在乙醛精制装置中的应用

提出了一种乙醛精制装置的多变量预测控制策略。该策略应用自主开发的多变量预测控制软件将该装置两个精馏塔统一考虑实施多变量预测控制,减小了成品塔温度的波动,稳定了最终乙醛产品的质量,并使得其运行于最优的稳态工作点上。     

Model predictive control with active learning under model uncertainty: Why,when, and how

Optimal control relies on a model, which is generally uncertain because of incomplete knowledge of the system and changes in the dynamics over time. Probing the system under closed‐loop control can reduce the model uncertainty through generating input‐output data that is more informative than the data generated from normal operation. This paper addresses the problem of model predictive control (MPC) with active learning, with a particular focus on how incorporating probing in the control action can reduce model uncertainty. We discuss some of the central theoretical questions in this problem, and demonstrate the potential of active learning for maintaining MPC performance in the presence of uncertainty in model parameters and structure. Simulation results show that active learning is particularly beneficial when a system undergoes abrupt changes (such as the sudden occurrence of a fault) that can compromise operational safety, reliability, and profitability. © 2018 American Institute of Chemical Engineers AIChE J, 64: 3071–3081, 2018     

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.     

Iterative learning model predictive control for constrained multivariable control of batch processes

In this paper, we propose a model predictive control (MPC) technique combined with iterative learning control (ILC), called the iterative learning model predictive control (ILMPC), for constrained multivariable control of batch processes. Although the general ILC makes the outputs converge to reference trajectories under model uncertainty, it uses open-loop control within a batch; thus, it cannot reject real-time disturbances. The MPC algorithm shows identical performance for all batches, and it highly depends on model quality because it does not use previous batch information. We integrate the advantages of the two algorithms. The proposed ILMPC formulation is based on general MPC and incorporates an iterative learning function into MPC. Thus, it is easy to handle various issues for which the general MPC is suitable, such as constraints, time-varying systems, disturbances, and stochastic characteristics. Simulation examples are provided to show the effectiveness of the proposed ILMPC.     

基于自适应模糊神经网络的非线性系统模型预测控制

针对非线性动态系统的控制问题,提出了一种基于自适应模糊神经网络(adaptive fuzzy neural network,AFNN)的模型预测控制(model predictive control, MPC)方法。首先,在离线建模阶段,AFNN采用规则自分裂技术产生初始模糊规则,采用改进的自适应LM学习算法优化网络参数;然后,在实时控制过程,AFNN根据系统输出和预测输出之间的误差调整网络参数,从而为MPC提供一个精确的预测模型;进一步,AFNN-MPC利用带有自适应学习率的梯度下降寻优算法求解优化问题,在线获取非线性控制量,并将其作用到动态系统实施控制。此外,给出了AFNN-MPC的收敛性和稳定性证明,以保证其在实际工程中的成功应用。最后,利用数值仿真和双CSTR过程进行实验验证。结果表明,AFNN-MPC能够取得优越的控制性能。     

Disturbance rejection of ball mill grinding circuits using DOB and MPC

Ball mill grinding circuit is essentially a multivariable system with couplings, time delays and strong disturbances. Many advanced control schemes, including model predictive control (MPC), adaptive control, neuro-control, robust control, optimal control, etc., have been reported in the field of grinding process. However, these control schemes including the MPC scheme usually cannot achieve satisfying effects in the presence of strong disturbances. In this paper, disturbance observer (DOB), which is widely used in motion control applications, is introduced to estimate the disturbances in grinding circuit. A compound control scheme, consisting of a feedforward compensation part based on DOB and a feedback regulation part based on MPC (DOB-MPC), is thus developed. A rigorous analysis of disturbance rejection performance is given with the considerations of both model mismatches and external disturbances. Simulation results demonstrate that when controlling the ball mill grinding circuit, the DOB-MPC method possesses a better performance in disturbance rejection than that of the MPC method.     

Constrained model predictive control in ball mill grinding process

Stable control of grinding process is of great importance for improvements of operation efficiency, the recovery of the valuable minerals, and significant reductions of production costs in concentration plants. Decoupled multi-loop PID controllers are usually carried out to manage to eliminate the effects of interactions among the control loops, but they generally become sluggish due to imperfect process models and a close control of the process is usually impossible in real practice. Based on its inherent decoupling scheme, model predictive control (MPC) is employed to handle such highly interacting system. For high quality requirements, a three-input three-output model of the grinding process is constructed. Constrained dynamic matrix control (DMC) is applied in an iron ore concentration plant, and operation of the process close to their optimum operating conditions is achieved. Some practical problems about the application of MPC in grinding process are presented and discussed in detail.     

High-order iterative learning model predictive control for batch chemical processes

In order to address two-dimensional (2D) control issue for a class of batch chemical processes, we propose a novel high-order iterative learning model predictive control (HILMPC) method in this paper. A set of local state-space models are first constructed to represent the batch chemical processes by adopting the just-in-time learning (JITL) technique. Meanwhile, a pre-clustered strategy is used to lessen the computational burden of the modelling process and improve the modelling efficiency. Then, a two-stage 2D controller is designed to achieve integrated control by combining high-order iterative learning control (HILC) on the batch domain with model predictive control (MPC) on the time domain. The resulting HILMPC controller can not only guarantee the convergence of the system on the batch domain, but also guarantee the closed-loop stability of the system on the time domain. The convergence of the HILMPC method is ensured by rigorous analysis. Two examples are presented in the end to demonstrate that the developed method provides better control performance than its previous counterpart.     

Online machine learning modeling and predictive control of nonlinear systems with scheduled mode transitions

This work develops a model predictive control (MPC) scheme using online learning of recurrent neural network (RNN) models for nonlinear systems switched between multiple operating regions following a prescribed switching schedule. Specifically, an RNN model is initially developed offline to model process dynamics using the historical operational data collected in a small region around a certain steady-state. After the system is switched to another operating region under a Lyapunov-based MPC with suitable constraints to ensure satisfaction of the prescribed switching schedule policy, RNN models are updated using real-time process data to improve closed-loop performance. A generalization error bound is derived for the updated RNN models using the notion of regret, and closed-loop stability results are established for the switched nonlinear system under RNN-based MPC. Finally, a chemical process example with the operation schedule that requires switching between two steady-states is used to demonstrate the effectiveness of the proposed RNN-MPC scheme.     

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.     

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.