Industrial, large-scale model predictive control with structured neural networks

Industrial, large-scale model predictive control with structured neural networks
复制标题

使用结构化神经网络进行工业大规模模型预测控制

DOI:
10.1016/j.compchemeng.2021.107291
复制
发表时间:
2021
影响因子:
4.3
通讯作者:
Wright, Stephen J.
Wright, Stephen J.
中科院分区:
工程技术2区
文献类型:
--
作者:
Kumar, Pratyush;Rawlings, James B.;Wright, Stephen J.

文献摘要

参考文献

被引文献

相似文献

提出了神经网络(NNs)的设计,用于处理大型线性模型预测控制(MPC)应用,这些应用无法用可用的二次规划(QP)解算器实现。首先,我们引入了一种新的前馈网络架构,使从业者能够通过神经网络获得无偏移的闭环性能。其次,我们讨论了基于预期在线设定值变化和植物干扰对训练神经网络相关的状态空间进行采样的数据生成过程。第三,我们使用MPC文献中可用的输入到状态稳定性结果并建立神经网络控制器的鲁棒性。最后,给出了过程控制实例的说明性仿真研究。我们应用神经网络设计方法,并将其性能与基于在线QP的MPC在工业原油蒸馏装置模型上进行了比较,该模型具有252个状态,32个控制输入,控制样本水平长度为140。并行计算用于数据生成,图形处理单元用于网络训练。对于神经网络训练,必须对具有设定值和运行过程中可能发生变化的干扰的预期工厂操作场景进行采样。在离线设计阶段之后,神经网络执行MPC的速度比可用的QP求解器快3到5个数量级,闭环性能损失小于1%。
The design of neural networks (NNs) is presented for treating large, linear model predictive control (MPC) applications that are out of reach with available quadratic programming (QP) solvers. First, we introduce a new feedforward network architecture that enables practitioners to obtain offset-free closed-loop performance with NNs. Second, we discuss the data generation procedure to sample the state space relevant to training the NNs based on anticipated online setpoint changes and plant disturbances. Third, we use the input-to-state stability results available in the MPC literature and establish robustness properties of NN controllers. Finally, we present illustrative simulation studies on process control examples. We apply the NN design approach and compare the performance with online QP based MPC on an industrial crude distillation unit model with 252 states, 32 control inputs, and a control-sample horizon length of 140. Parallel computing is used for data generation and graphical processing units are used for network training. Anticipated plant operational scenarios with setpoints and disturbances that may change during operation must be sampled for NN training. After the offline design phase, NNs execute MPC three to five orders of magnitude faster than an available QP solver with less than 1% loss in the closed-loop performance.
DOI: 10.1002/rnc.5696
发表时间: 2019-10
影响因子: 3.9
作者:
B. Karg;T. Alamo;S. Lucia
通讯作者: B. Karg;T. Alamo;S. Lucia
具有保证稳定性和约束满足的近似闭环鲁棒模型预测控制
DOI: 10.1109/lcsys.2020.2980479
发表时间: 2020
影响因子: 3
作者:
J. Paulson;A. Mesbah
通讯作者: A. Mesbah
DOI: --
发表时间: 2018
期刊: Handbook of Model Predictive Control
影响因子: --
作者:
Stephen J. Wright
通讯作者: Stephen J. Wright
DOI: 10.1073/pnas.1903070116
发表时间: 2019-08-06
影响因子: 11.1
作者:
Belkin, Mikhail;Hsu, Daniel;Mandal, Soumik
通讯作者: Mandal, Soumik