.png){kind=icon}
返回
A data-driven predictive control strategy with application to tandem cold rolling process
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.129418.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The thickness and tension control is crucial for the improvement of strip product quality in the tandem cold rolling process, which is essentially a coupling control problem. In addition, since the great scale and complexity of the rolling process, it is hard to establish an accurate mechanism model. Asa result, the traditional model-based decoupling control methods are infeasible. To cope with such problem, the gated recurrent unit network is first used to predict the thickness and tension. And the Bayesian optimization algorithm is utilized to select the network hyperparameters automatically. Then, based on the predicted values, the coupling control problem is transformed into a multi-objective optimization problem and further solved by using an adaptive gradient descent method. Specifically, a watermarking based encryption scheme is given to enhance the security of data transmission. Furthermore, the convergence of the network predictive model and the stability of the proposed control method are also proved theoretically. Finally, a tandem cold rolling process is applied to show the effectiveness of the developed method.
Keyword:
Data-driven
Model predictive control (MPC)
Bayesian optimization-gated recurrent unit
(BO-GRU)
Multi-objective optimization
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
LSTM-MPC: A Deep Learning Based Predictive Control Method for Multimode Process ControlLstm-mpc: 一种基于深度学习的多模式过程预测控制方法
PREAI
分享收藏Robust Switching Time Optimization for Networked Switched Systems via Model Predictive Control基于模型预测控制的网络切换系统切换时间鲁棒优化
PREAI
分享收藏Multi-model based MPC to improve the ramp rate for renewable energy consumption.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Disturbance-Observer-Based Model Predictive Control for Discrete-Time Noncooperative Game Over Undirected Graph基于扰动观测器的无向图离散时间非合作博弈模型预测控制
PREAI
分享收藏分享收藏Saturated-threshold event-triggered adaptive global prescribed performance control for nonlinear Markov jumping systems and application to a chemical reactor model非线性马尔可夫跳跃系统的饱和阈值事件触发自适应全局规定性能控制及其在化学反应器模型中的应用
PREAI
分享收藏A novel dual-mode robust model predictive control approach via alternating optimizationsAUTOMATICA
AUTOMATICAIF5.9
PREAI
分享收藏
查看更多内容