Journal of Process Control ( IF 4.2 ) Pub Date : 2022-07-06 , DOI: 10.1016/j.jprocont.2022.06.012 Shu-Bo Yang , Zukui Li , Jesús Moreira
A recurrent neural network (RNN)-based approach is proposed in this paper to handle joint chance-constrained stochastic optimal control problems (SOCP) and stochastic model predictive control (SMPC) implementations. In the proposed approach, the joint chance constraint (JCC) in a SOCP is first reformulated as a quantile-based inequality. Then, the sample average approximation (SAA) method is used to build the RNN-based surrogate model for the quantile function. Afterwards, the RNN-based model is embedded into the probabilistic constraint of the SOCP. Subsequently, the SOCP involving the RNN-based model can be solved using a deterministic nonlinear optimization solver. Moreover, while applying the proposed approach to the SMPC, the SOCP involving the RNN-based model is solved repeatedly at different sampling instants, based on different initial system states. The proposed approach is applied to a numerical illustrating example and a chemical process case study to demonstrate its capability of handling the SOCP and the SMPC implementation.
中文翻译:
基于递归神经网络的联合机会约束随机最优控制方法
本文提出了一种基于循环神经网络 (RNN) 的方法来处理联合机会约束随机最优控制问题 (SOCP) 和随机模型预测控制 (SMPC) 实现。在所提出的方法中,SOCP 中的联合机会约束 (JCC) 首先被重新表述为基于分位数的不等式。然后,使用样本平均逼近(SAA)方法为分位数函数建立基于RNN的代理模型。之后,将基于 RNN 的模型嵌入到 SOCP 的概率约束中。随后,可以使用确定性非线性优化求解器来求解涉及基于 RNN 的模型的 SOCP。此外,在将所提出的方法应用于 SMPC 时,涉及基于 RNN 的模型的 SOCP 在不同的采样时刻重复求解,基于不同的初始系统状态。所提出的方法应用于数值说明示例和化学过程案例研究,以证明其处理 SOCP 和 SMPC 实施的能力。