Control of a chaotic polymerization reactor: A neural network based model predictive approach
Control of a chaotic polymerization reactor: A neural network based model predictive approach
复制标题
DOI：
10.1002/pen.10431
复制
发表时间：
1996-02-01
影响因子：
3.2
通讯作者：
Lima, EL
中科院分区：
文献类型：
--
作者：
De Souza, MB;Pinto, JC;Lima, EL
连续聚合方法可能对操作条件的微小变化非常敏感。连续VA（醋酸乙烯酯）溶液均聚反应器可能存在多稳态和振荡行为。一个预测控制方案，使用的过程的内部模型，以稳定这样的反应器，使它们不太敏感的干扰，同时受到“硬”的控制动作约束。ANN（人工神经网络）被用作内部模型，导致相当好的预测反应器的行为，包括其多重性。所得到的控制算法的性能进行比较，一个“良好调谐”的传统比例积分微分（PID）控制器。
Continuous polymerization processes may be very sensitive to small changes of the operation conditions. Continuous VA (vinyl acetate) solution homopolymerization reactors may present multiple steady-states and oscillatory behavior. A predictive control scheme that uses an internal model of the process is employed to stabilize such reactors and make them less sensitive to disturbances while subject to ''hard'' control action constraints. An ANN (artificial neural network) is used as the internal model, leading to fairly good predictions of the reactor behavior, including its multiplicities. The performance of the resulting control algorithm is compared to that of a ''well-tuned'' conventional proportional-integral-derivative (PID) controller.