Dynamic Modeling and Optimal Control of Batch Reactors, Based on Structure Approaching Hybrid Neural Networks

作者：Wang, J.; Cao, L. Lin^*; Wu, H. Yan; Li, X. Guang; Jin, Q. Bing

来源：Industrial & Engineering Chemistry Research, 2011, 50(10): 6174-6186.

DOI：10.1021/ie1015377

• POLYMERIZATION REACTORS
• TEMPERATURE CONTROL
• PRIOR KNOWLEDGE
• OPTIMIZATION
• PREDICTION

A novel Structure Approaching Hybrid Neural Network (SAHNN) approach to model batch reactors is presented. The Virtual Supervisor Artificial Immune Algorithm method is utilized for the training of SAHNN, especially for the batch processes with partial unmeasurable state variables. SAHNN involves the use of approximate mechanistic equations to characterize unmeasured state variables. Since the main interest in batch process operation is on the end-of-batch product quality, an extended integral square error control index based on the SAHNN model is applied to track the desired temperature profile of a batch process. This approach introduces model mismatches and unmeasured disturbances into the optimal control strategy and provides a feedback channel for control. The performance of robustness and antidisturbances of the control system are then enhanced. The simulation result indicates that the SAHNN model and model-based optimal control strategy of the batch process are effective.

• 出版日期2011-5-18
• 单位北京化工大学