A neural network-based strategy for the integrated batch-to-batch control and within-batch control of batch processes

An integrated batch-to-batch control and within-batch re-optimization control strategy for batch processes using neural network models is presented in this paper. In order to overcome the difficulties in developing detailed mechanistic models, neural network models are developed from process operation data. Due to model-plant mismatches and unknown disturbances, the optimal control policy calculated based on the neural network model may not be optimal when applied to the actual process. Utilizing the repetitive nature of batch processes, neural network model-based iterative learning control is used to improve the process performance from batch to batch. However, batch-to-batch control can only improve the performance of the future batches but cannot improve the performance of the current batch. Within-batch re-optimization should be used to overcome the detrimental effect of disturbances on the current batch. In the proposed integrated control scheme, the effect of unknown disturbance is estimated using a neural network-based inverse model using mid-batch process measurements. The estimated effect of unknown disturbance is then used to re-optimize the control actions for the remaining period of the batch operation. The proposed technique is successfully applied to a simulated batch polymerization process.