Neural network model based batch-to-batch optimal control

A neural network based batch to batch optimal control strategy is proposed in this paper. To overcome the difficulty in developing mechanistic models for batch processes, neural network models are developed from process operational data. The developed neural network model can only approximate the batch process and model plant mismatches usually exist. Thus the optimal control policy calculated based on a neural network model may not be optimal when applied to the true process. Due to the repetitive nature of batch processes, it is possible to improve the operation of the next batch using the information of the current and previous batch runs. A batch to batch optimal control strategy based on the linearization of the neural network model is proposed in this paper. Applications to a simulated batch polymerisation reactor demonstrate that the proposed method can improve process performance from batch to batch in the presence of model plant mismatches and unknown disturbances.