Batch-to-Batch Iterative Learning Control Using Updated Models Based on a Moving Window of Historical Data

This paper presents batch-to-batch iterative learning control (ILC) of a fed-batch fermentation process using batchwise linearised models identified from current and previous process operation data. The newly obtained process operation data after each batch is added to the historical data base. A moving window of the historical batches is used to develop batch-wise linearised model. The historical batches are updated after every batch run and only a moving window of recent historical batches are used to re-identify the process model. The new model is used to compute control policy for the next trial. The control actions at different batch stages are generally correlated, so to address the colinearity issue, principal component regression is used in estimating the linearised model parameters. The proposed strategy is applied to a simulated fed-batch fermentation process and the performance is evaluated. The effect of window sizes was studied. Simulation results show that the proposed approach improves the batch-to-batch ILC performance.