Synthesis of state feedback laws for end-point optimization in batch processes

Development and Validation of Advanced Nonlinear Predictive Control Algorithms for Trajectory Tracking in Batch Polymerization

In this work, a computationally efficient nonlinear model-based control (NMBC) strategy is developed for a trajectory-tracking problem in an acrylamide polymerization batch reactor. The performance of NMBC is compared with that of nonlinear model predictive control (NMPC). To estimate the reaction states, a nonlinear state estimator, an unscented Kalman filter (UKF), is employed. Both algorithms are implemented experimentally to track a time-varying temperature profile for an acrylamide polymerization reaction in a lab-scale polymerization reactor. It is shown that in the presence of state estimators the NMBC performs significantly better than the NMPC algorithm in real time for the batch reactor control problem.

A neural network strategy for end-point optimization of batch processes

The traditional way of operating batch processes has been to utilize an open-loop "golden recipe". However, there can be substantial batch to batch variation in process conditions and this open-loop strategy can lead to non-optimal operation. In this paper, a new approach is presented for end-point optimization of batch processes by utilizing neural networks. This strategy involves the training of two neural networks; one to predict switching times and the other to predict the input profile in the singular region. This approach alleviates the computational problems associated with the classical Pontryagin's approach and the nonlinear programming approach. The efficacy of this scheme is illustrated via simulation of a fed-batch fermentation.