No abstract

No abstract

This paper presents the use of neural network-based model predictive control (NNMPC) incorporated with a neural network (NN) estimator for handling the predefined optimal policy tracking of a batch reactive distillation. The predefined optimal policy has been determined by dynamic optimization strategy. Then, the NNMPC incorporated with the NN estimator has been implemented to provide tracking of the obtained optimal policy. The NN model in the MPC algorithm gives as a one-step-ahead prediction of states, and it is therefore used in every iteration over a prediction horizon. Thus, the measured distillate composition at current time, needed as one of NN model inputs, is needed. However, the composition measurement is rarely available online in practice. Hence, an NN estimator is developed to estimate the current composition from the available measured composition with delay of 10 min. Both NNs are trained based on Levenberg-Marquardt algorithm. It has been found that the NNMPC provides satisfactory control performance for set point tracking problems. The robustness of the NNMPC is investigated with respect to parametric plant uncertainties and temperature measurement noise. Comparisons are made with a proportional integral derivative (PID) controller incorporated with the NN estimator. The results show that the NNMPC provides better control performance than the PID controller in all cases. 

Industrial grade ethyl acetate is available with minimum purity of 85.0%. It is mostly produced by an ethanol esterification in a distillation process on both batch and continuous modes. However, researches on high purity production with short operating time are rarely achieved. Therefore, the objective in this work is to study an approach to produce ethyl acetate of 90.0% by 8 hours using a batch reactive distillation column. Based on open-loop simulations, the distillation with constant reflux ratio cannot achieve the product specification. Thus, the dynamic optimization strategy is proposed to handle this problem. For the process safetypreventing the dried column and fractured, a minimum reflux ratio must be determined in advance and then an optimal reflux profile is calculated to achieve optimal product yield. Simulation results show that the industrial grade ethyl acetate can be produced by the dynamic optimization programming with two or more time intervals. Besides, the increasing of time intervals can produce more distillate product.

No abstract