Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer
A main difficult task in batch crystallization is to control the size distribution of crystal products. Complexity and highly nonlinear dynamic behavior directly affect to model-based control strategies which heavily depend on the rigorous knowledge of crystallization. In this work, neural network-based model predictive control and inverse neural network control strategies are proposed and integrated with an optimization based on neural network-based hybrid model to control temperatures of a purified terephthalic acid batch crystallizer. A neural network-based hybrid model of the batch crystallizer is developed to provide nonlinear dynamic responses used in optimization algorithm for finding an optimal temperature profile related to the quality of a crystal product. Then, the obtained optimal profile is used as set points of the proposed control strategies for improving the crystal product quality. The performances and robustness of the proposed controllers are evaluated in several cases such as for set point tracking and plant/model mismatches. Simulation results show that the neural network-based model predictive control gives the best control performance among the inverse neural network control and a conventional PID controller in all cases.
Authors who publish with Engineering Journal agree to transfer all copyright rights in and to the above work to the Engineering Journal (EJ)'s Editorial Board so that EJ's Editorial Board shall have the right to publish the work for nonprofit use in any media or form. In return, authors retain: (1) all proprietary rights other than copyright; (2) re-use of all or part of the above paper in their other work; (3) right to reproduce or authorize others to reproduce the above paper for authors' personal use or for company use if the source and EJ's copyright notice is indicated, and if the reproduction is not made for the purpose of sale.