Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer

Abstract

Abstract. 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.

Application of Heuristic Algorithms in Improving Performance of Soft Computing Models for Prediction of Min, Mean and Max Air Temperatures

“…There are mainly two approaches for fuzzy inference systems, namely the approaches of Mamdani and Sugeno [23,24]. It has many applications in controlling, predicting and different fields [25][26][27][28]. In order to prevent the manuscript to become voluminous, the classic ANFIS steps are not explained in the present study, and one can find them in the existing studies [6,20,24].…”

“…Among them, artificial intelligence models including artificial neural network (ANN) and adaptive neurofuzzy inference system (ANFIS) have shown suitable performance related to the prediction of different factors such as climate and environmental conditions due to the lack of physical perception of the issue [7,8]. Smith et al (2005) optimized ANN performance to model environment temperature using seasonal data.…”

Integration of statistical methods and neural networks for temperature regulation parameter optimization

“…Neural networks have been demonstrated to be effective in identifying and controlling nonlinear dynamical systems, showcasing their potential in enhancing temperature control system optimization [10]. Moreover, the integration of neural network-based model predictive control and inverse neural network control strategies with optimization based on neural network models has been successfully applied to controlling temperatures in various systems, such as batch crystallizers [11]. Gao and Chai [12] allow for the optimization of control strategies through neural networks, leading to enhanced temperature regulation.…”