Neural Network Based Modeling and Control for a Batch Heating/Cooling Evaporative Crystallization Process

Abstract

Abstract. Crystallization processes have been widely used for separation in many fields to provide a high purity product. In this work, dynamic optimization and neural network (NN) have been applied to improve the quality of the product: citric acid. In the dynamic optimization, optimization problems maximizing both crystal yield and crystal size have been formulated. The neural networks have been developed to provide NN models to be used in the formulation of not only neural network inverse control (NNDIC) but also neural network model predictive control (NNMPC) strategies. The Levenberg Marquadt algorithm has been used to train the network and optimal neural network architectures have been determined by a mean squared error (MSE) minimization technique. In addition, a neural network model has been designed to provide estimates of the temperature and the concentration of the crystallizer. These estimates have been incorporated into the NNMPC controller. In the NNDIC controller, another neural network model has been applied to predict the set point of jacket temperature. The simulation results have shown that the obtained crystal size is increased by 19% and 30% compared to that by cooling and evaporation methods respectively and the obtained yield is increased more than 50%. The robustness of the proposed controller is investigated with respect to parameters mismatches. The results have shown that the NNMPC controller provides superior control performances in all case studies.

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].…”

Rationalising crystal nucleation of organic molecules in solution using artificial neural networks

“…The solvent refractive index (19) shows a low relative importance rating, and as previously mentioned it is correlated with other included parameters, such as the solvent density (12). The density is combined with the solvent molar mass (9), to obtain a descriptor for the molar volume of the solvent molecule, and the refractive index and molar mass are removed.…”

“…6 There have been a number of studies on the use of ANNs in the design and control of industrial crystallisers. [7][8][9][10][11][12][13] However, little has been reported on using this method for gaining understanding about the fundamental underlying mechanisms of crystal nucleation. In a study by Kumar,14 ANNs were used to predict the solution-solid interfacial energy for 57 different inorganic systems.…”

Model-Based Evaluation of a Data-Driven Control Strategy: Application to Ibuprofen Crystallization

“…Moreover, an a priori model was required, and no initial data were demanded for the case scenario. More recently, Daosud et al [15] applied an inverse NN with the Levenberg-Marquardt training data approach and tan-sigmoidal hidden layers to the crystallization of citric acid. Two hidden layers were used, performing a total of 4 layers of NN.…”