Production optimization for concentration and volume-limited fed-batch reactors in biochemical processes

Since a very slight violation of constraint could cause process safety and product quality problems in biochemical processes, an adaptive approach of fed-batch reactor production optimization that can strictly satisfy constraints over the entire operating time is presented. In this approach, an improved smooth function is proposed such that the inequality constraints can be transformed into smooth constraints. Based on this, only an auxiliary state is needed to monitor violations in the augmented performance index. Combined with control variable parameterization (CVP), the dynamic optimization is executed and constraint violations are examined by calculating the sensitivities of states to ensure that the inequality constraints are satisfied everywhere inside the time interval. Three biochemical production optimization problems, including the manufacturing of ethanol, penicillin and protein, are tested as illustrations. Meanwhile, comparisons with pure penalty CVP method, famous dynamic optimization toolbox DOTcvp and literature results are carried out. Research results show that the proposed method achieves better performances in terms of optimization accuracy and computation cost.

Artificial Neural Network and Adaptive Neuro-Fuzzy Interface System Modeling of Supercritical CO2 Extraction of Glycyrrhizic Acid from Glycyrrhiza glabra L

In this study, the extraction of Glycyrrhizic acid (GA) from Glycyrrhiza glabra (licorice) root was investigated by Soxhlet extraction and modified supercritical CO2 with water as co-solvents and 30 min of static extraction time. The high performance liquid chromatography (HPLC) was used to identify and quantitatively determine the amount of extracted GA recovery of supercritical CO2 extraction of GA. The extraction recovery was modeled by adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN). Different ANFIS networks (by changing the type of membership functions) were compared with evaluation of networks accuracy in GA recovery prediction and subsequently the suitable network was determined. A three-layer artificial neural network was also developed for modeling of GA extraction from licorice plant root. In this regard, different networks (by changing the number of neurons in the hidden layer and algorithm of network training) were compared with evaluation of networks accuracy in extraction recovery prediction. One-step secant back propagation algorithm with six neurons in hidden layer was found to be the most suitable network and the coefficient of determination (R2) was 98.5 %. Gaussian combination membership function (gauss2mf) using 2 membership function to each input was obtained to be optimum ANFIS architecture with mean square error (MSE) of 0.05,0.17 and 0.07 for training, testing and checking data, respectively.