Online prediction of total sugar content and optimal control of glucose feed rate during chlortetracycline fermentation based on soft sensor modeling

Abstract

<abstract> <p>In the process of chlortetracycline (CTC) fermentation, no instrument can be used to measure the total sugar content of the fermentation broth online due to its high viscosity and large amount of impurities, so it is difficult to realize the optimal control of glucose feed rate in the fermentation process. In order to solve this intractable problem, the relationship between on-line measurable parameters and total sugar content (One of the parameters that are difficult to measure online) in fermentation tank is deeply analyzed, and a new soft sensor model of total sugar content in fermentation tank and a new optimal control method of glucose feed rate are proposed in this paper. By selecting measurable variables of fermentation tank, determining different fermentation stages, constructing recursive fuzzy neural network (RFNN) and applying network rolling training method, an online soft sensor model of total sugar content is established. Based on the field multi-batch data, the change trend of the amount of glucose feed required at each fermentation stage is divided, and the online prediction of total sugar content and the optimal control strategy of glucose feed rate are realized by using the inference algorithm of expert experience regulation rules and soft sensor model of total sugar content. The experiment results in the real field demonstrate that the proposed scheme can effectively predict the total sugar content of fermentation broth online, optimize the control of glucose feed rate during fermentation process, reduce production cost and meet the requirements of production technology.</p> </abstract>

Soft Sensor Modeling Method for the Marine Lysozyme Fermentation Process Based on ISOA-GPR Weighted Ensemble Learning

“…It can be obtained in Figure 7 that, except for some individual data points (e.g., the 15th data point), the ISOA-GPR weighted ensemble learning model has This paper established two sets of comparison experiments with ISOA-GPR single global, ISOA-GPR weighted ensemble learning and ISOA-GPR weighted ensemble learning; and ISOA-BP weighted ensemble learning. The predicted curves of key biochemical parameters (bacterium concentration, substrate concentration, and relative enzyme activity) for the marine lysozyme fermentation process were derived using each of the three models, as shown in Figures 6,8 From the above figures and table analysis the following can be seen.…”

“…Soft sensor technology is an effective method to solve the above problems [5][6][7][8][9]. Hua et al [10] proposed a new hybrid soft sensor model based on RF-IHHO-LSTM (random forest-improved Harris hawks optimization-long short-term memory) for the penicillin fermentation process.…”