文献类型：期刊文献

英文题名：Develop Dynamic Hybrid Modeling of Fuel Ethanol Fermentation Process by Integrating Biomass Concentration XGBoost Model and Kinetic Parameters Artificial Neural Network Model into Mechanism Model

作者：Li, Xinzhe[1]; Dong, Yufeng[1]; Chang, Lu[2]; Chen, Lifan[2]; Wang, Guan[2]; Zhuang, Yingping[2]; Yan, Xuefeng[1]

机构：[1] Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, 200237, China; [2] State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology, Shanghai, 200237, China

年份：2022

外文期刊名：SSRN

收录：EI(收录号：20220341291)

语种：英文

外文关键词：Biomass - Ethanol - Fermentation - Forecasting - Fuels - Glucose - Kinetic parameters - Process control

摘要：Two problems are identified when the unstructured kinetic model of the fuel ethanol batch fermentation process with large differences in initial glucose concentrations is established. First, the unstructured kinetic model has poor accuracy in predicting the growth of yeast. Second, the environmental conditions have an impact on the kinetic parameters, resulting in a decrease in the prediction accuracy under production conditions that are different from the modeling samples. Therefore, a dynamic hybrid model of the fuel ethanol fermentation process is proposed. Firstly, a biomass concentration prediction model based on extreme gradient boosting (XGBoost) is developed to provide the predicted values of biomass concentration and mycelium growth rate, which are added to the prediction models of ethanol and glucose as supplementary mechanism knowledge. Secondly, the kinetic parameters model based on artificial neural network provides parameters according to the time variable and environmental variables. Finally, the time series of ethanol and glucose concentrations are predicted by combining the parameters model with the mechanism. The dynamic hybrid model not only solves the two problems mentioned above, but also performs with satisfactory accuracy in describing the fuel ethanol fermentation process. ? 2022, The Authors. All rights reserved.