当前位置: X-MOL 学术Bioresource Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Modeling and optimization of microbial lipid fermentation from cellulosic ethanol wastewater by Rhodotorula glutinis based on the support vector machine
Bioresource Technology ( IF 9.7 ) Pub Date : 2020-01-10 , DOI: 10.1016/j.biortech.2020.122781
Lihe Zhang 1 , Bin Chao 1 , Xu Zhang 1
Affiliation  

To establish the models of microbial lipid production from cellulosic ethanol wastewater by , the biomass, lipid yield, and COD removal rate were investigated under different conditions. Subsequently, the genetic algorithm based on SVM was adopted to optimize parameters for obtaining the maximum biomass. The results demonstrated that the initial COD and glucose content had a significant effect on lipids synthesis. Most of the organic matter in the wastewater was consumed with the production of lipid. Compared with BP-ANN, SVM had better fitting and generalization ability for small amount of experimental data. By genetic algorithm optimization based on SVM, the maximum biomass and lipid yield could reach 11.87 g/L and 2.18 g/L, respectively. The results suggest that the SVM model could be used as an effective tool to optimize fermentation conditions.

中文翻译:


基于支持向量机的纤维素乙醇废水微生物脂质发酵建模与优化



为了建立微生物从纤维素乙醇废水中生产脂质的模型,研究了不同条件下的生物量、脂质产率和COD去除率。随后,采用基于SVM的遗传算法来优化参数以获得最大生物量。结果表明,初始COD和葡萄糖含量对脂质合成有显着影响。废水中的大部分有机物随着脂质的产生而被消耗。与BP-ANN相比,SVM对于少量实验数据具有更好的拟合和泛化能力。通过基于SVM的遗传算法优化,最大生物量和脂质产量分别达到11.87 g/L和2.18 g/L。结果表明,SVM 模型可以作为优化发酵条件的有效工具。
更新日期:2020-01-10
down
wechat
bug