基于支持向量机的青霉素发酵过程建模

由于微生物发酵过程的复杂性和高度非线性,更多的简单的数学模型不能很好地描述这类生化系统。支持向量机(SVM)是近几年发展起来的机器学习的新方法,它较好地解决了小样本、非线性、高维数和局部极小点等实际问题。SVM方法建立了青霉素效价预估模型,此模型具有良好的拟合和泛化能力。通过实验分析了SVM参数调整对支持向量机建模的影响。通过由现场数据建立的各种模型可以发现,SVM建模方法优于神经网络(ANN)建模方法。

Modeling for Penicillin Fermentation Process Based on Support Vector Machine

Due to the complexity and high non-linearity of microbial fermentation process, most simple mathematical models cannot describe the behavior of biochemistry systems very well. Support vector machine (SVM) is a novel machine learning method, which is powerful for the problem characterized by small sample, non-linearity, high dimension and local minima, and has high generalization. A model for titer pre-estimate in penicillin fermentation process was developed by SVM method. The model possesses the strong capability of fitting and generalization. The effects of parameter adjusting on model quality were analyzed by simulation experiments. Some models based on ANN methods were also presented. The results show that SVM is superior to ANN modeling methods.