基于支持向量机与遗传算法的发酵过程软测量建模

Soft-Sensing Modeling of a Fermentation Process Through Support Vector Machines and Genetic Algorithms

提出了基于支持向量机的生物量浓度在线估计软测量建模方法,采用遗传算法进行模型输入的选择与支持向量机参数的选取,目的是找到对模型估计结果贡献最大的输入特征变量,降低了输入空间维数,缩小了求解问题的规模,从而减低计算方面的难度,减少了训练实际,同时又通过参数的调整,得到更好的决策函数,提高支持向量机的性能.模型的训练与验证数据都是取自实际的实验过程——诺西肽发酵.结果表明采用遗传算法进行优化的支持向量机软测量模型对生物量质量浓度具有好的预估性能.

A soft-sensing model is developed for on-line estimate of biomass concentration based on support vector machines. And genetic algorithms are introduced in selection of model input and the parameters of support vector machines. The purpose is to find out the input characteristic variables which contribute most to the model＇ s estimation result for reducing the number of dimensions of space to input and scope of the problem to solve, thus decreasing the difficulties in computation and training practice. Meanwhile, the decision function can be obtained better to improve the performance of support vector machines by way of readjusting parameters. The training/verifying data of the model are all based on the actual experimental process, i.e. Nosiheptide fermentation. Result shows that soft-sensing model optimized by genetic algorithms is highly beneficial to the estimate of biomass concentration.