|
生物工程学报 1999
Multivariate Statistical Analysis for Streptomycin Fermentation
|
Abstract:
Principal Component Analysis,a method of multivariate statistical analysis,is used for analyzing the datum of actual industrial streptomycin fermentation.This method is ideal for analysis of large multivariate datasets with highly correlated and noisy measurements by compressing it into a lower dimension space which contains most of the variance of the original matrix.A rule based identification system is developed for dividing streptomycin fermentation process into three phases.The method built by multivariate regressive method can predict the production concentration of streptomycin fermentation according to three different phases.Good result is obtained.