In this paper, a novel fuzzy neural network model, in which an adjustable fuzzy subspace was designed by uniform design, has been established and used in fed-batch yeast fermentation as an example. A brand-new optimization sub-network with special structure has been built and genetic algorithm, guaranteeing the optimization in overall space, is introduced for the feed rate optimization. On the basis of the model network, the optimal substrate concentration and the optimal amount of fed-batch at different periods have been studied, aided with the optimization network and the genetic algorithm separately. The above results can be used as a basis for the establishment of a fuzzy neural network controller.