Semi−Supervised Hybrid Modeling of the Yeast Fermentation Process

This study focuses on modeling the yeast fermentation process using hybrid method. To improve prediction accuracy of model and reduce training time, this paper presents a semi−supervised method based an extreme learning machine for process. The is composed mechanism residual model. built from residuals between real used in parallel with Considering that might be related to inaccurate parameters or structure process, output taken as unlabeled data, suitable inputs are selected Pearson’s maximum correlation minimum redundancy criterion (RRPC). Meanwhile, employed model’s speed while maintaining accuracy. Consequently, proposal proved its efficacy through simulation.