Bioreactor Modeling and Control by Principal Component Based Neural Networks

Abstract

In the work are developed structures for training and prediction by neural networks based on principal components analysis of input/output patterns. The structures are composed of functional modules dedicated for specific tasks in view of process engineering applications. The structures are serial connections of the following modules: ARMA for approximation by autoregression moving averages of process dynamics and process or transport delays; PS for statistical preprocessing, detection of gross errors, and rejection of redundant patterns; PCA for decomposition of patterns into principal components aimed for data compression and random noise elimination; and SISO-NN subsystem with a parallel connection of separated single input smgle output neural networks. Each NN submodule is structured with a single hidden layer with static neurons and feedforward progression. Parameters of NN modules are determined by Pollak-Ribiére-Powell conjugate gradient optimization. Number of principal components and elements in a hidden layer are optimized for minimal predicted sum of squares (PRESS) with untrained set of patterns The models are applied on data from industrial production of baker s yeast in a deep jet bioreactor.