Soft sensors development for on-line bioreactor state estimation

During a fermentation process, variables such as concentrations are determi ned by off-line laboratory analysis, making this set of variables of limite d use for control purposes. However, these variables can be on-line estimat ed using soft sensors. The objective of this study is to present the state of the art of state estimator techniques. Special attention was given to fi ltering techniques, namely extended Kalman filter, adaptive observers, and artificial neural networks (ANN). It is shown that software based state est imation is a powerful technique that can be successfully used to enhance au tomatic control performance of biological systems as well as in system moni toring and on-line optimisation. (C) 2000 Elsevier Science Ltd. All rights reserved.