FEATURE-BASED MODEL IDENTIFICATION OF NONLINEAR BIOTECHNOLOGICAL PROCESSES

Modelling ill-defined systems requires powerful tools to attain a quan titatively description of the studied systems. In this paper, a modell ing concept is presented that tackles the problems inherent to process es for which the necessary a priori knowledge for deductive analysis i s lacking. The approach can be summarised as follows. By means of rela tionship detectors, such as SAPS or fractional factorials, the existen ce of a causal structure can be deduced qualitatively. In a next step of the modelling task, the goal is to find the quantitative descriptio n of this relationship. This step can be subdivided in two phases, i.e . model structure characterisation and finally parameter estimation. I n this paper new techniques are proposed (and validated on real-life e xperimental results) to achieve the latter steps, In order to separate the structure characterisation from the parameter estimation task, an approach is taken in which parameter-invariant features are extracted from the data. The properties of these features are chosen in such a way that a classifier can select a specific model description. The dec omposition in Zernike features and the recurrent neural network classi fier, introduced by Sudharsanan, constitute the implementation of this concept. To check the feasibility of this modelling approach, a biote chnological application is chosen as a test case. Due to the changing nature of the wastewater treatment process, reflected in a set of math ematical descriptions applicable at different time instances, the afor ementioned methodology will give the possibility to develop more effic ient adaptive controllers.