Classification of fermentation process models using recurrent neural networks

In this article we present the classification of batch fermentation models. A recurrent neural network uses temporal information on the state variable s together with the time values. It can select from several possible models of the process the model that best describes the dynamics of the process. A pre-treatment of the data, denoted by 'self-normalization' is also propos ed. It is shown by a parameter sensitivity study that the 'self-normalizati on' assigns to a family of models (same structure of model, with different parameters) an approximately unique representation. This representation is used for training the recurrent neural network. The dimension of the learni ng set is considerably reduced. The trained neural network is used for the classification of real lactic fermentation data. The model which best suits the experimental data is determined and, from this, the main phenomena gov erning the process. The response of the neural classifier represents only a comparative measure of belonging to each of the considered models. The res ults show the good capacity of the network to recognise the 'best' model. T his technique can be used as an assisting tool to modelling of batch biotec hnological processes.