ANN for hybrid modelling of batch and fed-batch chemical reactors

•Unconventional modelling based on ANN to rapidly develop a model from batch experiments.•Recurrent ANN’s (one per species) are assembled to predict time evolution of concentrations.•Balanced esterification reaction of methanol by acetic acid is chosen as application.•The global neural model is integrated in a reactor hybrid model.•The hybrid model permits to transpose the reaction to a semi-batch chemical reactor. An unconventional modelling methodology based on artificial neural networks is proposed to rapidly develop a model from data obtained during different batch experiments. The objective of the global model is to predict time evolution of concentrations of all species present in the reaction medium. For this, different recurrent neural networks are elaborated to estimate a particular species as a function of operating parameters and concentrations of all species and then assembled in a complex global model. To validate the approach, the esterification reaction of methanol by acetic acid, which presents equilibrium, has been chosen. The kinetic evolution of the chemical species during experiments conducted in batch mode are correctly represented whatever the operating conditions. Finally, the global model based on neural networks is integrated in a hybrid model. This permits to transpose the reaction to a semi-batch chemical reactor which has not been considered during the learning phase.