A modeling methodology is suggested aimed to deal with new processes, particularly with process uncertainties, non-linearity and knowledge insufficiency. The model architecture is a modular neural network The data space is partitioned into several overlapping domains and a neural-network in each domain maps input-output relations. Each data feature vector has a membership value related to every ＇local＇ neural-net. The total output is a weighted sum of the local networks outputs. The domains are defined by unsupervised fuzzy clustering procedure.The model architecture enables efficient learning and tuning. Defining the optimal number of domains (i.e. clusters) is of great importance. The effectiveness of several cluster validity measures was compared with the generalization capability of the model and the information criteria suggested by Akaike. The validity measures were tested with data obtained from fermentation model simulations and a fermentation of yeast-like fungus Aureobasidium pullulans.