Generic bi-layered net of the "functional nodes" in process modeling

There is a tendency to integrate the \´a priori\´ knowledge in neural networks in the form of "functional nodes". This paper presents a novel method for the appropriate description of the whole process model in the form of a net, consisting of two basic kinds of "functional nodes". The generic bi-layered net (GBN) model provides a common framework for the simulation of the hybrid (continuous and discrete, quantitative and qualitative) balance-based and rule-based processes. The common features of the process models are represented by a bi-layered net that also determines the network (ring) structures of the influence routes and of the flux routes, as well as the Gantt chart view of the time-variant process. Artificial neural networks seem to be a useful collaborating tool of the GBN in the model based problem solving. The structure of the GBN models can be homomorphic or isomorphic with the recurrent neural networks.