The paradigm of Cyber-Physical Systems may be successfully applied to a large number of case-studies, but the most challenging of them are focusing on large scale systems whose dynamics is adapting to various functional scenarios and environmental conditions as energy networks, traffic systems and especially different kinds of cooperative networks of enterprises. However, the large spectrum of possible configurations of such processes raises many issues with respect to the identification of problems to be solved, and furthermore, of the solving method itself, making the efficient use of available knowledge a real challenge. This paper is presenting a neuro-inspired approach for the design of a knowledge management system dedicated to complex networking enterprises organized as Cyber-Physical Systems, and whose functioning is implying dynamical reconfiguration in response to environmental changes, based on the gathering and use of large flows of information, which are referred to as Intelligent Cyber-Enterprises. The proposed ideas are based on a human brain model of reasoning and learning.

The paper presents respectively a modeling and a control approach of urban traffic networks, integrated into a software application. These approaches are based on an agent-oriented methodology and have as a goal the possibility of simulating, evaluating and optimizing the traffic in crowded areas, such as large cities, using both off line scenario policies and fine tuning scenario control.

The paper presents the conceptual framework and the synthesis procedure for temporal discrete event system supervisor. The approach is suitable in controlling systems as flexible manufacturing systems, in which certain durations of operations are not precisely known a priori. In this way, the model embodies temporal uncertainties of the process and the supervisor is "robust" to this indeterminism. The synthesis procedure could result in one ore more controllable supervision policies.

The paper presents the architecture and functioning of an intelligent supervisory module designed for building a supervising heterarchy for real-time manufacturing systems control. The supervisory module is conceived to have intrinsic properties such as robustness to a class of modeling uncertainties (i.e. duration of operations) and adaptivity to a class of resource break-downs. The robustness property is assured by using a modeling support capable of integrating nondeterministic time: T-temporal Petri nets (TTPN). The adaptivity is a consequence of specific local rescheduling procedures based on the modeling approach and of the structure of the control/supervision architecture. A case study illustrates the basic functioning of a supervision module.