Towards smart factory for industry 4.0: a self-organized multi-agent system with big data based feedback and coordination

Abstract

The proliferation of cyber-physical systems introduces the fourth stage of industrialization, commonly known as Industry 4.0. The vertical integration of various components inside a factory to implement a flexible and reconfigurable manufacturing system, i.e., smart factory, is one of the key features of Industry 4.0. In this paper, we present a smart factory framework that incorporates industrial network, cloud, and supervisory control terminals with smart shop-floor objects such as machines, conveyers, and products. Then, we provide a classification of the smart objects into various types of agents and define a coordinator in the cloud. The autonomous decision and distributed cooperation between agents lead to high flexibility. Moreover, this kind of self-organized system leverages the feedback and coordination by the central coordinator in order to achieve high efficiency. Thus, the smart factory is characterized by a self-organized multi-agent system assisted with big data based feedback and coordination. Based on this model, we propose an intelligent negotiation mechanism for agents to cooperate with each other. Furthermore, the study illustrates that complementary strategies can be designed to prevent deadlocks by improving the agents’ decision making and the coordinator's behavior. The simulation results assess the effectiveness of the proposed negotiation mechanism and deadlock prevention strategies.