معماری سیستم چند عامله تنظیم دوباره برای بازیابی خطا در سیستم های تولید

Multi-agent systems for manufacturing systems appear to provide adequate response to abrupt disturbances on the shop floor. To date, most of the work has been focused on planning and scheduling but very little work has been done on issues pertaining to monitoring, diagnostics and error recovery. Our approach addresses the issue of combining the discipline of hierarchical systems with the agility of multi-agent systems. Within the context of a hierarchy, the focus is on the workstation level and, in particular, the construction of a re-configurable system having production agents, error recovery agents, and a mediator agent structure connecting production and recovery agent hierarchies. In addition, the relationship to a multi-level, multi-layer hierarchy control is established. This latter hierarchy, based on Petri Net constructs, serves, in one sense, as a retrieval based resource for process planning and generation of recovery plans for production and recovery agents within the proposed multi-agent system. An objective of this effort is to provide a test-bed for comparison of hierarchical systems, heterarchical, and a hybrid combination which is the focus of the investigation presented here.

Today's manufacturing companies need to effectively adapt to sudden changes in customer demand, constant evolution of software and hardware, and unpredictable events such as failures and disruptions. Multi-agent based architectures for manufacturing systems appear to provide adequate responses to such requirements since their distributed nature provides flexibility and reactivity to changing situations [1]. Several intelligent-based architectures for manufacturing systems have been proposed in the literature: examples are Holonic Manufacturing [2] and [3], the NIST Real-Time Control System (RCS) [4], the MetaMorph Architecture [5], and the AARIA project [6]. While several performance tests [7] and [8] suggest that intelligent agent architectures for manufacturing systems outperform other control architectures in disruption-prone scenarios, the lack of standards on design methodologies, communication protocols, and task distribution among the agents imposes difficulties to their introduction to real-life applications. As a counterpoint to such intelligent-agent-based architectures, classical hierarchical architectures have been conceived with such standardization issues in mind. A major drawback of hierarchical architectures is that the structure can be overly rigid and consequently difficult to adapt to unanticipated disturbances [3].