Agent-based Manufacturing Systems Research Articles

Adaptive Agents in Distributed Manufacturing Systems

The paper briefly introduces the main distributed artificial intelligence approaches to support the realization of distributed manufacturing structures, such as agent-based and holonic manufacturing systems. Two attempts to enhance the performance of agent-based manufacturing systems using adaptation/learning techniques are presented. New agent-level parameters are introduced, by which the system behavior can be tuned. The research was carried out with the help of a simulation framework for agent-based manufacturing architectures developed by the authors earlier. A short description of the framework, including the communication and cooperation techniques, is also given.

MODELING OF AGENT-BASED MANUFACTURING SYSTEMS

ABSTRACT The increasing complexity of manufacturing systems imposes significant problems regarding to the design and implementation for those systems. Agent-based manufacturing system is one of the potential solutions. Many issues of agent-based manufacturing systems (ABMS) are still open to the researchers. This paper presents a two-stage approach for the modeling of ABMS. At the first stage, an object-oriented method with distributed computing technique is applied to construct agent primitives of ABMS; whereas in the second stage system architecture, execution procedure, and distributed computing platform of ABMS are presented. A closed loop, agent-based manufacturing system centered by a material handling equipment for multi-operation jobs is implemented to demonstrate the feasibility of the proposed approach.

Autonomy and viability-measures for agent-based manufacturing systems

An Agent-Based Manufacturing System (ABMS), represented as a model of future manufacturing systems, is introduced in this article. In an ABMS, computerized agents are autonomous and working collaboratively through the regulation of structured dialogues. The autonomy functions of an agent are demonstrated by four internal functions: internal resource management, a reflexivity mechanism, a goal adjustment mechanism, and collaboration management. The four functions assist an agent in interacting with other agents and with the environment and to adjust itself to the situation in the dynamic environment. Agents are similar to living systems. Based on the concept of living systems, autonomy and viability at the agent level are proposed and defined as new measures for manufacturing systems. A theory of coexistence and parasitism of ABMS is developed to identify the coexistent and parasitic characteristics of ABMS. Applications of the theory to real cases are also illustrated. Finally, a road map for the future research of distributed, collaborative manufacturing organizations is shown, based on the ABMS model developed.

Enhancing the performance of an agent-based manufacturing system through learning and forecasting

Agent-based technology has been identified as an important approach for developing next generation manufacturing systems. One of the key techniques needed for implementing such advanced systems will be learning. This paper first discusses learning issues in agent-based manufacturing systems and reviews related approaches, then describes how to enhance the performance of an agent-based manufacturing system through “learning from history” (based on distributed case-based learning and reasoning) and “learning from the future” (through system forecasting simulation). “Learning from history” is used to enhance coordination capabilities by minimizing communication and processing overheads. “Learning from the future” is used to adjust promissory schedules through forecasting simulation, by taking into account the shop floor interactions, production and transportation time. Detailed learning and reasoning mechanisms are described and partial experimental results are presented.

Agent-Based Systems for Intelligent Manufacturing: A State-of-the-Art Survey

Agent technology has been considered as an important approach for developing distributed intelligent manufacturing systems. A number of researchers have attempted to apply agent technology to manufacturing enterprise integration, supply chain management, manufacturing planning, scheduling and control, materials handling, and holonic manufacturing systems. This paper gives a brief survey of some related projects in this area, and discusses some key issues in developing agent-based manufacturing systems such as agent technology for enterprise integration and supply chain management, agent encapsulation, system architectures, dynamic system reconfiguration, learning, design and manufacturability assessments, distributed dynamic scheduling, integration of planning and scheduling, concurrent scheduling and execution, factory control structures, potential tools and standards for developing agent-based manufacturing systems. An extensive annotated bibliography is provided.

Hierarchical and heterarchical behaviour in agent-based manufacturing systems

Agent-based models appear to be a promising solution for managing manufacturing systems in environments where demanding requirements in terms of flexibility, adaptiveness and robustness are present. Although the agent-based approach is usually associated with heterarchical forms of production management architectures, it is possible to develop models in which hierarchical behaviour is encoded in the agents, thus leading to self-organising system architectures characterised by flexible and adaptive structures. In this paper an agent-based model with such characteristics is introduced, and preliminary simulation results are presented.