抄録
Autonomous distributed manufacturing systems(ADMS) consist of multiple intelligent components with each component acting according to its own judgments. The ADMS objective is to realize more agile and adaptive manufacturing systems. This paper presents the introduction of context-dependent agents (CDAs) in ADMS have been proposed, and switch strategies depending on system conditions to achieve better performance than can be realized by agents that use the same strategies under all system conditions. For the real-time job scheduling problem, the paper recalls a basic CDA architecture, and presents the results of an extensive empirical evaluation its performance relative to other rule-based schemes based on several common indices for real-time dispatch.
