基于多Agent的车间任务招投标粗模糊集建模研究

首先通过相识集、招标集、投标集和任务集的概念 ,描述制造执行系统中的调度 Agent与资源 A-gent间任务招投标过程模型 ;基于任务的属性和资源 Agent完成任务的成本、质量、负荷和时间等属性 ,定义论域上的模糊集 ,将模糊集中的隶属度函数作为粗集的属性 ,在模糊集上作截集 ,从而获得系统的分类知识 ;收集样本数据 ,构造并分析决策表 ,进而获得调度 Agent调度决策知识 ;应用调度知识进行推理 ,从争取获得招标任务的若干个资源 Agent中 ,选出最适合招标任务的中标者 .

A Rough Fuzzy Model of the Scheduling Agent for Task Bidding

The process model of bidding for tasks between the scheduling agent and the resource agent in the control system of shop floor are described in terms of acquaintance set, invitee set, bidder set and bid winner at first. Some fuzzy sets on the universe are defined based on the attributes of tasks and the attributes of the cost, quality, load and time for resource agents to accomplish the tasks. Considering the membership degrees of the fuzzy sets as attributes of rough sets, the knowledge base can been obtained by making up a series cutting sets of the fuzzy sets and then we can make use of collected samples to build a decision table. By analyzing the decision table scheduling rules or scheduling knowledge are deduced. Finally the method of fuzzy comprehensive judgment is instructed so as to select a bid-winner.