高级检索

    基于GPGP协同机制的多Agent车间调度方法研究

    Study on GPGP-Cooperation-Mechanism-Based Multi-Agent Job Shop Scheduling Method

    • 摘要: 车间调度作为车间制造系统的重要组成部分,影响着整个车间制造系统的敏捷性和智能性.但是,由于资源和工艺约束的并存,使得车间调度成为一类NP-hard问题.基于静态的智能算法与动态的多Agent思想,提出了一种结合通用部分全局规划(generalized partial global planning,GPGP)机制与多种智能算法的多Agent车间调度模型,设计了从“初始宏观调度”到“微观再调度”的大规模复杂问题的调度步骤,并构建了一个柔性强且Agent可自我动态调度的仿真系统.同时,从理论上总结了GPGP基本协同机制的策略,实现了二级多目标优化调度.最后使用DECAF仿真Agent 软件模拟了车间调度的GPGP协同机制,并与CNP,NONE机制进行了比较.结果表明,所提出的模型不仅提高了调度的效率,而且降低了资源的损耗.

       

      Abstract: As an important part of the job shop manufacturing system, the job shop scheduling problem (JSSP) affects the agility and intelligence of the whole enterprise. In the real scenarios, the resource restriction coexists with the process restriction, which makes JSSP become NP-hard. Therefore, there is not yet an applicable method for solving the JSSP. In this paper, a job shop scheduling model combining MAS (multi-agent system) with multi-intelligence algorithms is presented. The proposed model is based on the generalized partial global planning (GPGP) mechanism and utilizes the advantages of static intelligence algorithms with dynamic MAS. A scheduling process from “initialized macro-scheduling” to “repeated micro-scheduling” is designed for large-scale complex problems to enable to implement an effective and widely applicable prototype system for JSSP. Under this scheme, a set of theoretic strategies in the GPGP are summarized in detail. A two-stage multi-objective optimization scheduling is performed and the GPGP-cooperation-mechanism is simulated by using simulation software DECAF for the JSSP. Meanwhile, those simulation results are compared with CNP-cooperation-mechanism and NONE mechanism. The results show that the proposed model based on the GPGP-cooperation-mechanism not only improves the effectiveness, but also reduces the resource cost.

       

    /

    返回文章
    返回