摘要
通过对并行设计任务拓扑层次的研究,提出了以马尔科夫决策过程(MDP)模型为基础的任务分派解决方案。首先对给出的设计任务节点进行拓扑排序,得到设计任务拓扑层次结构。其次计算设计师对设计任务的匹配程度,作为任务分派依据。然后通过马尔科夫决策过程(MDP)模型结合拓扑层次进行分层任务分派,分层任务分派依据为设计任务总体匹配度达到最大值,任务分派完成以拓扑层次循环结束为标准。最后通过实例对该模型的可靠性及实用性进行了验证。
Through the study of task topological of concurrent design, it puts forward the task assignment solutions based on Markov Decision Process (MDP). Firstly, gets the topological of design task by the "topological sort of design task nodes.Then computes the matching degree between designers and design tasks, andit will be the basis of task assignment.Then does the task assignment by the Markov decision process (MDP) model with topological of design task, and the basis of the assignment is that task matching degree reaches the maximum value. Finally the reliability and practicability of the model are validated by an example.
出处
《机械设计与制造》
北大核心
2015年第6期245-247,251,共4页
Machinery Design & Manufacture
基金
国家科技支撑计划项目"面向企业创新应用链的知识管理体系建设与集成应用示范"子课题"模具行业试点知识库建设"(2012BAH34F04)