云制造模式下采用Rough-ANP的机械设计知识优选推送策略
Optimal Selection Strategy of Mechanical Design Knowledge via Rough-anp in Cloud Manufacturing Environment

合理应用机械设计知识可以辅助提升创新设计的效率和质量。本文立足于云模式下的机械设计过程，提出基于行为-结构-知识的机械设计知识解构模型；提出一种云制造模式下基于Rough-ANP的机械设计知识优选推送策略，该方法充分结合了粗糙集理论（Rough set theory）在处理模糊性和不确定性方面的优势以及网络层次分析法（ANP）在处理多目标评估问题的优势。最后以电动铲运机设计为案例，验证了该机械设计知识优选推送策略的有效性。
Reasonable application of mechanical design knowledge can help improve the efficiency and quality of innovative design. The proposal based on the mechanical design process in cloud manufacturing, a deconstructive approach of design knowledge based on the behavior-structure-knowledge model is provided. And then, in this paper a novel optimal selection strategy of mechanical design knowledge based on Rough-ANP is proposed. The novel approach makes use of the strength of rough set theory in handling vagueness and uncertainty and the superiority of analytic network process (ANP) in non-independent hierarchy evaluation. Finally, a case is presented to demonstrate the effective auxiliary function of the novel approach