产品模块化中的若干智能方法

Some Intelligent Methods in Product Modularization

产品模块化是实现大批量定制的关键技术之一,也是工业4.0的基础,能够有效支持智能制造。传统的产品模块化方法需要依靠有经验的设计人员,需要花费大量时间。并且随着定制产品的数量越来越多,产品的变化越来越快,这种传统的方法越来越难以适应当前形势的发展需要。为了解决这些问题,提出产品模块化中的若干智能方法,包括:产品名称本体建立、产品模块划分、模块通用化和标准化、产品主结构建立等方面的智能方法,利用群体智能、大数据智能、人机协同智能等新一代人工智能技术,对大量产品模块数据、用户订单数据、设计人员使用产品模块的行为数据等进行智能分析,挖掘数据中隐藏的产品名称关系、模块关系等数据中的相似性和关联性等信息,帮助确定产品名称本体、产品模块划分、通用模块、模块主模型、产品主结构等,帮助快速实现大范围的产品模块化,减少开展产品模块化成本和时间。

Product modularization is one of the key technologies to realize mass customization,and it is also the foundation of industry 4.0,which can effectively support intelligent manufacturing.The traditional method of product modularization relies on experienced designers and takes a lot of time.And with the increasing number of customized products,the product changes faster and faster,this traditional method is more and more difficult to adapt for the development needs of the current situation.To solve these problems,some intelligent methods in product modularization are proposed,including:product name ontology establishment,product module partition optimization,module generalization and standardization,product main structure establishment etc.By using new generation of artificial intelligence technologies such as swarm intelligence,big data analysis and man-machine coordination,a large number of product module data,user order data and designers’behavior data of using product module are analyzed.By mining the similarity and relevance information such as product name relationship and module relationship hidden in the data,product name ontology,product module division,product common module,module main model and product main structure are determined.As a result,rapid large-scale product modularization is achieved,and the cost and time of product modularization are reduced.