基于数据挖掘的绿色设计中客户需求向工程特性权重转化方法  

Method of Transform Customer Demands to Engineering Characteristic Weights in Green Design Based on Data Mining

作　　者：张雷[1] 钟言久 袁远 李璟 秦旭 董万富 ZHANG Lei;ZHONG Yanjiu;YUAN Yuan;LI Jing;QIN Xu;DONG Wanfu(School of Mechanical Engineering,Hefei University of Technology,Hefei,230009)

机构地区：[1]合肥工业大学机械工程学院,合肥230009

出　　处：《中国机械工程》2019年第2期174-182,共9页China Mechanical Engineering

基　　金：国家自然科学基金资助项目(51575152)

摘　　要：针对客户需求向工程特性转化过程中存在的主观性、模糊性和复杂性等问题,提出了一种基于数据挖掘的客户需求数据向工程特性权重的转化方法。利用模糊层次分析法对采集到的客户需求数据进行分析,得到客户需求重要度,建立了单一客户的质量屋,获取该客户需求对应的工程特性权重。构建了多层感知器模型,挖掘客户需求数据与工程特性权重之间的关系,确定客户需求向工程特性权重之间的转化模型。最后以减速器的客户需求与工程特性的转化为例,验证了所提方法的可行性和有效性。Due to the subjectivity,ambiguity and complexity of the transformation customer's demands into engineering characteristics,a method was proposed based on data mining,which converted customer's demand data into engineering characteristic weights.This paper used fuzzy analytic hierarchy process to analyze customer's demands and obtained the importance of customer's demands.Single customer's quality house was established to obtain engineering characteristic weights corresponding with customer's demands.The model of MLP was built to mine the relationships between customer's demand data and engineering characteristic weights.Finally,the feasibility and effectiveness of the proposed method were verified by the example of conversion from customer's demands to engineering characteristics.

关 键 词：数据挖掘 客户需求 多层感知器 工程特性 

分 类 号：TH122[机械工程—机械设计及理论]