不确定客户需求驱动的相似实例提取方法研究
|
摘要
针对大规模定制背景下的产品选型设计,从不确定性客户需求出发,建立了集基于关联规则的合理性判别、基于三角模糊数的语义量化处理、基于主成分分析的冗余信息约简和基于层次分析法的权重值分配的客户需求智能化处理模型;通过欧氏距离计算产品相似度和K近邻分类算法在实例库中检索出最能满足客户需求的产品实例,该实例所对应的设计参数即为定制产品设计参数;最后以某工程机械公司平地机为例,对以上相似实例提取方法进行了验证,结果表明,该方法能实现个性化不确定客户需求到定制产品设计参数的映射,有效提高了后续产品配置设计的成功率。
In view of the product selection design under the background of mass customization and the uncertainty of customer demand, the paper establishes the intelligent processing model of customer demand, which integrates the rationality discrimination based on association rules, and the semantic quantization processing based on triangular fuzzy numbers, redundant information reduction based on principal component analysis, weight value assignment based on analytic hierarchy process. The product similarity is calculated by the Euclidean distance method. The K-nearest neighbor classification algorithm is used to retrieve the product instance that best meets the customer's needs. The design parameters corresponding to the instance are the custom product design parameters. Taking a grader of a construction machinery company as an example, the above similar example extraction method is verified. The results show that the method can realize the mapping of individualized uncertain customer requirements to custom product design parameters.The success rate of subsequent product configuration design is effectively improved.
In view of the product selection design under the background of mass customization and the uncertainty of customer demand, the paper establishes the intelligent processing model of customer demand, which integrates the rationality discrimination based on association rules, and the semantic quantization processing based on triangular fuzzy numbers, redundant information reduction based on principal component analysis, weight value assignment based on analytic hierarchy process. The product similarity is calculated by the Euclidean distance method. The K-nearest neighbor classification algorithm is used to retrieve the product instance that best meets the customer's needs. The design parameters corresponding to the instance are the custom product design parameters. Taking a grader of a construction machinery company as an example, the above similar example extraction method is verified. The results show that the method can realize the mapping of individualized uncertain customer requirements to custom product design parameters.The success rate of subsequent product configuration design is effectively improved.
引文
[1]AAMODT A,PLAXA E.Case-based reasoning:foundational issues,methodological variations,and system approaches[J].AICommunications,1994,7(1):39-59.
[2]郗涛,王莉静.平地机产品客户需求智能化处理模型[J].制造业自动化,2017,39(3):1-4,10.
[3]杨燕燕.基于粗糙集的增量属性约简机理与算法研究[D].北京:华北电力大学(北京),2017.
[4]WANG Pengjia,GONG Yadong,XIE Hualong,et al,Applying CBR to machine tool product configuration design oriented to customer requirements[J].Chinese Journal of Mechanical Engineering,2017,30(1):60-76.
[5]陈红,夏青,左婷,等.基于纹理分析的香菇品质分选方法[J].农业工程学报,2014,30(3):285-292.
[2]郗涛,王莉静.平地机产品客户需求智能化处理模型[J].制造业自动化,2017,39(3):1-4,10.
[3]杨燕燕.基于粗糙集的增量属性约简机理与算法研究[D].北京:华北电力大学(北京),2017.
[4]WANG Pengjia,GONG Yadong,XIE Hualong,et al,Applying CBR to machine tool product configuration design oriented to customer requirements[J].Chinese Journal of Mechanical Engineering,2017,30(1):60-76.
[5]陈红,夏青,左婷,等.基于纹理分析的香菇品质分选方法[J].农业工程学报,2014,30(3):285-292.