基于模糊支持向量机的产品造型特征研究  

Study on Product Form Feature Based on Fuzzy Support Vector Machine

作　　者：刘刚田[1] 曹慧敏[1] 王巍[2] 霍银磊[1] 

机构地区：[1]河南科技大学,河南洛阳471003 [2]燕山大学,河北秦皇岛066004

出　　处：《机床与液压》2010年第21期52-55,共4页Machine Tool & Hydraulics

基　　金：河南省教育厅自然科学基金项目(2006460003)

摘　　要：消费者的喜好往往影响着各种产品的造型特征。传统上,产品造型设计的质量在很大程度上依靠设计师的直觉,在市场上并不总是成功的。提出基于模糊支持向量机的产品造型设计方法。依据消费者的喜好构造产品造型设计分类模型,采用一对一的方法将多级问题分解成两级问题进行处理。收集产品样本和造型特征制定分类问题并进行系统研究,每个产品的样本和模糊隶属度被指定为一类标记,利用收集的产品样本建立一对一模糊支持向量机模型。通过交叉验证法确定模型的理想训练参数。Consumer preferences often affect form features of a large variety of product. Traditionally, the quality of product form design depends heavily on designers’ intuitions and they are not always proved to be successful in the marketplace. To help product designers develop appealing products in a more effective manner, an approach based on fuzzy support vector machines （FSVM） was proposed. A classification model of product form design was constructed based on consumer preferences. The one-versus-one （OVO） method was adopted to handle a multi-class problem by breaking it into various two-class problems. Product samples were collected and their form features were systematically examined. To formulate a classification problem, each product sample was assigned a class label and a fuzzy membership that corresponded to this label. The OVO-FSVM model was constructed using collected product samples. The optimal training parameters for the model were determined by cross-validation.

关 键 词：消费者喜好 模糊支持向量机 产品设计 

分 类 号：O29[理学—应用数学]