基于BP神经网络的产品造型设计  

Product Form Design Based on Back Propagation Neural Network

作　　者：刘刚田[1] 宋晓磊[2] 曹慧敏[3] 张丰收[3] 

机构地区：[1]河南科技大学艺术与设计学院,河南洛阳471003 [2]机械工业出版社,北京100037 [3]河南科技大学机电工程学院,河南洛阳471003

出　　处：《河南科技大学学报（自然科学版）》2009年第6期23-26,共4页Journal of Henan University of Science And Technology:Natural Science

基　　金：河南省自然科学基金项目(2009B460003);河南省教育厅自然科学基金项目(2006460003);河南科技大学科研基金资助项目(2008ZY056;2006QN039)

摘　　要：提出了一种基于BP神经网络的产品造型设计方法,采用计算机建模、模糊集理论和语义差异方法进行模拟研究。研究结果对采用BP神经网络建立产品造型参数和形容词的形象之间关系进行了分析。依据设计要素、产品造型和形状规则建造一个新的数据库连接,设计师可以生成产品图像不同的三维模型的基本的设计元素和形状规则。因此,改变参数的配置得到可接受和可修改产品的形状图像,运用这种方法所设计的产品可以更密切地配合消费者的需求。Based on neural network the approach for product form design is proposed.Fuzzy set theory and semantic difference method are applied to set up the simulation study.The results are analyzed by back-propagation neural network,which establishes the relationships between product-form parameters and adjective image words.A database for the connections among the design elements,product images and shape generation rules is constructed.A designer can generate 3D models of any product with different images by providing basic design elements and shape generation rules.Simultaneously,a rendered 3D model of the designed product and its images are also presented by this system.Therefore,changing the configuration parameters can modify the image of a product until the product shape is acceptable.In this manner,the designed product can fit more closely to the consumers' desire.

关 键 词：工业设计 产品造型设计 BP神经网络 

分 类 号：TB472[一般工业技术—工业设计] TP183[自动化与计算机技术—控制理论与控制工程]