基于BP神经网络的轿车造型意象设计与量化预测模型建立

目的 构建产品造型意象设计与产品造型量化间的预测模型，将产品的设计元素与消费者的需求和感知相关联。方法 分析小轿车造型与感性意象之间的关系，基于用户对产品外观形态感受进行打分，采用感性工学方法进行量化；用双BP神经网络训练的思路，建立外观设计元素与感性意象间的对应关系，得到小轿车外观方案的感性意象预测模型。结论 获得产品造型设计方案的感性意象预测模型，能高效解决设计师的产品造型设计方案与消费者的目标达成趋同，通过高效的产品外观设计，为未来轿车及机电类产品的造型设计转向以消费者精神需求为导向提供了一种新的设计方法。

Design and Quantification of Cars Modeling Imagery Based on BP Neural Network

The work aims to construct the predictive model between product modeling imagery design and product modeling quantification to associate product design elements with consumer needs and perceptions. The relationship between car modeling and perceptual imagery was analyzed. Based on the user''s perception of product appearance, the perceptual engineering method was utilized to quantify it. The corresponding relationship between design elements and perceptual imagery was established with the training thought of dual BP neural network, so as to obtain the perceptual imagery predictive model of car appearance scheme. The perceptual imagery predictive model of product modeling design scheme obtained can effectively achieve the convergence of designer''s product modeling design scheme and consumer''s demand. The efficient product appearance design provides a new design method that future car and mechanical and electrical products are oriented to consumers'' spiritual needs.