摘要
为进一步探讨产品设计中形态特征和用户情感匹配的问题,提出了一种基于语义的自适应混合免疫遗传产品形态设计优化方法。通过目标语义的模糊隶属度的匹配来生成初始抗体集合,再利用专家建议来生成疫苗集合,并在演化过程中通过疫苗接种和基于亲和度的选择来加速收敛并保持种群多样性,利用反向传播神经网络(BPNN)将形态特征语义空间映射到情感语义空间并构造适应度函数。此外,疫苗接种概率按接种效果进行自适应调节,并基于信息熵理论定义抗体之间的亲合度及抗体的选择概率。原型系统实现了形态设计的快速生成和设计评价,验证了方法的有效性。
To investigate the shape characteristic and the user emotion in the product shape design process,a semantic-based adaptive hybrid immune genetic design approach is proposed. The initial antibody set was generated as a result of matching with the target design fussy definition. Then the extracted vaccine set was created based on the experts’ feedback and evaluation. During the evolution process,the antibodies convergence was accelerated and the diversity was maintained by the vaccination and affinity-based selection. Also,the fitness function was defined with a back-propagation neural network which maps the semantic space of the shape characteristic design to the semantic space of the emotion. In addition,the vaccination possibilities of vaccines adapt to the effects of vaccination and the affinities and selection possibilities of antibodies were defined according to the information entropy theory. The results of prototype system demonstrated that the present method can efficiently generate and evaluate product shape design scheme.
出处
《机械科学与技术》
CSCD
北大核心
2014年第11期1627-1632,共6页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(51105310)资助
关键词
免疫
遗传算法
反向传播神经网络
形态设计
antibodies
back propagation neural network
backpropagation algorithms
design
feedforward control
genetic algorithms
immunity
immunology
knowledge based systems
neural networks
semantics
shape design
shape optimization
vaccines
