基于神经网络的注塑制品材料选择方法

分析了注塑制品的功能要求与注塑材料性能之间的相互关系,提出了一种基于BP神经网络的注塑材料选择方法,采用模糊数学方法表示对材料的选定度.通过训练样本使神经网络学习选材知识,利用测试样本对网络的性能进行验证.结果表明,此网络可以较好地解决注塑材料的选择问题,并且具有可扩展性, 新材料可以方便地添加到选材网络中.

A neural network approach to material selection for injection molded parts

A BP neural network based plastic material selection methodology is developed by analyzing the relationship between performance requirements of injection molded part and properties of plastic material, and then the selection of the material is represented by a fuzzy mathematics method. The neural network was trained with material selection knowledge. Testing sample sets and injection molded parts were used to check the performance of the neural network. The results show that the neural network approach can be used efficiently for material selection for injection molded parts, the network has a good extensibility, and new materials can be easily added into it.