基于均匀设计的BP神经网络在橡胶配方研究中的应用

Application of the backpropagation neural network based on the uniform design in the study of rubber formulation

采用均匀实验设计与神经网络相结合,对氯化聚乙烯橡胶的阻燃性能进行了研究,以较少的实验次数成功地建立了因素一性能之间的定量关系,具有较好的预测性和实用性。

In this paper, the backpropaga the flame-retardant properties of chlorinated the performances and influencing factors are and practicality. tion neura polyethyl 1 network with uniform ene rubber. The quantit design is used to study ative relations between gained in a few trials. The network has good prediction