塑料熔体黏度的神经网络拟合

Neural Networks-based Fitting of Viscosity of Plastics Melt

阐述了塑料熔体黏度在注射成型CAE软件中的重要意义及其实验方法。针对传统经验公式拟合法的不足,采用BP神经网络来拟合黏度与温度、剪切速率的定量关系,并将拟合的效果同公式拟合法进行了比较,显示了神经网络拟合方法的可行性和优越性。

It Introduced the significance and of the viscosity of plastics melt In injection molding CAE software, as well as its experiment methods. In view of the shortcomings of the fitting method of traditional empirical formula, it employed the BP neural network to fit the quantitative relationships between the viscosity and temperature and shear rate, and compared the fitting result with that of traditional formula method. It demonstrated the feasibility and superiority of neural networks-based fitting method.