人工神经网络在EPDM硫化胶性能预测中的应用

Application of MATLAB Artificial Neural Network in Forecast of EPDM Vulcanizates' Properties

该文将人工神经网络方法应用于EPDM硫化胶的性能预测 ,用按回归通用旋转组合设计方法设计的EPDM硫化胶 2 0次性能试验数据作为人工神经网络的样本数据 ,利用MATLAB 6 5软件包中的神经网络工具箱 ,构造BP神经网络 ,优选最佳的神经网络参数 ,通过训练后 ,用于预测EPDM硫化胶的氧指数、扯断强度和伸长率性能。结果表明 ,训练好的神经网络可准确地预测EPDM硫化胶的有关性能 ,基于MATLAB 6 5的人工神经网络是分析EPDM配方各组分对硫化胶性能影响的一种快捷、可靠的新方法。

In this paper, artificial neural network (ANN) was applied to forecast the properties of EPDM vulcanizates. Twenty groups of sample data were applied to train the ANN by neural network tool of MATLAB 6.5. Back-Propagation (BP) neural network was established and the optimum parameters of ANN were chosen. The properties of EPDM vulcanizates were forecasted by the trained ANN. The results show that the trained ANN can exactly forecast the properties of oxygen indexes, tearing strength and elongation. ANN based on MATLAB 6.5 also offers an efficient and credible method for analyzing the effect of vulcanizates' components.