用人工神经网络预测聚乙烯及其共混物机械性能

Analysis and Prediction of Mechanical Properties of Polyethylene and Its Blends by Artificial Neural Networks

人工神经网络专家系统具有学习、记忆和泛化推广功能。MATLAB软件可根据用户的要求自动生成人工神经网络程序。本文应用BP模型人工神经网络对聚乙烯及其共混物的机械性能进行预测研究。结果表明 ,所建立的网络程序具有高速、容错和自适应等特点 ,在本领域的应用性能良好 ,预测准确率较高 。

Artificial neural networks (ANN),as high synthetic subjects,have parallel architecture and ability of parallel processing.The networks also have the abilities of learning,memorizing and generalizing.MATLAB software platform can organize the artificial neural network programme according to user's desires.An error back propagation neural network was constructed on the MATLAB platform to predict the mechanical properties of polyethylene (PE) and its blends.The results showed that the network had high processing speed,the abilities of error correcting and self organizing.The network had favorable performance in this field.