机构地区: 广东工业大学材料与能源学院
出 处: 《塑料》 2002年第2期16-20,共5页
摘 要: 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.
关 键 词: 人工神经网络 模型 聚乙烯 共混物 机械性能 预测 软件
领 域: [化学工程] [自动化与计算机技术] [自动化与计算机技术]