机构地区: 厦门理工学院
出 处: 《嘉应学院学报》 2010年第11期46-48,共3页
摘 要: 提出了基于人工神经网络的复合材料覆盖件电厚度设计模型和设计方法。影响复合材料覆盖件电厚度的多因素性使其很难得到精确的解析解。应用人工神经网络方法结合实验实测数据,模拟覆盖件各项参数与电厚度之间的非线性关系,以玻璃钢材料为例,对相近使用条件下的覆盖件电厚度进行设计,计算结果表明该方法计算速度快,精度高,为复合材料电厚度的设计分析提供了一种新方法。 The objective of the research is to setup electrical thickness designing model and method of composite based on artificial neural network.It is very difficult to find an accurate resolution of composite electrical thickness for various causations.BP neural network is chosen to simulate the nonlinear relationship between electrical thickness and the causations.Experimental data are applied to train network as samples.Finally,the trained network is put to predict electrical thickness of composite shell.Electrical thickness of same material at similar conditions could be yielded from the outputs of BP.The prediction results show that this method is an accurate way with a reasonable computational cost.