ANN技术在复合材料胶接修理分析中的应用

基于改进的BP人工神经网络(ANN)建立了复合材料胶接修理分析模型,结合采用复合材料胶接修理的正交试验及有限元分析的结果为训练和检测神经网络提供样本,有效地利用了神经网络、试验设计技术与有限元分析的优点。胶接修理实例分析结果表明,所建神经网络模型对胶接参数与修理效果之间关系的预测与试验结果一致,说明将人工神经网络应用于复合材料胶接修理参数分析是一种行之有效的方法。

Application of Artificial Neutral Network to Bonding Repair Analysis of Composite Structure

To assist the parameter selection in bonding repair of composite laminates,an analytic model based on back-propagation Artificial Neural Network(ANN) was established in this paper.The data of experiment and the finite element were used to get the training and testing set for Back-Propagation neural network prediction model.The advantages of artificial neural network,experimental design technique and finite element method were exploited.The Back-Propagation neural network was used to set up a prediction mode...