基于动力有限元分析和神经网络技术的含分层复合材料层合板的损伤诊断  

DELAMINATION DETECTION IN COMPOSITE LAMINATES USING DYNAMIC FINITE ELEMENT ANALYSIS AND NEURAL NETWORKS

作　　者：庄小燕[1] 陈浩然[1] 

机构地区：[1]大连理工大学工业装备结构分析国家重点实验室,大连116024

出　　处：《玻璃钢／复合材料》2004年第5期3-6,共4页Fiber Reinforced Plastics/Composites

基　　金：国家自然科学基金项目 (1 0 2 72 0 2 5)

摘　　要：本文基于作者提出的含层间分层损伤层合板的动力有限元分析模型和方法 ,计算了分层长度和位置对含层间分层损伤层合板结构的固有频率的影响 ,然后应用MATLAB的神经网络工具箱建立了人工神经网络 ,通过典型结构的仿真结果比较 ,证明了采用有限元动力分析和BP网络技术相结合的方法是一种可用于复合材料层合板的分层损伤诊断的有效方法。A strategy for detecting delamination of composite laminates is proposed in this paper, which is based on the dynamic finite element method in conjunction of neural networks scheme. Firstly the influences of the length and location of delamination upon the natural frequency of the composite laminates are calculated by a nonlinear dynamic finite element method for the delaminated composite laminates developed by authors. Then,the back propagation (BP) neural network in the Toolbox of MATLAB software is established for training and testing the network. From the simulating results it can be shown that the present strategy is efficient for detecting delamination of the composite laminates.

关 键 词：动力有限元分析 神经网络 复合材料层合板 损伤诊断 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置] TQ327[自动化与计算机技术—控制科学与工程]