海洋平台结构损伤识别与定位新方法及试验验证  

Model test studies on the new method of offshore platform damage identification and localization

作　　者：嵇春艳[1] 陈明璐[1] 元志明[1] 张健[1] 

机构地区：[1]江苏科技大学船舶与海洋工程学院,江苏镇江212003

出　　处：《海洋工程》2010年第4期9-17,共9页The Ocean Engineering

基　　金：国家自然科学基金资助项目(50609009);江苏省船舶先进设计制造技术重点实验室项目(GJ0807)

摘　　要：基于小波变换的时频局域化特性和BP神经网络的非线性映射特性,结合两者优点提出了基于小波包分析和神经网络方法的海洋平台三步法损伤定位方法。对海洋平台结构加速度响应信号进行小波包分析,提取小波包特征向量,将小波包结点能量变化量指标作为BP网络的输入向量,逐步确定损伤位置。设计一典型导管架式海洋平台试验模型,分别进行岸上脉冲激励及水池中波浪激励下平台结构损伤识别与定位模型试验,对该方法的可行性和适用性进行了验证。Based on the advantages of the good time-frequency characteristics of wavelet transform and the excellent property of nonlinear mapping of neural network,a three-step damage localization method based on wavelet packet analysis and neural network of offshore platforms is developed.The acceleration response of the offshore platform is analyzed with wavelet packet.The signal feature vectors are extracted based on energy parameters of wavelet packet transform.Damage location can be determined by taking the variation of energy parameters as the BP network input vector.Finally,an experimental model of typical offshore platform is designed to carry out the model test of damage identification and localization under the pulse excitation ashore and wave excitation in the pool respectively.Thus,the feasibility and applicability of the proposed method in this paper are validated by the model test results.

关 键 词：海洋平台 神经网络 损伤定位 模型试验 

分 类 号：P751[交通运输工程—港口、海岸及近海工程]