基于随机森林的导管架海洋平台结构模型修正方法

Structural Model Correction Methods of Jacket Offshore Platform Based on Random Forest

提出一种基于随机森林的有限元模型修正方法,能够快速、准确地给出导管架海洋平台结构模型的修正参数。选定平台不同的设计参数,对设计参数和基频进行Pearson相关性分析,得到与基频相关系数较大的参数,并重新设计试验参数获得基频。通过随机森林网络增加两者之间的非线性差异,验证网络精度及其泛化能力。结合实测数据,对比分析有限元模型的修正的效果。结果表明:模型的回归分数可达0.998,修正后的有限元模型可更准确地反映真实平台的动力特性。

A finite element model correction method based on random forest is proposed,which can give the model correction parameters of the jacket offshore platform quickly and accurately.Different design parameters of the platform are selected,and the Pearson correlation analysis on the design parameters and the corresponding fundamental frequencies is performed to get the parameters with large correlation coefficient with the fundamental frequencies.The test parameters are redesigned to obtain the fundamental frequency.The random forest network is used to increase the nonlinear difference between the two to verify the accuracy and generalization ability of the network.Combined with the measured data,the modification effect of the finite element model is compared and analyzed.The results show that the regression fraction of the model can reach 0.998,and the modified finite element model can more accurately reflect the dynamic characteristics of the real platform.