Structural Model Correction Methods of Jacket Offshore Platform Based on Random Forest
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.
万方数据
维普
