VIBRATION MEASUREMENT AND LOAD IDENTIFICATION OF OFFSHORE PLATFORMS

摘要

The vibration measurement and load identification of offshore platforms were performed in this paper, where the neural network is introduced in order to overcome the disadvantages of the commonly used method. The first step is to establish a finite element model of the platform using ANSYS software. The training data of neural network is obtained by applying simulation to get response at the identification point of the model. The neural network model of the platform is then set up. The network is trained until the convergence state by using the above data. Finally, the vibration load identification for W12-1 oil production platform is performed using the method, where the measured response data are inputted to the trained network and the identification loads of the platform are obtained. The results indicate that there are more advantages of the method as compared with commonly used load identification method when used for such large and complex structures as offshore platforms and the identification accuracy of the method is satisfactory.