Jacket platform structure response computing method based on BP neural network

Abstract

The invention relates to the technical field of structure design of ocean platforms, and specifically discloses a jacket platform structure response computing method based on a BP neural network. The computing method comprises the following steps: step one, establishing a BP neural network system, wherein the BP neural network system comprises an input layer, a hidden layer and an output layer, the input layer and the hidden layer are interconnected as the first stage of the jacket platform stress, and the hidden layer and the output layer are interconnected as the second stage of the jacket platform stress; step two, training the BP neural network system; step three, applying the BP neural network system, and inputting any wind, wave and stream environment load combined numerical value into the BP neural network system as an input vector to obtain the corresponding platform structure response. An artificial neural network system established by the invention is applied to compute the structure response of the jacket platform, the structure response quite close to numerical simulation can be immediately obtained by inputting any environment load combination into a neural network system, and the operation is accurate and fast.

Description

technical field [0001] The invention relates to the technical field of structural design of offshore platforms, in particular to a structural response calculation method for such offshore platforms as jacket platforms. Background technique [0002] Offshore platforms are large offshore engineering structures used for offshore oil and gas production and operations. The structure of the offshore platform is complex, bulky, and expensive, and its service environment is very complex and harsh. It is not only affected by the combined effects of wind, waves, currents, and ice, but also threatened by extreme loads such as earthquakes. Once an accident occurs, the resulting The economic and environmental harm is very huge. [0003] In the structural design of offshore platforms and related reliability analysis, a large number of environmental load simulation calculations such as wind, wave and current are required to obtain the structural response of the platform. Although there a...

AI Technical Summary

Problems solved by technology

[0005] (1) 3D modeling of large and complex marine structures such as offshore platforms is very complicated and has the disadvantage of difficult modeling;

[0006] (2) The operation of large-scale finite element software has high requirements on computer hardware. At the same time, the cost of purchasing professional finite element software is high and requires systematic training to master how to operate

For the same structure, using different cell types and meshing methods, the calculation results obtained may be very different. Improper operations may lead to non-convergence of calculations and run failures. The early debugging of the program is very cumbersome. Relevant personnel Requires fairly systematic and comprehensive finite element and software operation knowledge to complete relevant calculations, which has the disadvantage of high technical threshold;

[0007] (3) The finite element algorithm is an iterative algorithm. For large-scale structures, even if the advanced finite element division method is used, the amount of calculation required in a single iteration is very large. Although this technical method can obtain a more accurate structural response, but It has the disadvantages of slow calculation speed and low efficiency;

However, due to the complex nonlinear structure of the offshore platform itself, the structural response obtained by using this technology has a large error with the real situation. Generally, the relative error can be controlled at 30%, which is an ideal result, and it cannot be widely used in practice.

Images