Wellhead fatigue damage estimation using probabilistic generative ai models
AssigneeChevron U.S.A. Inc.
InventorsShuxing Cheng, Wangming Lu
Life of this patent
Estimating the term…
Abstract
Different probabilistic generative AI models are used to estimate wellhead fatigue damage. A load probabilistic generative AI model is used to determine the load for the wellhead based on the design of the wellhead and the metocean conditions for the wellhead in conjunction with the riser and facility information. A stress probabilistic generative AI model is used to determine the stress on the wellhead based on the design of the wellhead and the load for the wellhead. The fatigue damage on the wellhead is determined based on the stress on the wellhead and fatigue resistance parameters of the wellhead materials. The fatigue damage on the wellhead is used to make operational decisions for the wellhead.
Claims20
A system for estimating wellhead fatigue damage using probabilistic generative AI models, the system comprising:
- one or more physical processors configured by machine-readable instructions to:
- obtain wellhead design information, the wellhead design information defining a design of a wellhead;
- obtain metocean information, the metocean information characterizing metocean conditions for the wellhead;
- determine, via a load probabilistic generative AI model, load for the wellhead based on the design of the wellhead and the metocean conditions for the wellhead, wherein the load probabilistic generative AI model serves as a surrogate for simulation of fluid-structure interaction dynamics for the wellhead;
- determine, via a stress probabilistic generative AI model, stress on the wellhead based on the design of the wellhead and the load for the wellhead, wherein the stress probabilistic generative AI model serves as a surrogate for finite element analysis for the wellhead;
- determine fatigue damage for the wellhead based on the stress on the wellhead;
- and
- facilitate one or more operations for the wellhead based on the fatigue damage for the wellhead.
A method for estimating wellhead fatigue damage using probabilistic generative AI models, the method comprising:
- obtaining wellhead design information, the wellhead design information defining a design of a wellhead;
- obtaining metocean information, the metocean information characterizing metocean conditions for the wellhead;
- determining, via a load probabilistic generative AI model, load for the wellhead based on the design of the wellhead and the metocean conditions for the wellhead, wherein the load probabilistic generative AI model serves as a surrogate for simulation of fluid-structure interaction dynamics for the wellhead;
- determining, via a stress probabilistic generative AI model, stress on the wellhead based on the design of the wellhead and the load for the wellhead, wherein the stress probabilistic generative AI model serves as a surrogate for finite element analysis for the wellhead;
- determining fatigue damage for the wellhead based on the stress on the wellhead;
- and
- facilitating one or more operations for the wellhead based on the fatigue damage for the wellhead.
Dependencies are inferred from the claim text.