Oil reservoir injection and production parameter multi-objective optimization method based on a support vector machine agent model

Abstract

The invention belongs to the technical field of oil reservoir model simulation production, and particularly relates to an oil reservoir injection-production parameter multi-objective optimization method based on a support vector machine agent model, which comprises the following steps: generating a certain number of injection-production schemes as samples through numerical simulation software; inputting the sample into a least square support vector machine to form an alternative model, and optimizing by adopting a particle swarm optimization algorithm to achieve convergence if the condition ofnon-convergence occurs in the process; after an initial injection-production parameter population with the size of M is generated based on a least square support vector machine, selecting an appropriate objective function, a parto level and a crowding distance and then adopting a non-dominated sorting multi-objective optimization genetic algorithm NSGA-with an elitist strategy; optimizing the injection and production parameters with a multi-target optimization genetic algorithm NSGA-II to obtain a pareto solution set; and according to the demand of the objective function, finding out the optimal oil reservoir injection-production parameter in the pareto solution set. In the application of the method for realizing the multi-objective optimization design of the oil reservoir injection and production parameters, the prediction precision of the agent model is ensured, and meanwhile, the efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of oil reservoir model simulation production, and in particular relates to a multi-objective optimization method for oil reservoir injection-production parameters based on a substitute model. Background technique [0002] Reservoir waterflooding, as an important method of enhancing oil recovery, has been widely used in most oilfields in the world. Selecting appropriate injection-production parameters is very important for efficient reservoir development. [0003] The existing commonly used injection-production parameter optimization method is to use numerical simulation technology or orthogonal design experiment method to study the parameters to meet the specific development requirements through numerical simulation technology or numerical simulation plus optimization algorithm. In the process of parameter optimization, the steps are cumbersome, more data are required, and a lot of time is needed. At the sam...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned problem of difficult selection of suitable injection-production parameters in the production process of water flooding reservoirs, the present invention provides a multi-objective optimization method for reservoir injection-production parameters based on a support vector machine proxy model, expecting to follow the target in the shortest time The requirements of the function to find the optimal solution

Images