Local well pattern water injection development optimization method based on graph neural network

Abstract

The invention discloses a local well pattern water injection development optimization method based on a graph neural network. The method specifically comprises the steps as follows: (1) obtaining geometrical information of a local target well pattern, and constructing a graph neural network structure of an injection-production well pattern according to the topological structure characteristics ofa water injection well and an oil production well; (2) acquiring historical production data of a target well pattern; (3) training the graph neural network structure in the step (1) by utilizing the historical production data in the step (2), and establishing a graph neural network model; and (4) performing sensitivity analysis on the parameters of the injection-production well pattern by utilizing the graph neural network model to obtain sensitivity factors in the injection-production well pattern. According to the method, the basis for adjusting the water injection amount is provided for water injection development, the oil production amount is predicted, meanwhile, the importance of different wells and different static parameters in each well pattern is given, and main influence wells and secondary influence well points are distinguished when the water injection amount is adjusted.

Description

technical field [0001] The invention relates to the technical field of oil and gas exploration and development, in particular to a graph neural network-based optimization method for local well pattern water injection development. Background technique [0002] Injecting water into the reservoir can effectively maintain the pressure of the reservoir, increase the oil recovery rate and recovery rate of the reservoir, and is an important means of oil and gas exploration and development. The prediction of oil well production change law in the process of water flooding development is the core content of reservoir engineering research, and it is also an important basis for formulating and adjusting development plans. [0003] However, in the face of complex geological conditions such as medium-high permeability reservoirs with severe planar heterogeneity and low-permeability fractured reservoirs, it is difficult to expand the swept volume due to fast water breakthrough in high-perm...

AI Technical Summary

Problems solved by technology

[0003] However, in the face of complex geological conditions such as medium-high permeability reservoirs with severe planar heterogeneity and low-permeability fractured reservoirs, it is difficult to expand the swept volume due to fast ...

Images