Oil reservoir production prediction method based on graph wavelet neural network model

Abstract

The invention discloses an oil reservoir production prediction method based on a graph wavelet neural network model, and belongs to the technical field of oil reservoir development, and the method comprises the following steps: collecting oil reservoir data, generating different oil reservoir production systems, calculating the yield of each production well under different production systems by using a numerical simulator, and constructing a sample library. Dividing a training set and a test set; constructing a graph wavelet neural network model; performing hyper-parameter optimization of the graph wavelet neural network model, and training the constructed graph wavelet neural network model; verifying the performance of the trained graph wavelet neural network model; and outputting the trained graph wavelet neural network model with good evaluation performance, collecting oil reservoir production data in real time through monitoring equipment arranged in an oil field block, inputting the data into the model, and predicting the oil reservoir yield change in real time. According to the method, the oil and water production condition of the production well in oil reservoir production can be predicted with similar precision and greatly improved speed.

Description

technical field [0001] The invention belongs to the technical field of oil reservoir development, and in particular relates to an oil reservoir production prediction method based on a graph wavelet neural network model. Background technique [0002] Reservoir production prediction is the process of using known reservoir information and historical data to predict reservoir production for different development scenarios. Reservoir production prediction is the basis and basis for the design and adjustment of development plans, and is of great significance to the scientific arrangement, deployment and selection of various measures, and to ensure the realization of planned goals. There are two traditional reservoir production prediction methods, reservoir engineering method and numerical simulation method. Reservoir engineering methods form empirical formulas or charts based on existing data and data to guide the production and development of reservoir blocks, such as production...

AI Technical Summary

Problems solved by technology

[0004] In view of the lack of interpretability of existing reservoir production prediction proxy models and the lack of information exchange between samples, and the shortcomings of traditional reservoir engineering methods that are highly restrictive, reservoir numerical simulation calculations involve many grids, a large amount of calculation, and time-consuming , the present invention proposes a reservoir production prediction method based on the graph wavelet neural network model, which can improve the performance of existing proxy models, effectively improve the calculation speed in the reservoir production prediction task, and save calculation time

Images