CN-121982158-A - Lithofacies plane distribution diagram drawing method, system, electronic equipment and storage medium

CN121982158ACN 121982158 ACN121982158 ACN 121982158ACN-121982158-A

Abstract

The invention relates to the technical field of stratum exploration and development and data processing visualization, and provides a diagenetic phase plane distribution diagram drawing method, a diagenetic phase plane distribution diagram drawing system, electronic equipment and a storage medium, wherein the method comprises reconstructing a well information data matrix based on longitude and latitude coordinates of a regional range; the method comprises the steps of constructing a regional lithofacies prediction matrix based on longitude and latitude coordinates of data points, updating the data points in the regional lithofacies prediction matrix based on a reconstructed well information data matrix, determining an unknown data point information list in the updated regional lithofacies prediction matrix based on a delineating radius, calculating the weight of each lithofacies type label in the unknown data point information list, assigning the maximum weight lithofacies type label to the unknown data points, and drawing a lithofacies plane distribution diagram based on the lithofacies type labels corresponding to the data points in the regional lithofacies prediction matrix. And drawing a diagenetic plane distribution map based on diagenetic type labels of unknown data points in the prediction area based on a multi-well diagenetic phase identification result, namely the diagenetic type labels.

Inventors

MAO ZHIGUO
Chen Lumeng
Zou Tianbo
ZHANG LIYING
SHI BINGBO
LI YUKUN
JIANG LIN
ZHANG ZHONGYI
DAN WEIDONG
HE JINGYU
LI JIHONG

Assignees

中国石油天然气股份有限公司

Dates

Publication Date: 20260505
Application Date: 20241029

Claims (10)

1. A diagenetic phase plane distribution diagram drawing method is characterized in that, The method may include the steps of, Establishing a well information data matrix based on a plurality of single well information, wherein the single well information comprises single well coordinates and diagenetic type labels corresponding to single wells; Defining a defined radius, longitude and latitude coordinates of a region range and longitude and latitude coordinates of data points, reconstructing a well information data matrix based on the longitude and latitude coordinates of the region range, and constructing a region diagenetic prediction matrix based on the longitude and latitude coordinates of the data points; Updating data points in the regional diagenetic phase prediction matrix based on the reconstructed well information data matrix to obtain an updated regional diagenetic phase prediction matrix, wherein data points which are not updated in the regional diagenetic phase prediction matrix become unknown data points, and the updated data points become known data points; Calculating the weight of each diagenetic type label in the unknown data point information list, and assigning the diagenetic type label with the maximum weight to the unknown data point to obtain a final regional diagenetic phase prediction matrix; and drawing a diagenetic plane distribution map based on diagenetic type labels corresponding to the data points in the final regional diagenetic prediction matrix.
2. The method of claim 1, wherein determining the list of unknown data point information in the updated regional diagenetic phase prediction matrix based on the delineating radius comprises: searching known data points with the distance from the known data points being smaller than or equal to the radius of the delineation; and taking the searched known data points as an unknown data point information list in the updated regional diagenetic phase prediction matrix.
3. The method of claim 2, wherein defining the number of coiled wells, and wherein calculating each diagenetic type tag weight in the list of unknown data point information comprises: When the number of known data points meeting near well conditions in the unknown data point information list is larger than or equal to the delineating number, determining that the unknown data points belong to a dense logging zone, and calculating the weight of each diagenetic type label in the unknown data point information list by adopting an inverse radial basis function interpolation method, wherein the near well conditions are that the distance between the known data points and the unknown data points is smaller than or equal to a near well radius, the near well radius is a near well coefficient multiplied by the delineating radius, and the near well coefficient is smaller than 1.
4. The method of claim 2 or 3, wherein defining the number of well-defined circles, calculating each diagenetic type tag weight in the list of unknown data point information, comprises: determining that the unknown data point belongs to a sparse logging zone when the number of known data points meeting the near-well condition in the unknown data point information list is smaller than the number of the delineating wells and the number of known data points in the unknown data point information list is larger than the number of the delineating wells; and calculating the weight of each diagenetic phase type label in the unknown data point information list by adopting an inverse distance weight weighted interpolation method.
5. The method of claim 4, wherein after determining that the unknown data point belongs to a sparse logging zone, the method further comprises: Judging whether the number of the known data points in the unknown data point information list is larger than the number of the delineating wells or not; The step of calculating the weight of each diagenetic phase type label in the unknown data point information list by adopting an inverse distance weight weighted interpolation method specifically comprises the following steps: when the number of known data points in the unknown data point information list is larger than the number of the delineating wells, calculating the weight of each diagenetic type label in the unknown data point information list by adopting an inverse distance weight weighted interpolation method; when the number of the known data points in the unknown data point information list is smaller than the number of the delineating wells, calculating the weight of each diagenetic phase type label of the known data points meeting the near-well condition in the unknown data point information list by adopting an inverse distance weight weighted interpolation method.
6. A diagenetic phase plane distribution diagram drawing system based on multi-well identification is characterized in that, The system comprises a well information data matrix building unit, a prediction matrix updating unit, a prediction matrix determining unit and a drawing unit, wherein: The system comprises a well information data matrix establishing unit, a well information data matrix establishing unit and a well information processing unit, wherein the well information data matrix establishing unit is used for establishing a well information data matrix based on a plurality of single well information, and the single well information comprises single well coordinates and diagenetic type labels corresponding to single wells; the prediction matrix construction unit is used for defining a radius, longitude and latitude coordinates of a regional range and longitude and latitude coordinates of data points, reconstructing a well information data matrix based on the longitude and latitude coordinates of the regional range, and constructing a regional diagenetic facies prediction matrix based on the longitude and latitude coordinates of the data points; The prediction matrix updating unit is used for updating data points in the regional diagenetic phase prediction matrix based on the reconstructed well information data matrix to obtain an updated regional diagenetic phase prediction matrix, wherein data points which are not updated in the regional diagenetic phase prediction matrix become unknown data points, and the updated data points become known data points; The prediction matrix determining unit is used for determining an unknown data point information list in the updated regional diagenetic facies prediction matrix based on the delineating radius, calculating the weight of each diagenetic facies type label in the unknown data point information list, and assigning the maximum weight diagenetic facies type label to the unknown data point to obtain a final regional diagenetic facies prediction matrix; and the drawing unit is used for drawing a rock phase plane distribution diagram based on the diagenetic type label corresponding to the data point in the final regional diagenetic prediction matrix.
7. The system according to claim 6, wherein the prediction matrix determining unit is specifically configured to search for known data points with a distance from the unknown data point being equal to or smaller than a radius of the delineation from the known data points, and take the searched known data points as the unknown data point information list in the updated regional diagenetic facies prediction matrix.
8. The system of claim 7, wherein the prediction matrix construction unit is configured to define a number of wells to be defined; The prediction matrix determining unit is specifically configured to determine that the unknown data point belongs to a dense logging zone when the number of known data points satisfying a near-well condition in the unknown data point information list is greater than or equal to a delineating number, and calculate each diagenetic type tag weight in the unknown data point information list by adopting an inverse radial basis function interpolation method, where the near-well condition is that a distance between the known data point and the unknown data point is less than or equal to a near-well radius, the near-well radius is a near-well coefficient multiplied by the delineating radius, and the near-well coefficient is less than 1.
9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; a memory for storing a computer program; A processor for carrying out the method steps of any one of claims 1-5 when executing a program stored on a memory.
10. A computer storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-5.

Description

Lithofacies plane distribution diagram drawing method, system, electronic equipment and storage medium Technical Field The disclosure belongs to the technical field of stratum exploration and development and data processing visualization, and particularly relates to a diagenetic phase plane distribution diagram drawing method, a diagenetic phase plane distribution diagram drawing system, electronic equipment and a storage medium. Background In the field of geological exploration and in the field of earth science, understanding the lithology distribution of the subsurface has been one of the important problems in geology. Logging is an important means for obtaining physical parameters of reservoirs, and finding and evaluating oil and gas reservoirs and predicting oil and gas reserves. With the continuous iteration of machine learning techniques, techniques for predicting lithofacies from single well log data have been perfected. The lithofacies types of multiple wells within a block may be predicted by machine learning methods, but methods for drawing a block lithofacies plane map using the multiple well recognition results are lacking. At present, machine learning has made remarkable progress in the aspects of complex lithology lithofacies fine division, fluid identification, crack identification and classification, reservoir classification, logging curve reconstruction, reservoir parameter prediction, imaging logging image processing, reservoir micro-pore structure logging intelligent characterization and the like. For example, machine learning based tight sandstone reservoir facies prediction methods have been capable of automatically classifying and predicting tight sandstone reservoir facies types through unsupervised and supervised machine learning models. In addition, scholars have also explored how to improve the performance of machine learning models by optimizing feature selection, especially in the case of processing sparse logging data. The lithofacies plane distribution map is usually drawn by adopting a junction graph method, a diagenetic coefficient contour line method and the like. Patent CN118114542a discloses a lithofacies plane distribution map drawing method based on single well TOC and brittle mineral content estimation, the accuracy of the method may be affected by the rock type and TOC and mineral content actual characteristics of the research area, the requirement on the accuracy of logging data is higher, and the method still is a method for lithofacies plane division by using logging data. Therefore, the prior art lacks a drawing method for drawing a lithofacies plane distribution map based on the diagenetic identification results of multiple wells. Disclosure of Invention In order to solve the problems, the invention discloses a diagenetic phase plane distribution diagram drawing method, a diagenetic phase plane distribution diagram drawing system, electronic equipment and a storage medium. The invention is realized by the following technical scheme: establishing a well information data matrix based on a plurality of single well information, wherein the single well information comprises single well coordinates and diagenetic type labels corresponding to single wells; Defining a defined radius, longitude and latitude coordinates of a region range and longitude and latitude coordinates of data points, reconstructing a well information data matrix based on the longitude and latitude coordinates of the region range, and constructing a region diagenetic prediction matrix based on the longitude and latitude coordinates of the data points; Updating data points in the regional diagenetic phase prediction matrix based on the reconstructed well information data matrix to obtain an updated regional diagenetic phase prediction matrix, wherein data points which are not updated in the regional diagenetic phase prediction matrix become unknown data points, and the updated data points become known data points; Calculating the weight of each diagenetic type label in the unknown data point information list, and assigning the diagenetic type label with the maximum weight to the unknown data point to obtain a final regional diagenetic phase prediction matrix; and drawing a diagenetic plane distribution map based on diagenetic type labels corresponding to the data points in the final regional diagenetic prediction matrix. Further, the method comprises the steps of, The determining the unknown data point information list in the updated regional diagenetic phase prediction matrix based on the delineating radius comprises the following steps: searching known data points with the distance from the known data points being smaller than or equal to the radius of the delineation; and taking the searched known data points as an unknown data point information list in the updated regional diagenetic phase prediction matrix. Further, the method comprises the steps of, Defining a circle number of wells, and calcula