CN-121993144-A - Drilling speed prediction method, system, equipment and medium

CN121993144ACN 121993144 ACN121993144 ACN 121993144ACN-121993144-A

Abstract

The invention belongs to the technical field of mechanical drilling speed prediction, and provides a drilling speed prediction method, a drilling speed prediction system, electronic equipment and a storage medium. The method comprises the steps of obtaining a logging characteristic data set of at least one adjacent well of a well to be predicted, carrying out geological stratification on the adjacent well by utilizing a clustering algorithm according to the logging characteristic data set to obtain a plurality of candidate geological layers, determining a target geological layer where the well to be predicted is located at the current moment from the candidate geological layers in real time in the drilling process of the well to be predicted, and carrying out real-time prediction on the drilling rate of the target geological layer according to a drilling rate prediction model corresponding to the target geological layer. According to the method, the actual situation of the site is fully considered, so that the prediction result is more fit with the actual construction requirement. And the reliability of the prediction result is ensured through the fusion and verification of various algorithms.

Inventors

CHEN YE
LI WENZHE
WU PENGCHENG
WANG XUDONG
HUANG MEI
YE XIAOKE

Assignees

中国石油天然气股份有限公司

Dates

Publication Date: 20260508
Application Date: 20241105

Claims (10)

1. A method of predicting a rate of penetration, the method comprising: acquiring a logging feature data set of at least one adjacent well of a well to be predicted; according to the logging characteristic data set, carrying out geological stratification on the adjacent wells by using a clustering algorithm to obtain a plurality of candidate geological layers; In the drilling process of the well to be pre-measured, determining a target geological layer of the well to be pre-measured at the current moment from the candidate geological layers in real time; And predicting the drilling speed of the target geological layer in real time according to the drilling speed prediction model corresponding to the target geological layer.
2. The method of predicting according to claim 1, wherein said using a clustering algorithm to geologic stratify said adjacent wells from said log feature dataset to obtain a plurality of candidate geologic layers comprises: The logging characteristic data set comprises a plurality of logging characteristic data samples, and a plurality of core training samples are determined from the logging characteristic data samples; According to a preset threshold value and points, at least the logging characteristic data samples with the points exist in the range of the threshold value; And taking one core training sample as a cluster center of one cluster, and determining edge points corresponding to the cluster center by taking the threshold value as a radius to obtain a plurality of geological feature cluster clusters, wherein one geological feature cluster is one geological layer.
3. The method of predicting as set forth in claim 2, wherein said determining, from among the candidate geologic layers, a target geologic layer in which the well to be predicted is located at a current time, comprises: acquiring the real-time drilling data sample of the well to be pre-measured; and calculating the distance between the real-time drilling data sample and each core training sample through a Euclidean distance formula, determining a candidate geological layer where the well to be predicted is located in real time according to a calculation result, and taking the candidate geological layer as a target geological layer.
4. The method of predicting as set forth in claim 2, wherein said using a clustering algorithm to geologic stratify said adjacent wells to obtain a plurality of candidate geologic layers comprises: Acquiring a logging data set of the adjacent well after data processing; intercepting a training data subset corresponding to the candidate geological layer from the logging data set; and obtaining the drilling rate prediction model corresponding to the candidate geological layer according to the training data subset.
5. The method of claim 4, wherein the log data set of the neighboring wells after data processing comprises: and the data processing is to perform characteristic correlation analysis and characteristic importance analysis on the logging data set and perform dimension reduction processing on the logging data set according to analysis results.
6. The method of claim 5, wherein the log data set of the neighboring wells after data processing comprises: And carrying out normalized cleaning and arrangement on the logging data set.
7. The prediction method according to claim 6, wherein the data processing includes: the logging data set comprises a plurality of logging samples and a plurality of geological features, and a correlation coefficient between any two logging samples is calculated through a correlation function; calculating the contribution degree of each geological feature to the logging data set through a random forest algorithm; And performing dimension reduction processing on the logging data set according to the correlation coefficient between any two logging samples and the contribution degree of each geological feature to the logging data set.
8. The drilling rate prediction system is characterized by comprising a data acquisition module, a geological stratification determination module and a drilling rate prediction module; The data acquisition module is used for acquiring a logging characteristic data set of at least one adjacent well of the well to be predicted; the geological stratification module is used for carrying out geological stratification on the adjacent wells by utilizing a clustering algorithm according to the logging characteristic data set to obtain a plurality of candidate geological layers; The geological layer determining module is used for determining a target geological layer of the well to be predicted at the current moment from the candidate geological layers in real time in the well drilling process of the well to be predicted; and the drilling speed prediction module is used for predicting the drilling speed of the target geological layer in real time according to the drilling speed prediction model corresponding to the target geological layer.
9. An electronic device, comprising: A processor; and a memory storing computer-executable instructions that, when executed, cause the processor to perform the method of any of claims 1-7.
10. A computer storage medium, wherein the computer storage medium stores one or more programs which, when executed by a processor, implement the method of any of claims 1-7.

Description

Drilling speed prediction method, system, equipment and medium Technical Field The invention belongs to the technical field of mechanical drilling speed prediction, and particularly relates to a drilling speed prediction method, a drilling speed prediction system, electronic equipment and a storage medium. Background In the drilling process, the mechanical drilling speed of the well is accurately predicted, so that on one hand, the occurrence of drilling accidents can be monitored and prevented in advance, the drilling risk is reduced, the safety of the well is improved, and on the other hand, a powerful support can be provided for a well drilling optimization method based on real-time prediction, the period of the well drilling is reduced, and the cost is reduced. CN111434886B discloses a mechanical drilling speed calculation method and device for a drilling process, and provides a mechanical drilling speed calculation method for the drilling process, wherein the method comprises the steps of determining lithology information of a stratum corresponding to a well section to be measured of a target well, calculating the mechanical drilling speed of the well section to be measured according to a constructed mechanical drilling speed prediction model to obtain a predicted drilling speed value, carrying out rationality judgment on the predicted drilling speed value according to block drilling speed information of a block to which the target well belongs and adjacent well drilling speed information of an adjacent well of the target well, adjusting influence parameters influencing the mechanical drilling speed in the mechanical drilling speed prediction model based on a judgment result of rationality judgment, and obtaining the mechanical drilling speed value of the well section to be measured according to the adjusted mechanical drilling speed prediction model. However, the method has strong data dependence, the model method is highly dependent on the drilling speed information of the oil field block database and the adjacent wells of the target well, and a plurality of calculation steps and data processing processes are involved, so that the calculation process is relatively complex and time-consuming. Disclosure of Invention In order to solve the problems, the invention provides a drilling rate prediction method, a system, electronic equipment and a storage medium, wherein geological layers are clustered, and prediction methods are not used for different geological layers correspondingly, so that the accuracy of drilling rate prediction is improved. In order to solve the above technical problem, a first aspect of the present invention provides a drilling rate prediction method, which includes: acquiring a logging feature data set of at least one adjacent well of a well to be predicted; according to the logging characteristic data set, carrying out geological stratification on the adjacent wells by using a clustering algorithm to obtain a plurality of candidate geological layers; In the drilling process of the well to be pre-measured, determining a target geological layer of the well to be pre-measured at the current moment from the candidate geological layers in real time; And predicting the drilling speed of the target geological layer in real time according to the drilling speed prediction model corresponding to the target geological layer. According to a preferred embodiment of the present invention, the geological stratification of the neighboring wells according to the logging feature data set by using a clustering algorithm, to obtain a plurality of candidate geological layers, includes: The logging characteristic data set comprises a plurality of logging characteristic data samples, and a plurality of core training samples are determined from the logging characteristic data samples; According to a preset threshold value and points, at least the logging characteristic data samples with the points exist in the range of the threshold value; And taking one core training sample as a cluster center of one cluster, and determining edge points corresponding to the cluster center by taking the threshold value as a radius to obtain a plurality of geological feature cluster clusters, wherein one geological feature cluster is one geological layer. According to a preferred embodiment of the present invention, the determining, from the candidate geological layers, a target geological layer in which the well to be predicted is located at the current time includes: acquiring the real-time drilling data sample of the well to be pre-measured; and calculating the distance between the real-time drilling data sample and each core training sample through a Euclidean distance formula, determining a candidate geological layer where the well to be predicted is located in real time according to a calculation result, and taking the candidate geological layer as a target geological layer. According to a preferred embodiment of the