A drilling operation cycle prediction method based on random forest regression model

Abstract

The present invention discloses a drilling cycle prediction method based on a random forest regression model, which relates to the field of drilling data processing technology and includes the following steps: S1, collecting and screening drilling data to obtain standard drilling data; S2, classifying and processing the standard drilling data to obtain classification results; S3, obtaining a random forest-based regression result based on the classification results, and using the regression result to predict the drilling cycle. The present invention can meet pre-drilling prediction and real-time parameter adjustment requirements as needed, continuously supplementing training samples to optimize the model, and can improve the model's adaptability to the operational characteristics of the study area. The random forest regression prediction model is of great significance for subsequent drilling plan planning and cost assessment, and has good promotion value.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling data processing, and in particular to a drilling operation cycle prediction method based on a random forest regression model. Background Art

[0002] Oil and gas drilling, a large-scale, high-investment, and extremely risky production activity, plays a crucial role in energy exploration and development. The entire drilling process involves multiple steps, including pre-drill preparation, drilling tool assembly, drilling operations, and cementing. This requires significant human, material, and financial resources, while also facing numerous uncertainties. An accurate drilling cycle forecast is crucial for ensuring that overall oil and gas field exploration and development goals are achieved on schedule, and also facilitates the rational planning and scheduling of subsequent work.

[0003] With the continuous advancement of technology, technologies such as machine learning and neural networks have made great progress in the fields of drilling machinery drilling speed prediction, well condition identification and time analysis. Their application also shows potential in drilling cycle prediction. At present, the drilling cycle prediction model focuses more on the overall operation process, pays less attention to the characteristics and connections of the well sections, and does not adequately consider actual operation parameters such as formation level, lithology and drilling fluid, resulting in limited model adaptability. The prediction of the drilling operation cycle should integrate more actual data, deeply explore the relationship between well sections, geological conditions and uncertain factors, and build a model with adaptability and updatability. Machine learning and neural networks are effective means of drilling cycle prediction. They can effectively deal with the multi-dimensional data generated during the drilling operation process, are good at capturing complex nonlinear relationships between data, and the model has adaptability, updatability and excellent generalization ability. Therefore, the present invention proposes a machine learning model method based on random forest to describe the timeliness of drilling operations. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a drilling operation cycle prediction method based on a random forest regression model.

[0005] The technical solution of the present invention is: a drilling operation cycle prediction method based on a random forest regression model comprises the following steps:

[0006] S1. Collect drilling data and screen the drilling data to obtain standard drilling data;

[0007] S2. Classify and process the standard drilling data to obtain classification results;

[0008] S3. Based on the classification results, a regression result based on random forest is obtained, and the regression result is used to predict the drilling operation cycle.

[0009] Furthermore, in S1, the drilling data include well depth, wellbore dimensions, drilling fluid parameters, layer thickness, and lithology thickness;

[0010] In S1, the drilling data is screened using the kernel K-means method to obtain standard drilling data.

[0011] Furthermore, S2 includes the following sub-steps:

[0012] S21. Use standard drilling data to construct a training set;

[0013] S22, randomly sampling the training set to generate a self-service sampling set;

[0014] S23. Classify the self-service sampling set to obtain a classification result.

[0015] Furthermore, in S22, the self-service sampling set The expression is:

[0016] ;

[0017] Where, Indicates the current node The drilling operation cycle of each sample, Indicates the current node The cumulative number of working days for each sample, Indicates the total number of samples of the current node.

[0018] Furthermore, S23 includes the following sub-steps:

[0019] S231. Calculate the intra-class consistency of each sample based on the automatic sampling set;

[0020] S232. Calculate inter-class differences based on the automatic sampling set;

[0021] S233, generating the best node classification model based on the inter-class differences and the intra-class consistency of each sample;

[0022] S234. Classify the automatic sampling set using the node optimal classification model to generate the optimal splitting point and obtain the classification result.

[0023] Further, in S231, the automatic sampling is concentrated Relative intra-class consistency WCV of class samples Relative The calculation formula for (k) is:

[0024] ;

[0025] Where WCV(k) represents the number of Intra-class consistency of class samples, Represents the variance of the automatically sampled set.

[0026] Furthermore, in S232, the inter-class difference The calculation formula is:

[0027] ;

[0028] Where, Indicates the first The mean of the class samples, represents the overall mean of the automatically sampled set, represents the standard deviation of the automatically sampled set, Indicates the total number of samples in the automatic sampling set.

[0029] Furthermore, in S233, the node best classification model The expression is:

[0030] ;

[0031] Where, Indicates the total number of samples in the automatic sampling set, represents the number of samples in the kth class, Indicates the total number of samples of the current node, Represents the weight of the penalty term.

[0032] Furthermore, in S234, the optimal splitting point The calculation formula is:

[0033] ;

[0034] Where, Indicates the number of samples of the left child node, Indicates the number of samples of the right child node, Represents the calculation result of the purity measurement function of the left child node, Represents the calculation result of the purity measurement function of the right child node, Represents the left child node, which is the left child node generated after the current node is split. It contains samples classified to the left according to the splitting condition of a certain feature. Represents the right child node, which is the right child node generated after the current node is split. It contains samples classified to the right based on the splitting condition of a certain feature.

[0035] Furthermore, in S3, the regression results The calculation formula is:

[0036] ;

[0037] Where, Indicates the The regression results of a decision tree, Indicates the number of decision trees.

[0038] The present invention has the following beneficial effects: it prioritizes factors influencing drilling timeliness and uses a random forest regression model to predict the drilling cycle for multiple drilling runs. This improves upon the previous method's insufficient drilling cycle predictions, achieving high prediction accuracy for each run, meeting practical needs. The present invention can implement pre-drilling predictions and real-time parameter adjustment as needed, continuously supplementing training samples to optimize the model, and improving its adaptability to the operational characteristics of the study area. The random forest regression prediction model is of great significance for subsequent drilling plan planning and cost assessment, and has good promotional value. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Flowchart of the drilling operation cycle prediction method based on random forest regression model. DETAILED DESCRIPTION

[0040] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0041] like Figure 1 As shown, the present invention provides a drilling operation cycle prediction method based on a random forest regression model, comprising the following steps:

[0042] S1. Collect drilling data and screen the drilling data to obtain standard drilling data;

[0043] S2. Classify and process the standard drilling data to obtain classification results;

[0044] S3. Based on the classification results, a regression result based on random forest is obtained, and the regression result is used to predict the drilling operation cycle.

[0045] The random forest algorithm is an integrated machine learning method whose basic unit is the CART decision tree, which can be used for classification and regression problems. In random forest regression, each decision tree is constructed independently, and samples are usually extracted from the original data set using self-service sampling. In addition, feature selection during node splitting is also based on a random subset of features, thereby increasing the diversity of the forest and further reducing the risk of overfitting. The output of the model is obtained by summarizing the results of all decision trees (such as averaging). The random forest regression algorithm has good robustness to noisy data and missing outliers. In addition, the random forest algorithm reduces the dependence on data preprocessing during the training phase, and its implementation process is standardized and has high learning efficiency. Since the characteristic parameters for drilling operation cycle prediction contain complex and interdependent classification features, when facing more complex situations, the model needs to have a strong tolerance for random errors and missing values. Based on the advantages of the random forest regression model algorithm, the present invention uses the random forest regression model for research.

[0046] In the embodiment of the present invention, in S1, the drilling data includes well depth, wellbore size, drilling fluid parameters, layer thickness and lithology thickness;

[0047] In S1, the drilling data is screened using the kernel K-means method to obtain standard drilling data.

[0048] In this embodiment of the present invention, S2 includes the following sub-steps:

[0049] S21. Use standard drilling data to construct a training set;

[0050] S22, randomly sampling the training set to generate a self-service sampling set;

[0051] S23. Classify the self-service sampling set to obtain a classification result.

[0052] In the embodiment of the present invention, in S22, the self-service sampling set The expression is:

[0053] ;

[0054] Where, Indicates the current node The drilling operation cycle of each sample, Indicates the current node The cumulative number of working days for each sample, Indicates the total number of samples of the current node.

[0055] In this embodiment of the present invention, S23 includes the following sub-steps:

[0056] S231. Calculate the intra-class consistency of each sample based on the automatic sampling set;

[0057] S232. Calculate inter-class differences based on the automatic sampling set;

[0058] S233, generating the best node classification model based on the inter-class differences and the intra-class consistency of each sample;

[0059] S234. Classify the automatic sampling set using the node optimal classification model to generate the optimal splitting point and obtain the classification result.

[0060] In the embodiment of the present invention, in S231, the automatic sampling set Relative intra-class consistency WCV of class samples Relative The calculation formula for (k) is:

[0061] ;

[0062] Where WCV(k) represents the number of Intra-class consistency of class samples, Represents the variance of the automatically sampled set.

[0063] In the embodiment of the present invention, in S232, the difference between classes The calculation formula is:

[0064] ;

[0065] Where, Indicates the first The mean of the class samples, represents the overall mean of the automatically sampled set, represents the standard deviation of the automatically sampled set, Indicates the total number of samples in the automatic sampling set.

[0066] In the embodiment of the present invention, in S233, the node best classification model The expression is:

[0067] ;

[0068] Where, Indicates the total number of samples in the automatic sampling set, represents the number of samples in the kth class, Indicates the total number of samples of the current node, Represents the weight of the penalty term.

[0069] In the embodiment of the present invention, in S234, the optimal splitting point The calculation formula is:

[0070] ;

[0071] Where, Indicates the number of samples of the left child node, Indicates the number of samples of the right child node, Represents the calculation result of the purity measurement function of the left child node, Represents the calculation result of the purity measurement function of the right child node, Represents the left child node, which is the left child node generated after the current node is split. It contains samples classified to the left according to the splitting condition of a certain feature. Represents the right child node, which is the right child node generated after the current node is split. It contains samples classified to the right based on the splitting condition of a certain feature.

[0072] In the embodiment of the present invention, in S3, the regression result The calculation formula is:

[0073] ;

[0074] Where, Indicates the The regression results of a decision tree, Indicates the number of decision trees.

[0075] The following is an explanation with reference to specific embodiments. Taking Well S15 as an example, the well is deployed at the front edge of the inversion structural belt in the eastern area of ​​the Wushi Sag in the Beibu Gulf Basin. It is an evaluation well of the three-opening directional type. Its data did not participate in the model training. The well parameter data are shown in Table 1. The pre-drilling prediction results of the model are shown in Table 2. The cumulative time for opening one to three were 3.46d, 8.43d and 18.34d respectively, and the difference in days from the actual time was 0.02d, 0.57d and 1.25d respectively. Comparing the model prediction results with the original design cumulative days calculated by the quota, it can be found that the model results are closer to the actual cumulative days, which greatly improves the efficiency and accuracy of the drilling operation cycle prediction and can provide a reference for subsequent drilling planning and cost evaluation.

[0076] Table 1

[0077]

[0078] Table 2

[0079]

[0080] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. A drilling operation cycle prediction method based on a random forest regression model, characterized in that: The following steps are involved: S1. Collect drilling data and screen the drilling data to obtain standard drilling data; S2. Classify and process the standard drilling data to obtain classification results; S3. Obtain a regression result based on the random forest according to the classification result, and use the regression result to predict the drilling operation cycle; The S2 includes the following sub-steps: S21. Use standard drilling data to construct a training set; S22, randomly sampling the training set to generate a self-service sampling set; S23, classifying the self-service sampling set to obtain a classification result; The S23 includes the following sub-steps: S231. Calculate the intra-class consistency of each sample based on the automatic sampling set; S232. Calculate inter-class differences based on the automatic sampling set; S233, generating the best node classification model based on the inter-class differences and the intra-class consistency of each sample; S234, using the node optimal classification model to classify the automatic sampling set, generate the optimal splitting point, and obtain the classification result; In the above S231, the automatic sampling is concentrated Relative intra-class consistency WCV of class samples Relative The calculation formula for (k) is: ； Where WCV(k) represents the number of Intra-class consistency of class samples, represents the variance of the automatic sampling set; In S232, the difference between classes The calculation formula is: ； Where, Indicates the first The mean of the class samples, represents the overall mean of the automatically sampled set, represents the standard deviation of the automatically sampled set, Indicates the total number of samples in the automatic sampling set; In S233, the node best classification model The expression is: ； Where, Indicates the total number of samples in the automatic sampling set, represents the number of samples in the kth class, Indicates the total number of samples of the current node, represents the weight of the penalty term; In S234, the optimal splitting point The calculation formula is: ； Where, Indicates the number of samples of the left child node, Indicates the number of samples of the right child node, Represents the calculation result of the purity measurement function of the left child node, Represents the calculation result of the purity measurement function of the right child node, represents the left child node, Represents the right child node.

2. The drilling operation cycle prediction method based on the random forest regression model according to claim 1 is characterized in that: In said S1, the drilling data includes well depth, wellbore size, drilling fluid parameters, layer thickness and lithology thickness; In S1, the drilling data is screened using the kernel K-means method to obtain standard drilling data.

3. The drilling operation cycle prediction method based on the random forest regression model according to claim 1 is characterized in that: In S22, the self-service sampling set The expression is: ； Where, Indicates the current node The drilling operation cycle of each sample, Indicates the current node The cumulative number of working days for each sample, Indicates the total number of samples of the current node.

4. The drilling operation cycle prediction method based on the random forest regression model according to claim 1, characterized in that: In S3, the regression results The calculation formula is: ； Where, Indicates the The regression results of a decision tree, Indicates the number of decision trees.

Images