Intelligent comprehensive management method and system for drilling platform

Abstract

The invention is suitable for the technical field of drilling platforms, and provides an intelligent comprehensive management method and system for a drilling platform, and the method comprises the following steps: collecting drilling platform information based on the Internet of Things, the drilling platform information comprising drilling parameters, geological parameters and wellbore internal environment parameters; constructing a speculation model based on a machine learning algorithm and historical drilling data, wherein the historical drilling data comprises drilling parameters, geological parameters and wellbore internal environment parameters; drilling platform information is input into the speculation model, and speculation results of the change trend of the internal environment of a shaft, drill bit abrasion data and the drilling speed are obtained; and determining an objective function according to the speculation result, performing iterative optimization on the drilling parameters in the drilling platform information through an optimization algorithm to obtain an optimal objective function, and determining optimal drilling parameters. According to the method, intelligent adjustment of the drilling parameters is achieved, the drilling efficiency is improved, the cost is reduced, and risks and uncertainty in the drilling process are remarkably reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling platforms, and in particular to an intelligent integrated management method and system for drilling platforms. Background Art

[0002] In the process of oil and gas exploration and development, drilling operations are a vital link. With the rapid development of Internet of Things technology and machine learning technology, it has become an urgent need in the industry to apply these advanced technologies to the management of drilling platforms to improve operational efficiency, reduce risks and costs. However, the existing drilling management platforms still have many shortcomings in terms of intelligence. Traditional analysis methods are difficult to provide accurate and timely predictions of the changing trends of the internal environment of the wellbore and the interaction between the drill bit and the formation, resulting in delayed or improper decision-making in drilling operations. In addition, the optimization of drilling parameters also mainly depends on the experience of engineers, and lacks scientific and systematic optimization methods, resulting in low drilling efficiency. Therefore, it is necessary to provide an intelligent comprehensive management method and system for drilling platforms to solve the above problems. Summary of the invention

[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an intelligent integrated management method and system for a drilling platform to solve the problems existing in the above-mentioned background technology.

[0004] The present invention is implemented as follows: a drilling platform intelligent integrated management method, the method comprising the following steps:

[0005] Based on the Internet of Things, the drilling platform information is collected and pre-processed, wherein the drilling platform information includes drilling parameters, geological parameters, and wellbore internal environment parameters;

[0006] Building a speculation model based on a machine learning algorithm and historical drilling data, the speculation model is used to analyze the trend of changes in the internal environment of the wellbore and the interaction between the drill bit and the formation, the historical drilling data including drilling parameters, geological parameters and internal environment parameters of the wellbore;

[0007] The drilling platform information is input into the inference model to obtain the inference results of the wellbore internal environment change trend, drill bit wear data and drilling speed;

[0008] The objective function is determined based on the inference results, and the drilling parameters in the drilling platform information are iteratively optimized through the optimization algorithm to obtain the optimal objective function, determine the optimal drilling parameters, and adjust the drilling parameters.

[0009] As a further solution of the present invention: the step of building a speculation model based on a machine learning algorithm and historical drilling data specifically includes:

[0010] The training set and the test set are determined based on the historical drilling data and the target variables. The historical drilling data correspond to the target variables, and the target variables are the change trend of the internal environment of the wellbore, the drill bit wear data, and the drilling speed.

[0011] Determine the kernel function, kernel function parameters and penalty parameter C, and use the data in the training set to train the SVM model;

[0012] The performance of the SVM model is evaluated using the data in the test set, and the parameters of the kernel function are optimized based on the evaluation results.

[0013] As a further solution of the present invention: the step of training the SVM model using the data in the training set specifically includes:

[0014] Construct the input matrix X and target vector y of the training set. Each row of the input matrix X corresponds to the input variable of a training sample. The input variables include drilling parameters, geological parameters, and wellbore internal environment parameters. Each element of the target vector y corresponds to the target variable of a training sample.

[0015] Call the SVM training algorithm, input the matrix X, the target vector y, the kernel function, the parameters of the kernel function and the penalty parameter C, output the optimal weight vector, bias term and support vector set, and obtain the inference model.

[0016] As a further solution of the present invention: the step of determining the objective function according to the inference result, iteratively optimizing the drilling parameters in the drilling platform information by the optimization algorithm, and obtaining the optimal objective function specifically includes:

[0017] According to the change trend of the internal environment of the wellbore, the internal environment stability index of the wellbore is determined, and the objective function f(P)=α×internal environment stability index of the wellbore+β×(1-drill bit wear data)+γ×drilling speed is obtained, where α, β and γ are weight coefficients;

[0018] A set of initial drilling parameters P0 is determined based on geological parameters and wellbore internal environmental parameters, and an initial objective function f(P0) is calculated;

[0019] The drilling parameters in the drilling platform information are iteratively optimized according to the gradient ascent method to obtain the optimal objective function.

[0020] As a further solution of the present invention: the step of iteratively optimizing the drilling parameters in the drilling platform information according to the gradient ascent method to obtain the optimal objective function specifically includes:

[0021] Calculate the gradient of the objective function f(P) under the current drilling parameters Pk n is the number of drilling parameters, Represents the gradient component of parameter pi;

[0022] Update drilling parameters according to the gradient direction, η is the step size, which is used to control the update amplitude;

[0023] Calculate the new objective function f(Pk+1) based on the updated drilling parameter Pk+1 and the inference model;

[0024] Iterative calculation is performed until the change of the objective function is less than the change threshold. After the iteration is completed, the last set of drilling parameters obtained is the optimal drilling parameters, and the optimal objective function is determined.

[0025] As a further solution of the present invention: the calculation formula of the gradient component of the parameter pi is: Here, ei is a unit vector that is 1 only at position i and 0 at all other positions.

[0026] Another object of the present invention is to provide an intelligent integrated management system for a drilling platform, the system comprising:

[0027] A drilling platform information module, which is used to collect drilling platform information based on the Internet of Things and pre-process the drilling platform information, wherein the drilling platform information includes drilling parameters, geological parameters, and wellbore internal environment parameters;

[0028] A speculation model building module, for building a speculation model based on a machine learning algorithm and historical drilling data, wherein the speculation model is used to analyze the changing trend of the wellbore internal environment and the interaction between the drill bit and the formation, wherein the historical drilling data includes drilling parameters, geological parameters, and wellbore internal environment parameters;

[0029] The inference result determination module is used to input the drilling platform information into the inference model to obtain the inference results of the wellbore internal environment change trend, drill bit wear data and drilling speed;

[0030] The optimal drilling parameter module is used to determine the objective function according to the inference results, iteratively optimize the drilling parameters in the drilling platform information through the optimization algorithm, obtain the optimal objective function, determine the optimal drilling parameters, and adjust the drilling parameters.

[0031] As a further solution of the present invention: the inference model building module includes:

[0032] A data set determination unit, used to determine a training set and a test set according to historical drilling data and target variables, the historical drilling data and the target variables correspond to each other, and the target variables are the change trend of the wellbore internal environment, drill bit wear data and drilling speed;

[0033] The SVM model training unit is used to determine the kernel function, the parameters of the kernel function and the penalty parameter C, and train the SVM model using the data in the training set;

[0034] The SVM model testing unit is used to evaluate the performance of the SVM model using the data in the test set and optimize the parameters of the kernel function based on the evaluation results.

[0035] As a further solution of the present invention: the optimal drilling parameter module includes:

[0036] The objective function determination unit is used to determine the wellbore internal environment stability index according to the wellbore internal environment change trend, and obtain the objective function f(P)=α×wellbore internal environment stability index+β×(1-drill bit wear data)+γ×drilling speed, where α, β and γ are weight coefficients;

[0037] An initial objective function unit, used to determine a set of initial drilling parameters P0 based on geological parameters and wellbore internal environmental parameters, and calculate an initial objective function f(P0);

[0038] The parameter iteration optimization unit is used to iteratively optimize the drilling parameters in the drilling platform information according to the gradient ascent method to obtain the optimal objective function.

[0039] As a further solution of the present invention: the parameter iteration optimization unit includes:

[0040] Gradient calculation subunit, used to calculate the gradient of the objective function f(P) under the current drilling parameters Pk n is the number of drilling parameters, Represents the gradient component of parameter pi;

[0041] The drilling parameter update subunit is used to update the drilling parameters according to the gradient direction. η is the step size, which is used to control the update amplitude;

[0042] The objective function updating subunit is used to calculate a new objective function f(Pk+1) according to the updated drilling parameter Pk+1 and the inference model;

[0043] The iterative calculation subunit is used to perform iterative calculation until the change of the objective function is less than the change threshold. After the iteration is completed, the last set of drilling parameters obtained is the optimal drilling parameters, and the optimal objective function is determined.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention constructs a speculation model through machine learning algorithms and historical drilling data. The speculation model is used to analyze the changing trend of the internal environment of the wellbore and the interaction between the drill bit and the formation. By inputting real-time drilling platform information into the speculation model, the speculation results of the changing trend of the internal environment of the wellbore, drill bit wear data and drilling speed can be obtained, providing timely and accurate prediction information for drilling operations. In addition, the objective function is determined according to the speculation results, and the drilling parameters in the drilling platform information are iteratively optimized through the optimization algorithm to obtain the optimal objective function, determine the optimal drilling parameters, and remotely adjust the drilling parameters, realizing the intelligent adjustment of the drilling parameters, which not only improves the drilling efficiency and reduces the cost, but also significantly reduces the risk and uncertainty in the drilling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The present invention is a flow chart of an intelligent integrated management method for a drilling platform.

[0047] Figure 2 A flowchart for constructing a speculation model in an intelligent integrated management method for a drilling platform.

[0048] Figure 3 The figure is a flowchart of training SVM model in an intelligent integrated management method for drilling platforms.

[0049] Figure 4 The present invention is a flowchart for obtaining the optimal objective function in an intelligent integrated management method for a drilling platform.

[0050] Figure 5 The present invention is a flowchart for iteratively optimizing drilling parameters in an intelligent integrated management method for a drilling platform.

[0051] Figure 6 The figure is a schematic diagram of the structure of an intelligent integrated management system for a drilling platform. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0054] like Figure 1 As shown, an embodiment of the present invention provides a drilling platform intelligent integrated management method, the method comprising the following steps:

[0055] S100, collecting drilling platform information based on the Internet of Things and preprocessing the drilling platform information, wherein the drilling platform information includes drilling parameters, geological parameters, and wellbore internal environment parameters;

[0056] S200, constructing a speculation model based on a machine learning algorithm and historical drilling data, wherein the speculation model is used to analyze the change trend of the internal environment of the wellbore and the interaction between the drill bit and the formation, wherein the historical drilling data includes drilling parameters, geological parameters, and internal environment parameters of the wellbore;

[0057] S300, inputting the drilling platform information into the inference model to obtain inference results of the wellbore internal environment change trend, drill bit wear data and drilling speed;

[0058] S400, determining the objective function according to the inference result, iteratively optimizing the drilling parameters in the drilling platform information through the optimization algorithm, obtaining the optimal objective function, determining the optimal drilling parameters, and adjusting the drilling parameters.

[0059] It should be noted that the traditional drilling management platform mainly relies on manual monitoring and experience judgment. This method is not only inefficient, but also difficult to accurately predict and respond to various complex situations in the drilling process. With the rapid development of Internet of Things technology and machine learning technology, it has become an urgent need in the industry to apply these advanced technologies to the management of drilling platforms to improve operational efficiency, reduce risks and costs. However, the existing drilling management platform still has many shortcomings in terms of intelligence. First, the drilling process involves a large amount of data, including drilling parameters (such as drilling pressure, rotation speed, drilling fluid flow, etc.), geological parameters (such as formation hardness, permeability, etc.) and wellbore internal environmental parameters (such as temperature, pressure, etc.), which are often scattered in different systems and lack a unified data collection and processing mechanism. Secondly, for the changing trend of the wellbore internal environment and the interaction between the drill bit and the formation, traditional analysis methods are difficult to provide accurate and timely predictions, resulting in delayed or improper decision-making in drilling operations. In addition, the optimization of drilling parameters also mainly depends on the experience of engineers, lacks scientific and systematic optimization methods, resulting in low drilling efficiency and high costs. The embodiments of the present invention are intended to solve the above problems.

[0060] In the embodiment of the present invention, the Internet of Things technology is used to realize the unified collection and preprocessing of drilling platform information, which solves the problem of data dispersion and difficulty in unified management. That is, the Internet of Things can collect drilling parameters, geological parameters and wellbore internal environmental parameters and other drilling platform information, and then preprocess the drilling platform information, specifically including identifying and processing missing values. For missing data points, interpolation methods (such as linear interpolation, polynomial interpolation) or the average value of neighboring data points can be used to fill them; and outliers are removed: statistical methods (such as 3σ principle, box plot method) are used to identify and remove abnormal data points to avoid them from interfering with subsequent analysis. Then, historical drilling data is retrieved, and the historical drilling data includes drilling parameters, geological parameters and wellbore internal environmental parameters. A speculation model is constructed through machine learning algorithms and historical drilling data. The speculation model is used to analyze the change trend of the wellbore internal environment and the interaction between the drill bit and the formation. The real-time drilling platform information is input into the speculation model, and the speculation results of the wellbore internal environment change trend, drill bit wear data and drilling speed are obtained, providing timely and accurate prediction information for drilling operations. In addition, the embodiment of the present invention will also determine the objective function based on the inference results, iteratively optimize the drilling parameters in the drilling platform information through the optimization algorithm, obtain the optimal objective function, determine the optimal drilling parameters, and remotely adjust the drilling parameters to achieve intelligent adjustment of the drilling parameters. Compared with the traditional manual adjustment method, this method not only improves the drilling efficiency and reduces the cost, but also significantly reduces the risk and uncertainty in the drilling process, which is of great significance to improving the efficiency and safety of oil and gas exploration and development.

[0061] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of building a speculation model based on a machine learning algorithm and historical drilling data specifically includes:

[0062] S201, determining a training set and a test set according to historical drilling data and target variables, the historical drilling data and the target variables correspond to each other, and the target variables are the change trend of the wellbore internal environment, drill bit wear data, and drilling speed;

[0063] S202, determining a kernel function, kernel function parameters, and a penalty parameter C, and training an SVM model using data in a training set;

[0064] S203, using the data in the test set to evaluate the performance of the SVM model, and optimizing the parameters of the kernel function according to the evaluation results.

[0065] In the embodiment of the present invention, in order to construct the inference model, the training set and the test set are determined according to the historical drilling data and the target variable. Usually, the training set accounts for 70%-80% of the total data, and the test set accounts for the rest. The historical drilling data corresponds to the target variable. The target variable is the change trend of the internal environment of the wellbore, the drill bit wear data and the drilling speed. The historical drilling data and the target variable are known. Then it is necessary to determine the kernel function, the parameters of the kernel function and the penalty parameter C. In the scenario of drilling data, since the data is often nonlinearly separable, the kernel function selects the radial basis function (RBF) kernel. Here, it is necessary to determine the parameter γ of the kernel function. The penalty parameter C is used to control the balance between the complexity of the model and the training error. The larger the C value, the more the model tends to overfit; the smaller the C value, the more the model tends to underfit. Parameters γ and C are optimized through cross-validation (such as K-fold cross-validation). The specific steps are as follows: divide the training set into K subsets, and for each set of parameter combinations (including kernel function parameters and penalty parameters C), perform K iterations. In each iteration: use one subset as the validation set and the remaining subsets as the training set. Use the training set to train the SVM model, use the validation set to evaluate the performance of the model, record performance indicators (such as accuracy, MSE, etc.), calculate the average performance indicator of K iterations, and select the parameter combination with the best average performance indicator as the optimal parameter. After the optimal parameters are determined, the SVM model can be trained using the data in the training set, and then the performance of the SVM model can be evaluated using the data in the test set. The parameters of the kernel function are optimized based on the evaluation results. Common evaluation indicators include mean square error (MSE), root mean square error (RMSE), R 2 Scores, etc.

[0066] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of training the SVM model using the data in the training set specifically includes:

[0067] S2021, constructing an input matrix X and a target vector y of the training set, wherein each row of the input matrix X corresponds to an input variable of a training sample, the input variables include drilling parameters, geological parameters, and wellbore internal environment parameters, and each element of the target vector y corresponds to a target variable of a training sample;

[0068] S2022, calling the SVM training algorithm, inputting the matrix X, the target vector y, the kernel function, the parameters of the kernel function and the penalty parameter C, outputting the optimal weight vector, bias term and support vector set, and obtaining the inference model.

[0069] In the embodiment of the present invention, when training the SVM model, it is first necessary to construct the input matrix X and target vector y of the training set, each row of the input matrix X corresponds to the input variable of a training sample, the input variables include drilling parameters, geological parameters and wellbore internal environment parameters, and each element of the target vector y corresponds to the target variable of a training sample; then call the SVM training algorithm (such as the SMO algorithm), input the matrix X, the target vector y, the kernel function, the kernel function parameters and the penalty parameter C, output the optimal weight vector, bias term and support vector set, and obtain the inference model. After the training is completed, the SVM model can be used to predict the wellbore internal environment change trend, drill bit wear data and drilling speed corresponding to the new drilling data. The specific prediction process is as follows: for the new drilling data, construct the input vector, then use the kernel function to calculate the kernel function value between the input vector and the support vector set, and finally calculate the prediction result according to the weight vector, bias term, and kernel function value.

[0070] like Figure 4 As shown, as a preferred embodiment of the present invention, the step of determining the objective function according to the inference result, iteratively optimizing the drilling parameters in the drilling platform information by the optimization algorithm, and obtaining the optimal objective function specifically includes:

[0071] S401, determining the wellbore internal environment stability index according to the wellbore internal environment change trend, and obtaining the objective function f(P)=α×wellbore internal environment stability index+β×(1-drill bit wear data)+γ×drilling speed, where α, β and γ are weight coefficients;

[0072] S402, determining a set of initial drilling parameters P0 based on geological parameters and wellbore internal environment parameters, and calculating an initial objective function f(P0);

[0073] S403, iteratively optimizing the drilling parameters in the drilling platform information according to the gradient ascent method to obtain an optimal objective function.

[0074] In the embodiment of the present invention, in order to obtain the optimal drilling parameters, it is necessary to determine the wellbore internal environment stability index according to the wellbore internal environment change trend. Here, it is necessary to construct a functional relationship between the wellbore internal environment stability index and the wellbore internal environment change trend in advance, and then obtain the objective function f(P)=α×wellbore internal environment stability index+β×(1-drill wear data)+γ×drilling speed, α, β and γ are weight coefficients, all of which are pre-set constants, and then determine a set of initial drilling parameters P0 based on geological parameters and wellbore internal environment parameters. Here, a working condition table is established in advance, and the working condition table contains several working condition categories, each working condition category corresponds to a set of initial drilling parameters, and the working condition category is determined by geological parameters and wellbore internal environment parameters. Then, the initial objective function f(P0) is calculated, and finally, the drilling parameters in the drilling platform information are iteratively optimized according to the gradient ascent method to obtain the optimal objective function.

[0075] like Figure 5 As shown, as a preferred embodiment of the present invention, the step of iteratively optimizing the drilling parameters in the drilling platform information according to the gradient ascent method to obtain the optimal objective function specifically includes:

[0076] S4031, calculate the gradient of the objective function f(P) under the current drilling parameter Pk

[0077] S4032, update drilling parameters according to the gradient direction, η is the step length;

[0078] S4033, calculating a new objective function f(Pk+1) according to the updated drilling parameter Pk+1 and the inference model;

[0079] S4034, performing iterative calculation until the change of the objective function is less than the change threshold. After the iteration is completed, the last set of drilling parameters obtained is the optimal drilling parameters, and the optimal objective function is determined.

[0080] In the embodiment of the present invention, in order to obtain the optimal objective function, the gradient of the objective function f(P) under the current drilling parameter Pk is first calculated. n is the number of drilling parameters, Represents the gradient component of the parameter pi, and then updates the drilling parameters according to the gradient direction, η is the step size, which is a preset constant here to control the update amplitude. Then, according to the updated drilling parameter Pk+1 and the inference model, the new objective function f(Pk+1) is calculated, and then iterative calculation is performed until the change of the objective function is less than the change threshold. After the iteration, the last set of drilling parameters obtained is the optimal drilling parameters, and the optimal objective function is determined. Among them, the calculation formula of the gradient component of the parameter pi is: ei is a unit vector that is 1 only at position i and 0 at all other positions.

[0081] like Figure 6 As shown, the embodiment of the present invention further provides an intelligent integrated management system for a drilling platform, the system comprising:

[0082] The drilling platform information module 100 is used to collect drilling platform information based on the Internet of Things and pre-process the drilling platform information, wherein the drilling platform information includes drilling parameters, geological parameters, and wellbore internal environment parameters;

[0083] A speculation model building module 200 is used to build a speculation model based on a machine learning algorithm and historical drilling data, wherein the speculation model is used to analyze the change trend of the internal environment of the wellbore and the interaction between the drill bit and the formation, wherein the historical drilling data includes drilling parameters, geological parameters, and internal environment parameters of the wellbore;

[0084] The inference result determination module 300 is used to input the drilling platform information into the inference model to obtain the inference results of the wellbore internal environment change trend, drill bit wear data and drilling speed;

[0085] The optimal drilling parameter module 400 is used to determine the objective function according to the inference results, iteratively optimize the drilling parameters in the drilling platform information through the optimization algorithm, obtain the optimal objective function, determine the optimal drilling parameters, and adjust the drilling parameters.

[0086] As a preferred embodiment of the present invention, the inference model building module 200 includes:

[0087] A data set determination unit, used to determine a training set and a test set according to historical drilling data and target variables, the historical drilling data and the target variables correspond to each other, and the target variables are the change trend of the wellbore internal environment, drill bit wear data and drilling speed;

[0088] The SVM model training unit is used to determine the kernel function, the parameters of the kernel function and the penalty parameter C, and train the SVM model using the data in the training set;

[0089] The SVM model testing unit is used to evaluate the performance of the SVM model using the data in the test set and optimize the parameters of the kernel function based on the evaluation results.

[0090] As a preferred embodiment of the present invention, the optimal drilling parameter module 400 includes:

[0091] The objective function determination unit is used to determine the wellbore internal environment stability index according to the wellbore internal environment change trend, and obtain the objective function f(P)=α×wellbore internal environment stability index+β×(1-drill bit wear data)+γ×drilling speed, where α, β and γ are weight coefficients;

[0092] An initial objective function unit, used to determine a set of initial drilling parameters P0 based on geological parameters and wellbore internal environmental parameters, and calculate an initial objective function f(P0);

[0093] The parameter iteration optimization unit is used to iteratively optimize the drilling parameters in the drilling platform information according to the gradient ascent method to obtain the optimal objective function.

[0094] As a preferred embodiment of the present invention, the parameter iteration optimization unit includes:

[0095] Gradient calculation subunit, used to calculate the gradient of the objective function f(P) under the current drilling parameters Pk n is the number of drilling parameters, Represents the gradient component of parameter pi;

[0096] The drilling parameter update subunit is used to update the drilling parameters according to the gradient direction. η is the step size, which is used to control the update amplitude;

[0097] The objective function updating subunit is used to calculate a new objective function f(Pk+1) according to the updated drilling parameter Pk+1 and the inference model;

[0098] The iterative calculation subunit is used to perform iterative calculation until the change of the objective function is less than the change threshold. After the iteration is completed, the last set of drilling parameters obtained is the optimal drilling parameters, and the optimal objective function is determined.

[0099] The above only describes in detail the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0100] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0101] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0102] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A drilling platform intelligent integrated management method, characterized in that: The method comprises the following steps: Based on the Internet of Things, the drilling platform information is collected and pre-processed, wherein the drilling platform information includes drilling parameters, geological parameters, and wellbore internal environment parameters; Building a speculation model based on a machine learning algorithm and historical drilling data, the speculation model is used to analyze the trend of changes in the internal environment of the wellbore and the interaction between the drill bit and the formation, the historical drilling data including drilling parameters, geological parameters and internal environment parameters of the wellbore; The drilling platform information is input into the inference model to obtain the inference results of the wellbore internal environment change trend, drill bit wear data and drilling speed; The objective function is determined based on the inference results, and the drilling parameters in the drilling platform information are iteratively optimized through the optimization algorithm to obtain the optimal objective function, determine the optimal drilling parameters, and adjust the drilling parameters.

2. The drilling platform intelligent integrated management method according to claim 1, characterized in that: The step of building a speculation model based on a machine learning algorithm and historical drilling data specifically includes: The training set and the test set are determined based on the historical drilling data and the target variables. The historical drilling data correspond to the target variables, and the target variables are the change trend of the internal environment of the wellbore, the drill bit wear data, and the drilling speed. Determine the kernel function, kernel function parameters and penalty parameter C, and use the data in the training set to train the SVM model; The performance of the SVM model is evaluated using the data in the test set, and the parameters of the kernel function are optimized based on the evaluation results.

3. The drilling platform intelligent integrated management method according to claim 2, characterized in that: The step of using the data in the training set to train the SVM model specifically includes: Construct the input matrix X and target vector y of the training set. Each row of the input matrix X corresponds to the input variable of a training sample. The input variables include drilling parameters, geological parameters, and wellbore internal environment parameters. Each element of the target vector y corresponds to the target variable of a training sample. Call the SVM training algorithm, input the matrix X, the target vector y, the kernel function, the parameters of the kernel function and the penalty parameter C, output the optimal weight vector, bias term and support vector set, and obtain the inference model.

4. The drilling platform intelligent integrated management method according to claim 1, characterized in that: The step of determining the objective function according to the inference result and iteratively optimizing the drilling parameters in the drilling platform information by an optimization algorithm to obtain the optimal objective function specifically includes: According to the change trend of the internal environment of the wellbore, the internal environment stability index of the wellbore is determined, and the objective function f(P)=α×internal environment stability index of the wellbore+β×(1-drill bit wear data)+γ×drilling speed is obtained, where α, β and γ are weight coefficients; A set of initial drilling parameters P0 is determined based on geological parameters and wellbore internal environmental parameters, and an initial objective function f(P0) is calculated; The drilling parameters in the drilling platform information are iteratively optimized according to the gradient ascent method to obtain the optimal objective function.

5. The drilling platform intelligent integrated management method according to claim 4, characterized in that: The step of iteratively optimizing the drilling parameters in the drilling platform information according to the gradient ascent method to obtain the optimal objective function specifically includes: Calculate the gradient of the objective function f(P) under the current drilling parameters Pk n is the number of drilling parameters, Represents the gradient component of parameter pi; Update drilling parameters according to the gradient direction, η is the step size, which is used to control the update amplitude; Calculate the new objective function f(Pk+1) based on the updated drilling parameter Pk+1 and the inference model; Iterative calculation is performed until the change of the objective function is less than the change threshold. After the iteration is completed, the last set of drilling parameters obtained is the optimal drilling parameters, and the optimal objective function is determined.

6. The drilling platform intelligent integrated management method according to claim 5, characterized in that: The calculation formula of the gradient component of parameter pi is: Here, ei is a unit vector that is 1 only at position i and 0 at all other positions.

7. An intelligent integrated management system for a drilling platform, characterized in that: The system comprises: A drilling platform information module, which is used to collect drilling platform information based on the Internet of Things and pre-process the drilling platform information, wherein the drilling platform information includes drilling parameters, geological parameters, and wellbore internal environment parameters; A speculation model building module, for building a speculation model based on a machine learning algorithm and historical drilling data, wherein the speculation model is used to analyze the changing trend of the wellbore internal environment and the interaction between the drill bit and the formation, wherein the historical drilling data includes drilling parameters, geological parameters, and wellbore internal environment parameters; The inference result determination module is used to input the drilling platform information into the inference model to obtain the inference results of the wellbore internal environment change trend, drill bit wear data and drilling speed; The optimal drilling parameter module is used to determine the objective function according to the inference results, iteratively optimize the drilling parameters in the drilling platform information through the optimization algorithm, obtain the optimal objective function, determine the optimal drilling parameters, and adjust the drilling parameters.

8. The intelligent integrated management system for drilling platforms according to claim 7, characterized in that: The inference model building module includes: A data set determination unit, used to determine a training set and a test set according to historical drilling data and target variables, the historical drilling data and the target variables correspond to each other, and the target variables are the change trend of the wellbore internal environment, drill bit wear data and drilling speed; The SVM model training unit is used to determine the kernel function, the parameters of the kernel function and the penalty parameter C, and train the SVM model using the data in the training set; The SVM model testing unit is used to evaluate the performance of the SVM model using the data in the test set and optimize the parameters of the kernel function based on the evaluation results.

9. The intelligent integrated management system for drilling platforms according to claim 7, characterized in that: The optimal drilling parameter module includes: The objective function determination unit is used to determine the wellbore internal environment stability index according to the wellbore internal environment change trend, and obtain the objective function f(P)=α×wellbore internal environment stability index+β×(1-drill bit wear data)+γ×drilling speed, where α, β and γ are weight coefficients; An initial objective function unit, used to determine a set of initial drilling parameters P0 based on geological parameters and wellbore internal environmental parameters, and calculate an initial objective function f(P0); The parameter iteration optimization unit is used to iteratively optimize the drilling parameters in the drilling platform information according to the gradient ascent method to obtain the optimal objective function.

10. The intelligent integrated management system for drilling platforms according to claim 9, characterized in that: The parameter iteration optimization unit comprises: Gradient calculation subunit, used to calculate the gradient of the objective function f(P) under the current drilling parameters Pk n is the number of drilling parameters, Represents the gradient component of parameter pi; The drilling parameter update subunit is used to update the drilling parameters according to the gradient direction. η is the step size, which is used to control the update amplitude; The objective function updating subunit is used to calculate a new objective function f(Pk+1) according to the updated drilling parameter Pk+1 and the inference model; The iterative calculation subunit is used to perform iterative calculation until the change of the objective function is less than the change threshold. After the iteration is completed, the last set of drilling parameters obtained is the optimal drilling parameters, and the optimal objective function is determined.

Images