Well drilling leakage velocity prediction method, system and equipment based on RBF (Radial Basis Function) and medium

Abstract

The invention belongs to the technical field of oil exploration and development, and provides an RBF-based drilling leakage velocity prediction method and system, electronic equipment and a storage medium. The method comprises the steps that historical drilling data and real-time drilling data of a target block are collected, and data preprocessing is carried out; obtaining a parameter vector and a hyperplane formula according to the preprocessed historical drilling data, and performing RTF dual transformation according to the parameter vector segmented by the hyperplane formula to obtain a kernel matrix of an RBF support vector machine; and generating a sensor model according to the parameter vector, the hyperplane formula and the kernel matrix to obtain a real-time prediction model of the drilling leakage velocity based on an RBF support vector machine, and predicting real-time drilling data by using the real-time prediction model to obtain a real-time prediction result of the drilling leakage velocity. On the basis of the method, the effect of predicting the leakage speed in real time is achieved, and a more accurate and effective decision basis is provided for drilling leakage stoppage technicians and constructors.

Description

Technical Field

[0001] This invention belongs to the field of petroleum exploration and development technology, and particularly relates to a method, system, electronic device and storage medium for predicting drilling leakage rate based on RBF. Background Technology

[0002] Loss in wells is a common and complex situation in drilling engineering. Most drilling processes involve varying degrees of loss. Severe loss in wells can lead to a drop in well pressure, affecting normal drilling, causing wellbore instability, inducing formation fluid to rush into the wellbore and triggering a blowout, ultimately resulting in a catastrophic accident. Currently, there are two main methods for measuring loss velocity: (1) After loss is detected, the approximate loss velocity is first determined by repeated cycles, and then fluid is replenished periodically, and the fluid level is measured periodically using a fluid level monitor. The loss velocity is determined based on the changes in the fluid level. Although this method is simple to operate, it has low accuracy. It not only causes a large amount of drilling fluid waste and formation pollution, but also has limited effectiveness. It is helpless in the face of most large fracture loss. (2) Imaging logging technology is used to determine the nature of the fracture, and then the loss velocity is calculated based on parameters such as drilling fluid density and shear stress. Although this method has high accuracy, imaging logging technology is complex and expensive. A single measurement of a long well section can cost hundreds of thousands or even millions of RMB, so it is difficult to popularize.

[0003] CN103015996A discloses a method for predicting the leakage rate of drilling fluid in steep structural formations before drilling. This method can predict the leakage rate of drilling fluid in wells drilled in steep and complex structural formations before drilling, which can provide some guidance for preventing severe leakage in steep structural formations and also help in the selection of plugging material size. However, its shortcomings are as follows: First, the main principle of this scheme is to obtain the formation leakage rate by mechanically simulating the formation stress. However, due to the complexity of geological composition, it is difficult to obtain accurate results by using simulation alone. Whether it is lithology or temperature, even a small deviation in one of the initial conditions will have a great impact on the prediction result of the formation leakage rate, thus leading to errors in the prediction result. Second, the formation leakage rate is not only related to the formation. Parameters such as drilling fluid density, drilling pressure, and drilling speed can all affect the formation leakage rate. Therefore, studying the geological structure alone cannot obtain accurate prediction results of the formation leakage rate. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides a method, system, electronic device, and storage medium for predicting drilling leakage rates based on RBF (Reverse Boring Force). By performing data analysis and data mining on historical and real-time drilling data related to the target block, this invention provides a convenient, accurate, and real-time method for predicting drilling leakage rates.

[0005] To address the aforementioned technical problems, the first aspect of this invention proposes a method for predicting drilling leakage rates based on RBF (Recovery Rate Forecasting), the method comprising:

[0006] Collect historical and real-time drilling data of the target block and perform data preprocessing;

[0007] Based on the preprocessed historical drilling data, parameter vectors and hyperplane formulas are obtained. The parameter vectors segmented by the hyperplane formulas are subjected to RTF dual transformation to obtain the kernel matrix of the RBF support vector machine.

[0008] Based on the parameter vector, the hyperplane formula, and the kernel matrix, a perceptron model is generated, and a real-time prediction model for drilling leakage velocity based on RBF support vector machine is obtained. The real-time prediction model is then used to predict real-time drilling data to obtain the real-time prediction result for drilling leakage velocity.

[0009] According to a preferred embodiment of the present invention, the data preprocessing includes:

[0010] Data denoising involves using a box plot method to identify historical drilling data, resulting in irrelevant data, duplicate data, and smoothed noise data. The irrelevant data, duplicate data, and smoothed noise data are then deleted.

[0011] Data imputation involves using the k-nearest neighbor algorithm to fill in irrelevant data, duplicate data, and smoothed noise data that were removed during the data denoising process.

[0012] Data conversion involves using a one-hot encoding method to convert the textual parameters of formation lithology and drill bit type in the data obtained after data denoising into numerical parameters.

[0013] Data integration, merging and processing historical drilling data in multi-file or multi-database operating environments.

[0014] According to a preferred embodiment of the present invention, obtaining the parameter vector and hyperplane formula based on the preprocessed historical drilling data includes:

[0015] The preprocessed historical drilling data is divided into training and testing sets.

[0016] The training set and the test set are normalized according to the different parameters and mapped to parameter vectors;

[0017] The hyperplane formula is obtained by mapping the parameter vector to a Gaussian distribution.

[0018] According to a preferred embodiment of the present invention, the generated perceptron model includes:

[0019] The perceptron model is tested using the test set.

[0020] If the test results do not meet the accuracy requirements, the perceptron model is regenerated.

[0021] According to a preferred embodiment of the present invention, obtaining the real-time prediction model of drilling leakage velocity based on RBF support vector machine includes:

[0022] The sensor model that meets the accuracy requirements is connected to an instant acquisition platform that obtains real-time drilling data to obtain a real-time prediction model for drilling leakage rate based on RBF support vector machine.

[0023] To address the aforementioned technical problems, a second aspect of this invention proposes an RBF-based drilling leakage rate prediction system, characterized in that the system comprises: a data acquisition module, a data processing module, and a model generation module;

[0024] The data acquisition module is used to collect historical and real-time drilling data of the target block and perform data preprocessing.

[0025] The data processing module is used to obtain parameter vectors and hyperplane formulas based on the preprocessed historical drilling data, and to perform RTF dual transformation on the parameter vectors segmented by the hyperplane formula to obtain the kernel matrix of the RBF support vector machine.

[0026] The model generation module is used to generate a perceptron model based on the parameter vector, the hyperplane formula, and the kernel matrix, to obtain a real-time prediction model for drilling leakage velocity based on RBF support vector machine, and to use the real-time prediction model to predict real-time drilling data to obtain the real-time prediction result of drilling leakage velocity.

[0027] According to a preferred embodiment of the present invention, it includes:

[0028] The data acquisition module is also used for data noise reduction. It uses the box plot method to identify historical drilling data, obtain irrelevant data, duplicate data, and smoothed noise data, and deletes the irrelevant data, duplicate data, and smoothed noise data.

[0029] The data acquisition module is also used for data completion, which uses the k-nearest neighbor algorithm to complete the data by removing irrelevant data, duplicate data and smoothed noise data that were deleted during the data denoising process.

[0030] The data acquisition module is also used for data conversion, converting textual parameters of formation lithology and drill bit type in the data obtained by data noise reduction into numerical parameters through the one-hot encoding method;

[0031] The data acquisition module is also used for data integration, merging and processing historical drilling data in multi-file or multi-database operating environments.

[0032] According to a preferred embodiment of the present invention, it includes:

[0033] The data processing module is also used to divide the preprocessed historical drilling data into training and testing sets;

[0034] The data processing module is also used to normalize the training set and the test set according to the different parameters, and map them into parameter vectors;

[0035] The data processing module is also used to perform Gaussian distribution mapping on the parameter vector to obtain the hyperplane formula.

[0036] To address the aforementioned technical problems, a third aspect of the present invention provides an electronic device, comprising:

[0037] processor;

[0038] And a memory storing computer-executable instructions, which, when executed, cause the processor to perform the method described in any of the above embodiments.

[0039] To address the aforementioned technical problems, a fourth aspect of the present invention provides a computer storage medium, wherein the computer storage medium stores one or more programs, which, when executed by a processor, implement the method described in any of the above embodiments.

[0040] Compared with existing technologies, the present invention has the following advantages: The present invention overcomes the shortcomings of existing technologies that are limited by complex geological environments and cannot predict leakage rates in real time. By performing data mining on historical drilling data of the target block and establishing a real-time prediction model of drilling leakage rate based on RBF support vector machine, the present invention achieves the effect of real-time prediction of leakage rate. This provides drilling and plugging technicians and construction personnel with more accurate and effective decision-making basis, thereby improving the efficiency of plugging work, increasing the success rate of plugging operations, and avoiding repeated operations.

[0041] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A schematic diagram of a method for predicting drilling leakage rate based on RBF according to an embodiment of the present invention is shown.

[0044] Figure 2 A second schematic diagram of a method for predicting drilling leakage rate based on RBF according to an embodiment of the present invention is shown.

[0045] Figure 3 A schematic diagram of a method for predicting well leakage rate based on RBF according to an embodiment of the present invention is shown in part three.

[0046] Figure 4 A schematic diagram of a method for predicting drilling leakage rate based on RBF according to an embodiment of the present invention is shown in Figure 4.

[0047] Figure 5 A structural diagram of an RBF-based drilling loss rate prediction system according to an embodiment of the present invention is shown.

[0048] Figure 6 A schematic diagram of an electronic device structure according to an embodiment of the present invention is shown. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] The same reference numerals in the accompanying drawings denote the same or similar elements, components, or parts, and therefore, repeated descriptions of the same or similar elements, components, or parts may be omitted below. It should also be understood that although terms such as first, second, third, etc., indicating numbers may be used herein to describe various devices, elements, components, or parts, these devices, elements, components, or parts should not be limited by these terms. That is, these terms are only used to distinguish one from another. For example, a first device may also be referred to as a second device, without departing from the essential technical solution of the invention. Furthermore, the terms "and / or" and "and / or" refer to all combinations including any one or more of the listed items.

[0051] Please see Figure 1 , Figure 1 This is a schematic diagram of one of the flowcharts of a drilling leakage rate prediction method based on RBF provided by the present invention, as shown below. Figure 1 As shown, the method includes:

[0052] S11. Collect historical and real-time drilling data of the target block and perform data preprocessing.

[0053] In this embodiment, data such as historical drilling data, historical drilling leakage rate, and real-time drilling data related to the target block are preprocessed.

[0054] S12. Based on the preprocessed historical drilling data, obtain the parameter vector and hyperplane formula. Perform RTF dual transformation on the parameter vector segmented by the hyperplane formula to obtain the kernel matrix of the RBF support vector machine.

[0055] In this embodiment, the preprocessed historical drilling data is divided into a training set and a test set. Since the drilling data is complex and chaotic, it is necessary to normalize the data according to the different parameters and map it into a vector form to obtain the parameter vector.

[0056] In this embodiment, the normalized well history data vectors are mapped using a Gaussian distribution to obtain the hyperplane formula for parameter vector segmentation. Then, the parameter vectors segmented according to the hyperplane formula are subjected to RTF dual transformation to obtain the kernel matrix of the RBF support vector machine.

[0057] S13. Generate a perceptron model based on the parameter vector, the hyperplane formula, and the kernel matrix to obtain a real-time prediction model for drilling leakage velocity based on RBF support vector machine. Use the real-time prediction model to predict real-time drilling data to obtain the real-time prediction result of drilling leakage velocity.

[0058] In this embodiment, a new perceptron model is generated based on the obtained parameter vector, hyperplane formula, and kernel matrix. This model is the RBF support vector machine perceptron model for leakage velocity prediction. The RBF support vector machine perceptron model for leakage velocity prediction is tested using test set data. If the test results do not meet the accuracy requirements, the RBF support vector machine perceptron model for leakage velocity prediction is regenerated.

[0059] In this embodiment, the final generated RBF support vector machine perceptron model for predicting leakage rate that meets the accuracy requirements is connected to the real-time drilling data acquisition platform. The resulting model is the real-time drilling leakage rate prediction model based on RBF support vector machine. This model is used to predict real-time drilling data, thereby achieving the effect of real-time drilling leakage rate prediction.

[0060] Please see Figure 2 , Figure 2 This is a schematic diagram of the second part of the process of predicting drilling leakage rate based on RBF provided by the present invention. Figure 2 As shown, the method includes:

[0061] S21. Data denoising: Historical drilling data is determined by box plot method to obtain irrelevant data, duplicate data and smoothed noise data, and the irrelevant data, duplicate data and smoothed noise data are deleted.

[0062] In this embodiment, data denoising first uses the box plot method to identify noisy data in the drilling history data, then deletes irrelevant and duplicate data in the original dataset of drilling history data, smooths the noisy data, and at the same time filters out data that is not related to leak rate prediction, and handles missing values, outliers, etc.

[0063] S22. Data imputation: The irrelevant data, duplicate data, and smoothed noise data that were deleted during the data denoising process are imputed using the k-nearest neighbor algorithm.

[0064] In this embodiment, data imputation is performed by using the k-nearest neighbor algorithm to fill in the various types of data deleted during the data denoising process, thereby ensuring data integrity.

[0065] S23. Data conversion: The textual parameters of strata lithology and drill bit type in the data obtained by data denoising are converted into numerical parameters using the unique thermal encoding method.

[0066] In this embodiment, the data conversion uses the unique thermal coding method to convert the two parameters in the data, namely stratigraphy and drill bit type, which are described in words, into a digital form that can be used for data mining.

[0067] S24. Data integration: Merge and process historical drilling data in multi-file or multi-database operating environments.

[0068] In this embodiment, data integration involves merging drilling history data from multiple file or multiple database operating environments.

[0069] Please see Figure 3 , Figure 3 This is a schematic diagram of the third step in the process of predicting drilling leakage rate based on RBF provided by the present invention. Figure 3 As shown, the method includes:

[0070] S31. Divide the preprocessed historical drilling data into training set and test set.

[0071] In this embodiment, the historical data in the preprocessed drilling history database is divided into any reasonable proportion, such as 70% of the data being allocated to the training set S and 30% to the test set T.

[0072] S32. Normalize the training set and the test set according to the different parameters, and map them into parameter vectors.

[0073] In this embodiment, the standard deviation σ is taken.2 =3, and the drilling data is normalized in units of each drilling parameter.

[0074] S33. Apply Gaussian distribution mapping to the parameter vector to obtain the hyperplane formula.

[0075] In this embodiment, the normalized drilling data is mapped, transforming it from the original individual data x1, x2, ..., x... n , mapped to parameter vector φ(x i x j ).

[0076] Specifically, φ(x) i x j )={(x i x j )};

[0077] Where, x i x j For the collected well history data.

[0078] In this embodiment, a Gaussian distribution mapping in a high-dimensional space is completed, where the larger σ is, the smoother the curve of the normal distribution.

[0079] Specifically,

[0080] Where K(x) i x j ) is the kernel function for this Gaussian distribution mapping.

[0081] In this embodiment, the mapped parameter vector φ(x) is obtained. i x j After that, its dividing hyperplane can be represented as wφ(x) i )+b, where w and b are the slope and intercept of the hyperplane, respectively, so w and b can be calculated.

[0082] Specifically,

[0083] Where ξ is the slack variable, α and β are the value vectors of the hyperplane, and y is the leakage velocity vector.

[0084] In this embodiment, the data vectors segmented according to the hyperplane formula are subjected to RTF dual transformation.

[0085] Specifically,

[0086] Please see Figure 4 , Figure 4 This is a schematic diagram of the fourth step in the process of predicting drilling leakage rate based on RBF provided by the present invention. Figure 4 As shown, the method includes:

[0087] S41. Test the perceptron model using the test set.

[0088] S42. If the test results do not meet the accuracy requirements, regenerate the perceptron model.

[0089] In this embodiment, the two unknown functional variables g(x) and E(x) of the RBF support vector machine perceptron model for predicting leakage velocity are determined.

[0090] Specifically,

[0091]

[0092] In this embodiment, the variable factor vi of the support vector machine RBF function is obtained.

[0093] Specifically,

[0094] In this embodiment, the objective function W(α1, α2) is obtained based on the parameter vector, the hyperplane formula, and the kernel matrix.

[0095] Specifically,

[0096] In this embodiment, a new perceptron model is obtained based on the objective function. This model is the RBF support vector machine perceptron model for predicting leakage velocity.

[0097] Please see Figure 5 , Figure 5 This is a structural diagram of an RBF-based drilling loss rate prediction system provided by the present invention, as shown in the figure. Figure 5 As shown, the system includes: a data acquisition module, a data processing module, and a model generation module.

[0098] In this embodiment, the data acquisition module is specifically used to collect historical drilling data and real-time drilling data of the target block and perform data preprocessing.

[0099] In this embodiment, the data processing module is specifically used to obtain parameter vectors and hyperplane formulas based on the preprocessed historical drilling data, and to perform RTF dual transformation on the parameter vectors segmented by the hyperplane formulas to obtain the kernel matrix of the RBF support vector machine.

[0100] In this embodiment, the model generation module is specifically used to generate a perceptron model based on the parameter vector, the hyperplane formula, and the kernel matrix, to obtain a real-time prediction model for drilling leakage velocity based on RBF support vector machine, and to use the real-time prediction model to predict real-time drilling data to obtain a real-time prediction result for drilling leakage velocity.

[0101] In this embodiment, the data acquisition module is specifically used for data noise reduction. It uses the box plot method to determine historical drilling data, obtains irrelevant data, duplicate data, and smoothed noise data, and deletes the irrelevant data, duplicate data, and smoothed noise data.

[0102] In this embodiment, the data acquisition module is specifically used for data completion. It uses the k-nearest neighbor algorithm to complete the data by removing irrelevant data, duplicate data, and smoothed noise data that were deleted during the data denoising process.

[0103] In this embodiment, the data acquisition module is specifically used for data conversion, which uses a one-hot encoding method to convert the textual parameters of strata lithology and drill bit type in the data obtained by data denoising into digital parameters.

[0104] In this embodiment, the data acquisition module is specifically used for data integration and merging historical drilling data in multi-file or multi-database operating environments.

[0105] In this embodiment, the data processing module is specifically used to divide the preprocessed historical drilling data into a training set and a test set.

[0106] In this embodiment, the data processing module is specifically used to normalize the training set and the test set according to different parameters, and map them into parameter vectors.

[0107] In this embodiment, the data processing module is specifically used to perform Gaussian distribution mapping on the parameter vector to obtain the hyperplane formula.

[0108] like Figure 6 As shown, this embodiment of the invention provides an electronic device, including a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140.

[0109] Memory 1130 is used to store computer programs;

[0110] When the processor 1110 executes the program stored in the memory 1130, it implements any of the above-described determination methods.

[0111] The electronic device provided in this embodiment of the invention includes a processor 1110 that executes a program stored in a memory 1130 to obtain the fluid flow rate of each branch under different switching states and determines the initial volumetric flow rate of each branch; it corrects the initial volumetric flow rate based on the pipe parameters and fluid parameters of each branch when it is in operating condition and standard condition to obtain the standard condition volumetric flow rate of each branch; it obtains multiple total standard condition volumetric flow rates based on the standard condition volumetric flow rates of each branch under different switching states, and determines the optimal switching state of each branch by using the switching state of each branch when the total standard condition volumetric flow rate reaches a preset target.

[0112] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, it is shown in the figure with only one thick line, but this does not indicate that there is only one bus or one type of bus.

[0113] The communication interface 1120 is used for communication between the above-mentioned electronic device and other devices.

[0114] The memory 1130 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1130 may also be at least one storage device located remotely from the aforementioned processor 1110.

[0115] The processor 1110 mentioned above can be a general-purpose processor 1110, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0116] This invention provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors 1110 to implement the determination method of any of the above embodiments.

[0117] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0118] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting well leakage rate based on RBF (Recovery-Based Flow Rate), characterized in that, The method includes: Collect historical and real-time drilling data of the target block and perform data preprocessing; Based on the preprocessed historical drilling data, parameter vectors and hyperplane formulas are obtained. The parameter vectors segmented by the hyperplane formulas are subjected to RTF dual transformation to obtain the kernel matrix of the RBF support vector machine. Based on the parameter vector, the hyperplane formula, and the kernel matrix, a perceptron model is generated, and a real-time prediction model for drilling leakage velocity based on RBF support vector machine is obtained. The real-time prediction model is then used to predict real-time drilling data to obtain the real-time prediction result for drilling leakage velocity.

2. The prediction method according to claim 1, characterized in that, The data preprocessing includes: Data denoising involves using a box plot method to identify historical drilling data, resulting in irrelevant data, duplicate data, and smoothed noise data. The irrelevant data, duplicate data, and smoothed noise data are then deleted. Data imputation involves using the k-nearest neighbor algorithm to fill in irrelevant data, duplicate data, and smoothed noise data that were removed during the data denoising process. Data conversion involves using a one-hot encoding method to convert the textual parameters of formation lithology and drill bit type in the data obtained after data denoising into numerical parameters. Data integration, merging and processing historical drilling data in multi-file or multi-database operating environments.

3. The prediction method according to claim 1, characterized in that, The process of obtaining the parameter vector and hyperplane formula based on the preprocessed historical drilling data includes: The preprocessed historical drilling data is divided into training and testing sets. The training set and the test set are normalized according to the different parameters and mapped to parameter vectors; The hyperplane formula is obtained by mapping the parameter vector to a Gaussian distribution.

4. The prediction method according to claim 3, characterized in that, The generative perceptron model includes: The perceptron model is tested using the test set. If the test results do not meet the accuracy requirements, the perceptron model is regenerated.

5. The prediction method according to claim 4, characterized in that, The obtained real-time prediction model for drilling loss velocity based on RBF support vector machine includes: The sensor model that meets the accuracy requirements is connected to an instant acquisition platform that obtains real-time drilling data to obtain a real-time prediction model for drilling leakage rate based on RBF support vector machine.

6. A drilling loss rate prediction system based on RBF, characterized in that, The system includes: a data acquisition module, a data processing module, and a model generation module; The data acquisition module is used to collect historical and real-time drilling data of the target block and perform data preprocessing. The data processing module is used to obtain parameter vectors and hyperplane formulas based on the preprocessed historical drilling data, and to perform RTF dual transformation on the parameter vectors segmented by the hyperplane formula to obtain the kernel matrix of the RBF support vector machine. The model generation module is used to generate a perceptron model based on the parameter vector, the hyperplane formula, and the kernel matrix, to obtain a real-time prediction model for drilling leakage velocity based on RBF support vector machine, and to use the real-time prediction model to predict real-time drilling data to obtain the real-time prediction result of drilling leakage velocity.

7. The prediction system according to claim 6, characterized in that, include: The data acquisition module is also used for data noise reduction. It uses the box plot method to identify historical drilling data, obtain irrelevant data, duplicate data, and smoothed noise data, and deletes the irrelevant data, duplicate data, and smoothed noise data. The data acquisition module is also used for data completion, which uses the k-nearest neighbor algorithm to complete the data by removing irrelevant data, duplicate data and smoothed noise data that were deleted during the data denoising process. The data acquisition module is also used for data conversion, converting textual parameters of formation lithology and drill bit type in the data obtained by data noise reduction into numerical parameters through the one-hot encoding method; The data acquisition module is also used for data integration, merging and processing historical drilling data in multi-file or multi-database operating environments.

8. The prediction system according to claim 6, characterized in that, include: The data processing module is also used to divide the preprocessed historical drilling data into training and testing sets; The data processing module is also used to normalize the training set and the test set according to the different parameters, and map them into parameter vectors; The data processing module is also used to perform Gaussian distribution mapping on the parameter vector to obtain the hyperplane formula.

9. An electronic device, characterized in that, include: processor; And a memory storing computer-executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1-5.

10. A computer storage medium, characterized in that, in, The computer storage medium stores one or more programs, which, when executed by a processor, implement the method of any one of claims 1-5.

Images