Drilling cycle processing method and device based on probability density fitting

Abstract

The invention provides a drilling cycle processing method and device based on probability density fitting, and relates to the technical field of oil exploration and development drilling engineering.The method comprises the steps that drilling geological data and drilling engineering data are obtained; the drilled wells with the drilling geology and drilling engineering similarity reaching a set threshold value are screened, and a production cycle data set corresponding to the drilled wells is obtained; adopting data statistical distribution and parameter estimation to obtain a parameter set and a probability distribution function of each distribution; for the probability distribution function of each distribution, combining the prediction data and actual data of a drilled well to calculate a residual sum of squares corresponding to each distribution; a probability distribution function corresponding to the minimum residual sum of squares is selected, and whether the fitting effect of the well drilling prediction model reaches the standard or not is judged through goodness-of-fit test; according to the determined well drilling prediction model, the expected completion probability is calculated by inputting the expected completion probability and calculating the production cycle data, or inputting the design production cycle data and calculating the expected completion probability.

Description

Technical Field

[0001] The invention relates to the technical field of oil exploration and development drilling engineering, and in particular to a drilling cycle processing method and device based on probability density fitting. Background Art

[0002] This section is intended to provide a background or context for embodiments of the present invention. No description herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Drilling cycle design directly affects the efficiency, safety and economy of the entire drilling process, and comprehensively considers multiple factors such as efficiency, safety, cost and production efficiency. Optimizing drilling cycle design is crucial to the operation and management of the oil and gas industry, and directly affects the success of the overall project.

[0004] A properly designed drilling cycle can significantly improve the efficiency of drilling operations. This includes optimizing the switching of drilling sections, reducing the time of drilling and lifting drill tools, etc., which can minimize unnecessary pauses and waiting time. Efficient drilling cycle design can ensure the continuous progress of drilling operations and maximize the utilization of drilling equipment and human resources. Proper drilling cycle design can reduce safety risks in drilling operations. Through effective planning and scheduling, the possibility of accidents and unexpected events can be reduced. For example, avoiding equipment overload, reducing personnel fatigue, and reducing potential risks in drilling fluid circulation. Drilling cycle design directly affects the control and management of drilling costs. By properly planning the use of drilling tools, fluids, personnel and equipment, unnecessary resource waste can be reduced and the overall cost of drilling operations can be reduced. In addition, by optimizing the drilling cycle design, drilling time can be shortened and the rental time of expensive equipment and services can be reduced, thereby further reducing costs. Drilling cycle design not only affects the efficiency of drilling operations, but also directly affects the subsequent production stage. Efficient drilling cycle design can ensure wellbore quality and integrity, reduce the need for subsequent workovers and operations, and thus improve the overall production and efficiency of oil and gas wells.

[0005] At present, when designing the drilling cycle, each link of drilling is often subdivided into separate processes and determined according to the standard time requirements of each process. However, this design method has the following shortcomings: it does not take into account the additional time caused by various uncertain factors in actual production; it ignores the differences in geological conditions and drilling conditions in each block; it fails to make good use of the information on the drilling cycle of the block, and it is impossible to know the probability of the cycle meeting the standard.

[0006] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects, comprehensively analyze drilling-related data, and analyze the drilling cycle and completion probability. Summary of the invention

[0007] In order to solve the problems existing in the prior art, the present invention proposes a drilling cycle processing method and device based on probability density fitting. The present invention can conveniently, quickly, accurately and reliably process the drilling cycle, quickly and efficiently utilize the information of the wells that have been drilled in the block, provide probability data on whether the designed cycle can be realized, and provide a basis for relevant personnel to design the cycle.

[0008] In a first aspect of an embodiment of the present invention, a drilling cycle processing method based on probability density fitting is proposed, the method comprising:

[0009] Obtain drilling geological data and drilling engineering data;

[0010] According to the drilling geological data and drilling engineering data, the drilled wells whose drilling geological and drilling engineering similarities reach a set threshold are selected to obtain a production cycle data set corresponding to the drilled wells;

[0011] For the production cycle data set, using data statistical distribution and parameter estimation, a parameter set and a probability distribution function of each distribution are obtained;

[0012] constructing a drilling prediction model using the parameter set, and obtaining prediction data according to the drilling prediction model;

[0013] For the probability distribution function of each distribution, the residual sum of squares corresponding to each distribution is calculated by combining the predicted data and the actual data of the wells that have been drilled;

[0014] Selecting a probability distribution function corresponding to the minimum residual square sum, and judging whether the fitting effect of the drilling prediction model meets the standard through a goodness of fit test, if not, adjusting the parameter set to reconstruct the drilling prediction model, and if it meets the standard, determining the drilling prediction model;

[0015] According to the determined drilling prediction model, by inputting the expected completion probability, the production cycle data corresponding to the expected completion probability is calculated, or by inputting the designed production cycle data, the expected completion probability corresponding to the production cycle data is calculated.

[0016] In a second aspect of an embodiment of the present invention, a drilling cycle processing device based on probability density fitting is proposed, the device comprising:

[0017] Data acquisition module, used to acquire drilling geological data and drilling engineering data;

[0018] A screening module is used to screen the drilled wells whose drilling geology and drilling engineering similarity reaches a set threshold according to the drilling geological data and drilling engineering data, and obtain a production cycle data set corresponding to the drilled wells;

[0019] A data processing module, for obtaining a parameter set and a probability distribution function of each distribution by using data statistical distribution and parameter estimation for the production cycle data set;

[0020] A model building module, used to build a drilling prediction model using the parameter set, and obtain prediction data according to the drilling prediction model;

[0021] A residual square sum calculation module, for calculating the residual square sum corresponding to each distribution based on the probability distribution function of each distribution, in combination with the predicted data and the actual data of the wells that have been drilled;

[0022] A judgment module is used to select a probability distribution function corresponding to the minimum residual square sum, and to judge whether the fitting effect of the drilling prediction model meets the standard through a goodness of fit test. If it does not meet the standard, the parameter set is adjusted to reconstruct the drilling prediction model. If it meets the standard, the drilling prediction model is determined;

[0023] The output module is used to calculate the production cycle data corresponding to the expected completion probability by inputting the expected completion probability according to the determined drilling prediction model, or to input the designed production cycle data to calculate the expected completion probability corresponding to the production cycle data.

[0024] In a third aspect of an embodiment of the present invention, a computer device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a drilling cycle processing method based on probability density fitting when executing the computer program.

[0025] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a drilling cycle processing method based on probability density fitting is implemented.

[0026] In a fifth aspect of an embodiment of the present invention, a computer program product is proposed. The computer program product includes a computer program. When the computer program is executed by a processor, a drilling cycle processing method based on probability density fitting is implemented.

[0027] The drilling cycle processing method and device based on probability density fitting proposed by the present invention obtain drilling geological data and drilling engineering data; according to the drilling geological data and drilling engineering data, screen the drilled wells whose drilling geological and drilling engineering similarities reach the set threshold value to obtain the production cycle data set corresponding to the drilled wells; for the production cycle data set, adopt data statistical distribution and parameter estimation to obtain a parameter set and a probability distribution function of each distribution; use the parameter set to build a drilling prediction model, and obtain prediction data according to the drilling prediction model; for the probability distribution function of each distribution, combine the prediction data and the actual data of the drilled wells to calculate the residual sum of squares corresponding to each distribution; select the probability distribution function corresponding to the minimum residual sum of squares, and judge whether the fitting effect of the drilling prediction model meets the standard through the goodness of fit test. If not, adjust the parameter set to reconstruct the drilling prediction model, and if it meets the standard, determine the drilling prediction model; according to the determined drilling prediction model, by inputting the expected completion probability, calculate the production cycle data corresponding to the expected completion probability, or input the designed production cycle data, calculate the expected completion probability corresponding to the production cycle data. The present invention can process the drilling cycle conveniently, quickly, accurately and reliably, and quickly and efficiently utilize the information of the wells that have been drilled in the block to provide probability data on whether the designed cycle can be achieved, and provide a basis for relevant personnel to design the cycle. The overall solution takes into account the extra time caused by various uncertain factors in actual production, and combines the differences in geological conditions and drilling conditions of each block, and uses the information of the wells that have been drilled in the block to analyze the probability of reaching the cycle standard and the drilling completion cycle, providing strong data support for drilling construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 It is a flow chart of a drilling cycle processing method based on probability density fitting according to an embodiment of the present invention.

[0030] Figure 2 It is a flowchart of a goodness of fit test according to an embodiment of the present invention.

[0031] Figure 3 Schematic diagram of the probability density function of Weibull distribution according to an embodiment of the present invention.

[0032] Figure 4 Schematic diagram of the cumulative distribution function of Weibull distribution according to an embodiment of the present invention.

[0033] Figure 5 Schematic diagram of calculation results of the residual sum of squares of each distribution according to an embodiment of the present invention.

[0034] Figure 6 It is a schematic diagram of hypothesis testing results and period design results according to an embodiment of the present invention.

[0035] Figure 7 It is a schematic diagram of the architecture of a drilling cycle processing device based on probability density fitting according to an embodiment of the present invention.

[0036] Figure 8 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0038] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0039] According to the implementation mode of the present invention, a drilling cycle processing method and device based on probability density fitting are proposed, which relates to the field of oil exploration and development drilling engineering technology. The overall solution proposes a convenient, fast, accurate and reliable drilling cycle design method, which can quickly and efficiently utilize the block's drilled well information, provide probability data for whether the design cycle can be realized, and provide a basis for relevant personnel to design the cycle.

[0040] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0041] Figure 1 FIG. 1 is a flow chart of a drilling cycle processing method based on probability density fitting according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0042] S101, obtaining drilling geological data and drilling engineering data;

[0043] S102, based on the drilling geological data and the drilling engineering data, screening the drilled wells whose drilling geological and drilling engineering similarities reach a set threshold, and obtaining a production cycle data set corresponding to the drilled wells;

[0044] S103, for the production cycle data set, using data statistical distribution and parameter estimation to obtain a parameter set and a probability distribution function of each distribution;

[0045] S104, constructing a drilling prediction model using the parameter set, and obtaining prediction data according to the drilling prediction model;

[0046] S105, for each distribution probability distribution function, combining the predicted data and the actual data of the wells that have been drilled, calculating the residual sum of squares corresponding to each distribution;

[0047] S106, selecting a probability distribution function corresponding to the minimum residual square sum, and judging whether the fitting effect of the drilling prediction model meets the standard through a goodness of fit test, if not, adjusting the parameter set to reconstruct the drilling prediction model, and if meeting the standard, determining the drilling prediction model;

[0048] S107, according to the determined drilling prediction model, by inputting the expected completion probability, calculating the production cycle data corresponding to the expected completion probability, or by inputting the designed production cycle data, calculating the expected completion probability corresponding to the production cycle data.

[0049] In order to explain the above-mentioned drilling cycle processing method based on probability density fitting more clearly, it is described in detail below in conjunction with an embodiment.

[0050] In one embodiment, the drilling geological data at least includes: geological conditions of the well area and data of the well area to which it belongs; the geological conditions of the well area at least include: burial depth of formation, exposed formation, and structural category;

[0051] Drilling engineering data shall at least include: drilling conditions, drilling equipment, well type, wellbore structure, completed well depth and drilling technology.

[0052] In one embodiment, for data analysis and statistical modeling, the data used may have errors, missing data, large format differences, etc., which affect the data analysis and modeling effect. The data can be preprocessed to avoid the above problems. Specifically, the method also includes:

[0053] The drilling geological data and drilling engineering data are preprocessed; wherein, duplicate or erroneous data are removed by data cleaning; the data are standardized by data conversion, and continuous variables are discretized to obtain categorical variables; and missing data are filled with the mean, median or mode.

[0054] Data cleaning: Remove duplicate records; correct or delete erroneous and inconsistent data; handle missing values, such as by deletion, filling, or interpolation.

[0055] Data integration: Merging data from different sources; dealing with inconsistencies between data sources.

[0056] Data transformation: standardizing or normalizing data to make it have a uniform scale; discretizing data to convert continuous variables into categorical variables; feature engineering, such as creating new features or modifying existing features to improve model performance.

[0057] Data dimensionality reduction: Reducing the number of features while retaining the most important information through methods such as principal component analysis (PCA).

[0058] Feature encoding: Convert categorical variables into numerical variables, such as using One-Hot Encoding.

[0059] Data discretization: Splitting continuous variables into intervals or categories to simplify the model or deal with nonlinear relationships.

[0060] Data smoothing: Reducing noise in the data, such as using a moving average or median filter.

[0061] Outlier detection and handling: Identify and handle outliers, possibly by removing, replacing, or adjusting them using the model.

[0062] Data Resampling: In an imbalanced dataset, balance the data by oversampling the minority class or undersampling the majority class.

[0063] Time series data preprocessing: detrending and seasonal adjustment of time series data.

[0064] Data normalization: transforming data into a standard normal distribution, often used in machine learning algorithms.

[0065] Missing value handling: fill missing values ​​using mean, median, mode or other algorithms.

[0066] Data type conversion: Convert data into a format suitable for analysis, such as conversion of date and time formats.

[0067] Data encoding: Convert text data into numerical values, for example using word embeddings or label encoding.

[0068] Data batching: Split the data into small batches for processing to fit within memory constraints.

[0069] In drilling cycle design, data preprocessing may include processing drilling log data, processing time series data, processing missing values, outlier detection and processing, etc. to ensure the quality of data and the accuracy of analysis.

[0070] In one embodiment, the method of data statistical distribution includes at least: normal distribution, exponential distribution, Weibull distribution, Student's t distribution, generalized extreme value distribution, gamma distribution, lognormal distribution, beta distribution, uniform distribution, loggamma distribution, Pareto distribution;

[0071] In one embodiment, the parameter estimation method includes at least: maximum likelihood estimation, moment estimation method, least squares method, Bayesian estimation, and Monte Carlo method.

[0072] In one embodiment, S105, for the probability distribution function of each distribution, the residual sum of squares corresponding to each distribution is calculated by combining the predicted data and the actual data of the wells that have been drilled, including:

[0073] The residual sum of squares is calculated as:

[0074]

[0075] In the formula, RSS represents the residual sum of squares, n represents the number of data, and e i represents the i-th residual, y i represents the i-th actual data, Represents the i-th predicted data;

[0076] The residual sum of squares is used to measure the quality of the model fitting the data. The smaller the value, the better the model fitting effect and the smaller the difference between the predicted data and the actual data.

[0077] In one embodiment, the method of goodness of fit test at least includes: KS test;

[0078] refer to Figure 2 , is a flow chart of a goodness of fit test according to an embodiment of the present invention. Figure 2 As shown, for S106, the probability distribution function corresponding to the minimum residual square sum is selected, and the goodness of fit test is performed to determine whether the fitting effect of the drilling prediction model meets the standard. If it does not meet the standard, the parameter set is adjusted to reconstruct the drilling prediction model. If it meets the standard, the drilling prediction model is determined, including:

[0079] S1061, for the drilling prediction model, set a reference distribution, and calculate a cumulative distribution function corresponding to the reference distribution; wherein the cumulative distribution function is an integral of a probability distribution function, and is used to represent the probability that a random variable is less than or equal to a preset value;

[0080] S1062, calculating the maximum absolute difference according to the probability distribution function corresponding to the minimum residual sum of squares and the cumulative distribution function corresponding to the reference distribution;

[0081] The maximum absolute difference is calculated as:

[0082] D=sup x |F n (x1)-F(x2)|;

[0083] In the formula, D represents the statistic of KS test, sup x represents the maximum absolute difference, x represents all samples, F n (x1) represents the cumulative distribution function of the sample data, x1 represents the sample data, F(x2) represents the cumulative distribution function of the reference data, x2 represents the sample of the reference distribution;

[0084] S1063, setting the significance critical value of KS check;

[0085] Among them, determine the critical value or p-value: according to the sample size and significance level (such as 0.05), find the critical value of the KS test or calculate the p-value. The critical value or p-value is used to judge statistical significance.

[0086] If the calculated KS statistic is greater than the critical value, or the p-value is less than the significance level, then the null hypothesis is rejected, that is, the sample distribution is considered to be significantly different from the reference distribution.

[0087] If the KS statistic is less than the critical value, or the p-value is greater than the significance level, the null hypothesis cannot be rejected, that is, there is insufficient evidence to show that the sample distribution is different from the reference distribution.

[0088] If the model fits well, the results of the KS test should indicate that there is no significant difference between the distribution generated by the model and the actual data distribution.

[0089] S1064, if the statistic of the KS test is greater than the set threshold, or the distribution probability of the statistic is less than the significance critical value, it means that the fitting effect does not meet the standard; otherwise, it is determined that the fitting effect meets the standard.

[0090] It should be noted that, although the operations of the method of the present invention are described in a specific order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0091] Through indicators such as well type, wellbore structure, completed well depth, and well area, we screened wells with similar geological profiles and drilling conditions, and collected the full-well production cycle data of these wells (i.e., the effective period after deducting non-production periods such as complex time, accident time, and group downtime from the drilling cycle).

[0092] Specifically, similar wells are screened based on geological and engineering characteristics, and their production cycle data sets are obtained.

[0093] According to common data distribution methods (such as normal distribution (norm), exponential distribution (expon), Weibull distribution (dweibull), Student's t distribution (t), generalized extreme value distribution (genextreme), gamma distribution (gamma), lognormal distribution (lognorm), beta distribution (beta), uniform distribution (uniform), loggamma distribution (loggamma), Pareto distribution (pareto), etc.), use maximum likelihood estimation or other parameter estimation methods to optimize parameter values ​​to minimize the residual sum of squares RSS, and then find the parameter combination that makes the fitting model fit the actual data best. According to the minimum residual sum of squares RSS, determine the final probability distribution function and its model parameter set.

[0094] Specifically, according to common statistical distributions, the parameter set θ is determined in combination with the parameter estimation method to obtain the probability distribution function of each distribution, for example, f1(x), f2(x), ..., fn'(x); n' is the total number of distributions, and x is all samples; combining the actual data and the predicted data, the residual sum of squares RSS1, RSS2, ..., RSS n' corresponding to each distribution is calculated in turn.

[0095] According to the principle of minimizing RSS, the probability distribution function is determined. Assuming it is f(x), the corresponding distribution function is t represents the production cycle data.

[0096] Use goodness-of-fit test methods, such as the KS test (Kolmogorov-Smirnov test) to measure the model's fit and determine whether the model's fit is good.

[0097] After the probability distribution function is determined, the distribution function value under the corresponding probability (ie, the production cycle data) can be calculated by inputting the probability, or the corresponding probability can be obtained by integrating the input production cycle data.

[0098] If the model fitting effect is good, the probability of completing drilling within the design period can be determined based on the fitted distribution function.

[0099] For example, assuming that the designed production cycle is a, then its probability is

[0100] Taking the production cycle of the specified design as an example, the probability of achieving the design is 0.3, and the corresponding production cycle a is calculated to meet the requirements.

[0101] The following is described in conjunction with a specific embodiment:

[0102] Filter the cycle data of completed wells in a certain main area, remove the non-production time, and obtain the cycle data set. Draw common descriptive statistics to roughly understand its cycle distribution.

[0103] According to common statistical distributions, combined with parameter estimation methods, the parameter set θ is determined to obtain the probability distribution functions f1(x), f2(x), ..., fn'(x) of each distribution. Combined with actual data and predicted data, the residual sum of squares RSS1, RSS2, ..., RSS n' corresponding to each distribution is calculated in turn.

[0104] refer to Figure 3 , which is a schematic diagram of the probability density function of the Weibull distribution according to an embodiment of the present invention. Figure 4 , is a schematic diagram of the cumulative distribution function of the Weibull distribution according to an embodiment of the present invention. Figure 5 , which is a schematic diagram of calculation results of the residual sum of squares of each distribution according to an embodiment of the present invention.

[0105] refer to Figures 3 to 5 , the smallest RSS (residual sum of squares) is the Weibull distribution (dweibull), whose value is 0.000565578, and the corresponding parameter set θ = {loc = 37.826 (often omitted, location parameter), scale = 12.292 = λ, k = 1.17}, and its corresponding probability distribution function is:

[0106]

[0107] Wherein, x represents a sample (random variable), λ>0 is a scale parameter, which is equal to scale=12.292 here; k>0 is a shape parameter, which is equal to 1.17 here.

[0108] According to calculations, at a 90% confidence level, the overall period mean falls within [12.86, 62.79], unit, day (d).

[0109] According to the distribution function, the probability of completing the drilling within the design period can be determined. For example, assuming that the design drilling period is 50 days, the cumulative probability of completion within 50 days is:

[0110]

[0111] The calculated result is 0.628.

[0112] If the specified design cycle can meet the realization probability of 0.3, calculate the corresponding design cycle a; that is, calculate a to meet:

[0113]

[0114] refer to Figure 6 , which is a schematic diagram of hypothesis test results and cycle design results according to an embodiment of the present invention. Figure 6 The calculated result is 42.92, and the fitting result is good (the null hypothesis is rejected).

[0115] After introducing the method of the exemplary embodiment of the present invention, next, refer to Figure 7 A drilling cycle processing device based on probability density fitting according to an exemplary embodiment of the present invention is introduced.

[0116] The implementation of the drilling cycle processing device based on probability density fitting can refer to the implementation of the above method, and the repeated parts will not be repeated. The term "module" or "unit" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0117] Based on the same inventive concept, the present invention also proposes a drilling cycle processing device based on probability density fitting, such as Figure 7 As shown, the device comprises:

[0118] Data acquisition module 710, used to acquire drilling geological data and drilling engineering data;

[0119] A screening module 720 is used to screen the drilled wells whose drilling geology and drilling engineering similarity reaches a set threshold according to the drilling geological data and drilling engineering data, and obtain a production cycle data set corresponding to the drilled wells;

[0120] A data processing module 730 is used to obtain a parameter set and a probability distribution function of each distribution using data statistical distribution and parameter estimation for the production cycle data set;

[0121] A model building module 740 is used to build a drilling prediction model using the parameter set and obtain prediction data according to the drilling prediction model;

[0122] A residual square sum calculation module 750 is used to calculate the residual square sum corresponding to each distribution based on the probability distribution function of each distribution, combined with the predicted data and the actual data of the wells that have been drilled;

[0123] A judgment module 760 is used to select a probability distribution function corresponding to the minimum residual square sum, and to judge whether the fitting effect of the drilling prediction model meets the standard through a goodness of fit test. If not, the parameter set is adjusted to reconstruct the drilling prediction model. If it meets the standard, the drilling prediction model is determined.

[0124] The output module 770 is used to calculate the production cycle data corresponding to the expected completion probability by inputting the expected completion probability according to the determined drilling prediction model, or to calculate the expected completion probability corresponding to the production cycle data by inputting the designed production cycle data.

[0125] It should be noted that although several modules of the drilling cycle processing device based on probability density fitting are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules for embodiment.

[0126] Based on the above invention concept, Figure 8 As shown, the present invention also proposes a computer device 800, including a memory 810, a processor 820, and a computer program 830 stored in the memory 810 and executable on the processor 820, wherein the processor 820 implements the aforementioned drilling cycle processing method based on probability density fitting when executing the computer program 830.

[0127] Based on the aforementioned inventive concept, the present invention proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the aforementioned drilling cycle processing method based on probability density fitting is implemented.

[0128] Based on the aforementioned inventive concept, the present invention proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, a drilling cycle processing method based on probability density fitting is implemented.

[0129] The drilling cycle processing method and device based on probability density fitting proposed by the present invention obtain drilling geological data and drilling engineering data; according to the drilling geological data and drilling engineering data, screen the drilled wells whose drilling geological and drilling engineering similarities reach the set threshold value to obtain the production cycle data set corresponding to the drilled wells; for the production cycle data set, adopt data statistical distribution and parameter estimation to obtain a parameter set and a probability distribution function of each distribution; use the parameter set to build a drilling prediction model, and obtain prediction data according to the drilling prediction model; for the probability distribution function of each distribution, combine the prediction data and the actual data of the drilled wells to calculate the residual sum of squares corresponding to each distribution; select the probability distribution function corresponding to the minimum residual sum of squares, and judge whether the fitting effect of the drilling prediction model meets the standard through the goodness of fit test. If not, adjust the parameter set to reconstruct the drilling prediction model, and if it meets the standard, determine the drilling prediction model; according to the determined drilling prediction model, by inputting the expected completion probability, calculate the production cycle data corresponding to the expected completion probability, or input the designed production cycle data, calculate the expected completion probability corresponding to the production cycle data. The present invention can process the drilling cycle conveniently, quickly, accurately and reliably, and quickly and efficiently utilize the information of the wells that have been drilled in the block to provide probability data on whether the designed cycle can be achieved, and provide a basis for relevant personnel to design the cycle. The overall solution takes into account the extra time caused by various uncertain factors in actual production, and combines the differences in geological conditions and drilling conditions of each block, and uses the information of the wells that have been drilled in the block to analyze the probability of reaching the cycle standard and the drilling completion cycle, providing strong data support for drilling construction.

[0130] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations.

[0131] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The present invention is described with reference to flowcharts and / or block diagrams of methods and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A drilling cycle processing method based on probability density fitting, characterized in that: The method includes: Obtain drilling geological data and drilling engineering data; According to the drilling geological data and drilling engineering data, the drilled wells whose drilling geological and drilling engineering similarities reach a set threshold are selected to obtain a production cycle data set corresponding to the drilled wells; For the production cycle data set, using data statistical distribution and parameter estimation, a parameter set and a probability distribution function of each distribution are obtained; constructing a drilling prediction model using the parameter set, and obtaining prediction data according to the drilling prediction model; For the probability distribution function of each distribution, the residual sum of squares corresponding to each distribution is calculated by combining the predicted data and the actual data of the wells that have been drilled; Selecting a probability distribution function corresponding to the minimum residual square sum, and judging whether the fitting effect of the drilling prediction model meets the standard through a goodness of fit test, if not, adjusting the parameter set to reconstruct the drilling prediction model, and if it meets the standard, determining the drilling prediction model; According to the determined drilling prediction model, by inputting the expected completion probability, the production cycle data corresponding to the expected completion probability is calculated, or by inputting the designed production cycle data, the expected completion probability corresponding to the production cycle data is calculated.

2. The drilling cycle processing method based on probability density fitting according to claim 1, characterized in that: The drilling geological data at least include: geological conditions of the well area and data of the well area to which it belongs; the geological conditions of the well area at least include: burial depth of strata, exposed strata, and structural categories; Drilling engineering data shall at least include: drilling conditions, drilling equipment, well type, wellbore structure, completed well depth and drilling technology.

3. The drilling cycle processing method based on probability density fitting according to claim 1, characterized in that: The method further includes: The drilling geological data and drilling engineering data are preprocessed; wherein, duplicate or erroneous data are removed by data cleaning; the data are standardized by data conversion to obtain data with a uniform proportion; and missing data are filled with the mean, median or mode.

4. The drilling cycle processing method based on probability density fitting according to claim 1, characterized in that: The method of data statistical distribution includes at least: normal distribution, exponential distribution, Weibull distribution, Student's t distribution, generalized extreme value distribution, gamma distribution, lognormal distribution, beta distribution, uniform distribution, loggamma distribution, Pareto distribution; The parameter estimation method includes at least: maximum likelihood estimation, moment estimation method, least squares method, Bayesian estimation, and Monte Carlo method.

5. The drilling cycle processing method based on probability density fitting according to claim 1, characterized in that: For the probability distribution function of each distribution, the residual sum of squares corresponding to each distribution is calculated by combining the predicted data and the actual data of the wells that have been drilled, including: The residual sum of squares is calculated as: In the formula, RSS represents the residual sum of squares, n represents the number of data, and e i represents the i-th residual, y i represents the i-th actual data, Represents the i-th predicted data; The residual sum of squares is used to measure the quality of the model fitting the data. The smaller the value, the better the model fitting effect and the smaller the difference between the predicted data and the actual data.

6. The drilling cycle processing method based on probability density fitting according to claim 1, characterized in that: The method of the goodness of fit test at least includes: KS test; The probability distribution function corresponding to the minimum residual square sum is selected, and whether the fitting effect of the drilling prediction model meets the standard is judged through the goodness of fit test. If it does not meet the standard, the parameter set is adjusted to reconstruct the drilling prediction model. If it meets the standard, the drilling prediction model is determined, including: For the drilling prediction model, a reference distribution is set, and a cumulative distribution function corresponding to the reference distribution is calculated; wherein the cumulative distribution function is the integral of the probability distribution function, and is used to represent the probability that a random variable is less than or equal to a preset value; Calculating the maximum absolute difference based on the probability distribution function corresponding to the minimum residual sum of squares and the cumulative distribution function corresponding to the reference distribution; The maximum absolute difference is calculated as: D=sup x |F n (x1)-F(x2)|; In the formula, D represents the statistic of KS test, sup x represents the maximum absolute difference, x represents all samples, F n (x1) represents the cumulative distribution function of the sample data, x1 represents the sample data, F(x2) represents the cumulative distribution function of the reference data, x2 represents the sample of the reference distribution; Set the significance critical value of KS test; If the statistic of the KS test is greater than the set threshold, or the distribution probability of the statistic is less than the significance critical value, it means that the fitting effect does not meet the standard; otherwise, it is judged that the fitting effect meets the standard.

7. A drilling cycle processing device based on probability density fitting, characterized in that: The device includes: Data acquisition module, used to acquire drilling geological data and drilling engineering data; A screening module is used to screen the drilled wells whose drilling geology and drilling engineering similarity reaches a set threshold according to the drilling geological data and drilling engineering data, and obtain a production cycle data set corresponding to the drilled wells; A data processing module, for obtaining a parameter set and a probability distribution function of each distribution by using data statistical distribution and parameter estimation for the production cycle data set; A model building module, used to build a drilling prediction model using the parameter set, and obtain prediction data according to the drilling prediction model; A residual square sum calculation module, for calculating the residual square sum corresponding to each distribution based on the probability distribution function of each distribution, in combination with the predicted data and the actual data of the wells that have been drilled; A judgment module is used to select a probability distribution function corresponding to the minimum residual square sum, and to judge whether the fitting effect of the drilling prediction model meets the standard through a goodness of fit test. If it does not meet the standard, the parameter set is adjusted to reconstruct the drilling prediction model. If it meets the standard, the drilling prediction model is determined; The output module is used to calculate the production cycle data corresponding to the expected completion probability by inputting the expected completion probability according to the determined drilling prediction model, or to input the designed production cycle data to calculate the expected completion probability corresponding to the production cycle data.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images