A method, device, equipment and storage medium for reducing the risk of sticking

Abstract

The present application provides a method, device, equipment and storage medium for reducing the risk of sticking, comprising: obtaining input data of a prediction model and sticking probability corresponding to the input data, wherein the input data comprises fixed parameters and controllable parameters; when the sticking probability is higher than a first sticking threshold, generating a random population according to the controllable parameters; after adaptive screening, crossover operation and mutation operation on the random population, obtaining random parameters; inputting the random parameters and the fixed parameters into the prediction model to obtain an optimized sticking probability; if the optimized sticking probability is lower than a second sticking threshold, using the random parameters as the controllable parameters to guide the deployment of horizontal well drilling; when the sticking probability is higher than the first sticking threshold, generating random parameters according to the controllable parameters and inputting the random parameters and the fixed parameters into the prediction model to obtain an adjusted sticking probability according to the prediction model; when the sticking probability is lower than the second sticking threshold, using the random parameters to guide the deployment of horizontal well drilling.

Description

Technical Field

[0001] This invention relates to the field of drilling technology, and in particular to a method, apparatus, equipment and storage medium for reducing the risk of stuck pipe. Background Technology

[0002] Horizontal well drilling is a crucial component in obtaining industrial gas flow from shale gas. During the drilling process, handling complex situations and drilling accidents accounts for approximately 6% to 8% of the total construction time, and stuck pipe accidents account for 40% to 50% of all drilling accidents. From 2018 to 2020 alone, 75 wells in southern Sichuan experienced stuck pipe incidents, with an average stuck pipe rate as high as 10.15%. Stuck pipe incidents significantly increased non-productive time and resulted in substantial direct economic losses from buried drilling tools. To effectively address the problems of long drilling cycles and high costs caused by stuck pipe incidents and improve drilling efficiency, targeted monitoring methods are needed to provide timely warnings of potential stuck pipe risks, thereby assisting engineers in taking timely and effective measures during construction.

[0003] However, the existing overflow stuck drill alarm method can only issue an early warning when the probability of stuck drill is high, but it cannot inform technicians which controllable factors can be adjusted to reduce the probability of stuck drill. Therefore, the existing overflow stuck drill alarm method has certain limitations. Summary of the Invention

[0004] To address the aforementioned problems in the prior art, the purpose of this paper is to provide a method, apparatus, device, and storage medium for reducing the risk of stuck drill pipe, thereby solving the problem that the prior art can only provide early warnings to technicians when the probability of stuck drill pipe is high, but cannot inform technicians how to reduce the probability of stuck drill pipe.

[0005] To solve the above-mentioned technical problems, the specific technical solution presented in this paper is as follows:

[0006] On the one hand, this article provides a method to reduce the risk of stuck drill bits, including:

[0007] Obtain the input data of the prediction model and the probability of stuck drill corresponding to the input data, wherein the input data includes fixed parameters and controllable parameters;

[0008] When the probability of the drill getting stuck is higher than the first threshold, a random population is generated according to the controllable parameters;

[0009] After performing adaptive screening, crossover, and mutation operations on the random population, random parameters are obtained;

[0010] Both the random parameters and the fixed parameters are imported into the prediction model to obtain the optimized probability of the drill getting stuck.

[0011] If the optimized stuck pipe probability is lower than the second stuck pipe threshold, the random parameter is used as the controllable parameter to guide the horizontal well drilling deployment.

[0012] As an embodiment of this article, the step of performing adaptive screening, crossover, and mutation operations on the random population to obtain random parameters further includes:

[0013] The probability range of the random population is determined based on the fitness of each individual in the random population.

[0014] Generate a probability random number, and select the individual according to the probability interval corresponding to the probability random number;

[0015] Using the above method, extract an even number of the individuals;

[0016] By interchanging several binary elements among the individuals, we obtain the swapped individuals;

[0017] By inverting at least one of the binary elements in the exchanged individual, a transformed individual is obtained;

[0018] The transformed individual is converted to decimal to obtain the random parameters.

[0019] As an embodiment of this article, determining the probability interval of the random population based on the fitness of each individual in the random population further includes:

[0020] Calculate the individual selection probability of each individual in the random population;

[0021] The cumulative probability of an individual is determined based on its selection probability, and the probability range of the random population is determined.

[0022] As an embodiment of this article, the step of generating a random population based on the controllable parameters further includes:

[0023] The controllable parameters are converted into binary arrays and treated as individuals, wherein the binary arrays include a plurality of the binary elements;

[0024] The controllable parameters are adjusted using a baseline step size, and several individuals are obtained using the above method and used as the random population.

[0025] As an embodiment of this article, calculating the individual selection probability of each individual in the random population further includes:

[0026] According to the fitness function f(s) = s 2 The fitness of the individual is determined, wherein s is the decimal value of the individual;

[0027] According to the fitness accumulation formula Determine the sum of the fitness of the random population, where N is the number of individuals in the random population;

[0028] Based on the individual choice probability function Determine the individual selection probability of the individual, where i is the individual's ID.

[0029] As an embodiment of this document, the step of determining the cumulative probability of an individual based on the individual selection probability and determining the probability interval of the random population further includes:

[0030] According to the cumulative probability function Determine the cumulative probability of the individual, where i is the individual's ID;

[0031] Divide the number line into intervals according to the cumulative probability of the individuals, and use the divided intervals as the probability intervals of the random population.

[0032] As an embodiment of this article, the step of cross-transforming several binary elements between the individuals to obtain the exchanged individuals further includes:

[0033] Align the two individuals according to their digits;

[0034] By swapping the corresponding binary elements of the two individuals, two swapped individuals are obtained.

[0035] As an embodiment of this document, the step of performing an inverse transformation on at least one of the binary elements in the exchanged individual to obtain the transformed individual further includes:

[0036] Randomly determine the number of digits to be changed in the individuals to be exchanged;

[0037] If the digit is 1, then change that digit to 0 to obtain the transformed individual;

[0038] If the digit is 0, then the digit is changed to 1 to obtain the transformed individual.

[0039] As an example of this paper, the prediction model is obtained through pre-training;

[0040] The input data for the prediction model includes engineering data, geological data, and mud data;

[0041] The input data for the prediction model includes the probability of a stuck drill.

[0042] The engineering data includes fixed parameters and controllable parameters, including drilling pressure and displacement.

[0043] On the other hand, this article also provides a device for reducing the risk of stuck drill bits, including:

[0044] An acquisition unit is used to acquire the input data of the prediction model and the stuck probability corresponding to the input data, wherein the input data includes fixed parameters and controllable parameters;

[0045] A random population generation unit is used to generate a random population based on the controllable parameters when the drill jam probability is higher than the first drill jam threshold.

[0046] The random parameter unit is used to obtain random parameters after performing adaptive screening, crossover operation, and mutation operation on the random population;

[0047] An import unit is used to import both the random parameters and the fixed parameters into the prediction model to obtain an optimized stuck drill probability.

[0048] An adjustment unit is used to, if the optimized stuck pipe probability is lower than the second stuck pipe threshold, use the random parameter as the controllable parameter to guide the horizontal well drilling deployment.

[0049] On the other hand, this document also provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements any one of the methods described herein.

[0050] On the other hand, this document also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements any one of the methods described herein.

[0051] Using the above technical solution, when the probability of stuck drill bit is higher than the first stuck drill bit threshold, random parameters can be generated based on controllable parameters. The random parameters and fixed parameters are then input into the prediction model, and the adjusted stuck drill bit probability is obtained based on the prediction model. When the probability of stuck drill bit is lower than the second stuck drill bit threshold, the random parameters can be used to guide the construction personnel in deploying horizontal well drilling.

[0052] To make the above and other objects, features and advantages of this document more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments or prior art described herein, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this article. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This document illustrates an overall system diagram for reducing the risk of stuck drill bits according to an embodiment of the present invention.

[0055] Figure 2 A schematic diagram illustrating the steps of a method for creating a prediction model according to an embodiment of this paper is shown.

[0056] Figure 3 This document illustrates a step diagram of a method for reducing the risk of stuck drill pipe according to an embodiment of the invention.

[0057] Figure 4 This document illustrates a schematic diagram of the random parameter determination process in an embodiment of the invention.

[0058] Figure 5 This paper illustrates a schematic diagram of the probability interval determination process in an embodiment of the invention.

[0059] Figure 6 This paper illustrates a probability interval diagram according to an embodiment of the invention.

[0060] Figure 7 A schematic diagram of an apparatus for reducing the risk of stuck drill bit according to an embodiment of this article is shown;

[0061] Figure 8 A schematic diagram of a computer device according to an embodiment of this article is shown.

[0062] Explanation of symbols in the attached drawings:

[0063] 1. Sensors;

[0064] 2. Server;

[0065] 3. Controller;

[0066] 701. Acquisition Unit;

[0067] 702. Random population generation unit;

[0068] 703, Random Parameter Unit;

[0069] 704. Importing Unit;

[0070] 705. Adjustment unit;

[0071] 802. Computer equipment;

[0072] 804, Processor;

[0073] 806. Memory;

[0074] 808. Drive mechanism;

[0075] 810. Input / Output Module;

[0076] 812. Input devices;

[0077] 814. Output devices;

[0078] 816. Presentation equipment;

[0079] 818. Graphical User Interface;

[0080] 820. Network interface;

[0081] 822. Communication link;

[0082] 824. Communication bus. Detailed Implementation

[0083] The technical solutions in the embodiments described below will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, and not all of the embodiments. Based on the embodiments described herein, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this document.

[0084] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0085] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0086] Stuck drill incidents are frequent occurrences in oil and gas extraction, causing numerous accidents. The mechanisms and causes of stuck drills are complex, and the main controlling factors are unclear, making it difficult to reduce the frequency of these incidents. Currently, many technicians use mathematical methods of risk management to identify and analyze stuck drill risks. However, most risk identification methods only utilize static pre-drilling design data, such as drilling fluid type, geological data, or drill bit type, without combining actual drilling data and engineering calculation results, thus neglecting the importance of real-time downhole data for identifying stuck drill incidents.

[0087] Some technicians also match historical data of stuck pipe incidents with field data. When the field data is similar to the historical data, the drilling process is stopped to avoid stuck pipe. However, field data and historical data are rarely similar, so this method of judging stuck pipe is not accurate and has a lag.

[0088] Therefore, this paper proposes a prediction model that can combine drilling field data and pre-drilling data to determine the probability of stuck pipe during drilling. It also proposes a method to reduce the risk of stuck pipe, which automatically adjusts the field data when the probability of stuck pipe exceeds the first stuck pipe threshold, so as to minimize the probability of stuck pipe during drilling.

[0089] like Figure 1 The diagram shows an overall system for reducing the risk of stuck drill bits, including sensor 1, server 2, and controller 3.

[0090] Sensor 1 is used to acquire field data during drilling, including engineering data and mud data. The engineering data includes fixed parameters and controllable parameters. Controllable parameters include drilling pressure and displacement, while fixed parameters include drilling depth and wellbore diameter.

[0091] Server 2 is used to run the prediction model and also to store geological parameters of the wellbore area, such as distribution patterns, overburden pressure, and formation distribution patterns. When making predictions, the prediction model acquires the current engineering data, mud data, and preset geological data of the well, calculates the sticking probability, and after determining the sticking probability, Server 2 sends the sticking probability to Controller 3.

[0092] Controller 3 is used to display the probability of stuck drill pipe. When the probability of stuck drill pipe exceeds the first stuck drill pipe threshold, controller 3 can stop the drilling process and send an adjustment command to server 2. Server 2 runs a method to reduce the risk of stuck drill pipe and can adjust the controllable parameters. After the probability of stuck drill pipe is lower than the second stuck drill pipe threshold, server 2 sends an adjustment completion command to controller 3. Controller 3 can then send a continue drilling command to order the drilling process to continue.

[0093] In this paper, the first stuck drill threshold is greater than the second stuck drill threshold. The first stuck drill threshold can be selected as 50%, 55%, or 60%, etc., and this paper does not limit it. The second stuck drill threshold can be selected as 5%, 6%, or 7%, etc., and this paper does not limit it.

[0094] For ease of explanation, this article will first describe the method for creating the prediction model, and then, based on the prediction model, explain in detail the methods for reducing the risk of stuck drill pipe.

[0095] Because most risk identification methods only use static pre-drilling design data, such as drilling fluid type, geological data, or drill bit type, without combining actual drilling data and engineering calculation results, and ignoring the importance of real-time downhole data for identifying stuck pipe incidents, existing stuck pipe prediction models have low accuracy.

[0096] To address the aforementioned issues, this paper provides a method for creating prediction models that can generate highly accurate prediction models suitable for real-time drilling data. Figure 2 This is a schematic diagram illustrating the steps of a predictive model creation method provided in the embodiments of this document. This specification provides the operational steps of the method described in the embodiments or flowcharts, but based on conventional or non-creative labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual system or device products, the methods shown in the embodiments or drawings can be executed sequentially or in parallel. Specifically, as shown in the figures... Figure 2 As shown, the method may include:

[0097] Step 201: Obtain the raw data and preprocess the raw data to obtain noise-reduced data.

[0098] Step 202: Obtain the master control sample set based on the noise reduction data.

[0099] Step 203: Normalize the master control sample set and use it as input data. Use the stuck drill probability as the objective function to train the initial model to obtain the prediction model.

[0100] Through the above process, a prediction model can be established using the original samples, and then the probability of stuck pipe in drilling can be predicted using the prediction model.

[0101] As one embodiment of this article, before obtaining the raw data, the following steps are included:

[0102] Perform the following on historical data: check for misaligned rows and columns, check for null values, standardize units, handle outliers and invalid values, and merge data.

[0103] The processed historical data is mapped to a high-dimensional feature space using a nonlinear mapping φ, and then an orthogonalization algorithm is applied to obtain the original data.

[0104] In this paper, historical data can be cleaned and filtered by detecting misaligned rows and columns, checking for null values, standardizing units, handling outliers and invalid values, and merging data, so as to avoid Z-shaped convergence when training the prediction model.

[0105] Using orthogonalization algorithms can make the data more standardized, allowing the original data to be better classified in subsequent steps.

[0106] As an embodiment of this article, obtaining the master control sample set based on the noise reduction data includes:

[0107] Correlation analysis is performed on the noise reduction data to obtain the expanded original data;

[0108] The importance analysis of the expanded original data is performed to obtain the master control sample set.

[0109] To maximize the sample space of the prediction model with small data samples, this paper performs correlation analysis to include a series of parameters related to the parameters determined as inputs to the prediction model into the sample space. As an example, the correlation analysis performed on the denoised data to obtain expanded original data includes:

[0110] Determine the association parameters that are linked to the original data;

[0111] Calculate the correlation between the correlation parameters and the original data;

[0112] When the correlation of the correlation parameter is greater than the first correlation threshold, the correlation parameter is included in the original data.

[0113] In this step, we set xi as the correlation parameter and yi as a target parameter in the original data. It should be noted that in this paper, the original data consists of several target parameters, each of which is a dimension in the prediction model. We then calculate the correlation between xi and yi.

[0114] The specific correlation calculation process is as follows: Design a linear regression equation, which includes at least a correlation parameter, a target parameter, and a stuck drill probability. Calculate the correlation between the correlation parameter and the linear regression equation. If the correlation is greater than a first correlation threshold, the correlation parameter is included in the original data as a strongly correlated parameter; if the correlation is less than a second correlation threshold, the correlation parameter is removed.

[0115] To accelerate the convergence speed of the prediction model, this paper proposes to reduce the dimensionality of the original data based on importance analysis, thereby reducing the input dimension of the prediction model. The importance analysis performed on the expanded original data yields the master control sample set, which includes:

[0116] Principal component analysis is used to calculate the weights of each parameter in the original data, and several parameters are selected.

[0117] The selected parameters are then subjected to dimensionality reduction to obtain the master control sample set.

[0118] The above method can achieve two dimensionality reductions, where the number of parameters to be selected can be determined based on historical experience, such as 17, 18, or 19.

[0119] After selecting several parameters, the selected parameters are decentralized and dimensionality reduced to obtain a sample set that can roughly represent real-time drilling data and pre-drilling data.

[0120] Further, the selected parameters are dimensionality reduced to obtain the master control sample set, including the following sub-steps:

[0121] The original data D = (x(1), x(2), ..., x(n)) is decentered, and the sample covariance matrix xxT is calculated; where x(n) is the selected parameter.

[0122] The eigenvalues ​​of the sample covariance matrix xxT are decomposed to form the eigenvector matrix W.

[0123] The sample is transformed according to the formula z(i)=WTx(n), and the transformed sample is reduced in dimensionality to output the master control sample set D`=(z(1),z(2)….,z(m)), where z(m) is the parameter after dimensionality reduction.

[0124] After acquiring the complete data, the prediction model is trained to obtain the prediction model, which specifically includes:

[0125] Randomly select some parameters from the master control sample set as test samples, and use the remaining samples as training samples; use real-time data containing engineering type, geological type and mud type as input vector, and the stuck drill probability as target vector;

[0126] Input the training samples into the training model to perform training;

[0127] The parameters in the test sample are randomly divided into K parts. Each time, K-1 parts are taken as the training set and the remaining part is taken as the validation set. The validation is performed K times in a loop.

[0128] After verification, the root mean square error is used to evaluate the accuracy of the prediction model. If the accuracy of the prediction model reaches or exceeds the set value, the prediction model is qualified and can be applied; if the accuracy of the prediction model is less than the set value, the main control factors are remodeled.

[0129] In this article, the setting value can be 95%.

[0130] In existing technologies, predictive models can only warn technicians when the probability of stuck pipe is high, allowing them to stop the drilling process. However, they cannot tell technicians how to adjust relevant parameters to reduce the probability of stuck pipe and avoid extending the project time due to stopping the drilling process.

[0131] To address the aforementioned issues, this paper provides a method for reducing the risk of stuck pipe, which can create a highly accurate predictive model based on real-time drilling data. Figure 3 This document illustrates the steps of a method for reducing the risk of stuck drill bits, as provided in the embodiments. While this specification provides the operational steps described in the embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive methods. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible order. In actual system or device products, the methods shown in the embodiments or accompanying drawings can be executed sequentially or in parallel. Specifically, as shown... Figure 3 As shown, the method may include:

[0132] Step 301: Obtain the input data of the prediction model and the stuck drill probability corresponding to the input data, wherein the input data includes fixed parameters and controllable parameters.

[0133] Step 302: When the probability of the drill getting stuck is higher than the first threshold, a random population is generated according to the controllable parameters.

[0134] Step 303: After performing adaptive screening, crossover operation and mutation operation on the random population, random parameters are obtained.

[0135] Step 304: Import both the random parameters and the fixed parameters into the prediction model to obtain the optimized probability of the drill getting stuck.

[0136] Step 305: If the optimized stuck pipe probability is lower than the second stuck pipe threshold, the random parameter is used as the controllable parameter to guide the horizontal well drilling deployment.

[0137] Using the above method, when the probability of stuck drill bit is higher than the first stuck drill bit threshold, random parameters can be generated based on controllable parameters. These random parameters and fixed parameters are then input into the prediction model, and the adjusted stuck drill bit probability can be obtained based on the prediction model. When the probability of stuck drill bit is lower than the second stuck drill bit threshold, the random parameters can be used to guide the construction personnel in deploying horizontal well drilling.

[0138] As an embodiment of this article, the step of generating a random population based on the controllable parameters further includes:

[0139] The controllable parameters are converted into binary arrays and treated as individuals, wherein the binary arrays include a plurality of the binary elements.

[0140] The controllable parameters are adjusted using a baseline step size, and several individuals are obtained using the above method and used as the random population.

[0141] Taking a number as an example, such as 19, it can be converted into a binary array (10011). By changing a 1 in one of the binary digits of 19 to 0, or a 0 to 1, we get three binary arrays: 24 (11000), 13 (01101), and 8 (01000). These four numbers can be used as a random population.

[0142] like Figure 4 The schematic diagram of the random parameter determination process, as an embodiment of this article, further includes step 303, which involves subjecting the random population to adaptive screening, crossover, and mutation operations to obtain random parameters.

[0143] Step 401: Determine the probability range of the random population based on the fitness of each individual in the random population.

[0144] Step 402: Generate a probability random number, and select the individual according to the probability interval corresponding to the probability random number.

[0145] Step 403: Using the above method, extract an even number of the individuals.

[0146] Step 404: Cross-transform several binary elements between the individuals to obtain the exchanged individuals.

[0147] Step 405: Perform an inverse transformation on at least one of the binary elements in the exchanged individual to obtain the transformed individual.

[0148] Step 406: Convert the transformed individual into decimal to obtain the random parameters.

[0149] In this step, since the random population represents the characteristics of a series of parameters around the controllable parameter, in order to better select the most representative series of numbers in the random population, this paper presents a process for selecting parameters based on individual fitness.

[0150] In step 403, the above method is used to extract an even number of individuals. Since step 404 requires two individuals to undergo a difference transformation, when an odd number of individuals are extracted and cross-transformed, repeated transformations may occur, resulting in invalid transformations. Therefore, in a better case, this paper needs to extract an even number of individuals.

[0151] In step 401, since each individual belongs to a random population, the probability interval of the random population can be determined by summing the fitness of the individuals. Step 401 is based on the fitness of each individual in the random population, such as... Figure 5 The schematic diagram shown illustrates the process of determining the probability interval, including:

[0152] Step 501: Calculate the individual selection probability of each individual in the random population.

[0153] Step 502: Determine the cumulative probability of the individual based on the individual selection probability, and determine the probability range of the random population.

[0154] In this step, the individual selection probability is related to the individual's fitness. It can be seen that in a population, the higher the fitness of an individual, the higher the probability of selecting that individual in the future.

[0155] In this paper, the probability interval of a random population can be represented by the length of a line segment or the area of ​​a circle. If a line segment is chosen, the length of the line segment is 1. Thus, within the line segment, the longer the line segment of an individual, the greater the probability that individual will be selected.

[0156] In this paper, all individuals need to be sorted, and the cumulative probability of an individual is the sum of the probabilities of the top few individuals and the individual in the sorting result.

[0157] Step 501 specifically includes:

[0158] According to the fitness function f(s) = s 2 The fitness of the individual is determined, where s is the decimal value of the individual. It should be noted that s is the decimal value of the individual. For ease of explanation, individual 13 can be s1, individual 24 can be s2, individual 8 can be s3, and individual 19 can be s4. For example, when the individual is 8, the fitness of the individual is 64.

[0159] According to the fitness accumulation formula The sum of fitness of the random population is determined, where N is the number of individuals in the random population; it should be noted that the sum of fitness of the random population in this paper... The answer is 64 + 169 + 576 + 361 = 1170.

[0160] Based on the individual choice probability function Determine the individual selection probability of the individual, where i is the individual's ID.

[0161] For ease of explanation, we can sort 13, 24, 8, and 19 in sequence to obtain p(s1), p(s2), p(s3), and p(s4).

[0162] Step 502, determining the cumulative probability of an individual based on its selection probability and determining the probability interval of the random population, further includes:

[0163] According to the cumulative probability function Determine the cumulative probability of the individual, where i is the individual's ID;

[0164] For example, when it is necessary to determine the cumulative probability of individual s1,

[0165] When it is necessary to determine the cumulative probability of individual s2,

[0166] When it is necessary to determine the cumulative probability of individual s3,

[0167] When it is necessary to determine the cumulative probability of individual s4,

[0168] Divide the number line into intervals according to the cumulative probability of the individuals, and use the divided intervals as the probability intervals of the random population.

[0169] like Figure 6 The diagram shows a probability interval. Figure 6 This demonstrates that different fitness levels represent different proportions in a random population. The number line in this paper is a line segment of unit length 1, where the interval 0.00–0.14 is used as the probability interval for individual s1, 0.14–0.63 as the probability interval for individual s2, 0.63–0.69 as the probability interval for individual s3, and 0.69–1.00 as the probability interval for individual s4.

[0170] Step 402 generates a probability random number and selects the individual according to the probability interval corresponding to the probability random number, specifically including:

[0171] Generate a random number between 0 and 1, and determine if the random number falls into any of the following ranges: Figure 6 Which part of the sample? If the random number is 0.45, then select individual s2; if the random number is 0.70, then select individual s4. An even number of individuals are selected in this way, paired up, and then swapped and mutated.

[0172] As an embodiment of this article, the step of cross-transforming several binary elements between the individuals to obtain the exchanged individuals further includes:

[0173] Align the two individuals according to their digits;

[0174] By swapping the corresponding binary elements of the two individuals, two swapped individuals are obtained.

[0175] In this step, if individuals s2 and s4 are transformed, the first three digits of the binary array (11000) and the second-order array (10011) can be swapped, that is, (11000) is transformed into (10000) and (10011) is transformed into (11011).

[0176] As an embodiment of this document, the step of performing an inverse transformation on at least one of the binary elements in the exchanged individual to obtain the transformed individual further includes:

[0177] Randomly determine the number of digits to be changed in the individuals to be exchanged;

[0178] If the digit is 1, then change that digit to 0 to obtain the transformed individual;

[0179] If the digit is 0, then the digit is changed to 1 to obtain the transformed individual.

[0180] In this step, the binary element at a certain position in the binary array is reversed. For example, the third bit of (10000) can be reversed to get (10100), and the third bit of (11011) can be reversed to get (11111). In this way, after two transformations, the value of the controllable parameter can be increased as much as possible.

[0181] It should be noted that this article does not limit the number of bits in the binary array targeted by the commutation and inverse transformations; this article only provides an illustrative explanation.

[0182] As an example of this paper, the prediction model is obtained through pre-training;

[0183] The input data for the prediction model includes engineering data, geological data, and mud data;

[0184] The input data for the prediction model includes the probability of a stuck drill.

[0185] The engineering data includes fixed parameters and controllable parameters, including drilling pressure and displacement.

[0186] It should be noted that the individuals mentioned above in this article can be drilling pressure or displacement. After generating random parameters, the random parameters can replace the controllable parameters currently obtained by the sensors. After replacing the controllable parameters, the random parameters can be imported into the prediction model together with the fixed parameters to obtain the optimized stuck drill probability.

[0187] If the probability of stuck pipe is lower than the second stuck pipe threshold, the current random parameters are displayed to the user as controllable parameters, allowing the user to deploy horizontal drilling based on these parameters. This reduces the probability of stuck pipe during subsequent drilling.

[0188] like Figure 7 A schematic diagram of a device for reducing the risk of stuck drill pipe is shown, comprising:

[0189] The acquisition unit 701 is used to acquire the input data of the prediction model and the stuck probability corresponding to the input data, wherein the input data includes fixed parameters and controllable parameters.

[0190] The random population generation unit 702 is used to generate a random population based on the controllable parameters when the probability of the drill getting stuck is higher than the first drill getting stuck threshold.

[0191] The random parameter unit 703 is used to obtain random parameters by performing adaptive screening, crossover operation and mutation operation on the random population.

[0192] Import unit 704 is used to import both the random parameters and the fixed parameters into the prediction model to obtain the optimized stuck drill probability.

[0193] The adjustment unit 705 is used to use the random parameter as the controllable parameter to guide the horizontal well drilling deployment if the optimized stuck pipe probability is lower than the second stuck pipe threshold.

[0194] With the above-mentioned device, when the probability of stuck drill bit is higher than the first stuck drill bit threshold, random parameters can be generated based on controllable parameters. The random parameters and fixed parameters are then input into the prediction model, and the adjusted stuck drill bit probability is obtained based on the prediction model. When the probability of stuck drill bit is lower than the second stuck drill bit threshold, the random parameters can be used to guide the construction personnel in deploying horizontal well drilling.

[0195] like Figure 8As shown in this embodiment, a computer device is provided for running a predictive model and generating random parameters. The computer device 802 may include one or more processors 804, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 802 may also include any memory 806 for storing information of any kind, such as code, settings, data, etc. Non-limitingly, for example, the memory 806 may include any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 802. In one case, when the processor 804 executes associated instructions stored in any memory or combination of memories, the computer device 802 can perform any operation of the associated instructions. The computer device 802 also includes one or more drive mechanisms 808 for interacting with any memory, such as hard disk drive mechanisms, optical disk drive mechanisms, etc.

[0196] Computer device 802 may also include an input / output module 810 (I / O) for receiving various inputs (via input device 812) and providing various outputs (via output device 814). A specific output mechanism may include a presentation device 816 and an associated graphical user interface (GUI) 818. In other embodiments, the input / output module 810 (I / O), input device 812, and output device 814 may be omitted, and the device may function solely as a computer device within a network. Computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communication buses 824 couple the components described above together.

[0197] Communication link 822 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0198] Corresponding to Figures 2-5 In addition to the methods described above, this embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the above-described methods.

[0199] This embodiment also provides a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to perform the following: Figures 2 to 5 The method shown.

[0200] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0201] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0202] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0203] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0204] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0205] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0206] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0207] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this paper, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this paper. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0208] This document uses specific embodiments to illustrate the principles and implementation methods of this document. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this document. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this document. Therefore, the content of this specification should not be construed as a limitation of this document.

Claims

1. A method for reducing the risk of stuck drill bit, characterized in that, include: Obtain the input data of the prediction model and the probability of stuck drill corresponding to the input data, wherein the input data includes fixed parameters and controllable parameters; When the probability of the drill getting stuck is higher than the first threshold, a random population is generated according to the controllable parameters; After performing adaptive screening, crossover, and mutation operations on the random population, random parameters are obtained. Both the random parameters and the fixed parameters are imported into the prediction model to obtain the optimized probability of the drill getting stuck. If the optimized stuck pipe probability is lower than the second stuck pipe threshold, the random parameter is used as the controllable parameter to guide the horizontal well drilling deployment; The step of performing adaptive screening, crossover, and mutation operations on the random population to obtain random parameters further includes: The probability range of the random population is determined based on the fitness of each individual in the random population. Generate a probability random number, and select the individual according to the probability interval corresponding to the probability random number; Using the above method, extract an even number of the individuals; By interchanging several binary elements among the individuals, we obtain the swapped individuals; By inverting at least one of the binary elements in the exchanged individual, a transformed individual is obtained; The transformed individual is converted to decimal to obtain the random parameters; The step of determining the probability interval of the random population based on the fitness of each individual in the random population further includes: Calculate the individual selection probability of each individual in the random population; The cumulative probability of an individual is determined based on the individual selection probability, and the probability interval of the random population is determined accordingly. The step of generating a random population based on the controllable parameters further includes: The controllable parameters are converted into binary arrays and treated as individuals, wherein the binary arrays include a plurality of the binary elements; The controllable parameters are adjusted using a baseline step size, and several individuals are obtained using the above method and used as the random population.

2. The method for reducing the risk of stuck drill bit according to claim 1, characterized in that, The calculation of the individual selection probability of each individual in the random population further includes: Based on the fitness function Determine the fitness of the individual, wherein the s Convert the value of the individual into a decimal number; According to the fitness accumulation formula Determine the total fitness of the random population, where N is the number of individuals in the random population; Based on the individual choice probability function Determine the individual selection probability of the individual, where i is the individual's ID.

3. The method for reducing the risk of stuck drill bit according to claim 2, characterized in that, The step of determining the cumulative probability of an individual based on its selection probability, and determining the probability interval of the random population, further includes: Based on the cumulative probability function Determine the cumulative probability of the individual, where i is the individual's ID; Divide the number line into intervals according to the cumulative probability of the individuals, and use the divided intervals as the probability intervals of the random population.

4. The method for reducing the risk of stuck drill bit according to claim 1, characterized in that, The step of cross-transforming several binary elements between the individuals to obtain the exchanged individuals further includes: Align the two individuals according to their digits; By swapping the corresponding binary elements of the two individuals, two swapped individuals are obtained.

5. The method for reducing the risk of stuck drill bit according to claim 1, characterized in that, The step of performing an inverse transformation on at least one of the binary elements in the exchanged individual to obtain the transformed individual further includes: Randomly determine the number of digits to be changed in the individuals to be exchanged; If the digit is 1, then change that digit to 0 to obtain the transformed individual; If the digit is 0, then the digit is changed to 1 to obtain the transformed individual.

6. The method for reducing the risk of stuck drill bit according to claim 1, characterized in that, The prediction model is pre-trained; The input data for the prediction model includes engineering data, geological data, and mud data; The input data for the prediction model includes the probability of a stuck drill. The engineering data includes fixed parameters and controllable parameters, including drilling pressure and displacement.

7. A device for reducing the risk of stuck drill bit, characterized in that, include: An acquisition unit is used to acquire the input data of the prediction model and the stuck probability corresponding to the input data, wherein the input data includes fixed parameters and controllable parameters; A random population generation unit is used to generate a random population based on the controllable parameters when the drilling jam probability is higher than a first drilling jam threshold; the generation of the random population based on the controllable parameters further includes: converting the controllable parameters into a binary array and using it as an individual, wherein the binary array includes a plurality of binary elements; adjusting the controllable parameters with a reference step size, and obtaining a plurality of individuals using the above method and using them as the random population; The random parameter unit is used to obtain random parameters after performing adaptive screening, crossover, and mutation operations on the random population; it is further used to determine the probability interval of the random population based on the fitness of each individual in the random population; generate a probabilistic random number and select an individual according to the probability interval corresponding to the probabilistic random number; extract an even number of individuals using the above methods; cross-transform several binary elements between the individuals to obtain exchange individuals; reverse the transformation of at least one binary element in the exchange individuals to obtain transformed individuals; convert the transformed individuals to decimal to obtain the random parameters; the step of determining the probability interval of the random population based on the fitness of each individual in the random population further includes: calculating the individual selection probability of each individual in the random population; determining the cumulative probability of the individual based on the individual selection probability, and determining the probability interval of the random population; An import unit is used to import both the random parameters and the fixed parameters into the prediction model to obtain an optimized stuck drill probability. An adjustment unit is used to, if the optimized stuck pipe probability is lower than the second stuck pipe threshold, use the random parameter as the controllable parameter to guide the horizontal well drilling deployment.

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, it implements the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.

Images