Horizontal well guiding abnormality early warning method and device, storage medium and equipment

Abstract

The application discloses a horizontal well abnormal guidance early warning method and device, a storage medium and equipment, and belongs to the technical field of oil and gas engineering drilling and completion. The method comprises the following steps: acquiring three-dimensional position coordinate data, GR data while drilling, drilling time data and lithology logging data of drilled wells in a target block as an input data set; simulating GR data while drilling of a new well according to the GR data while drilling of the drilled wells, combining the input data set, and obtaining the predicted depth of the drill bit of the new well through a horizontal section intelligent guidance judgment model; and judging whether an abnormality occurs in the drilling process according to the predicted depth and a target formation. The application constructs a horizontal section borehole trajectory prediction model in the drilling process based on an artificial intelligence method, solves the problems that a drilled position cannot be found in time and a drill bit cannot be automatically adjusted in the horizontal well drilling process, improves the horizontal well drilling efficiency and reservoir drilling rate, improves the single-well production and recovery rate of an oil and gas reservoir, and reduces the field construction cost.

Description

Technical Field

[0001] This invention relates to the field of drilling and completion technology in oil and gas engineering, and in particular to a method, device, storage medium and equipment for early warning of horizontal well directional anomalies. Background Technology

[0002] In the field of oil and gas drilling and development, with the accelerated pace of unconventional oil and gas exploration, horizontal well drilling has gradually become the mainstream. The horizontal section of a horizontal well is prone to encountering formation crossing problems during drilling, thus requiring geosteering technology for directional prediction. Traditional geosteering technology uses measurement-while-drilling tools to collect underground drilling and geological parameter information, analyze the contact relationship between the drilling trajectory and the formation, and understand the wellbore trajectory and reservoir spatial distribution. The geosteering software in the surface system processes and analyzes the received information and guides the next drilling step, achieving accurate horizontal well landing and improving reservoir encounter rate.

[0003] However, traditional geological steering technology requires manual judgment and issuance of drilling instructions, resulting in low drilling efficiency and reservoir encounter rate, making it difficult to improve the production and recovery rate of single wells in complex oil and gas reservoirs. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method, device, storage medium, and equipment for early warning of horizontal well directional anomalies. This solves problems such as the inability to detect drilled formations in a timely manner and to automatically adjust the drill bit during horizontal well drilling, thereby improving the drilling efficiency and reservoir encounter rate of coalbed methane horizontal wells, increasing the production and recovery rate of single wells in complex oil and gas reservoirs, and reducing on-site construction costs.

[0005] The technical solution provided by this invention is as follows:

[0006] In a first aspect, the present invention provides a method for early warning of directional anomalies in horizontal wells, the method comprising:

[0007] The three-dimensional location coordinates, drilling GR data, drilling time data, and lithological logging data of the drilled wells within the entire target block are obtained as the input dataset.

[0008] Based on the drilling GR data of several existing wells in the target block, the drilling GR data of new wells in the target block are simulated. Based on the simulated drilling GR data of new wells and the input dataset, the predicted depth of the drill bit of the new well is obtained through the established horizontal section intelligent guidance judgment model.

[0009] Based on the predicted depth of the new well bit and the target formation, determine whether any abnormalities occurred during the drilling process.

[0010] Furthermore, the input dataset is obtained through the following method:

[0011] Based on the raw data collected on-site within the target block, the drilling GR data, drilling time data, and lithology logging data of the drilled wells within the target block were compiled.

[0012] The collected drilling GR data, drilling time data, and lithological logging data are loaded into 3D geological modeling software to establish a 3D geological model of the target block.

[0013] The input dataset is obtained by exporting the three-dimensional coordinate data of the geographical locations of drilled wells within the entire target block, the drilling GR data, the drilling time data, the lithological logging data, the established three-dimensional geological model, and the three-dimensional coordinate data of the geographical locations of drilled wells within the three-dimensional geological model according to the set precision.

[0014] Furthermore, the step of simulating the drilling GR data of newly drilled wells within the target block based on the drilling GR data of several existing wells within the target block includes:

[0015] Use the nearest existing wells around the new well in the target block as reference wells;

[0016] The drilling GR data of a portion of the reference well is used as the GR value of the corresponding section of the new well to simulate the drilling GR data of the new well.

[0017] Furthermore, the step of obtaining the predicted depth of the drill bit in the new well based on the simulated drilling GR data of the new well and the input dataset, through the established horizontal section intelligent steering judgment model, includes:

[0018] Based on the drilling GR data of the new well obtained from the simulation, an intelligent steering judgment model for the horizontal section is established.

[0019] The simulated GR data of the new well and the input dataset are used as input to the horizontal section intelligent steering judgment model, and the probability distribution of the specific depth of the drill bit in the new well is output.

[0020] The maximum value in the probability distribution is taken as the predicted depth of the drill bit for the new well.

[0021] Furthermore, the probability distribution of the specific depth of the drill bit in the new well is calculated using the following formula:

[0022]

[0023] in, Let f(φ) represent the probability distribution at a specific depth φ, i represent the i-th measurement point that has been drilled, γ represent the GR data while drilling, j represent the j-th point in the depth domain corresponding to the i-th measurement point, f() represents the probability density function, and p represents the prior probability distribution.

[0024] Furthermore, the step of determining whether any anomalies occurred during the drilling process of the new well, based on the predicted depth of the drill bit and the target formation, includes:

[0025] Determine whether the predicted depth of the new drilling bit has penetrated the top and bottom interfaces of the target formation. If it has, the drill bit has penetrated the formation, an anomaly is detected, and an alarm is triggered.

[0026] The data corresponding to the points where anomalies occurred are included in the original data, and the original data is updated.

[0027] Furthermore, the method also includes:

[0028] The three-dimensional geological model is updated in real time using updated raw data.

[0029] Secondly, the present invention provides a horizontal well steering anomaly early warning device, the device comprising:

[0030] The data acquisition module is used to acquire the three-dimensional location coordinates of drilled wells, drilling GR data, drilling time data, and lithology logging data within the entire target block as input datasets.

[0031] The prediction module is used to simulate the drilling GR data of a new well in the target block based on the drilling GR data of several existing wells in the target block, and to obtain the predicted depth of the drill bit of the new well based on the simulated drilling GR data of the new well and the input dataset through the established horizontal section intelligent guidance judgment model.

[0032] The early warning module is used to determine whether any abnormalities occur during the drilling process of a new well, based on the predicted depth of the drill bit and the target formation.

[0033] Furthermore, the input dataset is obtained through the following process:

[0034] The raw data acquisition unit is used to process the raw data collected on-site within the target block to obtain the drilling GR data, drilling time data and lithology logging data of the drilled wells within the target block;

[0035] The three-dimensional geological model building unit is used to load the processed drilling GR data, drilling time data and lithology logging data into the three-dimensional geological modeling software to build a three-dimensional geological model of the target block.

[0036] The input dataset export unit is used to export the three-dimensional coordinate data of the geographical locations of drilled wells within the entire target block, the drilling GR data, the drilling time data, the lithological logging data, the established three-dimensional geological model, and the three-dimensional coordinate data of the geographical locations of drilled wells within the three-dimensional geological model according to the set precision, to obtain the input dataset.

[0037] Furthermore, the prediction module includes:

[0038] The reference well prediction unit is used to select several nearest existing wells around the new well in the target block as reference wells.

[0039] The GR simulation unit is used to simulate the drilling GR data of the new well by using the drilling GR data of a portion of the reference well as the GR value of the corresponding well section.

[0040] Furthermore, the prediction module also includes:

[0041] The model building unit is used to build a horizontal section intelligent steering judgment model based on the drilling GR data of the new well obtained from the simulation.

[0042] The probability distribution prediction unit is used to take the simulated drilling GR data of the new well and the input dataset as input to the horizontal section intelligent guidance judgment model, and output the probability distribution of the specific depth of the drill bit in the new well.

[0043] The predicted depth determination unit is used to take the maximum value in the probability distribution as the predicted depth of the drill bit for new drilling.

[0044] Furthermore, the probability distribution of the specific depth of the drill bit in the new well is calculated using the following formula:

[0045]

[0046] in, Let f(φ) represent the probability distribution at a specific depth φ, i represent the i-th measurement point that has been drilled, γ represent the GR data while drilling, j represent the j-th point in the depth domain corresponding to the i-th measurement point, f() represents the probability density function, and p represents the prior probability distribution.

[0047] Furthermore, the early warning module includes:

[0048] The early warning unit is used to determine whether the predicted depth of the drill bit in the new well has penetrated the top and bottom interfaces of the target formation. If it has, the drill bit has penetrated the formation, an abnormality is detected, and an alarm is triggered.

[0049] The data update unit is used to incorporate the data corresponding to the points where anomalies occur into the original data and update the original data.

[0050] Furthermore, the device also includes:

[0051] The model update module is used to update the three-dimensional geological model in real time using updated raw data.

[0052] Thirdly, the present invention provides a computer-readable storage medium for early warning of horizontal well guidance anomalies, including a memory for storing processor-executable instructions, which, when executed by the processor, implement the steps of the horizontal well guidance anomaly early warning method described in the first aspect.

[0053] Fourthly, the present invention provides a device for early warning of horizontal well directional anomalies, characterized in that it includes at least one processor and a memory storing computer-executable instructions, wherein the processor executes the instructions to implement the steps of the horizontal well directional anomaly early warning method described in the first aspect.

[0054] The present invention has the following beneficial effects:

[0055] This invention utilizes artificial intelligence to construct a wellbore trajectory prediction model for horizontal sections during drilling, overcoming the challenge of drill bit positioning in coalbed methane horizontal well drilling. It solves problems such as the inability to promptly detect drilled formations and automatically adjust the drill bit during horizontal well drilling, significantly improving drilling efficiency and reservoir encounter rate in coalbed methane horizontal wells. This also substantially increases single-well production and recovery rates in complex oil and gas reservoirs, while reducing on-site construction costs. Furthermore, it reduces energy and resource waste caused by drill bit encountering formations and resulting drilling corrections or downtime, making oil and gas drilling and extraction greener, more energy-efficient, low-carbon, environmentally friendly, and highly efficient. Attached Figure Description

[0056] Figure 1 This is a flowchart of the horizontal well steering anomaly early warning method of the present invention;

[0057] Figure 2 The final prediction results are shown using a single well as a reference well.

[0058] Figure 3 The final prediction results are presented using two wells as reference wells;

[0059] Figure 4 This is a schematic diagram of the horizontal well guidance anomaly early warning device of the present invention. Detailed Implementation

[0060] To make the technical problems, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. The components of the embodiments of this invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0061] This invention provides a method for early warning of directional anomalies in horizontal wells, such as... Figure 1 As shown, the method includes:

[0062] S1: Acquire the three-dimensional location coordinates of drilled wells, drilling GR (natural gamma) data, drilling time data, and lithology logging data within the entire target block as input datasets.

[0063] As an example, the specific implementation process of this step includes:

[0064] S11: Based on the raw data collected on-site within the target block, the drilling GR data, drilling time data, and lithology logging data of the drilled wells within the target block are compiled.

[0065] For example, raw data collected in the field from a target block in the Ordos Basin can be cleaned (including checking for outliers and supplementing missing data) based on the increasing well depth pattern to obtain the drilling GR data, drilling time data, and lithological logging data for the target block. As an improvement, optionally, gas logging data and corresponding well depth information can also be obtained simultaneously; this information can also be included in subsequent input datasets.

[0066] S12: Load the collected drilling GR data, drilling time data, and lithological logging data into the 3D geological modeling software to establish a 3D geological model of the target block.

[0067] For example, the cleaned data can be organized into a standard format and loaded into PETREL software to create a three-dimensional geological model;

[0068] S13: Export the three-dimensional coordinate data of the geographical locations of the drilled wells within the entire target block (i.e., X, Y, Z data of the geographical location coordinates), drilling GR data, drilling time data, lithology logging data, the established three-dimensional geological model, and the three-dimensional coordinate data of the geographical locations of the drilled wells within the three-dimensional geological model (i.e., the X, Y, Z data of the geographical location coordinates corresponding to the X, Y, Z data within the three-dimensional geological model) according to the set precision to obtain the input dataset.

[0069] For example, the above data can be exported with an accuracy of 0.125m for a single well depth, and the data from all wells can be merged into a single data table as the input dataset.

[0070] S2: Simulate the drilling GR data of new wells in the target block based on the drilling GR data of several existing wells in the target block, and obtain the predicted depth of the drill bit of the new well based on the simulated drilling GR data of the new well and the input dataset through the established horizontal section intelligent guidance judgment model.

[0071] As an improvement to an embodiment of the present invention, one implementation of step S2 includes:

[0072] S21: Use the nearest few wells (e.g., one or more) drilled around the new well in the target block as reference wells.

[0073] S22: The GR data of a portion of the reference well is used as the GR value of the corresponding section of the new well to simulate the GR value obtained during the actual drilling of the new well, and finally the GR data of the new well is obtained by simulation, that is, the GR curve.

[0074] In this step, you can use the GR data from a drilled well to simulate the GR data from a new well, or you can use the GR data from different sections of multiple drilled wells to simulate the GR data from a new well.

[0075] S23: Based on the drilling GR data of the new well obtained from the simulation, establish an intelligent steering judgment model for the horizontal section.

[0076] For example, a horizontal section intelligent guidance judgment model can be established based on the Bayesian inversion algorithm and the simulated GR curve, and the problem of drill bit positioning during horizontal well drilling of coalbed methane can be solved by artificial intelligence.

[0077] S24: Use the simulated GR data of the new well while drilling and the input dataset as input to the horizontal section intelligent guidance judgment model, and output the probability distribution of the specific depth of the drill bit in the new well.

[0078] The probability distribution of the specific depth of the drill bit refers to the position probability of the drill bit relative to the top and bottom interfaces of the target formation, thereby obtaining the specific depth of the wellbore trajectory, and thus determining the position of the drill bit in the target formation in real time.

[0079] The posterior probability distribution of the specific depth φ of the wellbore trajectory is calculated using the following formula:

[0080]

[0081] in, Let f(i) represent the probability distribution at a specific depth φ, where i represents the i-th measurement point drilled, γ represents the GR data during drilling, j represents the j-th point in the depth domain corresponding to the i-th measurement point, f() represents the probability density function (e.g., the likelihood function), and p represents the prior probability distribution. The entire denominator is a normalization constant, which is usually not calculated, and the numerator is the unstandardized posterior distribution.

[0082] S25: Take the maximum value in the probability distribution as the predicted depth of the drill bit for the new well.

[0083] This step takes the maximum probability value of the different probability distribution points corresponding to the same depth obtained from the previous calculation as the predicted depth of the horizontal wellbore trajectory. The specific calculation formula is shown below:

[0084]

[0085] In the formula, ε represents independent and identically distributed random noise with zero mean.

[0086] The above method can be used to obtain the relative position of the wellbore trajectory in the target formation and display it in the form of a heat map. Figure 2 This is the final prediction result displayed using a single well as a reference well. Figure 3 This is a final prediction result using two wells as reference wells.

[0087] S3: Based on the predicted depth of the new well bit and the target formation, determine whether any abnormalities occurred during the drilling process.

[0088] Specifically, this step includes:

[0089] S31: Determine whether the predicted depth of the drill bit in the new well has penetrated the top and bottom interfaces of the target formation. If it has, the drill bit has penetrated the formation, an anomaly is detected, and an alarm is triggered.

[0090] This step uses the predicted horizontal wellbore trajectory and target formation to determine if any abnormalities occur during the drilling process. If no abnormalities occur, drilling continues; if abnormalities occur, an alarm is issued.

[0091] When it is determined that the drill bit has penetrated the stratum, an alarm is issued in a timely manner for manual verification by the on-site engineer. If the manual verification confirms that the drill bit has penetrated the stratum, the point is marked. If the drill bit has not penetrated the stratum, the point is considered an invalid warning.

[0092] S32: Incorporate the data corresponding to the points where an anomaly occurred into the original data and update the original data.

[0093] This step uses the results of manual review as a reference point and incorporates the corresponding data into the original dataset, providing an important reference for the next step of model updates.

[0094] Furthermore, embodiments of the present invention also include:

[0095] S4: Update the 3D geological model in real time using updated raw data.

[0096] This step updates the 3D geological model in real time based on the real-time data, optimizes the entire prediction model, and improves prediction accuracy.

[0097] This invention first collects drilling gaussing (GR) and drilling time information based on target block data to establish a 3D geological model. It then exports the X, Y, and Z coordinates of all drilled wells in the target block, along with GR, drilling time data, lithological logging data, and the corresponding X, Y, and Z coordinates of the established geological model, using this as the model training dataset. Secondly, it simulates the GR data during the drilling process of the target well using reference well and geological model data, and uses artificial intelligence algorithms to predict the relative position of the horizontal section of the target well's borehole within the formation. Finally, it uses a borehole trajectory prediction model for the horizontal section of the target well to determine whether abnormal situations such as bit contact with formations will occur during subsequent drilling and provides early warnings. Simultaneously, as new drilling data is added, the established 3D geological model can be updated in a timely manner, thereby continuously optimizing the prediction model.

[0098] This invention utilizes artificial intelligence to construct a wellbore trajectory prediction model for horizontal sections during drilling, overcoming the challenge of drill bit positioning in coalbed methane horizontal well drilling. It solves problems such as the inability to promptly detect drilled formations and automatically adjust the drill bit during horizontal well drilling, significantly improving drilling efficiency and reservoir encounter rate in coalbed methane horizontal wells. This also substantially increases single-well production and recovery rates in complex oil and gas reservoirs, while reducing on-site construction costs. Furthermore, it reduces energy and resource waste caused by drill bit encountering formations and resulting drilling corrections or downtime, making oil and gas drilling and extraction greener, more energy-efficient, low-carbon, environmentally friendly, and highly efficient.

[0099] This invention also provides a horizontal well steering anomaly early warning device, such as... Figure 4 As shown, the device includes:

[0100] Data acquisition module 1 is used to acquire the three-dimensional location coordinates of drilled wells, drilling GR data, drilling time data and lithology logging data within the entire target block as input datasets.

[0101] Prediction module 2 is used to simulate the drilling GR data of new wells in the target block based on the drilling GR data of several existing wells in the target block, and to obtain the predicted depth of the drill bit of the new well based on the simulated drilling GR data of the new well and the input dataset through the established horizontal section intelligent guidance judgment model.

[0102] The early warning module 3 is used to determine whether any abnormalities occur during the drilling process of the new well based on the predicted depth of the drill bit and the target formation.

[0103] As an example, the aforementioned input dataset is obtained through the following process:

[0104] The raw data acquisition unit is used to process the raw data collected on-site within the target block to obtain the drilling GR data, drilling time data, and lithology logging data of the drilled wells within the target block.

[0105] The 3D geological model building unit is used to load the processed drilling GR data, drilling time data and lithological logging data into the 3D geological modeling software to build a 3D geological model of the target block.

[0106] The input dataset export unit is used to export the three-dimensional coordinate data of the geographical locations of drilled wells within the entire target block, the drilling GR data, the drilling time data, the lithological logging data, the established three-dimensional geological model, and the three-dimensional coordinate data of the geographical locations of drilled wells within the three-dimensional geological model according to the set precision, to obtain the input dataset.

[0107] As an improvement to this embodiment of the invention, the aforementioned prediction module includes:

[0108] The reference well prediction unit is used to select several nearest existing wells around the new well in the target block as reference wells.

[0109] The GR simulation unit is used to simulate the drilling GR data of the new well by using the GR data of a certain section of the reference well as the GR value of the corresponding section of the new well.

[0110] The model building unit is used to establish a horizontal section intelligent steering judgment model based on the drilling GR data of the new well obtained from simulation.

[0111] The probability distribution prediction unit is used to take the simulated drilling GR data of the new well and the input dataset as input to the horizontal section intelligent guidance judgment model, and output the probability distribution of the specific depth of the drill bit in the new well.

[0112] The predicted depth determination unit is used to take the maximum value in the probability distribution as the predicted depth of the drill bit for new drilling.

[0113] The probability distribution of the specific depth of the drill bit in a new well can be calculated using the following formula:

[0114]

[0115] In the above formula, Let f(φ) represent the probability distribution at a specific depth φ, i represent the i-th measurement point that has been drilled, γ represent the GR data while drilling, j represent the j-th point in the depth domain corresponding to the i-th measurement point, f() represents the probability density function, and p represents the prior probability distribution.

[0116] Specifically, the early warning module includes:

[0117] The early warning unit is used to determine whether the predicted depth of the drill bit in a new well has penetrated the top and bottom interfaces of the target formation. If it has, the drill bit has penetrated the formation, an anomaly is detected, and an alarm is triggered.

[0118] The data update unit is used to incorporate the data corresponding to the points where anomalies occur into the original data and update the original data.

[0119] Furthermore, the apparatus of the present invention further includes:

[0120] The model update module is used to update the 3D geological model in real time using updated raw data.

[0121] This invention constructs a wellbore trajectory prediction model for horizontal sections during drilling based on artificial intelligence methods, overcoming the problem of drill bit positioning during coalbed methane horizontal well drilling. It solves problems such as the inability to detect drilled formations in a timely manner and the inability to automatically adjust the drill bit during horizontal well drilling, significantly improving the drilling efficiency and reservoir encounter rate of coalbed methane horizontal wells, significantly increasing the production and recovery rate of single wells in complex oil and gas reservoirs, and reducing on-site construction costs.

[0122] The apparatus provided in the above embodiments corresponds one-to-one with the embodiments of the aforementioned methods in terms of its implementation principle and the resulting technical effects. For the sake of brevity, any parts of the apparatus not mentioned in the embodiments can be referred to the corresponding content in the embodiments of the aforementioned methods. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the modules and units described in this apparatus can all be referred to the corresponding processes in the embodiments of the aforementioned methods, and will not be repeated here.

[0123] The horizontal well guidance anomaly early warning method described in the above embodiments of the present invention can implement business logic through a computer program and record it on a storage medium. The storage medium can be read and executed by a computer, achieving the effects of the scheme described in the method embodiments of this specification. Therefore, the embodiments of the present invention also provide a computer-readable storage medium for horizontal well guidance anomaly early warning, including a memory for storing processor-executable instructions. When executed by a processor, the instructions implement the steps of the horizontal well guidance anomaly early warning method of the foregoing embodiments.

[0124] The storage medium may include a physical device for storing information, typically digitizing the information and then storing it using electrical, magnetic, or optical methods. The storage medium may include: devices that store information using electrical energy, such as various types of memory, like RAM and ROM; devices that store information using magnetic energy, such as hard disks, floppy disks, magnetic tapes, magnetic core memory, bubble memory, and USB flash drives; and devices that store information using optical methods, such as CDs or DVDs. Of course, there are other readable storage media, such as quantum memories and graphene memories.

[0125] The storage medium described above may also include other implementation methods according to the description of the method embodiments. The implementation principle and technical effects of this embodiment are the same as those of the foregoing method embodiments. For details, please refer to the description of the relevant method embodiments, which will not be repeated here.

[0126] This invention also provides a device for early warning of horizontal well directional anomalies. The device can be a standalone computer, or it can include an actual operating device that uses one or more of the methods or embodiments described in this specification. The device for early warning of horizontal well directional anomalies may include at least one processor and a memory storing computer-executable instructions. When the processor executes the instructions, it implements the steps of any one or more of the aforementioned methods for early warning of horizontal well directional anomalies.

[0127] The device described above may also include other implementation methods according to the method embodiments. The implementation principle and technical effects of this embodiment are the same as those of the foregoing method embodiments. For details, please refer to the description of the relevant method embodiments, which will not be repeated here.

[0128] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the scope of the technology disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. All should be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for early warning of directional anomalies in horizontal wells, characterized in that, The method includes: The three-dimensional location coordinates, drilling GR data, drilling time data, and lithological logging data of the drilled wells within the entire target block are obtained as the input dataset. Based on the drilling GR data of several existing wells in the target block, the drilling GR data of new wells in the target block are simulated. Based on the simulated drilling GR data of new wells and the input dataset, the predicted depth of the drill bit of the new well is obtained through the established horizontal section intelligent guidance judgment model. Based on the predicted depth of the new well bit and the target formation, determine whether any abnormalities occurred during the drilling process. The step of simulating the drilling GR data of new wells drilled within the target block based on the drilling GR data of several existing wells within the target block includes: Use the nearest existing wells around the new well in the target block as reference wells; The drilling GR data of a portion of the reference well is used as the GR value of the corresponding section of the new well to simulate the drilling GR data of the new well. The process of obtaining the predicted depth of the drill bit in the new well based on the simulated drilling GR data of the new well and the input dataset, through the established horizontal section intelligent steering judgment model, includes: Based on the drilling GR data of the new well obtained from the simulation, an intelligent steering judgment model for the horizontal section is established. The simulated GR data of the new well and the input dataset are used as input to the horizontal section intelligent steering judgment model, and the probability distribution of the specific depth of the drill bit in the new well is output. The maximum value in the probability distribution is taken as the predicted depth of the drill bit for the new well. The probability distribution of the specific depth of the drill bit in the new well is calculated using the following formula: in, Let f(i) represent the probability distribution at a specific depth φ, i represent the i-th measurement point that has been drilled, γ represent the GR data while drilling, j represent the j-th point in the depth domain corresponding to the i-th measurement point, f() represent the probability density function, and p represent the prior probability distribution.

2. The horizontal well steering anomaly early warning method according to claim 1, characterized in that, The input dataset is obtained through the following method: Based on the raw data collected on-site within the target block, the drilling GR data, drilling time data, and lithology logging data of the drilled wells within the target block were compiled. The collected drilling GR data, drilling time data, and lithological logging data are loaded into 3D geological modeling software to establish a 3D geological model of the target block. The input dataset is obtained by exporting the three-dimensional coordinate data of the geographical locations of drilled wells within the entire target block, the drilling GR data, the drilling time data, the lithological logging data, the established three-dimensional geological model, and the three-dimensional coordinate data of the geographical locations of drilled wells within the three-dimensional geological model according to the set precision.

3. The horizontal well steering anomaly early warning method according to claim 2, characterized in that, The step of determining whether any anomalies occurred during the drilling process of the new well, based on the predicted depth of the drill bit and the target formation, includes: Determine whether the predicted depth of the new drilling bit has penetrated the top and bottom interfaces of the target formation. If it has, the drill bit has penetrated the formation, an anomaly is detected, and an alarm is triggered. The data corresponding to the points where anomalies occurred are included in the original data, and the original data is updated.

4. The horizontal well steering anomaly early warning method according to claim 3, characterized in that, The method further includes: The three-dimensional geological model is updated in real time using updated raw data.

5. A horizontal well steering anomaly early warning device, characterized in that, The device includes: The data acquisition module is used to acquire the three-dimensional location coordinates of drilled wells, drilling GR data, drilling time data, and lithological logging data within the entire target block as input datasets. The prediction module is used to simulate the drilling GR data of a new well in the target block based on the drilling GR data of several existing wells in the target block, and to obtain the predicted depth of the drill bit of the new well based on the simulated drilling GR data of the new well and the input dataset through the established horizontal section intelligent guidance judgment model. The early warning module is used to determine whether any abnormalities occur during the drilling process of the new well based on the predicted depth of the drill bit and the target formation. The prediction module includes: The reference well prediction unit is used to select several nearest existing wells around the new well in the target block as reference wells. The GR simulation unit is used to simulate the drilling GR data of the new well by using the drilling GR data of a portion of the reference well as the GR value of the corresponding well section of the new well. The model building unit is used to build a horizontal section intelligent steering judgment model based on the drilling GR data of the new well obtained from the simulation. The probability distribution prediction unit is used to take the simulated drilling GR data of the new well and the input dataset as input to the horizontal section intelligent guidance judgment model, and output the probability distribution of the specific depth of the drill bit in the new well. The predicted depth determination unit is used to take the maximum value in the probability distribution as the predicted depth of the drill bit for new drilling. The probability distribution of the specific depth of the drill bit in the new well is calculated using the following formula: in, Let f(i) represent the probability distribution at a specific depth φ, i represent the i-th measurement point that has been drilled, γ represent the GR data while drilling, j represent the j-th point in the depth domain corresponding to the i-th measurement point, f() represent the probability density function, and p represent the prior probability distribution.

6. A computer-readable storage medium for early warning of directional anomalies in horizontal wells, characterized in that, It includes a memory for storing processor-executable instructions, which, when executed by the processor, implement the steps of the horizontal well guidance anomaly early warning method according to any one of claims 1-4.

7. A device for early warning of directional anomalies in horizontal wells, characterized in that, It includes at least one processor and a memory storing computer-executable instructions, wherein the processor executes the instructions to implement the steps of the horizontal well guidance anomaly early warning method according to any one of claims 1-4.

Images