Well leakage risk early warning method and device

Abstract

The invention discloses a well leakage risk early warning method and device, and the method comprises the steps: collecting logging data in real time when a drilling tool micro-element is emptied in drilling operation, and carrying out time-depth conversion to obtain logging data for analysis; obtaining a well leakage judgment index value of a first preset window length from the well logging data for analysis; calculating a well leakage judgment index base value according to the well leakage judgment index value of the first preset window length; for each acquisition point of a second preset window length, calculating the deviation between each well leakage judgment index value and the well leakage judgment index base value, and obtaining a first well leakage judgment result according to the current well depth, the deviation corresponding to all the acquisition points, the first well leakage judgment threshold value and the second well leakage judgment threshold value; if the first well leakage judgment result is that the suspicious well leakage exists in the current shaft, whether well leakage early warning needs to be sent out or not is judged according to the hook height corresponding to the current well depth and the maximum value of the historical hook height. According to the invention, shaft leakage-prone points can be found in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of oil drilling technology, and particularly relates to a well leakage risk early warning method and device. BACKGROUND

[0002] In the drilling process, when the bottom hole pressure in the wellbore is greater than the formation leakage pressure, the drilling fluid will appear the downhole complex situation of leaking into the formation. The harm of well leakage is multifaceted. First, it destroys the integrity of the formation and damages the fluid storage and seepage conditions of the target layer; reduces the sand carrying capacity of the drilling fluid, forcing the drilling to be interrupted; at the same time, it also easily leads to more serious complex accidents such as well collapse, blowout, and sticking; and leads to a substantial increase in drilling fluid cost and prolongs the drilling cycle.

[0003] With the deepening of oil and gas exploration and development, oil and gas reservoirs are buried deeper and deeper, and the complexity of drilling geology is increasing. The safe density window of drilling fluid is narrow, and well leakage is more and more frequent. Serious well leakage and blowout coexist, which is one of the most significant complex problems that hinder safe drilling and optimal and fast drilling.

[0004] At present, there are mainly two methods to monitor well leakage. The first method is to monitor the surface parameters of the drilling fluid circulation system. This method mainly relies on two key parameters, tank volume and outlet flow rate, to determine whether well leakage occurs. In most field operations, the liquid level of the circulating tank is monitored in real time and continuously by using an ultrasonic liquid level meter. The increase and decrease of the tank volume is calculated by the change of the liquid level, and then it is determined whether there is well leakage. However, this method has obvious limitations. When there is a large fluctuation in the liquid level in the circulating tank, such as mechanical disturbance caused by the operation of the agitator, or there are bubbles on the liquid surface, etc., it will affect the measurement accuracy of the ultrasonic liquid level meter. The measurement signal will be disturbed, resulting in data deviation, which is easy to produce false alarms. Such false alarms may mislead the staff to make wrong decisions, and fail to detect the actual well leakage in time, which poses a certain safety hazard.

[0005] The other monitoring method is downhole while-drilling monitoring. Compared with the surface parameter monitoring method, the downhole while-drilling monitoring method can monitor the leakage more quickly and earlier. It installs a special measuring instrument downhole to obtain real-time pressure, flow rate and other parameter information downhole, so as to timely find the signs of well leakage. However, this method is not perfect. On the one hand, the cost of the downhole while-drilling measuring instrument is high, and a large amount of funds needs to be invested for equipment purchase, installation and maintenance. This undoubtedly increases the overall cost of drilling operations, which may cause economic pressure for some projects with limited budget. On the other hand, due to the harsh downhole environment, high temperature, high pressure, strong vibration and other factors threaten the normal operation of the while-drilling measuring instrument at all times, and the instrument has the risk of failure. Once the instrument fails, it cannot timely and accurately monitor the well leakage, which affects the judgment and treatment of the downhole complex situation.

[0006] Although the two existing well leakage monitoring methods can find the well leakage problem to some extent, they have obvious shortcomings. The monitoring results are often in the alarm stage, and the identification time of the leakage is relatively lagging. When the well leakage is monitored, the downhole situation may be already serious, which increases the difficulty and cost of subsequent processing. Both methods are difficult to accurately identify the leakage point position. After the well leakage occurs, it is not conducive to locate the leakage point in advance to formulate targeted well leakage disposal measures, and it is also not conducive to timely implement effective processing schemes, which still poses a serious threat to drilling safety, and an advanced and accurate well leakage monitoring technology is urgently needed to solve these problems. SUMMARY

[0007] In a first aspect, an embodiment of the present application provides a well leakage risk warning method, which can timely find the easy leakage point to realize well leakage risk warning through the mud logging data when the drilling tool micro element is empty, and has good application effect. The method comprises the following steps:

[0008] Real-time acquisition of the mud logging data when the drilling tool micro element is empty in the drilling operation, and time-depth conversion of the mud logging data to obtain analysis mud logging data;

[0009] Taking the latest well depth in the analysis mud logging data as a starting point, a sliding window analysis is performed on the shallow well section, and an index value of well leakage judgment of a first preset window length is obtained from the analysis mud logging data;

[0010] According to the index value of well leakage judgment of the first preset window length, a well leakage judgment index base value is calculated;

[0011] For each acquisition point of a second preset window length, a deviation of each well leakage judgment index value from the well leakage judgment index base value is calculated. If the current well depth is not greater than a first depth, a first well leakage judgment result is obtained according to the relationship between the deviations corresponding to all acquisition points and a first well leakage judgment threshold, otherwise, a first well leakage judgment result is obtained according to the relationship between the deviations corresponding to all acquisition points and a second well leakage judgment threshold;

[0012] If the first well leakage judgment result is that there is suspicious well leakage in the current wellbore, whether a well leakage warning needs to be issued is determined according to the maximum value of the hook height corresponding to the current well depth and the historical hook height.

[0013] In a second aspect, an embodiment of the present application further provides a well leakage risk warning device, which can timely find the easy leakage point to realize well leakage risk warning through the mud logging data when the drilling tool micro element is empty, and has good application effect. The device comprises the following steps:

[0014] A mud logging data acquisition module is configured to real-time acquisition of the mud logging data when the drilling tool micro element is empty in the drilling operation, and time-depth conversion of the mud logging data to obtain analysis mud logging data;

[0015] The well loss judgment index value calculation module is configured to analyze the latest well depth in the analysis logging data as a starting point to analyze a shallow well section by using a sliding window, and obtain a well loss judgment index value of a first preset window length from the analysis logging data.

[0016] The well loss judgment index base value calculation module is configured to calculate a well loss judgment index base value according to the well loss judgment index value of the first preset window length.

[0017] The well loss judgment module is configured to calculate a deviation of each well loss judgment index value from the well loss judgment index base value for each collection point of the second preset window length, obtain a first well loss judgment result according to a relationship between the deviations corresponding to all the collection points and a first well loss judgment threshold if the current well depth is not greater than the first depth, or obtain the first well loss judgment result according to a relationship between the deviations corresponding to all the collection points and a second well loss judgment threshold if the current well depth is greater than the first depth, and determine whether to issue a well loss warning according to a maximum value of the hook height corresponding to the current well depth and a historical hook height if the first well loss judgment result indicates that there is a suspicious well loss in the current wellbore.

[0018] In a third aspect, an embodiment of the present application further provides a computer device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the well loss risk warning method when executing the computer program.

[0019] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the well loss risk warning method.

[0020] In a fifth aspect, an embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program is executable on a processor to implement the well loss risk warning method.

[0021] In the embodiment of the present application, the mud logging data is collected in real time when the drilling tool micro element is vented, and the venting of the drilling tool micro element is often one of the early important signals of the occurrence of well leakage. Through the collection and analysis of the data at this specific moment, the monitoring work can be carried out when there is a sign of well leakage, compared with the traditional way of recognizing based on the overall parameter change after a certain time of well leakage, the potential risk of well leakage can be discovered earlier, so as to gain more time for subsequent measures. The time-depth conversion is performed on the collected mud logging data, the data in the time dimension is converted into depth sequence data based on the well depth, which is more in line with the actual situation of taking well depth as the key reference in drilling operation, so that the subsequent data mining and parameter analysis can be carried out on a more scientific and reasonable data basis, which is helpful to improve the accuracy of data analysis and provide more reliable data support for well leakage judgment. The sliding window analysis is used to determine the well leakage judgment index value and calculate the index base value. This way can dynamically build a well leakage judgment benchmark that meets the current formation conditions and drilling conditions according to the actual data status of different well sections according to the real-time progress of drilling operation, compared with the mode of using fixed threshold or experience parameter to judge well leakage, it can better adapt to various complex drilling scenes and reduce the probability of false alarm and omission. Different well leakage judgment thresholds are selected according to the well depth, and the comparison with the maximum value of the historical hook height is made, this hierarchical and multi-dimensional judgment mode can comprehensively consider the differences in formation characteristics under different well depth conditions and the actual running state of the drilling tool, can make the process of well leakage early warning more rigorous and reliable, avoid the inaccurate problem caused by single index or fixed standard judgment, and further improve the precision of well leakage early warning. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating any inventive labor. In the drawings:

[0023] Figure 1 The flow chart of the well leakage risk early warning method in the embodiment of the present application;

[0024] Figure 2 The flow chart of the well leakage risk early warning based on specific data in the embodiment of the present application;

[0025] Figure 3 The structure schematic diagram of the well leakage risk early warning device in the embodiment of the present application;

[0026] Figure 4 Another structure schematic diagram of the well leakage risk early warning device in the embodiment of the present application;

[0027] Figure 5 A schematic diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application are further described in detail below with reference to the drawings. Herein, the schematic embodiments of the present application and the descriptions thereof are used to explain the present application but not to limit the present application.

[0029] The principle of the scheme proposed in the embodiments of the present application is to perform intelligent early warning of well leakage risk based on drill tool micro-element emptying. By collecting and analyzing the mud logging data during drill tool micro-element emptying in real time, the downhole easy leakage points can be more accurately identified, and the subtle changes of the well leakage risk can be quickly captured, so as to realize early warning of the well leakage risk.

[0030] Drill tool micro-element emptying is a term used to describe a subtle abnormal phenomenon in the drilling process in drilling engineering. It mainly refers to the instantaneous weight loss or sudden advance phenomenon of the drill tool at a specific micro-depth section (micro-element), that is, the drill bit suddenly moves downward a small distance without being hindered, which is similar to emptying but extremely small in scale. Drill tool micro-element emptying is often an early signal of abnormal formation, which may indicate that there is a permeable unconsolidated formation, a small fracture or a cave (especially in carbonate rock formation), or an abnormal formation pressure zone below. These conditions may increase the risk of well leakage, blowout, etc. Therefore, in mud logging and drilling monitoring, the micro-element emptying phenomenon needs to be recorded and analyzed, so as to provide a basis for subsequent drilling parameter adjustment (such as reducing the drilling pressure and controlling the discharge capacity).

[0031] Figure 1 A flowchart of a well leakage risk early warning method in an embodiment of the present application is shown. The method comprises the following steps.

[0032] In step 101, the mud logging data during drill tool micro-element emptying in drilling operations is collected in real time, and the mud logging data is subjected to time-depth conversion to obtain analysis-use mud logging data.

[0033] In step 102, the latest well depth in the analysis-use mud logging data is taken as a starting point to perform sliding window analysis on the shallow well section, and the well leakage judgment index value of a first preset window length is obtained from the analysis-use mud logging data.

[0034] In step 103, the well leakage judgment index base value is calculated according to the well leakage judgment index value of the first preset window length.

[0035] In step 104, for each acquisition point of the second preset window length, the deviation of each well loss judgment index value from the well loss judgment index base value is calculated, if the current well depth is not greater than the first depth, the first well loss judgment result is obtained according to the relationship between the deviation corresponding to all acquisition points and the first well loss judgment threshold, otherwise the first well loss judgment result is obtained according to the relationship between the deviation corresponding to all acquisition points and the second well loss judgment threshold;

[0036] In step 105, if the first well loss judgment result is that there is suspicious well loss in the current wellbore, whether it is necessary to issue a well loss warning is judged according to the maximum value of the hook height corresponding to the current well depth and the historical hook height.

[0037] In the embodiment of the present application, real-time logging data acquisition is carried out when the drilling tool micro element is empty, and the drilling tool micro element emptying is often one of the important signals in the early stage of well loss. By collecting and analyzing the data at this specific moment, monitoring work can be carried out as soon as there is a sign of well loss. Compared with the traditional method of recognizing the change of the whole parameter after a certain time of well loss, the potential risk of well loss can be discovered earlier, so as to gain more time for subsequent measures. Time-depth conversion is carried out on the collected logging data, and the data in the time dimension is converted into depth sequence data based on well depth, which is more in line with the actual situation of drilling operation with well depth as the key reference, so that subsequent data mining, parameter analysis and the like can be carried out on a more scientific and reasonable data basis, which is helpful to improve the accuracy of data analysis and provide more reliable data support for well loss judgment. The sliding window analysis is used to determine the well loss judgment index value and calculate the index base value. This method can dynamically build a well loss judgment benchmark that meets the current formation conditions and drilling conditions according to the actual data status of different well sections according to the real-time progress of drilling operation. Compared with the mode of using fixed threshold or experience parameter to judge well loss, it can better adapt to various complex drilling scenes and reduce the probability of false alarm and omission. Different well loss judgment thresholds are selected according to the well depth, and the maximum value of the hook height and the historical hook height is compared. This hierarchical and multi-dimensional judgment mode can comprehensively consider the differences in formation characteristics and the actual running state of the drilling tool under different well depth conditions, so that the process of well loss warning and judgment is more rigorous and reliable, and the inaccuracy caused by single index or fixed standard judgment is avoided, which further improves the precision of well loss warning.

[0038] Each step will be described in detail below.

[0039] In step 101, real-time logging data of the drilling tool micro element emptying in the drilling operation is collected, and time-depth conversion is carried out on the logging data to obtain analysis logging data;

[0040] In specific implementation, the comprehensive logging instrument can be used to collect the logging data in the drilling operation from the target well site in real time and input into the database.

[0041] In one embodiment, real-time acquisition of logging data during drilling operation when a drill bit is emptied and time-depth conversion of the logging data are performed to obtain logging data for analysis include:

[0042] When the real-time collected logging data meets the drilling conditions, the logging data is standardized;

[0043] The standardized logging data are converted from time series to depth series to obtain logging data for analysis.

[0044] In the above embodiment, drilling condition identification is used to filter out non-real-time logging data and prevent monitoring. Subsequent monitoring is only performed on logging data that meets the drilling conditions. The drill tool micro-element emptying lost circulation warning system uses data characteristics such as fast drilling time, low bit pressure, and low mechanical specific energy (MSE) to provide an intelligent lost circulation risk warning when drilling into a thin formation with a high risk of lost circulation. Compared to the upper well section under similar drilling conditions, the micro-element emptying section (i.e., a leak-prone point) exhibits these characteristics, resulting in an intelligent early warning of lost circulation risk. Therefore, analysis during the drilling process is necessary.

[0045] Data standardization can be used to address missing and noisy data often caused by equipment failure, acquisition errors, and inconsistent units. Missing data points can be filled using methods such as weighted interpolation, mean interpolation, linear interpolation, and nearest neighbor interpolation. Machine learning interpolation models are also introduced: algorithms such as random forests and LSTMs, combined with historical data characteristics of similar well sections, predictively fill missing values ​​(more adaptable to nonlinear data than traditional interpolation). Anomalous data corrections are implemented using techniques such as fixed threshold judgment and the K-Sigma method to identify and address outliers and abnormal fluctuations, ensuring the accuracy and continuity of the logging data. Specifically, error compensation models (such as temperature correction formulas for ultrasonic level gauges) can be developed using historical calibration data to address systematic errors across different logging instrument models, eliminating noise caused by equipment differences. Wavelet transforms or Kalman filters can be used to separate high-frequency noise (such as agitator vibration) from valid signals (such as actual liquid level changes) in the data, improving the signal-to-noise ratio.

[0046] For example, the logging data is converted from time series to depth series based on a depth interval of 0.1 meters (such as collecting and calculating the instantaneous drilling time every 0.1 meters, in units of min / m), and the converted logging data for analysis is properly saved in the database for further analysis and research.

[0047] In specific implementation, the normalized logging data can be converted from time sequence to depth sequence at preset depth intervals, and the depth intervals can be adaptively adjusted based on formation changes. In drilling operations, a first depth interval (e.g., 0.1 m-0.5 m) is used for homogeneous formations (e.g., thick sandstone), and a second depth interval (e.g., 0.05 m) is used for non-homogeneous or thin interbedded formations (e.g., shale and limestone interbeds), thereby improving the identification accuracy of thin leaky layers.

[0048] In real-time logging data acquisition, the sampling frequency can be dynamically adjusted in combination with the drill bit type (e.g., PDC drill bit, roller bit). When the PDC drill bit is used, the sampling frequency is increased (e.g., 2 times per second) to balance the data volume and calculation efficiency.

[0049] In an embodiment, the analysis logging data includes one or any combination of time, well depth, drill bit position, instantaneous rotation speed, rotary table rotation speed, drilling pressure, and hook height. Examples of logging data are shown in Table 1.

[0050] Table 1

[0051]

[0052] Steps 102-105 are specific processes based on drilling tool micro-element blowout monitoring analysis. Expert research experience is integrated into intelligent early warning. Real-time data such as logging and drilling in drilling operations are continuously and automatically monitored. Through intelligent algorithms and data analysis, downhole leakage risks are identified, and early warning signals are sent in a timely manner. This replaces manual monitoring and analysis, enables well leakage monitoring, and improves well leakage monitoring levels. This helps optimize drilling measures, reduces well leakage risks, reduces well leakage occurrence rates, and ensures drilling safety. Steps 102-105 can be steps of an intelligent early warning model.

[0053] In step 102, the latest well depth in the analysis logging data is taken as a starting point to analyze the shallow well section with a sliding window. The well leakage judgment index value of the first preset window length is obtained from the analysis logging data.

[0054] In an embodiment, the well leakage judgment index value includes instantaneous drilling speed, drilling pressure, and rotary table rotation speed.

[0055] Take the latest well depth D in the analysis logging data as the starting point to analyze the shallow well section, take the first preset window length as 5 for example, record the current instantaneous drilling speed as ROP1, the current weight on bit as WOB1, and the current rotary table speed as RPM1; record the instantaneous drilling speed of the second collection point as ROP2, the weight on bit as WOB2, and the rotary table speed as RPM2; record the instantaneous drilling speed of the third collection point as ROP3, the weight on bit as WOB3, and the rotary table speed as RPM3; and so on, continuously record the instantaneous drilling speed, the weight on bit, and the rotary table speed in history in turn.

[0056] In step 103, the well loss judgment index base value is calculated according to the well loss judgment index value of the first preset window length;

[0057] The arithmetic mean values of the five instantaneous drilling speeds, the weight on bit, and the rotary table speed are calculated as the base values respectively, the arithmetic mean value of the instantaneous drilling speed is recorded as ROP0, the arithmetic mean value of the weight on bit is recorded as WOB0, and the arithmetic mean value of the rotary table speed is recorded as RPM0, forming the instantaneous drilling speed base value, the weight on bit base value, and the rotary table speed base value.

[0058] In step 104, the first well loss judgment result is obtained according to the current well depth, the well loss judgment index value of the second preset window length, and the well loss judgment index base value.

[0059] In an embodiment, the first well loss judgment result is obtained according to the current well depth, the well loss judgment index value of the second preset window length, and the well loss judgment index base value, including:

[0060] If the current well depth is not greater than the first depth, the deviation of each well loss judgment index value from the well loss judgment index base value is calculated at each collection point of the second preset window length, and if the deviations corresponding to the preset number of collection points are all less than the first well loss judgment threshold, it is determined that the well loss judgment index value can judge that there is suspicious well loss;

[0061] If the current well depth is greater than the first depth, the deviation of each well loss judgment index value from the well loss judgment index base value is calculated at each collection point of the second preset window length, and if the deviations corresponding to the preset number of collection points are all less than the second well loss judgment threshold, it is determined that the well loss judgment index value can judge that there is suspicious well loss;

[0062] If all well loss judgment index values can judge that there is suspicious well loss, it is determined that the first well loss judgment result is that there is suspicious well loss in the current wellbore.

[0063] In an embodiment, if the well loss judgment index value is the instantaneous drilling speed, the deviation is the first ratio of the instantaneous drilling speed to the instantaneous drilling speed base value.

[0064] If the well leakage judgment index value is the drilling pressure, the deviation is a second ratio of the drilling pressure and a drilling pressure base value;

[0065] If the well leakage judgment index value is the rotary table speed, the deviation is an absolute value of a difference between the rotary table speed and a rotary table speed base value.

[0066] Since the drilling speed, drilling pressure and rotary table speed characteristics of the easy leakage point will be different as the well depth increases, the first well depth (which can be 2500m) is taken as the division standard of the shallow well section and the deep well section, and different easy leakage point judgment conditions are given respectively.

[0067] Taking the second preset window length as 3, i.e. including 3 collection points, and the preset number as 2 as an example, different logical judgments are made for different well depths.

[0068] When the well depth is less than or equal to the first well depth, the following analysis and judgment are made:

[0069] a. The first ratio of the current (the first collection point) instantaneous drilling speed ROP1 / instantaneous drilling speed base value ROP0 is less than the first well leakage judgment threshold value (take 0.50 as an example) corresponding to the instantaneous drilling speed, or the first ratio of the second collection point instantaneous drilling speed ROP2 / instantaneous drilling speed base value ROP0 is less than 0.50, or the first ratio of the third instantaneous drilling speed ROP3 / instantaneous drilling speed base value ROP0 is less than 0.50, if two of the above three conditions are met, i.e. the drilling speed is fast.

[0070] b. The second ratio of the current drilling pressure WOB1 / drilling pressure base value WOB0 is less than the first well leakage judgment threshold value (take 0.70 as an example) corresponding to the drilling pressure, or the second ratio of the second collection point drilling pressure WOB2 / drilling pressure base value WOB0 is less than 0.70, or the second ratio of the third drilling pressure WOB3 / drilling pressure base value WOB0 is less than 0.70, if two of the above three conditions are met, i.e. the drilling pressure is small.

[0071] c. The absolute value of the current rotary table speed RPM1-rotary table speed base value RPM0 is less than (the first well leakage judgment threshold value corresponding to the rotary table speed, which is 5 here) i.e. ABS (RPM1-RPM0) <5 or the absolute value of the second collection point rotary table speed RPM2-rotary table speed base value RPM0 is less than 5 i.e. ABS (RPM2-RPM0) <5 or the absolute value of the third rotary table speed RPM3-rotary table speed base value RPM0 is less than 5 i.e. ABS (RPM3-RPM0) <5, if two of the above three conditions are met, i.e. the rotary table speed is stable.

[0072] When the well depth is greater than the first well depth, the following analysis and judgment are made:

[0073] a. The first ratio of the current rate of penetration ROP1 / the base value of instantaneous rate of penetration ROP0 is less than 0.70, or the first ratio of the second rate of penetration ROP2 / the base value of instantaneous rate of penetration ROP0 is less than the second well leakage judgment threshold value (here, 0.70) corresponding to the instantaneous rate of penetration, or the first ratio of the third rate of penetration ROP3 / the base value of instantaneous rate of penetration ROP0 is less than 0.70, if two of the above three conditions are met, that is, the judgment condition of the drilling time changing fast is met.

[0074] b. The second ratio of the current weight on bit WOB1 / the base value of weight on bit WOB0 is less than the second well leakage judgment threshold value (here, 0.80) corresponding to the weight on bit, or the second ratio of the second weight on bit WOB2 / the base value of weight on bit WOB0 is less than 0.80, or the second ratio of the third weight on bit WOB3 / the base value of weight on bit WOB0 is less than 0.80, if two of the above three conditions are met, that is, the judgment condition of the weight on bit changing small is met.

[0075] c. The absolute value of the current rotary table speed RPM1-the base value of rotary table speed RPM0 is less than the second well leakage judgment threshold value (here, 5) corresponding to the rotary table speed, that is, ABS (RPM1-RPM0) <5, or the absolute value of the second rotary table speed RPM2-the base value of rotary table speed RPM0 is less than 5, that is, ABS (RPM2-RPM0) <5, or the absolute value of the third rotary table speed RPM3-the base value of rotary table speed RPM0 is less than 5, that is, ABS (RPM3-RPM0) <5, if two of the above three conditions are met, that is, the judgment condition of the rotary table speed being stable is met.

[0076] In addition to the instantaneous rate of penetration, the weight on bit and the rotary table speed, the following well leakage judgment index values can be considered:

[0077] Mechanical specific energy (MSE): MSE (MSE = rotary energy + drilling energy / volume of cut) is directly calculated, MSE is significantly reduced when there is a well leakage, and MSE is taken as one of the core indexes, which is complementary to the rate of penetration and the weight on bit;

[0078] Bit torque (T): the abnormal fluctuation of the torque usually accompanies the leakage formation (such as the sudden decrease of the torque of the fracture formation), and the ratio of the bit torque to the base value of the bit torque is increased as an auxiliary judgment condition;

[0079] Hook load change rate: when there is a well leakage, the friction between the drilling tool and the well wall changes, which causes an abnormal trend of the hook load, the hook load change rate (ΔF / ΔD) per unit depth is calculated and included in the judgment system.

[0080] In the embodiment of the application, the first preset window length and the second preset window length can be adaptively adjusted based on the formation complexity, in an embodiment, the method further includes:

[0081] The formation entropy value of the current well section is calculated in real time, and when the formation entropy value is less than the entropy threshold value, the first preset window length and the second preset window length are increased according to a preset proportion.

[0082] The formation entropy value reflects the formation heterogeneity, and when the entropy value is high (complex formation), a short window (for example, 3-5 acquisition points) is used, and when the entropy value is low (homogeneous formation), a long window (for example, 8-10 acquisition points) is used, so as to avoid missing judgment of complex characteristics by a single window.

[0083] In step 105, if the first well leakage judgment result is that there is a suspected well leakage in the current wellbore, whether it is necessary to issue a well leakage warning is judged according to the maximum value of the hook height corresponding to the current well depth and the historical hook height.

[0084] In an embodiment, whether it is necessary to issue a well leakage warning is judged according to the maximum value of the hook height corresponding to the current well depth and the historical hook height, including:

[0085] A first difference value of the maximum value of the hook height corresponding to the current well depth and the historical hook height is calculated.

[0086] When the first difference value is less than a difference threshold value, it is determined that it is necessary to issue a well leakage warning.

[0087] The hook height corresponding to the current well depth is recorded as HH, and the maximum value of the historical hook height is recorded as HHmax, and if HH-HHmax< difference threshold value (for example, -0.3 m), it is indicated that the characteristics of the easy leakage point are not caused by the connection of the string, and a well leakage warning can be issued. At this time, under the condition that the rotating speed of the rotary table is stable, the drilling speed is accelerated, the drilling pressure is reduced, and the mechanical specific energy (MSE) is reduced, which indicates that the drill bit drills the easy leakage point, and the possibility of drilling a fracture, a high-permeability pore formation or the like is relatively large, and the risk of well leakage is relatively large.

[0088] Then, the time when it is determined that the well leakage warning needs to be issued is taken as a warning time, a warning information is generated, and the warning information includes the warning time and warning content. For example, the warning information can be expressed as: 2024 / 05 / 16 16:52:08, well depth 5659.95 m, suspected drilling of a high-permeability easy leakage formation, and attention should be paid to the well leakage.

[0089] The warning information this time can be stored into a well leakage warning database, a query interface can be created by a back-end developer, and the interface can be called by a front end and integrated and displayed on a page, so that an engineering and technical personnel can quickly obtain key warning information, and accordingly, a drilling risk disposal strategy can be made to ensure the safety of drilling operations.

[0090] The following gives a specific embodiment to illustrate the effectiveness of the method proposed in the embodiment of the present application, taking the LTX2 well as an example, Figure 2 The flowchart of the well leakage risk warning based on specific data in the embodiment of the present application.

[0091] (1) First, see Figure 2 , real-time logging data is collected when the drill bit micro-element is emptied during the drilling operation. When the real-time logging data meets the drilling conditions, the logging data is standardized; the standardized logging data is converted from a time series to a depth series to obtain logging data for analysis.

[0092] Afterwards, the instantaneous drilling rate, drilling pressure, and rotary table speed were analyzed and calculated to form the instantaneous drilling rate base value, drilling pressure base value, and rotary table speed base value. When the LTX2 well was in the drilling condition, the corresponding well depth was 7356.55m, the current instantaneous drilling rate ROP1 was 15m / hr, the current drilling pressure WOB1 was 5.26kN, and the current rotary table speed RPM1 was 27.56RPM. With a depth of 0.1 meter as the sampling interval, tracing back from the current well depth to the previous sampling point, that is, the second sampling point, the corresponding well depth was 7356.45m, the instantaneous drilling rate was 3.16m / hr, the drilling pressure WOB2 was 6.73kN, and the rotary table speed RPM2 was 27.4RPM. Using a 0.1-meter depth as the sampling interval, tracing back from the second sampling point to the previous sampling point (the third sampling point) yields a well depth of 7356.35 m, an instantaneous ROP of 3.47 m / hr, a WOB3 of 16.29 kN, and a rotary table speed RPM3 of 27.66 RPM. Similarly, tracing back through five consecutive sampling points, the calculated instantaneous ROP0 base value for these five data points is 5.73 m / hr, a WOB0 base value of 16.08 kN, and a rotary table speed base value of 27.57 RPM. These values ​​are then imported into the instantaneous ROP base value database, the WOB base value database, and the rotary table speed base value database.

[0093] (2) Early warning analysis of drilling tool micro-element emptying and well leakage

[0094] The current well depth is 7356.55m > 2500m. Make the following analysis and judgment:

[0095] ① The current instantaneous drilling rate (ROP1) / instantaneous drilling rate base value (ROP0) = 15 / 5.73 = 2.62 > 0.70, or the instantaneous drilling rate (ROP2) / instantaneous drilling rate base value (ROP0) at the second acquisition point = 3.16 / 5.73 = 0.55 < 0.70, or the third instantaneous drilling rate (ROP3) / instantaneous drilling rate base value (ROP0) = 3.47 / 5.73 = 0.61 < 0.70. Two of the above three threshold conditions are met.

[0096] ② The current WOB1 / WOB base value WOB0 = 5.26 / 16.08 = 0.33 < 0.80, or the second acquisition point WOB2 / WOB base value WOB0 = 6.73 / 16.08 = 0.42 < 0.80, or the third WOB3 / WOB base value WOB0 = 16.29 / 16.08 = 1.01 > 0.80. Two of the above three threshold conditions are met;

[0097] ③ The absolute value of the current turntable speed RPM1 minus the turntable speed base value RPM0 is less than 5, that is, ABS (RPM1-RPM0) = ABS (27.56-27.57) = 0.01 < 5. Or the absolute value of the turntable speed RPM2 at the second collection point minus the turntable speed base value RPM0 is less than 5, that is, ABS (RPM2-RPM0) = ABS (27.4-27.57) = 0.17 < 5. Or the absolute value of the third turntable speed RPM3 minus the turntable speed base value RPM0 is less than 5, that is, ABS (RPM3-RPM0) = ABS (27.66-27.57) = 0.09 < 5. All three threshold conditions are met.

[0098] ④ In summary, Well LTX2 experienced an increase in ROP, decrease in WOB, and lower mechanical specific energy (MSE) between 7355.95 and 7356.55 m, but a stable rotary table speed. Furthermore, the hook height HH corresponding to the current well depth was recorded as 13.81 m, and the historical maximum hook height HHmax was 16 m, satisfying the condition HH-HHmax=13.81-16.11=-2.3<-0.3 m. This indicates normal drilling conditions and conforms to the judgment logic for lost circulation warning identification based on micro-element venting of the drilling tool. This indicates a high probability that the drill bit encountered a leak-prone point, resulting in a high risk of lost circulation, and a subsequent lost circulation warning was issued.

[0099] (3) Send overflow warning information

[0100] The warning interface is shown in Table 2 below.

[0101] Table 2

[0102]

[0103] The drilling log on April 17, 2023 shows that "from 08:00 on April 16, 2023 to 05:00 on April 17, 2023, composite drilling was conducted to a well depth of 7359.27m and the well lost circulation. The vertical pressure dropped from 19.61 to 18.23 MPa, and the outlet flow rate dropped from 67.03% to 65.41%. Other parameters remained unchanged, and there was no loss of return at the wellhead. From 05:00 to 06:00, the drill string was lifted off the bottom of the well and the displacement was reduced to measure the leakage rate (displacement 10L / s, leakage rate 5.1m 3 / h, loss of 1.23 drilling fluids and 4.7m 3) ~ 08:00 directional composite drilling (walk the choke channel drilling). From the comparison of the early warning results and the drilling log, it can be seen that the well LTX2 gives the well leakage warning 51 minutes in advance and 2.61 m in well depth.

[0104] Through the above steps, the well leakage warning can be realized. In order to further improve the accuracy of the well leakage warning, the method of fusing the statistical model and the machine learning model and the spatio-temporal correlation analysis is proposed in the embodiment of the application. Through the logical progression of the data layer, the analysis layer, the verification layer and the correlation layer, the accurate well leakage warning is realized. The required data is the logging data and the historical logging data and the well leakage record of the adjacent well of the current wellbore. The adjacent well is the adjacent well in the same block. The screening standard is that the distance from the current well is less than or equal to 5 km, the geological horizon is the same, and the deviation of the drilled well depth is less than or equal to 500 m, so as to ensure the similarity of the geological conditions.

[0105] In an embodiment, the method further comprises:

[0106] When the first difference value is less than the difference value threshold, the deviation of the well leakage judgment index value and the well leakage judgment index base value is input to a random forest model to obtain a well leakage probability of the current wellbore, and the random forest model is obtained by training based on the historical logging data and the well leakage record of the adjacent well of the current wellbore;

[0107] If the well leakage probability is greater than a probability threshold, it is determined that the well leakage warning needs to be given.

[0108] In the embodiment of the application, the training set when the random forest model is trained is the historical logging data and the well leakage record of the adjacent well in the same block (corresponding to the correlation data in step 1). The input features are the deviation of the well leakage judgment index value and the well leakage judgment index base value in the historical logging data of the adjacent well of the current wellbore. The label data is the well leakage record of the adjacent well of the current wellbore (1 represents that the well leakage occurs, and 0 represents that it is normal). By training the random forest model, the parameters (such as the number of decision trees and the maximum depth) are optimized, so that the random forest model can identify the well leakage feature deviation pattern (such as the combination pattern of the sudden increase in drilling speed + the sudden decrease in drilling pressure + the sudden decrease in MSE). When predicting, the real-time deviation of the current wellbore is input into the random forest model, and the well leakage probability P of the current wellbore is output. The range of the well leakage probability P is 0-1. The larger P is, the higher the well leakage risk is. If P is greater than or equal to 0.7 (the probability threshold is determined by historical data verification), it means that there is suspicious well leakage, and it has been determined that the first difference value is less than the difference value threshold. At this time, the two methods are consistent in judgment. Therefore, it is determined that the well leakage warning needs to be given, the false judgment of a single model is eliminated through consistency check, and the high-credibility preliminary screening result is retained.

[0109] In an embodiment, the method further comprises:

[0110] After determining that the well kick early warning needs to be issued, a deviation of all well kick judgment index values of the nearest neighbor well of the current wellbore in the current well depth interval from the well kick judgment index base value is extracted from the block well kick feature map to form a query deviation vector;

[0111] A similarity of a to-be-analyzed deviation vector formed by the deviation of all well kick judgment index values of the current wellbore at the current well depth from the well kick judgment index base value and the query deviation vector is calculated.

[0112] According to the similarity, a warning credibility is determined.

[0113] According to the warning time, the warning type, the current well depth, the warning credibility and the warning description, a warning information is generated.

[0114] In the embodiment of the present application, when constructing the block well kick feature map, the historical logging data of the neighbor well can be used as the basis, and the deviation vector formed by the average value of the deviation of all well kick judgment index values from the well kick judgment index base value can be stored in each depth interval (such as every 100 meters as an interval). When calculating the similarity S, the calculation method of the cosine similarity can be used.

[0115] When determining the warning credibility according to the similarity, the following rules can be followed:

[0116] If S is greater than or equal to 0.6, the warning credibility is determined to be 0.9. (The threshold values of 0.6 and 0.9 are calibrated by historical data of the block), which indicates that the suspicious features of the current well are highly similar to the well kick features of the neighbor well in the same depth section, and the warning credibility is high.

[0117] If 0.4 is less than S and S is less than 0.6, the warning credibility is determined to be 0.7.

[0118] If S is less than 0.4, the warning credibility is determined to be 0.5.

[0119] In the embodiment of the present application, the warning can be classified into different levels:

[0120] High-risk warning: the warning credibility is 0.9.

[0121] Medium-risk warning: the warning credibility is 0.7.

[0122] Low-risk warning: the warning credibility is 0.5.

[0123] The warning level can be fed back together with the warning information.

[0124] The embodiment of the present application also proposes a well kick risk warning device, which has a similar principle to the well kick risk warning method, and will not be described here.

[0125] Figure 3A structure diagram of a well leakage risk early warning device in an embodiment of the present application, the device comprising:

[0126] A logging data acquisition module 301, configured to acquire logging data in real time when a drilling tool element is vented in drilling operations, and to perform time-depth conversion on the logging data to obtain analysis logging data;

[0127] A well leakage judgment index value calculation module 302, configured to perform sliding window analysis on a shallow well section from a latest well depth in the analysis logging data as a starting point, and to obtain a well leakage judgment index value of a first preset window length from the analysis logging data;

[0128] A well leakage judgment index base value calculation module 303, configured to calculate a well leakage judgment index base value according to the well leakage judgment index value of the first preset window length;

[0129] A well leakage judgment module 304, configured to calculate a deviation of each well leakage judgment index value from the well leakage judgment index base value for each acquisition point of a second preset window length, and to obtain a first well leakage judgment result according to a relationship between the deviations corresponding to all acquisition points and a first well leakage judgment threshold if a current well depth is not greater than a first depth, or to obtain a first well leakage judgment result according to a relationship between the deviations corresponding to all acquisition points and a second well leakage judgment threshold if the current well depth is greater than the first depth; and configured to determine whether to issue a well leakage early warning according to a maximum value of a current hook height corresponding to the current well depth and a historical hook height if the first well leakage judgment result is that there is suspicious well leakage in the current wellbore.

[0130] In an embodiment, the logging data acquisition module is configured to:

[0131] perform standardization processing on the logging data acquired in real time when the drilling condition is met;

[0132] perform conversion processing from a time sequence to a depth sequence on the logging data after the standardization processing to obtain the analysis logging data.

[0133] In an embodiment, the analysis logging data includes one or any combination of time, well depth, drill bit position, instantaneous rotation speed, rotary table rotation speed, drilling pressure, and hook height.

[0134] The well leakage judgment index value includes instantaneous drilling speed, drilling pressure, and rotary table rotation speed.

[0135] In an embodiment, the well leakage judgment module is configured to:

[0136] If the current well depth is not greater than the first depth, calculate a deviation of each well leakage judgment index value from the well leakage judgment index base value for each acquisition point of the second preset window length, and determine that the well leakage judgment index value can judge that there is suspicious well leakage if the deviations corresponding to a preset number of acquisition points are all less than the first well leakage judgment threshold.

[0137] If the current well depth is greater than the first depth, for each lost circulation indicator value, at each acquisition point in a second preset window length, a deviation of the lost circulation indicator value from a lost circulation indicator base value is calculated, and if the deviations corresponding to a preset number of acquisition points are all less than a second lost circulation judgment threshold, it is determined that the lost circulation indicator value can determine that there is a suspected lost circulation;

[0138] If all the lost circulation indicator values can determine that there is a suspected lost circulation, it is determined that the first lost circulation judgment result is that there is a suspected lost circulation in the current wellbore.

[0139] In an embodiment, if the lost circulation indicator value is instantaneous drilling speed, the deviation is a first ratio of the instantaneous drilling speed to an instantaneous drilling speed base value;

[0140] If the lost circulation indicator value is drilling pressure, the deviation is a second ratio of the drilling pressure to a drilling pressure base value;

[0141] If the lost circulation indicator value is rotary table speed, the deviation is an absolute value of a difference between the rotary table speed and a rotary table speed base value.

[0142] In an embodiment, the lost circulation judgment module is configured to:

[0143] calculate a first difference between a current well depth corresponding to a hook height and a maximum value of historical hook heights;

[0144] when the first difference is less than a difference threshold, determine that a lost circulation warning needs to be issued.

[0145] Figure 4 Another structural diagram of the lost circulation risk warning device in an embodiment of the present application, in an embodiment, the device further comprises a lost circulation probability obtaining module 401, configured to:

[0146] when the first difference is less than a difference threshold, input a deviation of the lost circulation indicator value from a lost circulation indicator base value into a random forest model to obtain a lost circulation probability of the current wellbore, the random forest model being trained based on historical logging data and lost circulation records of adjacent wells of the current wellbore;

[0147] The lost circulation judgment module is further configured to: if the lost circulation probability is greater than a probability threshold, determine that a lost circulation warning needs to be issued.

[0148] In an embodiment, the device further comprises a warning information generating module 402, configured to:

[0149] After determining that a lost circulation warning needs to be issued, extract all deviations of lost circulation indicator values of the nearest adjacent well of the current wellbore in a well depth interval in which the current well depth is located from a lost circulation indicator base value from a block lost circulation feature map to form a query deviation vector;

[0150] a similarity between a to-be-analyzed deviation vector formed by deviations of all well loss judgment index values of the current wellbore at the current well depth from the well loss judgment index base value and the query deviation vector;

[0151] determine a pre-warning credibility according to the similarity;

[0152] generate pre-warning information according to the pre-warning time, the pre-warning type, the current well depth, the pre-warning credibility and the pre-warning description.

[0153] The above-mentioned method and device proposed by the embodiments of the present application have the following beneficial effects:

[0154] The pre-warning effectiveness is significantly enhanced. Traditional well loss monitoring mainly relies on surface parameter tracking of the drilling fluid circulation system and post-completion logging interpretation analysis. These methods often result in delayed monitoring results, and cannot accurately identify the leakage point in real time, which leads to the inability to develop and accurately implement well loss treatment measures in advance, and still poses a great threat to drilling safety. The well loss risk intelligent pre-warning method based on drilling tool micro-element emptying can more accurately identify the easy-to-leak point in the well, quickly capture the subtle changes of the well loss risk, realize early warning of the well loss risk, and improve the timeliness and accuracy of the pre-warning.

[0155] The automation and intelligence level of risk monitoring are significantly improved. The present application realizes continuous and automatic monitoring of drilling operations by comprehensively collecting drilling data in real time by a logging instrument and analyzing the data by an intelligent pre-warning model. This intelligent monitoring method not only reduces the dependence on manual monitoring and reduces the work burden of the operating personnel, but also can guide the operating personnel to take optimization measures in real time and timely respond to well loss risks, thereby significantly improving the safety and efficiency of drilling operations.

[0156] The present application also provides a computer device, Figure 5 The computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520. The processor 520 executes the computer program 530 to implement the well loss risk pre-warning method described above.

[0157] The present application also provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the well loss risk pre-warning method described above.

[0158] The present application also provides a computer program product, which includes a computer program. The computer program is executed by a processor to implement the well loss risk pre-warning method described above.

[0159] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In a software embodiment, the present application can be implemented with computer programs (also referred to as software instructions, software code, computer code, and the like) that execute on programmable hardware including computer processors, digital signal processors, microprocessors, central processing units, microcontrollers, programmable hardware logic devices, and the like. Generally, the present application can be implemented in hardware, software, or any combination of hardware and software.

[0160] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0161] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0162] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0163] The specific embodiments described above have been disclosed by way of example and that, obviously, any modifications and / or alterations to the application shall be considered designed in the spirit and scope thereof. Accordingly, the scope of the application should be determined by the appended claims.

Claims

1. A method for early warning of lost circulation risk, characterized in that: include: Real-time acquisition of logging data when drilling tool micro-element is emptied during drilling operation, and time-depth conversion of the logging data to obtain logging data for analysis; Performing a sliding window analysis from the latest well depth in the analytical logging data to the shallow well section, and obtaining a lost circulation judgment index value of a first preset window length from the analytical logging data; Calculating a base value of a lost circulation judgment index according to the lost circulation judgment index value of the first preset window length; For each acquisition point of the second preset window length, the deviation of each well loss judgment index value and the well loss judgment index base value is calculated. If the current well depth is not greater than the first depth, a first well loss judgment result is obtained based on the relationship between the deviations corresponding to all acquisition points and the first well loss judgment threshold value. Otherwise, the first well loss judgment result is obtained based on the relationship between the deviations corresponding to all acquisition points and the second well loss judgment threshold value. If the first well leakage judgment result is that there is suspected well leakage in the current wellbore, it is determined whether a well leakage warning needs to be issued based on the hook height corresponding to the current well depth and the maximum value of the historical hook height.

2. The method according to claim 1, characterized in that Real-time acquisition of logging data during drilling tool micro-element emptying during drilling operations, and time-depth conversion of the logging data to obtain logging data for analysis, including: When the real-time collected logging data meets the drilling conditions, the logging data is standardized; The standardized logging data are converted from time series to depth series to obtain logging data for analysis.

3. The method according to claim 1, characterized in that The logging data for analysis includes one or any combination of time, well depth, drill bit position, instantaneous rotation speed, rotary table rotation speed, bit pressure, and hook height; The indicators for judging lost circulation include instantaneous drilling speed, drilling pressure and rotary table speed.

4. The method according to claim 3, characterized in that For each acquisition point of the second preset window length, the deviation of each well loss judgment index value and the well loss judgment index base value is calculated. If the current well depth is not greater than the first depth, a first well loss judgment result is obtained based on the relationship between the deviations corresponding to all acquisition points and the first well loss judgment threshold value. Otherwise, the first well loss judgment result is obtained based on the relationship between the deviations corresponding to all acquisition points and the second well loss judgment threshold value, including: If the current well depth is not greater than the first depth, for each lost circulation judgment index value at each acquisition point within the second preset window length, the deviation between the lost circulation judgment index value and the lost circulation judgment index base value is calculated; if the deviations corresponding to a preset number of acquisition points are all less than the first lost circulation judgment threshold, it is determined that the lost circulation judgment index value is sufficient to determine the presence of suspected lost circulation; If the current well depth is greater than the first depth, for each lost circulation judgment index value at each acquisition point within the second preset window length, the deviation between the lost circulation judgment index value and the lost circulation judgment index base value is calculated; if the deviations corresponding to the preset number of acquisition points are all less than the second lost circulation judgment threshold, it is determined that the lost circulation judgment index value is sufficient to determine the presence of suspected lost circulation; If all the lost circulation judgment index values ​​can determine that there is suspected lost circulation, the first lost circulation judgment result is determined to be that there is suspected lost circulation in the current wellbore.

5. The method according to claim 4, characterized in that If the lost circulation judgment index value is the instantaneous drilling rate, the deviation is a first ratio of the instantaneous drilling rate to the instantaneous drilling rate base value; If the lost circulation judgment indicator value is the bit pressure, the deviation is a second ratio of the bit pressure to the bit pressure base value; If the lost circulation determination index value is the rotary table speed, the deviation is the absolute value of the difference between the rotary table speed and the rotary table speed base value.

6. The method according to claim 1, characterized in that Based on the hook height corresponding to the current well depth and the maximum value of the historical hook height, it is determined whether a lost circulation warning needs to be issued, including: Calculate the first difference between the hook height corresponding to the current well depth and the maximum value of the historical hook height; When the first difference is smaller than a difference threshold, it is determined that a lost circulation warning needs to be issued.

7. The method according to claim 6, characterized in that The method further comprises: When the first difference is less than a difference threshold, inputting the deviation between the lost circulation judgment index value and the lost circulation judgment index base value into a random forest model to obtain a lost circulation probability of the current wellbore, wherein the random forest model is trained based on historical logging data and lost circulation records of neighboring wells of the current wellbore; If the probability of lost circulation is greater than the probability threshold, it is determined that a lost circulation warning needs to be issued.

8. The method according to claim 1, characterized in that The method further comprises: After determining that a lost circulation warning needs to be issued, the deviations between all lost circulation judgment index values ​​and the lost circulation judgment index base value of the nearest neighboring wells of the current wellbore in the depth interval of the current wellbore are extracted from the lost circulation characteristic map of the block to form a query deviation vector; similarity between the deviation vector to be analyzed formed by the deviation of all the lost circulation judgment index values ​​of the current wellbore at the current well depth and the base value of the lost circulation judgment index and the query deviation vector; Determining the credibility of the warning based on the similarity; Generate warning information based on warning time, warning type, current well depth, warning credibility and warning description.

9. A well leakage risk warning device, characterized in that: include: The logging data acquisition module is used to collect the logging data when the drilling tool micro-element is emptied in real time during the drilling operation, and perform time-depth conversion on the logging data to obtain logging data for analysis; A lost circulation judgment index value calculation module is used to perform a sliding window analysis from the latest well depth in the analysis logging data to the shallow well section, and obtain a lost circulation judgment index value of a first preset window length from the analysis logging data; A lost circulation judgment index base value calculation module, configured to calculate a lost circulation judgment index base value based on the lost circulation judgment index value of the first preset window length; The lost circulation judgment module is used to calculate the deviation of each lost circulation judgment index value and the lost circulation judgment index base value for each acquisition point within the second preset window length. If the current well depth is not greater than the first depth, a first lost circulation judgment result is obtained based on the relationship between the deviations corresponding to all acquisition points and the first lost circulation judgment threshold. Otherwise, the first lost circulation judgment result is obtained based on the relationship between the deviations corresponding to all acquisition points and the second lost circulation judgment threshold. If the first lost circulation judgment result indicates that the current wellbore has suspected lost circulation, a judgment is made as to whether a lost circulation warning needs to be issued based on the maximum value of the hook height corresponding to the current well depth and the historical hook height.

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

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images