An overflow recognition and processing method and device
By processing drilling data in real time and calling overflow recognition calculation methods dynamically, the problems of overflow recognition lag and low accuracy in the existing technology are solved, and more accurate and timely overflow recognition is achieved, which improves the automation and intelligence of the drilling process.
Patent Information
- Application Number
- CN202210748004.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-29
- Publication Date
- 2025-06-27
- Estimated Expiration
- 2042-06-29
AI Technical Summary
The prior art is difficult to accurately identify the occurrence of overflow during drilling, resulting in lag, relying on manual experience and low accuracy.
By obtaining real-time drilling measurement data, performing data processing and identifying drilling status, dynamically calling the corresponding overflow identification calculation method, and using the total pool volume and outlet flow data to calculate the overflow occurrence index to achieve early identification of overflow.
It improves the accuracy and timeliness of overflow identification, reduces manual intervention, and enhances the automation and intelligence of the drilling process.
Smart Images

Figure CN115126478B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of drilling, and particularly to a method and device for overflow identification and processing. Background Art
[0002] Drilling is an important means for oil and gas exploration and development. In drilling operations, drilling complications and accidents threaten the entire drilling process from beginning to end, seriously affecting the drilling speed, well construction quality, and exploration and development efficiency. Among them, overflow is one of the most common downhole complex accidents that affect drilling safety. Overflow will change the originally determined drilling operation plan and increase drilling costs; as the early stage of well kick and blowout, if the overflow is not detected and warned in time, the well control treatment time will be extended, and the overflow situation will worsen, and in severe cases, even blowout out of control may occur; therefore, early identification of overflow can avoid the occurrence of serious accidents such as blowout, which is of great significance to the safety and economy of drilling.
[0003] In actual drilling engineering, traditional overflow identification is carried out by manually monitoring the changes in the total pool volume and the flow difference between the inlet and outlet. Limited by the excessively large area of the mud pit, usually only when the change in the total pool volume reaches more than 2 square meters can the occurrence of overflow be identified, resulting in a lag in overflow identification; this method relying on manual monitoring, the identification results largely depend on manual experience, resulting in uneven levels of overflow identification and frequent false alarms. At the same time, at present, target flowmeters are mostly used on site, and the unit of the measured outlet flow is generally %, while the inlet flow is usually calculated from parameters such as pump strokes, and the unit is L / s. Therefore, it is difficult to directly obtain the flow difference between the inlet and outlet, which also causes difficulties in overflow identification. On the other hand, due to the complexity of the wellbore fluid mechanism, the uncertainty of formation pressure, and the incompleteness of data, traditional physical models are difficult to accurately simulate and describe the occurrence process of overflow. With the rapid development of data acquisition technology and analysis technology, drilling researchers have begun to use methods such as improving the measurement accuracy of the outlet flow and using big data artificial intelligence to analyze the measurement data to judge the occurrence of overflow. However, the accuracy of judging whether overflow occurs is not high. Summary of the Invention
[0004] In view of the problems in the prior art, embodiments of the present invention provide a method and device for overflow identification and processing, which can at least partially solve the problems existing in the prior art.
[0005] On the one hand, the present invention proposes a method for overflow identification and processing, including:
[0006] Obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling state according to the processed real-time drilling measurement data;
[0007] Determine the corresponding overflow identification calculation method according to the drilling state identification result, and use the overflow identification calculation method and the processed real-time drilling measurement data to identify whether an overflow occurs.
[0008] Among them, the identification of the drilling state according to the processed real-time drilling measurement data includes:
[0009] If it is determined that the well depth is equal to the bit depth, and the weight on bit is greater than zero, and the rotary table speed is greater than zero, and the pump strokes are greater than zero, then determine that the drilling state identification result is drilling;
[0010] If it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold;
[0011] Or, if it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is tripping down, then determine that the drilling state identification result is tripping down;
[0012] If it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold;
[0013] Or, if it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is tripping up, then determine that the drilling state identification result is tripping up.
[0014] Among them, using the overflow identification calculation method and the processed real-time drilling measurement data to identify whether an overflow occurs includes:
[0015] Obtain the average value of the total pit volume time series window and the base value of the total pit volume in the normal drilling state, and calculate the first overflow occurrence index based on the total pit volume according to the average value of the total pit volume time series window and the base value of the total pit volume;
[0016] Obtain the time series of the outlet flow rate data and the time series of the inlet flow rate data, and calculate the second overflow occurrence index based on the outlet flow rate according to the time series of the outlet flow rate data and the time series of the inlet flow rate data;
[0017] Calculate the comprehensive overflow occurrence index according to the first overflow occurrence index, the second overflow occurrence index and their respective weight indexes, and determine the identification result of whether an overflow occurs in the drilling state according to the comparison result between the comprehensive overflow occurrence index and the overflow identification threshold.
[0018] Among them, calculating a first overflow occurrence index based on the total pool volume includes: according to the average value of the total pool volume time series window and the total pool volume base value,
[0019] Calculating a deviation amount of the total pool volume value according to the total pool volume base value and the average value of the total pool volume time series window;
[0020] Calculating the first overflow occurrence index according to the deviation amount of the total pool volume value and the total pool volume change threshold.
[0021] Among them, calculating a second overflow occurrence index based on the outlet flow rate includes: according to the time series of the outlet flow rate data and the time series of the inlet flow rate data,
[0022] Identifying the change trend of the outlet flow rate according to the time series of the outlet flow rate data; and identifying the change trend of the inlet flow rate according to the time series of the inlet flow rate data;
[0023] Calculating the similarity between the identification results of the outlet flow rate change trend and the inlet flow rate change trend, and calculating the second overflow occurrence index according to the similarity calculation result and the outlet flow rate change threshold.
[0024] Among them, using the overflow identification calculation method and identifying whether an overflow occurs according to the processed real-time drilling measurement data includes:
[0025] Calculating the volume of the drill string lifted out of the wellbore according to the length, inner diameter, and outer diameter of the drill string;
[0026] If it is determined that the change amount of the volume of the trip tank is greater than the sum of the volume of the drill string lifted out of the wellbore and the drill string volume change threshold, it is determined that an overflow occurs during the trip out operation.
[0027] Among them, using the overflow identification calculation method and identifying whether an overflow occurs according to the processed real-time drilling measurement data includes:
[0028] Calculating the volume of the drill string entering the wellbore according to the length, inner diameter, and outer diameter of the drill string;
[0029] If it is determined that the change amount of the volume of the trip tank is greater than the sum of the volume of the drill string entering the wellbore and the drill string volume change threshold, it is determined that an overflow occurs during the trip in operation.
[0030] On the one hand, the present invention provides an overflow identification and processing device, including:
[0031] An acquisition unit for acquiring real-time drilling measurement data, processing the real-time drilling measurement data, and identifying the drilling state according to the processed real-time drilling measurement data;
[0032] An identification unit is configured to determine a corresponding overflow identification calculation method according to the drilling status identification result, and use the overflow identification calculation method to identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0033] On the other hand, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following method is implemented:
[0034] Obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling status based on the processed real-time drilling measurement data;
[0035] Determine a corresponding overflow identification calculation method according to the drilling status identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0036] An embodiment of the present invention provides a computer-readable storage medium, including:
[0037] The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method is implemented:
[0038] Obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling status based on the processed real-time drilling measurement data;
[0039] Determine a corresponding overflow identification calculation method according to the drilling status identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0040] An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the following method is implemented:
[0041] Obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling status based on the processed real-time drilling measurement data;
[0042] Determine a corresponding overflow identification calculation method according to the drilling status identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0043] The overflow identification and processing method and device provided by the embodiments of the present invention obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, identify the drilling state based on the processed real-time drilling measurement data; determine the corresponding overflow identification calculation method according to the drilling state identification result, and use the overflow identification calculation method and the processed real-time drilling measurement data to identify whether an overflow occurs, which can improve the accuracy of identifying whether an overflow occurs. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:
[0045] Figure 1 is a flowchart of the overflow identification and processing method provided by an embodiment of the present invention.
[0046] Figure 2 is a flowchart of the overflow identification and processing method provided by another embodiment of the present invention.
[0047] Figure 3 is a flowchart of the overflow identification and processing method provided by another embodiment of the present invention.
[0048] Figure 4 is a structural diagram of the overflow identification and processing device provided by an embodiment of the present invention.
[0049] Figure 5 is a schematic physical structure diagram of the computer device provided by the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer and more understandable, the following will further describe the embodiments of the present invention in detail with reference to the drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention. It should be noted that, without conflict, the embodiments and features in the embodiments of the present application can be combined with each other arbitrarily.
[0051] Figure 1 is a flowchart of the overflow identification and processing method provided by an embodiment of the present invention. As Figure 1 shown, the overflow identification and processing method provided by the embodiments of the present invention includes:
[0052] Step S1: Obtain real-time drilling measurement data, process the real-time drilling measurement data, and identify the drilling state based on the processed real-time drilling measurement data.
[0053] Step S2: Determine the corresponding overflow identification calculation method according to the drilling state identification result, and use the overflow identification calculation method to identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0054] In the above step S1, the device obtains real-time drilling measurement data, processes the real-time drilling measurement data, and identifies the drilling state based on the processed real-time drilling measurement data. The device can be a computer device that executes this method, such as a server. In the technical solution of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations. The real-time drilling measurement data can be time series data.
[0055] The original data sequence can be cleaned of single-point large noise by the data deviation constraint method, which maximally preserves the original value of the time series. This method first calculates the difference between adjacent data points of the time series to form a new data difference sequence. Assume the original sequence is X (X = X1, X2, X3,..., X n ), then the new difference sequence is X' (X' = X'1, X'2, X'3,..., X' n-1 ); X' i is obtained from the following formula:
[0056] X' i = X i+1 - X i (Equation 1)
[0057] The outlier threshold is obtained from the following formula:
[0058] TH noise = E(X') + 3S(X') (Equation 2)
[0059] Where:
[0060]
[0061]
[0062] When the i-th point in the original time series simultaneously satisfies the following two inequalities:
[0063] X' i > TH noise ; X' i+1 < -TH noise (Equation 5)
[0064] Or when the following two inequalities are satisfied simultaneously:
[0065] X′ i < -TH noise ; X′ i+1 >TH noise (Equation 6)
[0066] It can be determined that X i is a single-point large noise, and linear interpolation is used to fill it with the previous and next values to obtain a new data sequence after cleaning, (X new = X1, X2... X i-new ... X n ), where:
[0067] X i-new =(X i-1 + X i+1 ) / 2
[0068] The identification of the drilling state based on the processed real-time drilling measurement data includes:
[0069] If it is determined that the well depth is equal to the bit depth, and the weight on bit is greater than zero, and the rotary table speed is greater than zero, and the pump strokes are greater than zero, then the drilling state identification result is determined to be drilling;
[0070] If it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold;
[0071] Or, if it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is tripping, then the drilling state identification result is determined to be tripping;
[0072] If it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold;
[0073] Or, if it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is pulling out of the hole, then the drilling state identification result is determined to be pulling out of the hole. The explanation is as follows:
[0074] If HDEP i = BDEP i && BOP i >0 && RPM i >0 && PUMP i >0; then DS i is in the drilling state;
[0075] If BDEP i >BDEPi-1 &&(HDEP i -BDEP i >TH trip ||DS i-1 is drill down); then DS i It is in the drill-down state;
[0076] If BDEP i <BDEP i-1 &&(HDEP i -BDEP i >TH trip ||DS i-1 is the start of drilling); then DS i It is the drilling state;
[0077] Among them: HDEP i :T i The well depth at the time point, in m;
[0078] BDEP i :T i The drill bit depth at a given time point, in m;
[0079] BOP i :T i The drilling pressure at a time point, in kN;
[0080] RPM i :T i The drill speed at the time point, in RPM;
[0081] PUMP i :T i The pump impulse at a time point, in stk;
[0082] TH trip : The depth threshold of the drilling, in meters. The threshold used in this method is 27 meters.
[0083] DS i :T i The drilling status at a point in time, unitless.
[0084] In the above step S2, the device determines the corresponding overflow identification calculation method according to the drilling state identification result, and uses the overflow identification calculation method to identify whether overflow occurs according to the processed real-time drilling measurement data. Figure 2 As shown, according to T i Identify the drilling status at all times, dynamically call different overflow identification algorithms, and calculate the possibility of overflow in real time.
[0085] Using the above overflow identification calculation method, identify whether an overflow has occurred based on the real-time drilling measurement data obtained through processing, including:
[0086] Obtain the average value of the total pit volume time series window and the base value of the total pit volume under normal drilling conditions. Based on the average value of the total pit volume time series window and the base value of the total pit volume, calculate the first overflow occurrence index based on the total pit volume;
[0087] Obtain the time series of outlet flow rate data and the time series of inlet flow rate data. Based on the time series of outlet flow rate data and the time series of inlet flow rate data, calculate the second overflow occurrence index based on the outlet flow rate;
[0088] Based on the first overflow occurrence index, the second overflow occurrence index, and their respective weight indexes, calculate the comprehensive overflow occurrence index. Based on the comparison result between the comprehensive overflow occurrence index and the overflow identification threshold, determine the identification result of whether an overflow has occurred during the drilling state.
[0089] The calculation of the first overflow occurrence index based on the total pit volume according to the average value of the total pit volume time series window and the base value of the total pit volume includes:
[0090] Based on the base value of the total pit volume and the average value of the total pit volume time series window, calculate the deviation of the total pit volume value; the acquisition method is: at time T i Read the total pit volume data segment (PV i-w1 , PV i ) with a window length of w1 at the time point, calculate the variance Var(PV) of this data segment, and the calculation formula refers to (Equation 4); at the same time, obtain the total pit volume variance value of the same window length under normal drilling conditions (the inlet and outlet flow rates remain unchanged, there is no operation of adding or subtracting mud to the mud pit, and no drilling accidents occur) based on historical well data, and use this value as the variance threshold TH pvv ; if
[0091] Var(PV) < 1.5 × TH pvv
[0092] Then obtain the mean value of this time series segment (PV i-w1 , PV i ), and the calculation formula refers to (Equation 3), and use it as the base value PV of the total pit volume basic .
[0093] Using the moving window average method to calculate the average value Avg i with a window length of w2 at time T i , and the calculation formula refers to (Equation 3); combined with the calculated base value of the total pit volume, calculate the current deviation of the total pit volume value PV dif-i:
[0094] PV dif-i = Avg i - PV basic
[0095] Where:
[0096] Avgi: The average value of the total pond volume time series window (PV i-w2 , PV i ), that is, the estimated value of the total pond volume at time T i .
[0097] According to the deviation of the total pond volume value and the total pond volume change threshold, the first overflow occurrence index is calculated.
[0098] POK PV-at-i = min(max(PV dif-i / PV tolerance × 100%, 0), 1)
[0099] Where:
[0100] POK pV-at-i : The first overflow occurrence index at time T i , used to judge the overflow possibility according to the total pond volume change trend.
[0101] PV tolerance : The total pond volume change threshold. When the increase value of the total pond volume reaches the above threshold, the overflow possibility is 1.
[0102] Calculating the second overflow occurrence index based on the outlet flow rate according to the outlet flow rate data time series and the inlet flow rate data time series includes:
[0103] Identifying the outlet flow rate change trend according to the outlet flow rate data time series; and identifying the inlet flow rate change trend according to the inlet flow rate data time series; at time T i , taking the outlet flow rate time series segment FO with a window length of w3 (FO = FO i-w3 , FO i-w3+1 , …, FO i ), performing dimensionality reduction processing on the time series, and the dimensionality-reduced time series is FO′ (FO′ = FO′1, …, FO′ v ), v is the number of segments, usually (v << w3). FO′ k Is obtained by the following formula:
[0104]
[0105] For the dimensionality-reduced time series FO′ (FO′ = FO′1, …, FO′v ) Perform change trend pattern recognition. First, calculate the relative change of the time series FO′ to obtain a new series FO″ (FO″ = FO″1,..., FO″ v-1 ), FO″ k Calculate using the following formula:
[0106]
[0107] According to the calculated FO″ k value, divide the change pattern of the outlet flow rate into: sudden drop (-3), decrease (-2), slow decrease (-1), unchanged (0), slow increase (1), increase (2), sudden increase (3); the corresponding relationship between different change patterns and values is as follows:
[0108] If FO″ k > 70%, the change pattern of time T k is "sudden increase";
[0109] If 30% < FO″ k < 70%, the change pattern of time T k is "increase";
[0110] If 5% < FO″ k < 30%, the change pattern of time T k is "slow increase";
[0111] If -5% < FO″ k < 5%, the change pattern of time T k is "unchanged";
[0112] If -30% < FO″ k < -5%, the change pattern of time T k is "slow decrease";
[0113] If -70% < FO″ k < -30%, the change pattern of time T k is "decrease";
[0114] If FO″ k < -70%, the change pattern of time T k is "sudden drop";
[0115] So far, the time series FO′ after dimensionality reduction can be converted into a change pattern sequence of the outlet flow rate, and the change trend of the outlet flow rate can be recognized from the change pattern sequence.
[0116] For the recognition of the change trend of the inlet flow rate, refer to the above description of the recognition of the change trend of the outlet flow rate, and it will not be elaborated here.
[0117] Calculate the similarity between the recognition results of the outlet flow rate change trend and the recognition results of the inlet flow rate change trend, and calculate the second overflow occurrence index according to the similarity calculation result and the outlet flow rate change threshold. Since the outlet flow rate is closely related to the inlet flow rate, it is impossible to accurately judge the occurrence of overflow only by the change trend of the outlet flow rate; at the same time, the field usually uses a target flowmeter to measure the outlet displacement, with the unit of %, while the inlet flow rate is usually calculated, with the unit of L / s, and the inlet and outlet flow rates often cannot be directly compared in actual values. Under normal circumstances, the change trends of the inlet and outlet flow rate curves are the same, and the deviation of the change trends of the two curves can be used as a judgment for overflow or leakage. The present invention calculates the similarity of the inlet and outlet flow rate change trends by changing the outlet flow rate curve and the inlet flow rate curve from data to pattern, so as to calculate the possibility of overflow based on the change of the outlet flow rate.
[0118] Convert the inlet and outlet flow rate time series FO and FI into FO″′ (FO″′ = FO″′1,..., FO″′ v-1 ) and FI″′ (FI″′ = FI″′1,..., FI″′v -1 ) respectively according to the above method; where:
[0119] FO″′ k and FI″′ k ∈{sudden drop, decrease, slow decrease, unchanged, slow increase, increase, sudden increase};
[0120] Secondly, calculate the similarity of the inlet and outlet flow rate curve patterns; the formula used is as follows:
[0121]
[0122] Thirdly, calculate the possibility of overflow based on the change trend of the outlet flow rate:
[0123] POK F0-at-i = min(max(S / S tolerance × 100%, 0), 1)
[0124] where:
[0125] POK F0-at-i : The second overflow occurrence index at time T i , which is used to judge the possibility of overflow according to the change trend of the outlet flow rate.
[0126] S tolerance : The outlet flow rate change threshold. When S reaches this threshold, POK FO-at-i is 1.
[0127] POK total = Weight FO × POK FO-at-i+Weight PV ×POK PV-at-i
[0128] Wherein:
[0129] Weight F0 , Weight PV : are the weight indices of the outlet flow rate and the total pool volume respectively, and satisfy the following formula:
[0130] Weight F0 +Weight PV = 1
[0131] The overflow identification threshold can be set independently according to the actual situation, and can be selected as 75%. If the comprehensive index of overflow occurrence is greater than the overflow identification threshold, it is determined that overflow occurs in the drilling state; if the comprehensive index of overflow occurrence is less than or equal to the overflow identification threshold, it is determined that overflow does not occur in the drilling state.
[0132] Using the above-mentioned overflow identification calculation method, and identifying whether overflow occurs according to the real-time drilling measurement data obtained by processing, including:
[0133] According to the drill string length, drill string inner diameter and drill string outer diameter, calculate the volume of the drill string lifted out of the wellbore; the volume of the drill string lifted out of the wellbore can be calculated by using the corresponding calculation method according to the tripping operation mode. If the tripping operation mode is open discharge, then:
[0134]
[0135] If the tripping operation mode is closed discharge, then:
[0136]
[0137] Wherein:
[0138] PI is the pi;
[0139]
[0140] BDEP starttime : the start time of drill string lifting out;
[0141] BDEP endtime : the end time of drill string lifting out;
[0142] Tool.OD i : the outer diameter of drill string i, unit m;
[0143] Tool.ID i : the inner diameter of drill string i, unit m;
[0144] Tool.Lengthi : The length of the drill string i, unit: m;
[0145] If it is determined that the change in the volume of the trip tank is greater than the sum of the volume of the drill string pulled out of the wellbore and the drill string volume change threshold, it is determined that a kick occurs during the pulling out of the drill string.
[0146] The calculation method of the change in the volume of the trip tank is as follows:
[0147] V triptank-change = V triptank-sta - V triptank-end
[0148] V triptank-hange : The change in the volume of the trip tank, unit: m 3 ;
[0149] V triptank-st : The volume of the trip tank at the start of pulling out the drill string, unit: m 3 ;
[0150] V triptank-end : The volume of the trip tank at the end of pulling out the drill string, unit: m 3 ;
[0151] If:
[0152] |V triptank-hange | > |V total-out | + V torelance
[0153] Then it can be judged that a kick has occurred, where V torelance is the drill string volume change threshold.
[0154] Using the above kick identification calculation method, and based on the real-time drilling measurement data obtained through processing, identify whether a kick occurs, including:
[0155] According to the length, inner diameter and outer diameter of the drill string, calculate the volume of the drill string entering the wellbore; according to the tripping operation mode, the corresponding calculation method can be used to calculate the volume of the drill string entering the wellbore. If the tripping operation mode is open discharge, then:
[0156]
[0157] If the tripping operation mode is closed discharge, then:
[0158]
[0159] Where:
[0160] PI is the ratio of the circumference of a circle to its diameter;
[0161]
[0162] BDEP starttime : Start time of drill string lowering;
[0163] BDEP endtime : End time of drill string lowering;
[0164] Tool.OD i : Outer diameter of drill string i, unit: m;
[0165] Tool.ID i : Inner diameter of drill string i, unit: m;
[0166] Tool.Length i : Length of drill string i, unit: m;
[0167] If it is determined that the change in the volume of the trip tank is greater than the sum of the volume of the drill string entering the wellbore and the drill string volume change threshold, it is determined that a kick occurs during the drill string lowering state.
[0168] The calculation method of the change in the volume of the trip tank is as follows:
[0169] V triptank-change = V triptank-sta - V triptank-end
[0170] V triptank-change : Change in the volume of the trip tank, unit: m 3 ;
[0171] V triptank-sta : Volume of the trip tank at the start of drill string lowering, unit: m 3 ;
[0172] V triptank-end : Volume of the trip tank at the end of drill string lowering, unit: m 3 ;
[0173] If:
[0174] |V triptank-change | > |V total-ou | + V torelance
[0175] Then it can be judged that a kick occurs, where V torelance is the drill string volume change threshold.
[0176] It should be noted that pulling out of the wellbore and entering the wellbore are different drilling states, and the above real-time drilling measurement data are the same data in different drilling states, so the same symbol marks are used to represent them.
[0177] Such as Figure 3As shown, after the step of identifying whether a kick occurs based on the real-time drilling measurement data obtained through processing, the kick identification processing method further includes:
[0178] Step S3: If it is determined that the kick identification result is a kick, generate an alarm message for relevant personnel to take corresponding measures in a timely manner.
[0179] This is illustrated with an example as follows:
[0180] For a certain well in a certain oilfield, at 0:38 on September 21st, when drilling to a well depth of 5247.21m, gas logging was abnormal, the total pit volume increased, the well was shut in for observation, and the casing pressure rose, determining that a kick occurred. The present invention accurately identified the kick in a timely manner. The following is a detailed description of the identification process.
[0181] Step ①, data cleaning.
[0182] Take the start time of identification as 0:14 on September 21st and the end time as 0:37 on September 21st; read the real-time measurement data required for kick identification: well depth, bit depth, inlet flow rate, outlet flow rate, total pit volume; the present invention adopts the method of data deviation degree to clean single-point large noise according to the principle of the least change in the original data.
[0183] Obtain the data sequence of the inlet flow rate in the time period from 0:14 on September 21st to 0:36 on September 21st, calculate the difference between adjacent data to obtain a new time series, and calculate the average value and variance of this new time series, which are 0.000114 and 0.061674 respectively; according to the formula:
[0184] TH noise = E(X′) + 3S(X′)
[0185] Obtain the noise threshold TH noise = 0.1851; The algorithm traverses the inlet flow rate time series and finds that at the time point 0:28:07 on September 21st, the inlet flow rate is 15.26L / s, the difference from the previous value of 16.59L / s is -1.33, and the difference from the subsequent value of 16L / s is 0.74, satisfying (Equation 6), and it can be determined that this data point is an abnormal point, and it is filled with linear interpolation using the previous value and the subsequent value.
[0186] Steps ② and ③, automatically identify the drilling state and call the corresponding kick identification algorithm according to the drilling state.
[0187] Take the start time of identification as 0:14 on September 21st and the end time as 0:37 on September 21st; read the real-time measurement data required for automatic identification of the drilling state: well depth, bit depth, weight on bit, rotary speed.
[0188] Between 0:15 and 0:37, the bit depth is the same as the well depth, and the weight on bit and rotary speed are both greater than the minimum threshold, so it can be determined that the drilling state during this period is drilling; call the overflow recognition algorithm during drilling.
[0189] Step ④, the automatic overflow recognition algorithm during drilling.
[0190] a. Obtain the total pit volume base value PV under normal drilling conditions basic
[0191] Take the total pit volume time series segment from the start time 0:17 on September 21st to the end time 0:27 on September 21st. According to steps ② and ③, the drilling state during this time period is drilling, which meets the requirements for obtaining the total pit volume base value. Calculate the standard deviation of this time period, and the result is: 0.053; the set standard deviation threshold in this example is 0.05. Since 0.053 < 1.5×0.05, the average total pit volume of 109.32 during this time period can be used as the total pit volume base value.
[0192] b. Real-time identify the change of the total pit volume
[0193] At the time point 0:36:00 on September 21st, take a window with a time length of 2 minutes (0:34:00 - 0:36:00) and calculate the average value of 109.55; take the total pit volume change threshold as 0.3; then the overflow possibility index based on the total pit volume is:
[0194] POK PV-at-i =(109.55 - 109.32) / 0.3×100% = 76.67%
[0195] c. Real-time identify the change of the flow rate at the outlet
[0196] At the time point 0:36:00 on September 21st, take a window with a time length of 5 minutes (0:31:00 - 0:36:00), divide the window into 5 segments, and calculate the change trends of the inlet flow rate and the outlet flow rate respectively. The obtained results are:
[0197] Inlet flow rate = {0.011; 0.005; -0.004; -0.003}
[0198] Outlet flow rate = {0.041; 0.029; 0.120; 0.067}
[0199] Convert to the change pattern as:
[0200] Inlet flow rate = {constant; constant; constant; constant}
[0201] Outlet flow rate = {constant; constant; slow increase; slow increase}
[0202] d. Calculate the similarity of the inlet and outlet flow curves
[0203] By calculating the similarity of the inlet and outlet flow curves, we can obtain:
[0204] S = (0 - 0) + (0 - 0) + (1 - 0) + (1 - 0) = 2
[0205] Take S tolerance as 2 and calculate the overflow possibility based on the change trend of the outlet flow
[0206] POK F0-at-i = min(max(S / S tolerance × 100%, 0), 1) = 100%;
[0207] e. Calculate the overflow possibility index
[0208] Take Weight F0 as 0.5 and Weight PV as 0.5; calculate the comprehensive overflow possibility index as:
[0209] POK total = Weight F0 × POK F0-at-i + Weight PV × POK PV-at-i = 0.5 * 76.67% + 0.5 * 100% = 88.34%
[0210] Since it is greater than the overflow determination threshold of 75%, it can be determined that an overflow has occurred.
[0211] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0212] 1. The present invention adopts an early overflow recognition method driven by the drilling state. Through steps such as real-time data reception and cleaning, automatic recognition of the drilling state, and automatic invocation of the overflow recognition algorithm under different drilling states, the automation and intelligence of overflow recognition throughout the drilling process are realized.
[0213] 2. The method for automatically obtaining the total pool volume base value by combining historical data analysis is more accurate and intelligent than the commonly used method of manually setting the total pool volume base value, effectively avoiding the subjectivity and lag of manual setting.
[0214] 3. The inlet and outlet flow change trend pattern recognition method adopted by the present invention more accurately reflects the overall change trend of the curve through the methods of segmental averaging and change trend symbolization, weakening the influence of local changes on the calculation of the similarity of the next curve change trend; making the overflow recognition more accurate and timely.
[0215] 4. The present invention adopts a calculation method for the possibility of overflow, making the overflow identification more accurate and objective.
[0216] The overflow identification processing method provided by the embodiment of the present invention obtains real-time drilling measurement data, processes the real-time drilling measurement data, and identifies the drilling state according to the processed real-time drilling measurement data; determines a corresponding overflow identification calculation method according to the drilling state identification result, and uses the overflow identification calculation method and the processed real-time drilling measurement data to identify whether overflow occurs, which can improve the accuracy of identifying whether overflow occurs.
[0217] Further, the identifying the drilling state according to the processed real-time drilling measurement data includes:
[0218] If it is determined that the well depth is equal to the bit depth, and the weight on bit is greater than zero, and the rotary table speed is greater than zero, and the pump strokes are greater than zero, then determine that the drilling state identification result is drilling; reference may be made to the above description and will not be elaborated here.
[0219] If it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold;
[0220] Or, if it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is tripping down, then determine that the drilling state identification result is tripping down; reference may be made to the above description and will not be elaborated here
[0221] If it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold;
[0222] Or, if it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is tripping up, then determine that the drilling state identification result is tripping up. Reference may be made to the above description and will not be elaborated here.
[0223] Further, using the overflow identification calculation method and identifying whether overflow occurs according to the processed real-time drilling measurement data includes:
[0224] Obtain the average value of the total pit volume time series window and the base value of the total pit volume in the normal drilling state, and calculate a first overflow occurrence index based on the total pit volume according to the average value of the total pit volume time series window and the base value of the total pit volume; reference may be made to the above description and will not be elaborated here.
[0225] Obtain the time series of outlet flow rate data and the time series of inlet flow rate data, and calculate a second overflow occurrence index based on the outlet flow rate according to the time series of the outlet flow rate data and the time series of the inlet flow rate data. Refer to the above description for details and will not be elaborated here.
[0226] Calculate an overall overflow occurrence index according to the first overflow occurrence index, the second overflow occurrence index, and their respective weight indexes, and determine the recognition result of whether an overflow occurs in the drilling state according to the comparison result between the overall overflow occurrence index and the overflow recognition threshold. Refer to the above description for details and will not be elaborated here.
[0227] Further, the calculating the first overflow occurrence index based on the total pit volume, according to the time series window average value of the total pit volume and the total pit volume base value, includes:
[0228] Calculate the deviation of the total pit volume value according to the total pit volume base value and the time series window average value of the total pit volume. Refer to the above description for details and will not be elaborated here.
[0229] Calculate the first overflow occurrence index according to the deviation of the total pit volume value and the total pit volume change threshold. Refer to the above description for details and will not be elaborated here.
[0230] Further, the calculating the second overflow occurrence index based on the outlet flow rate, according to the time series of the outlet flow rate data and the time series of the inlet flow rate data, includes:
[0231] Identify the change trend of the outlet flow rate according to the time series of the outlet flow rate data; and identify the change trend of the inlet flow rate according to the time series of the inlet flow rate data. Refer to the above description for details and will not be elaborated here.
[0232] Calculate the similarity between the recognition result of the outlet flow rate change trend and the recognition result of the inlet flow rate change trend, and calculate the second overflow occurrence index according to the similarity calculation result and the outlet flow rate change threshold. Refer to the above description for details and will not be elaborated here.
[0233] Further, using the overflow recognition calculation method, and identifying whether an overflow occurs according to the processed real-time drilling measurement data, includes:
[0234] Calculate the volume of the drill string lifted out of the wellbore according to the length, inner diameter, and outer diameter of the drill string. Refer to the above description for details and will not be elaborated here.
[0235] If it is determined that the change amount of the volume of the trip tank is greater than the sum of the volume of the drill string lifted out of the wellbore and the drill string volume change threshold, it is determined that an overflow occurs during the trip out operation. Refer to the above description for details and will not be elaborated here.
[0236] Further, by using the overflow identification calculation method and based on the real-time drilling measurement data obtained through processing, the identification of whether an overflow occurs includes:
[0237] Calculate the volume of the drill string entering the wellbore based on the drill string length, inner diameter of the drill string, and outer diameter of the drill string; reference can be made to the above description and will not be elaborated here.
[0238] If it is determined that the change in the volume of the trip tank is greater than the sum of the volume of the drill string entering the wellbore and the drill string volume change threshold, it is determined that an overflow occurs in the tripping-in state. Reference can be made to the above description and will not be elaborated here.
[0239] Figure 4 is a schematic structural diagram of an overflow identification processing device provided by an embodiment of the present invention. As Figure 4 shown, the overflow identification processing device provided by the embodiment of the present invention includes an acquisition unit 401 and an identification unit 402, where:
[0240] The acquisition unit 401 is configured to acquire real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling state based on the real-time drilling measurement data obtained through processing; the identification unit 402 is configured to determine a corresponding overflow identification calculation method according to the drilling state identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the real-time drilling measurement data obtained through processing.
[0241] Specifically, the acquisition unit 401 in the device is configured to acquire real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling state based on the real-time drilling measurement data obtained through processing; the identification unit 402 is configured to determine a corresponding overflow identification calculation method according to the drilling state identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the real-time drilling measurement data obtained through processing.
[0242] The overflow identification processing device provided by the embodiment of the present invention acquires real-time drilling measurement data, performs data processing on the real-time drilling measurement data, and identifies the drilling state based on the real-time drilling measurement data obtained through processing; determines a corresponding overflow identification calculation method according to the drilling state identification result, uses the overflow identification calculation method, and identifies whether an overflow occurs based on the real-time drilling measurement data obtained through processing, which can improve the accuracy of identifying whether an overflow occurs.
[0243] The embodiments of the overflow identification processing device provided by the embodiments of the present invention can specifically be used to execute the processing procedures of the above-mentioned method embodiments, and its functions will not be elaborated here. Reference can be made to the detailed description of the above method embodiments.
[0244] Figure 5 is a schematic physical structure diagram of a computer device provided by an embodiment of the present invention. AsFigure 5 As shown, the computer device includes: a memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502. When the processor 502 executes the computer program, the following method is implemented:
[0245] Obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling state based on the processed real-time drilling measurement data;
[0246] Determine a corresponding overflow identification calculation method according to the drilling state identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0247] This embodiment discloses a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the following method is implemented:
[0248] Obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling state based on the processed real-time drilling measurement data;
[0249] Determine a corresponding overflow identification calculation method according to the drilling state identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0250] This embodiment provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the following method is implemented:
[0251] Obtain real-time drilling measurement data, perform data processing on the real-time drilling measurement data, and identify the drilling state based on the processed real-time drilling measurement data;
[0252] Determine a corresponding overflow identification calculation method according to the drilling state identification result, use the overflow identification calculation method, and identify whether an overflow occurs based on the processed real-time drilling measurement data.
[0253] Compared with the technical solutions in the prior art, in the embodiments of the present invention, real-time drilling measurement data is obtained, data processing is performed on the real-time drilling measurement data, and the drilling state is identified based on the processed real-time drilling measurement data; a corresponding overflow identification calculation method is determined according to the drilling state identification result, the overflow identification calculation method is used, and whether an overflow occurs is identified based on the processed real-time drilling measurement data, which can improve the accuracy of identifying whether an overflow occurs.
[0254] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.
[0255] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0256] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0257] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0258] In the description of this specification, the descriptions referring to terms such as "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.
[0259] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.
Claims
1. An overflow recognition and processing method, characterized in that, Including: Obtain real-time drilling measurement data, process the real-time drilling measurement data, and identify the drilling state based on the processed real-time drilling measurement data; Determine a corresponding overflow identification calculation method according to the drilling state identification result, and use the overflow identification calculation method to identify whether an overflow occurs based on the processed real-time drilling measurement data; Using the overflow identification calculation method to identify whether an overflow occurs based on the processed real-time drilling measurement data includes: Obtain the time series window average of the total pit volume and the base value of the total pit volume under normal drilling conditions, and calculate a first overflow occurrence index based on the total pit volume according to the time series window average of the total pit volume and the base value of the total pit volume; Obtain the time series of the outlet flow rate data and the time series of the inlet flow rate data, and calculate a second overflow occurrence index based on the outlet flow rate according to the time series of the outlet flow rate data and the time series of the inlet flow rate data; Calculate an integrated overflow occurrence index according to the first overflow occurrence index, the second overflow occurrence index and their respective corresponding weight indexes, and determine the identification result of whether an overflow occurs in the drilling state according to the comparison result between the integrated overflow occurrence index and the overflow identification threshold; The calculating a first overflow occurrence index based on the total pit volume according to the time series window average of the total pit volume and the base value of the total pit volume includes: Calculate the deviation of the total pit volume value according to the base value of the total pit volume and the time series window average of the total pit volume; Based on the deviation value of the total pond volume and the total pond volume change threshold, the first overflow occurrence index is calculated; the first overflow occurrence index POK is calculated according to the following expression PV-at-i : POK PV-at-i = min(max(PV dif-i / PV tolerance × 100%, 0), 1) Wherein: PV tolerance is the total pool volume change threshold, PV dif-i is the deviation of the current total pool volume value; The calculating a second overflow occurrence index based on the outlet flow rate according to the time series of the outlet flow rate data and the time series of the inlet flow rate data includes: Identify the change trend of the outlet flow rate according to the time series of the outlet flow rate data; and identify the change trend of the inlet flow rate according to the time series of the inlet flow rate data; Perform similarity calculation on the identification results of the outlet flow rate change trend and the inlet flow rate change trend, and calculate the second overflow occurrence index according to the similarity calculation result and the outlet flow rate change threshold; The second overflow occurrence index POK is calculated according to the following expression FO-at-i :[[-END]] POK FO-at-i = min(max(S / S tolerance × 100%, 0) Where: S is the calculation result of the similarity of the entrance and exit flow curve patterns, and S tolerance is the threshold value of the change in the exit flow rate.
2. The overflow recognition processing method according to claim 1, wherein The identifying the drilling state based on the processed real-time drilling measurement data includes: If it is determined that the well depth is equal to the bit depth, and the weight on bit is greater than zero, and the rotary table speed is greater than zero, and the pump strokes are greater than zero, then determine that the drilling state identification result is drilling; If it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold; Or, if it is determined that the bit depth at the current moment is greater than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is tripping, then determine that the drilling state identification result is tripping; If it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the difference between the well depth and the bit depth at the current moment is greater than the tripping threshold; Or, if it is determined that the bit depth at the current moment is less than the bit depth at the previous adjacent moment, and the drilling state identification result at the previous adjacent moment is pulling out of the hole, then determine that the drilling state identification result is pulling out of the hole.
3. The overflow recognition and processing method according to claim 2, wherein, Using the overflow identification calculation method, and identifying whether an overflow occurs based on the processed real-time drilling measurement data, including: Calculating the volume of the drill string lifted out of the wellbore according to the length, inner diameter, and outer diameter of the drill string; If it is determined that the change in the volume of the trip tank is greater than the sum of the volume of the drill string lifted out of the wellbore and the drill string volume change threshold, it is determined that an overflow occurs in the tripping out state.
4. The overflow recognition processing method according to claim 2, wherein Using the overflow identification calculation method, and identifying whether an overflow occurs based on the processed real-time drilling measurement data, including: Calculating the volume of the drill string entering the wellbore according to the length, inner diameter, and outer diameter of the drill string; If it is determined that the change in the volume of the trip tank is greater than the sum of the volume of the drill string entering the wellbore and the drill string volume change threshold, it is determined that an overflow occurs in the tripping in state.
5. An overflow recognition and processing device, characterized in that, Including: An acquisition unit for acquiring real-time drilling measurement data, processing the real-time drilling measurement data, and identifying the drilling state based on the processed real-time drilling measurement data; An identification unit for determining the corresponding overflow identification calculation method according to the drilling state identification result, using the overflow identification calculation method, and identifying whether an overflow occurs based on the processed real-time drilling measurement data; Using the overflow identification calculation method, and identifying whether an overflow occurs based on the processed real-time drilling measurement data, including: Obtaining the time series window average value of the total pit volume and the base value of the total pit volume in the normal drilling state, and calculating a first overflow occurrence index based on the total pit volume according to the time series window average value of the total pit volume and the base value of the total pit volume; Obtaining the time series of the outlet flow rate data and the time series of the inlet flow rate data, and calculating a second overflow occurrence index based on the outlet flow rate according to the time series of the outlet flow rate data and the time series of the inlet flow rate data; Calculating an overall overflow occurrence index according to the first overflow occurrence index, the second overflow occurrence index, and their respective corresponding weight indexes, and determining the identification result of whether an overflow occurs in the drilling state according to the comparison result between the overall overflow occurrence index and the overflow identification threshold; The calculating a first overflow occurrence index based on the total pit volume according to the time series window average value of the total pit volume and the base value of the total pit volume includes: Calculating the deviation of the total pit volume value according to the base value of the total pit volume and the time series window average value of the total pit volume; Based on the deviation value of the total pond volume and the total pond volume change threshold, the first overflow occurrence index is calculated; the first overflow occurrence index POK is calculated according to the following expression PV-at-i :[[]]END]] POK PV-at-i = min(max(PV dif-i / PV tolerance × 100%, 0), 1) Wherein: PV tolerance is the total pool volume change threshold, PV dif-i is the deviation of the current total pool volume value; The calculating a second overflow occurrence index based on the outlet flow rate according to the time series of the outlet flow rate data and the time series of the inlet flow rate data includes: Identifying the change trend of the outlet flow rate according to the time series of the outlet flow rate data; and identifying the change trend of the inlet flow rate according to the time series of the inlet flow rate data; Performing similarity calculation on the identification results of the change trend of the outlet flow rate and the change trend of the inlet flow rate, and calculating the second overflow occurrence index according to the similarity calculation result and the outlet flow rate change threshold; The second overflow occurrence index POK is calculated according to the following expression FO-at-i :[[-END]] POK FO-at-i = min(max(S / S tolerance × 100%, 0) Where: S is the calculation result of the similarity of the inlet and outlet flow curve patterns, and S tolerance is the threshold value of the outlet flow change.
6. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.
7. 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 4 is implemented.
8. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
Real-time recognition method for overflow and leakage based on random forest
CN108388921A
While-drilling identification method for early overflow layer in oil-gas drilling process
CN110795853A