Thin oil abnormal well identification method and equipment based on development dynamic data, and readable storage medium

Abstract

The invention discloses a thin oil abnormal well recognition method and device based on development dynamic data and a readable storage medium. The thin oil abnormal well recognition method comprises the following steps of data collection, wherein production data of a thin oil well, well bore pressure data of the thin oil well and construction data of the thin oil well are collected; the production data comprises automatic indicator diagram data and daily fluid production capacity; the daily fluid production capacity of the thin oil well is pretreated; preprocessing the automatic indicator diagram data of the thin oil well; comparing the preset standard threshold value of the daily liquid production with the fluctuation value of the daily liquid production, and comparing the preset standard threshold value of the automatic indicator diagram with the fluctuation value of the load difference of the current day and the load difference of the last month; and comparing a preset well bore pressure standard threshold value with a pressure value yesterday to obtain a difference value of the pressure value yesterday, and judging whether the well is an abnormal well or not. The abnormal oil well can be quickly and accurately identified, missed judgment and misjudgment are avoided, the identification efficiency is improved, meanwhile, the labor cost and the time cost are reduced, the production cost is reduced, and the economic benefits are improved.

Description

Technical Field

[0001] The present invention relates to the field of identification of abnormal thin oil wells, and particularly to a method, device, and readable storage medium for identifying abnormal thin oil wells based on development dynamic data. Background Art

[0002] With the transformation of oilfield management from extensive to refined and scientific management, the production dynamic monitoring of individual wells has become particularly important. The stable production capacity of old wells in old areas directly affects the sustainable development of the oilfield. By managing abnormal wells, production anomalies can be detected in a timely manner, the shutdown time and frequency can be reduced, and the stable growth of the overall plant output can be ensured. However, there are certain limitations in the current traditional methods for diagnosing abnormal wells. The process of finding patterns, comparative analysis, and screening level by level in a large amount of data is rather cumbersome, resulting in low efficiency in dealing with abnormal wells; relying on dynamometer cards for diagnosing abnormal wells, the diagnosis results often depend on the personal experience and judgment of engineers, lacking objectivity and consistency; a special person is required to analyze and process a large amount of data every day to screen the data, with low work efficiency and a large workload. Abnormal wells cannot be detected in a timely manner, and it is difficult to take measures in a timely manner, which may lead to the deterioration of problems.

[0003] Therefore, a method for quickly, timely, and accurately detecting abnormal wells is needed to assist grass-roots units in quickly identifying abnormal wells. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for identifying abnormal thin oil wells based on development dynamic data, so as to solve the foregoing problems existing in the prior art.

[0005] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] A method for identifying abnormal thin oil wells based on development dynamic data includes the following steps:

[0007] Data collection: Collect the production data, wellbore pressure data, and construction data of thin oil wells; the production data includes automated dynamometer card data and daily liquid production.

[0008] Preprocess the daily liquid production of thin oil wells to obtain the processed normal-period daily liquid production, last-week daily liquid production, current-day daily liquid production, and yesterday's daily liquid production.

[0009] Preprocess the automated dynamometer card data of thin oil wells to obtain the processed last-month load difference and current-day load difference.

[0010] Compare the preset standard threshold of daily liquid production with the fluctuation value of daily liquid production to determine whether it is an abnormal well.

[0011] Compare the preset standard threshold of the automated dynamometer card with the fluctuation value of the current-day load difference compared with the last-month load difference to determine whether it is an abnormal well.

[0012] Compare the difference between the preset wellbore pressure standard threshold and the pressure value of the current day with the pressure value of the previous day to determine whether it is an abnormal well.

[0013] Preferably, the production data further includes: historical monthly production data, daily production data of a single well, and automated metering data of thin oil wells;

[0014] The wellbore pressure data of thin oil wells includes: oil pressure, casing pressure, and back pressure.

[0015] Preferably, the calculation of the daily liquid production volume during the normal period is specifically as follows:

[0016] Extract the monthly liquid production volume and the number of production days in the current month from the historical monthly production data of the oil well to calculate the daily liquid production volume in the current month. According to formula (1), calculate the average value of the daily liquid production volumes in the previous three months in the historical monthly production data, that is: the daily liquid production volume of a single well during the normal period;

[0017]

[0018] Preferably, the calculation of the daily liquid production volume in the previous week is specifically as follows:

[0019] Extract the daily liquid production volumes on the current day and each day in the past week from the daily production data of a single well. According to formula (2), the calculated average value is the daily liquid production volume of a single well in the previous week;

[0020]

[0021] Preferably, the daily liquid production volume on the current day is based on real-time IoT data, and the latest metered liquid volume between 10:00 on the second day and after 10:00 on the first day is taken from the automated oil well metering data to ensure that the current production situation of the single well can be obtained;

[0022] The daily liquid production volume on the previous day is: based on real-time IoT data, the latest metered liquid volume between 10:00 on the previous day and after 10:00 the day before yesterday is taken from the automated oil well metering data.

[0023] Preferably, the calculation of the load difference in the previous month is specifically as follows: based on real-time IoT data, take the load differences measured by all automated dynamometer cards in the previous month, and calculate the average value according to formula (3);

[0024]

[0025] n represents the number of load differences measured by all automated dynamometer cards in the previous month

[0026] The load difference on the current day is: based on real-time IoT data, take the load difference measured by the nearest dynamometer card before 1:30 on the current day from the single well automated dynamometer card data.

[0027] Preferably, the standard threshold of the daily liquid production volume is set to T 0,

[0028] Calculate the production fluctuation value t of the daily liquid production volume compared with the normal - period daily liquid production volume according to formula (4) 0 ;

[0029] The production fluctuation value t 0 =(Daily liquid production volume - Normal - period daily liquid production volume) / Normal - period daily liquid production volume×100%; (4)

[0030] Calculate the production fluctuation value t of the weekly liquid production volume compared with the normal - period daily liquid production volume according to formula (5) 1 ;

[0031] The production fluctuation value t 1 =(Weekly liquid production volume - Normal - period daily liquid production volume) / Normal - period daily liquid production volume×100%; (5)

[0032] Calculate the production fluctuation value t of the daily liquid production volume compared with the previous - day liquid production volume according to formula (6) 2 ;

[0033] The production fluctuation value t 2 =(Daily liquid production volume - Previous - day liquid production volume) / Previous - day liquid production volume×100%; (6)

[0034] If the production fluctuation value t of the daily liquid production volume compared with the normal - period daily liquid production volume 0 is greater than the standard threshold T 0 ; then mark it as an abnormal well;

[0035] If the production fluctuation value t of the weekly liquid production volume compared with the normal - period daily liquid production volume 1 , then mark it as an abnormal well;

[0036] If the production fluctuation value t of the daily liquid production volume compared with the previous - day liquid production volume 2 , then mark it as an abnormal well.

[0037] Preferably, the standard threshold of the automated dynamometer card data is set to A;

[0038] Calculate the dynamometer card fluctuation value A of the daily load difference compared with the previous - month load difference according to formula (7) 1 ; Dynamometer card fluctuation value=(Daily load difference - Previous - month load difference) / Previous - month load difference×100% (7)

[0039] If the dynamometer card fluctuation value A of the daily load difference compared with the previous - month load difference 1 exceeds the standard threshold A, then mark it as an abnormal well;

[0040] The well - bore pressure standard threshold is set to B;

[0041] Calculate the difference B between the daily pressure value and the previous - day pressure value according to formula (8)1 ;

[0042] Wellbore pressure fluctuation value = current day pressure value - previous day pressure value (8)

[0043] If the difference between the current day pressure value and the previous day pressure value is greater than the wellbore pressure standard threshold B, it is determined as an abnormal well.

[0044] An embodiment of the present invention also 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, it implements a method for identifying abnormal thin oil wells.

[0045] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program for executing any of the above methods for identifying abnormal thin oil wells.

[0046] The beneficial effects of the present invention are as follows:

[0047] The present invention discloses a method for identifying abnormal thin oil wells based on development dynamic data, including the following steps: Data collection: Collect production data of thin oil wells, wellbore pressure data of thin oil wells, and construction data of thin oil wells; The production data includes automated dynamograph data and daily liquid production; Preprocess the daily liquid production of thin oil wells to obtain the processed normal period daily liquid production, last week's daily liquid production, current day's daily liquid production, and previous day's daily liquid production; Preprocess the automated dynamograph data of thin oil wells to obtain the processed last month's load difference and current day's load difference; Compare the preset standard threshold of daily liquid production with the fluctuation value of daily liquid production to determine whether it is an abnormal well; Compare the preset standard threshold of the automated dynamograph with the fluctuation value of the current day's load difference compared with the last month's load difference to determine whether it is an abnormal well; Compare the preset wellbore pressure standard threshold with the difference between the current day pressure value and the previous day pressure value to determine whether it is an abnormal well. The present invention can quickly and accurately identify abnormal oil wells, avoid missed judgments and misjudgments, construct a comprehensive abnormal oil well identification model based on multiple parameters and multiple time periods such as production, dynamograph, and pressure, improve the identification efficiency, reduce labor costs and time costs at the same time, reduce production costs, and improve economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flowchart of a method for identifying abnormal thin oil wells based on development dynamic data of the present invention;

[0049] Figure 2 is a flowchart of another embodiment of the invention. DETAILED DESCRIPTION

[0050] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] Referring to Figure 1 and Figure 2 shown in a method for identifying abnormal thin oil wells based on developing dynamic data, which includes the following steps:

[0052] S100, data collection: collecting production data of thin oil wells, wellbore pressure data of thin oil wells and construction data of thin oil wells; the production data includes automated dynamogram data and daily liquid production;

[0053] S200, preprocessing the daily liquid production of thin oil wells to obtain the processed normal period daily liquid production, last week's daily liquid production, today's daily liquid production and yesterday's daily liquid production;

[0054] S300, preprocessing the automated dynamogram data of thin oil wells to obtain the processed last month's load difference and today's load difference;

[0055] S400, comparing the preset standard threshold of daily liquid production with the fluctuation value of daily liquid production to determine whether it is an abnormal well;

[0056] S500, comparing the preset standard threshold of the automated dynamogram with the fluctuation value of the difference between today's load difference and last month's load difference to determine whether it is an abnormal well;

[0057] S600, comparing the preset wellbore pressure standard threshold with the difference between today's pressure value and yesterday's pressure value to determine whether it is an abnormal well.

[0058] Preferably, the production data further includes: historical monthly production data, single well daily production data, automated metering data of thin oil wells; it also includes time series data such as daily oil production, daily liquid production, water cut, load difference, etc.

[0059] The wellbore pressure data of thin oil wells includes: oil pressure, casing pressure, back pressure. Collecting pressure data such as the oil pressure, casing pressure, and back pressure of the oil well can help understand the production risks of the oil well.

[0060] Construction data: includes the measure records of the oil well, such as hot washing, adjusting the stroke frequency, adjusting the stroke length, changing the oil nozzle, pump inspection, etc. These factors will affect the outflow rate of the oil well and thus affect the production.

[0061] Preferably, the calculation of the normal period daily liquid production is specifically as follows:

[0062] Extract the monthly liquid production and the number of production days in the current month from the historical monthly production data of the oil well, calculate the daily liquid production in the current month, and calculate the average value of the daily liquid production in the previous three months in the historical monthly production data according to formula (1), that is: the normal daily liquid production of a single well;

[0063]

[0064] Preferably, the calculation of the daily liquid production in the last week is specifically as follows:

[0065] Extract the daily liquid production on the current day and every day in the past week from the daily production data of a single well, and calculate the average value obtained according to formula (2), which is the liquid production of a single well in the last week;

[0066]

[0067] Preferably, the daily liquid production on the current day is based on the real-time data of the Internet of Things, and the latest measured liquid volume between 10:00 on the first day and 10:00 on the second day is taken from the automated oil well measurement data, ensuring that the current production situation of the single well can be obtained;

[0068] The daily liquid production yesterday was: based on the real-time data of the Internet of Things, the latest measured liquid volume between 10:00 the day before yesterday and 10:00 yesterday was taken from the automated oil well measurement data.

[0069] Preferably, the calculation of the load difference in the previous month is specifically as follows: based on the real-time data of the Internet of Things, take the load differences measured by all automated dynamometer cards in the previous month, and calculate the average value according to formula (3);

[0070]

[0071] n represents the number of load differences measured by all automated dynamometer cards in the previous month

[0072] The load difference on the current day is: based on the real-time data of the Internet of Things, take the load difference measured by the nearest dynamometer card before 1:30 on the current day from the single well automated dynamometer card data.

[0073] Preferably, the standard threshold of the daily liquid production is set to T 0 ,

[0074] Calculate the production fluctuation value t of the daily liquid production compared with the normal daily liquid production according to formula (4) 0 ;

[0075] Production fluctuation value t 0 =(Daily liquid production - Normal daily liquid production) / Normal daily liquid production × 100%; (4)

[0076] Calculate the production fluctuation value t of the daily liquid production in the last week compared with the normal daily liquid production according to formula (5) 1 ;

[0077] Production fluctuation value t 1 =(Liquid production per day last week - Liquid production per day during normal period) / Liquid production per day during normal period × 100%; (5)

[0078] Calculate the production fluctuation value t of the liquid production per day today compared with that of yesterday according to formula (6) 2 ;

[0079] Production fluctuation value t 2 =(Liquid production per day today - Liquid production per day yesterday) / Liquid production per day yesterday × 100%; (6)

[0080] If the production fluctuation value t of the liquid production per day today compared with that during the normal period 0 is greater than the standard threshold T 0 ; then it is marked as an abnormal well;

[0081] If the production fluctuation value t of the liquid production per day last week compared with that during the normal period 1 , then it is marked as an abnormal well;

[0082] If the production fluctuation value t of the liquid production per day today compared with that of yesterday 2 , then it is marked as an abnormal well.

[0083] Preferably, the standard threshold of the automated dynamometer card data is set to A;

[0084] Calculate the dynamometer card fluctuation value A of the load difference today compared with that of last month according to formula (7) 1 ; Dynamometer card fluctuation value = (Load difference today - Load difference last month) / Load difference last month × 100% (7)

[0085] If the dynamometer card fluctuation value A of the load difference today compared with that of last month 1 exceeds the standard threshold A, then it is marked as an abnormal well;

[0086] The standard threshold of the wellbore pressure is set to B;

[0087] Calculate the difference B between the pressure value today and that of yesterday according to formula (8) 1 ;

[0088] Wellbore pressure fluctuation value = Pressure value today - Pressure value yesterday (8)

[0089] If the difference between the pressure value today and that of yesterday is greater than the standard threshold B of the wellbore pressure, it is determined as an abnormal well. Pressure (oil pressure, casing pressure, back pressure) fluctuation value = Pressure value today (oil pressure, casing pressure, back pressure) - Pressure value yesterday (oil pressure, casing pressure, back pressure)

[0090] Regarding pressure, the abnormal conditions are judged by analyzing the changing trends of the tubing head pressure, casing pressure, and back pressure of flowing wells. If the difference between the pressure value of the current day and that of the previous day exceeds a certain threshold, the well is determined to be an abnormal well.

[0091] Principle for identifying abnormal thin oil wells:

[0092] Regarding production data, it is identified by analyzing the change in the daily liquid production. Wells that have been thermally washed, had the pumping strokes adjusted, had the stroke lengths adjusted, had the nozzles replaced, or had the pumps inspected in the most recent week are excluded based on the daily well report data combined with the construction data. If the fluctuation values of the daily liquid production compared with the normal period daily liquid production, the daily liquid production of last week compared with the normal period daily liquid production, and the daily liquid production of the current day compared with the daily liquid production of the previous day exceed a certain threshold, it may be an abnormal situation and is marked as an abnormal well.

[0093] Regarding the operation of equipment, the working state of downhole equipment and the normal production of the oil well are judged by analyzing the load difference of the dynamometer card of the pumping unit (the difference between the maximum polished rod load and the minimum polished rod load within a stroke cycle). If the fluctuation value of the current day's load difference compared with the load difference of the previous month exceeds a certain threshold, it can be judged whether the working state of the downhole equipment and the production of the oil well are normal, and it may be an abnormal situation and is marked as an abnormal well.

[0094] An embodiment of the present invention also 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 method for identifying abnormal thin oil wells is implemented.

[0095] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program for executing any of the above methods for identifying abnormal thin oil wells.

[0096] Beneficial effects:

[0097] For abnormal oil wells, multi-parameters (fluctuations in measured liquid volume, pressure, and load) and multi-dimensions (compared with the previous day, last week, and the previous three months) are used for automatic judgment, automatic discovery, and automatic push, shortening the investigation cycle. Previously, more than 400 wells were identified every day. After continuous optimization, it was accurate to about 160 wells, and the accuracy rate increased by about 2.5 times, enabling the daily work efficiency of handling abnormal wells to increase by about 3 times, effectively reducing the labor intensity of on-site personnel.

[0098] It changes the traditional method of screening by consulting materials for data comparison + manual experience and the method of offline layer-by-layer reporting and review, and instead uses the system to automatically identify at a fixed time every day and approves the whole process online, reducing intermediate links, clarifying the job responsibilities between departments, establishing a "flat" management model, improving the information communication efficiency, enabling abnormal situations to be quickly reported and processed, and improving decision-making.

Claims

1. A method for identifying abnormal thin oil wells based on development dynamic data, characterized in that: The following steps are involved: Data collection: collecting production data of the thin oil well, the wellbore pressure data of the thin oil well and the thin oil well construction data; the production data includes automated power diagram data and daily liquid production; Pre-processing the daily liquid production of the thin oil well to obtain the normal daily liquid production, the previous week's daily liquid production, the current day's daily liquid production and the yesterday's daily liquid production after processing; Preprocessing the automated work diagram data of the thin oil well to obtain the processed load difference of the previous month and the load difference of the current day; Compare the preset standard threshold of the daily liquid production with the fluctuation value of the daily liquid production to determine whether it is an abnormal well; Compare the preset standard threshold of the automatic work diagram with the fluctuation value of the load difference of the current day compared with the load difference of the previous month to determine whether it is an abnormal well; Compare the preset wellbore pressure standard threshold with the pressure value of the day and the difference between the pressure value of yesterday to determine whether it is an abnormal well.

2. The method for identifying abnormal thin oil wells based on development dynamic data according to claim 1, characterized in that: The production data also includes: historical monthly production data, single well daily production data, and automated metering data of rare oil wells; The wellbore pressure data of the thin oil well includes: oil pressure, casing pressure and back pressure.

3. The method for identifying abnormal thin oil wells based on development dynamic data according to claim 2, characterized in that: The calculation of the daily liquid production during the normal period is specifically as follows: The monthly production volume and the number of production days in the current month are extracted from the historical monthly production data of the oil well to calculate the daily production volume in the current month. The average daily production volume of the previous three months in the historical monthly production data is calculated according to formula (1), that is, the daily production volume of a single well in the normal period.

4. The method for identifying abnormal thin oil wells based on development dynamic data according to claim 3 is characterized in that: The calculation of the daily liquid production last week is specifically as follows: The daily production volume of the single well on the current day and every day in the past week is extracted from the daily production data of the single well, and the average value is calculated according to formula (2), which is the liquid volume of the single well in the past week; 5. The method for identifying abnormal thin oil wells based on development dynamic data according to claim 4 is characterized in that: The daily production volume is based on the real-time data of the Internet of Things, and the latest measured liquid volume between 10 o'clock on the first day and 10 o'clock on the second day is obtained from the automated oil well metering data to ensure that the latest single well production situation can be obtained; Yesterday's daily liquid production refers to the latest measured liquid volume between 10 o'clock the previous day and 10 o'clock yesterday from the automated oil well metering data based on real-time data from the Internet of Things.

6. The method for identifying abnormal thin oil wells based on development dynamic data according to claim 5, characterized in that: The calculation of the load difference of the previous month is specifically as follows: based on the real-time data of the Internet of Things, the load differences measured by all the automation power diagrams of the previous month are taken, and the average value is calculated according to formula (3); n represents the number of load differences measured by all automated power diagrams in the previous month The load difference for the day is: based on the real-time data of the Internet of Things, the load difference of the most recent power diagram measurement before half past midnight of the day is taken from the single well automated power diagram data.

7. The method for identifying abnormal thin oil wells based on development dynamic data according to claim 6, characterized in that: The standard threshold of daily liquid production is set as T0, According to formula (4), the output fluctuation value t0 of the daily liquid production compared with the daily liquid production in the normal period is calculated; Output fluctuation value t0 = (daily liquid production on that day - daily liquid production in normal period) / daily liquid production in normal period × 100%; (4) According to formula (5), calculate the production fluctuation value t1 of the daily liquid production last week compared with the daily liquid production in the normal period; Output fluctuation value t1 = (daily liquid production last week - daily liquid production in normal period) / daily liquid production in normal period × 100%; (5) According to formula (6), calculate the production fluctuation value t2 of the daily liquid production of the current day compared with the daily liquid production of yesterday; Output fluctuation value t2 = (daily liquid production on this day - daily liquid production yesterday) / daily liquid production yesterday × 100%; (6) If the daily production volume of the well is greater than the standard threshold value T0, then it is marked as an abnormal well. If the daily liquid production of the previous week is compared with the daily liquid production of the normal period by a production fluctuation value of t1, it is marked as an abnormal well; If the daily liquid production on that day is compared with the production fluctuation value t2 of yesterday's daily liquid production, it is marked as an abnormal well.

8. The method for identifying abnormal thin oil wells based on development dynamic data according to claim 6, characterized in that: The standard threshold value of the automation diagram data is set to A; According to formula (7), the power diagram fluctuation value A1 of the load difference of the current day compared with the load difference of the previous month is calculated; Power diagram fluctuation value = (load difference of the current day - load difference of the previous month) / load difference of the previous month × 100% (7) If the power diagram fluctuation value A1 of the load difference of the current day compared with the load difference of the previous month exceeds the standard threshold A, it is marked as an abnormal well; The standard threshold value of the wellbore pressure is set to B; Calculate the difference B1 between the pressure value of the current day and the pressure value of yesterday according to formula (8); Wellbore pressure fluctuation value = today's pressure value - yesterday's pressure value (8) If the difference between today's pressure value and yesterday's pressure value is greater than the wellbore pressure standard threshold B, it is judged as an abnormal well.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for identifying abnormal wells with low oil content according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the method for identifying a rare oil abnormal well according to any one of claims 1 to 8.

Images