A single-parameter analysis-based abnormal working condition identification method for plunger gas lift

Abstract

The application belongs to the technical field of oil and gas field drainage gas recovery, and particularly discloses a plunger gas lift abnormal working condition identification method based on single parameter analysis; the application obtains production data related to a plunger gas lift system, identifies abnormal working conditions of single parameters through a trend algorithm according to the obtained production data related to the plunger gas lift system, and outputs abnormal working condition results; the application performs real-time data collection on a plurality of single parameters of long-term operation modes or faults of a well, performs trend algorithm calculation on the data, and obtains corresponding abnormal working condition results, so that the problem of low identification efficiency and poor accuracy in identifying plunger gas lift fault data is solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of drainage gas recovery in oil and gas fields, and particularly relates to a piston gas lift abnormal working condition identification method based on single parameter analysis. BACKGROUND

[0002] Piston gas lift is a high-efficiency drainage gas recovery technology. It puts a piston tool in the wellbore to form a mechanical seal, reduces liquid slip and gas channeling, and uses the energy of the gas well to push the piston to reciprocate in the wellbore to discharge accumulated liquid. It has the advantages of wide application range, high automation degree, high input-output ratio, green environmental protection, etc., and is suitable for the current development situation of wide area, many wells and few people in tight gas fields. With the popularization of technology, application problems have gradually emerged. The main performance is that the degree of dependence on artificial is high, and the aging of well site supporting equipment, wellbore foreign matter erosion and blockage are inevitable, which leads to problems such as control valve damage, sensor failure, network disconnection, etc. Artificial identification is needed to solve the problem, and the annual analysis workload is more than 200,000 times.

[0003] Piston gas lift operation fault identification is usually based on human experience. With the help of big data analysis and artificial intelligence technology, the trend of production data related to piston gas lift system, such as "well opening and closing state", "piston state", "casing pressure", "oil pressure" and its structure index, is analyzed. Through artificial experience analysis of production data, fault identification is easy to cause inaccurate identification and low identification efficiency. SUMMARY

[0004] In order to overcome the shortcomings of the prior art, the purpose of the present application is to provide a piston gas lift abnormal working condition identification method based on single parameter analysis, so as to solve the problems of low identification efficiency and poor accuracy when identifying piston gas lift fault data.

[0005] In order to achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0006] The present application provides a piston gas lift abnormal working condition identification method based on single parameter analysis, comprising:

[0007] Obtaining production data related to piston gas lift system;

[0008] According to the obtained production data related to piston gas lift system, the single parameter is identified by trend algorithm;

[0009] Output abnormal working condition result.

[0010] Further, the obtaining of production data related to piston gas lift system comprises:

[0011] Obtaining well opening and closing state data, piston state data, oil pressure data, casing pressure data and oil casing pressure difference data.

[0012] Further, the single parameter is subjected to abnormal condition recognition, and the recognition object includes: switch well state, plunger state, oil pressure state, casing pressure state and oil casing pressure difference.

[0013] Further, the trend algorithm includes: trend index calculation, 3σ extreme value recognition, constant value recognition and parameter overall rising and falling trend determination function.

[0014] Further, the trend index calculation is:

[0015]

[0016] Wherein, f m (x, y) is the trend index, x is the oil pressure, casing pressure, y is the time, and n is a natural number;

[0017] The 3σ extreme value recognition is:

[0018]

[0019]

[0020]

[0021] Wherein, p min is the minimum pressure, p max is the maximum pressure, δ is a fixed value, f l (x) is the calculated outlier, 1 is beyond the normal range, and 0 is the normal range;

[0022] The constant value recognition is:

[0023]

[0024] Wherein, x max is the maximum oil pressure or casing pressure, x min is the minimum oil pressure or casing pressure, j is the threshold value, y s1 is the constant value recognition result, 1 is the oil pressure difference or casing pressure difference, and 2 is the maximum and minimum oil pressure difference or casing pressure difference less than j.

[0025] The parameter overall rising and falling trend determination function is:

[0026]

[0027]

[0028] Wherein, x s is the slope of the oil pressure and casing pressure, y s2The parameter overall rising and falling trend determination result is 0 for normal state, 1 for abnormal rising, 2 for abnormal falling, and a is a discrimination threshold value.

[0029] Further, the switch well state includes: switch well normal, switch well data missing, and switch well time being too short;

[0030] The switch well normal refers to a normal switch well cycle;

[0031] The switch well data missing refers to no state data of the switch well;

[0032] The switch well time being too short refers to the opening time being less than 10 minutes.

[0033] Further, the plunger state includes: plunger normal, plunger being long-term at the well bottom, plunger being long-term at the well head, and plunger not matching the switch well;

[0034] The plunger normal refers to a normal plunger running state;

[0035] The plunger being long-term at the well bottom refers to the plunger not reaching;

[0036] The plunger being long-term at the well head refers to the plunger state being always in the reaching state;

[0037] The plunger not matching the switch well refers to the plunger lifting process not matching, the plunger not being in the reaching state when the well is opened, and the plunger not being at the well bottom when the well is closed.

[0038] Further, the oil pressure state includes: oil pressure state normal, oil pressure communication fault, oil pressure abnormal constant value, oil pressure approximate constant value, oil pressure abnormal rising, oil pressure abnormal falling, and oil pressure exceeding the normal range;

[0039] The oil pressure state normal refers to the oil pressure state meeting the normal plunger running state;

[0040] The oil pressure communication fault refers to the oil pressure fault caused by communication problems;

[0041] The oil pressure abnormal constant value refers to the oil pressure being a constant value;

[0042] The oil pressure approximate constant value refers to the segmented constant value being less than 0.7;

[0043] The oil pressure abnormal rising refers to the slope mean of the oil pressure cycle mean rising more than 0.07;

[0044] The oil pressure abnormal falling refers to the slope mean of the oil pressure cycle mean falling more than 0.05;

[0045] The oil pressure exceeding the normal range refers to the oil pressure exceeding the normal oil pressure range of the gas well, and the 3σ extreme value being identified as 1.

[0046] Further, the casing pressure state comprises: casing pressure state normal, casing pressure communication fault, casing pressure abnormal constant value, casing pressure approximate constant value, casing pressure abnormal rise, casing pressure abnormal drop and casing pressure exceeding normal range.

[0047] The casing pressure state normal refers to that the casing pressure state is consistent with the normal state of the plunger operation.

[0048] The casing pressure communication fault refers to the casing pressure fault caused by communication problems.

[0049] The casing pressure abnormal constant value refers to that the casing pressure is a constant value.

[0050] The casing pressure approximate constant value refers to that the segmented constant value is less than 0.7.

[0051] The casing pressure abnormal rise refers to that the slope mean of the casing pressure cycle mean rises more than 0.07.

[0052] The casing pressure abnormal rise refers to that the slope mean of the casing pressure cycle mean drops more than 0.05.

[0053] The casing pressure exceeding normal range refers to that the casing pressure exceeds the normal casing pressure range of the gas well, and the 3σ extreme value is identified as 1.

[0054] Further, the casing pressure difference comprises: casing pressure difference normal, casing pressure difference abnormal misplacement, casing pressure difference too large and casing pressure difference super large.

[0055] The casing pressure difference normal refers to that the casing pressure difference is less than 3MPa.

[0056] The casing pressure difference abnormal misplacement refers to that the casing pressure difference is a negative value.

[0057] The casing pressure difference too large refers to that the casing pressure difference is greater than 3MPa and less than or equal to 5MPa.

[0058] The casing pressure difference super large refers to that the casing pressure difference is greater than 5MPa.

[0059] The present application has at least the following beneficial effects:

[0060] The present application obtains the production data related to the plunger gas lifting system, identifies the abnormal working condition of a single parameter through a trend algorithm according to the obtained production data related to the plunger gas lifting system, and outputs the abnormal working condition result. The present application realizes real-time data acquisition of a plurality of single parameters of long-term operation mode or fault of a well, and obtains the corresponding abnormal working condition result through the calculation of the trend algorithm, thereby solving the problems of low identification efficiency and poor accuracy in identifying the plunger gas lifting fault data. BRIEF DESCRIPTION OF DRAWINGS

[0061] The drawings constituting a part of this disclosure serve to provide further understanding of the present application, the illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0062] Figure 1 A flowchart of a single-parameter analysis-based abnormal condition recognition method for plunger gas lift wells constituting a part of the present application;

[0063] Figure 2 A schematic diagram of a production curve for plunger gas lift wells with insufficient energy recovery constituting a part of the present application;

[0064] Figure 3 A schematic diagram of a production curve for plunger gas lift wells with liquid loading constituting a part of the present application;

[0065] Figure 4 A schematic diagram of a production curve for plunger gas lift wells with increased pipeline pressure constituting a part of the present application;

[0066] Figure 5 A schematic diagram of a production curve for plunger gas lift wells with process errors constituting a part of the present application;

[0067] Figure 6 A schematic diagram of a production curve for plunger gas lift wells with stuck plungers or sensor failures constituting a part of the present application;

[0068] Figure 7 A schematic diagram of a production curve for plunger gas lift wells with abnormal data constituting a part of the present application. DETAILED DESCRIPTION

[0069] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0070] The following detailed description is exemplary and is intended to provide further detailed description of the present application. Unless otherwise specified, all technical terms used in the present application have the same meanings as those generally understood by those skilled in the art. The terms used in the present application are only for the purpose of describing the specific embodiments and are not intended to limit the exemplary embodiments according to the present application.

[0071] As shown in Figure 1 After analyzing a large number of failure cases, especially after careful analysis of the fault diagnosis chart, it can be found that the long-term running mode of the plunger gas lift well is related to the long-term trend of a single parameter when the changes in a single cycle are not considered, and is a combination of the trend patterns of several single parameters. The single parameter abnormality recognition focuses on the long-term trend (ten cycles) of a single parameter for abnormality recognition.

[0072] A single-parameter analysis-based abnormal condition recognition method for plunger gas lift wells, comprising:

[0073] S1: Obtain production data related to the plunger gas lift system;

[0074] Obtain real-time switch well state data, plunger state data, oil pressure data, casing pressure data and oil casing pressure difference data;

[0075] S2: According to the obtained production data related to the plunger gas lift system, the single parameter is identified by trend algorithm, and the abnormal working condition result is output;

[0076] The single parameter is identified for abnormal working condition, and the identification object includes: switch well state, plunger state, oil pressure state, casing pressure state and oil casing pressure difference.

[0077] As a further improvement of the present scheme, the long-term operation mode or failure of a well is a combination of the trend mode of several single parameters; the slope and extreme value of the long period are calculated as the main means, and the real-time collected data is taken as the research object, and the trend algorithm is performed, including: trend index calculation, 3σ extreme value identification, constant value identification and parameter overall rising and falling trend determination function; judge the long-term trend of switch well state, plunger state, oil pressure, casing pressure, oil casing pressure difference five single parameters in the cycle, and combine the identification results according to the business characteristics.

[0078] As a further improvement of the present scheme, the specific formula of the trend algorithm is as follows:

[0079] (1) Trend index calculation is:

[0080]

[0081] Where, f m (x,y) is the trend index, x is the oil pressure, casing pressure and other values, y is the time, and n is a natural number.

[0082] (2) 3σ extreme value identification is:

[0083]

[0084]

[0085]

[0086] Where, p min is the minimum pressure, p max is the maximum pressure, δ is a fixed value, 0.67, f l (x) is the calculated outlier, 1 is more than the normal range, and 0 is the normal range.

[0087] (3) Constant value identification is:

[0088]

[0089] wherein, x max is the maximum value of oil pressure or casing pressure, x min is the minimum value of oil pressure or casing pressure, j is a threshold value (set value), y s1 is a constant identification result, 1 is that the oil pressure difference or casing pressure difference is constant, and 2 is that the maximum and minimum oil pressure difference or casing pressure difference is less than j.

[0090] (4) The parameter overall rising and falling trend judgment function is:

[0091]

[0092]

[0093] wherein, x s is the slope of the oil pressure or casing pressure, y s2 is the parameter overall rising and falling trend judgment result, 0 is normal, 1 is abnormal rising, 2 is abnormal falling, and a is a threshold value (set value).

[0094] The trend algorithm is applied to the switch well state, the plunger state, the oil pressure state, the casing pressure state, and the oil casing pressure difference of the five single parameters, and finally 25 kinds of conditions that can be identified in all single parameter abnormal identification are obtained, including:

[0095] The switch well state includes three kinds: normal switch well, switch well data missing, and switch well time too short.

[0096] Normal switch well means that the switch well cycle is normal; switch well data missing means that there is no state data for switch well; and switch well time too short means that the opening time is less than 10 minutes.

[0097] The plunger state includes four kinds: normal plunger, plunger long-term at the bottom of the well, plunger long-term at the wellhead, and plunger mismatching with switch well.

[0098] Normal plunger means that the plunger running state is normal; plunger long-term at the bottom of the well means that the plunger does not reach; plunger long-term at the wellhead means that the plunger state is always in the reached state; plunger mismatching with switch well means that the plunger lifting process does not match; the plunger is not in the reached state when the well is opened; and the plunger is not at the bottom of the well when the well is closed.

[0099] The oil pressure state includes seven kinds: normal oil pressure state, oil pressure communication failure, abnormal constant oil pressure, approximate constant oil pressure, abnormal rising oil pressure, abnormal falling oil pressure, and oil pressure exceeding the normal range.

[0100] Normal oil pressure means the oil pressure meets the normal operating conditions of the plunger; oil pressure communication failure means the oil pressure failure is caused by communication problems; abnormal constant oil pressure means the oil pressure is a constant value; approximately constant oil pressure means the segmented constant value is less than 0.7; abnormal rise in oil pressure means the average slope of the oil pressure cycle increases by more than 0.07; abnormal drop in oil pressure means the average slope of the oil pressure cycle decreases by more than 0.05; oil pressure exceeding the normal range means the oil pressure exceeds the normal oil pressure range of the gas well, and the 3σ extreme value is identified as 1.

[0101] There are 7 types of pressure conditions: normal pressure condition, pressure communication failure, abnormal constant pressure, near constant pressure, abnormal increase in pressure, abnormal decrease in pressure, and exceeding the normal range.

[0102] To further clarify, normal casing pressure means that the casing pressure meets the normal operating conditions of the plunger; casing pressure communication failure means that the casing pressure failure is caused by communication problems; abnormally constant casing pressure means that the casing pressure is a constant value; approximately constant casing pressure means that the segmented constant value is less than 0.7; abnormally rising casing pressure means that the average slope of the casing pressure cycle increases by more than 0.07; abnormally rising casing pressure means that the average slope of the casing pressure cycle decreases by more than 0.05; casing pressure exceeding the normal range means that the casing pressure exceeds the normal casing pressure range of the gas well, and the 3σ extreme value is identified as 1.

[0103] There are four types of oil-sleeve pressure differential: normal oil-sleeve pressure differential, abnormal oil-sleeve pressure differential, excessive oil-sleeve pressure differential, and excessive oil-sleeve pressure differential.

[0104] To further clarify, normal oil-casing pressure difference means the oil-casing pressure is less than 3 MPa; abnormal oil-casing pressure difference means the oil-casing pressure difference is negative; excessive oil-casing pressure difference means the oil-casing pressure difference is greater than 3 MPa and less than or equal to 5 MPa; and excessive oil-casing pressure difference means the oil-casing pressure difference is greater than 5 MPa.

[0105] Example 1

[0106] Insufficient energy recovery: such as Figure 2 As shown, a well with insufficient energy recovery due to a plunger failure exhibits the following long-term characteristics: increasing casing pressure, stable oil pressure, normal well opening, but the plunger pressure never reaches its target, and the well opening / closing status remains largely normal. This analysis only considers the long-term overall pattern of a single parameter, i.e., whether it is increasing, decreasing, or remaining stable in the long term. It does not consider the variation patterns within the plunger gas lift drainage cycle (the rationality of the three-stage trends and patterns of increasing, continuing flow, and recovery within a single cycle).

[0107] Example 2

[0108] Flooding due to fluid accumulation: such as Figure 3 As shown, the failure of the plunger gas lift well flooding due to liquid accumulation is specifically manifested in the long-term behavior of a single parameter as follows: the casing pressure continuously rises, the oil pressure remains stable, and the plunger pressure is never reached. Initially, the well can be opened and closed normally, but in the later stage, the gas well is flooded and shut down.

[0109] In terms of long-term performance of single parameters, water accumulation and insufficient energy recovery are the same, that is, both result in rising casing pressure and stable oil pressure. The difference lies in the variation pattern within the cycle (whether the three-segment pattern within the cycle conforms to the business characteristics) and other multi-parameter factors such as oil-casing pressure difference and load factor. This part will be analyzed in the multi-parameter anomaly identification.

[0110] Example 3

[0111] Pressure rise in gathering and transmission pipelines: such as Figure 4 As shown, the fault of increased pressure in the gathering and transportation pipeline is specifically manifested in the long-term behavior of a single parameter as follows: the casing pressure and oil pressure continue to rise, the plunger pressure has not been reached, and the well opening and closing status is performed as normal well opening and closing operations.

[0112] Example 4

[0113] Process error: such as Figure 5 As shown in the diagram, the production curve of the plunger gas lift process is unstable over a long period of time, that is, the changes in casing pressure and oil pressure do not have a fixed pattern, the plunger state has not been reached, and the well opening and closing state is performed normally.

[0114] Example 5

[0115] Piston jamming or sensor malfunction: such as Figure 6 As shown, wells with a long-term stable and normal casing pressure and oil pressure status due to plunger jamming or sensor failure exhibit a cycle-based change pattern consistent with operational characteristics. Some wells even show normal fluid discharge. Wells with a long-term stuck plunger status that has not reached the target area exhibit a long-term stuck plunger status that indicates normal well opening and closing operations.

[0116] Example 6

[0117] Data anomalies: such as Figure 7 As shown, in actual production environments, wells with abnormal plunger data exhibit a large number of data anomaly-related faults in addition to some classic fault types. A persistently constant casing pressure of 5 MPa could be due to sensor malfunction, resulting in a constant data value. A prolonged failure to reach the plunger status could be due to a lack of arrival time or data errors, requiring identification of missing well-opening / closing data. During certain periods, well-opening / closing data may be empty, possibly indicating a failure to transmit data back.

[0118] As is known from common technical knowledge, this invention can be implemented through other embodiments that do not depart from its spirit or essential characteristics. Therefore, the disclosed embodiments described above are merely illustrative in all respects and are not the only ones. All modifications within the scope of this invention or its equivalents are included in this invention.

[0119] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application but not to limit it. Although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for identifying abnormal operating conditions in a plunger gas lift system based on single-parameter analysis, characterized in that, include: Obtain production data related to the plunger air lift system; Based on the production data related to the plunger gas lift system, abnormal operating conditions of single parameters are identified through trend algorithms. Output abnormal operating condition results; The trend algorithm includes: trend index calculation, 3σ extreme value identification, constant value identification, and parameter overall upward and downward trend determination function; the abnormal working condition identification of single parameters includes: well opening and closing status, plunger status, oil pressure status, casing pressure status, and oil-casing pressure difference; The trend index is calculated as follows: in, Here, x represents the trend index, y represents the oil pressure and casing pressure, n represents the time, and n is a natural number. The 3σ extreme value is identified as: in, For minimum pressure, For maximum pressure, For fixed values, The outliers are calculated, with 1 indicating they are outside the normal range and 0 indicating they are within the normal range. The constant value is identified as: in, This represents the maximum oil pressure and sleeve pressure. Let j be the minimum oil pressure and casing pressure, j be the discrimination threshold, and y be the minimum value. s1 For constant value identification results, 1 indicates that the oil pressure difference or casing pressure difference is constant, and 2 indicates that the maximum and minimum oil pressure difference or casing pressure difference is less than j. The function for determining the overall upward or downward trend of parameters is: Where, x s The slope of the oil pressure and casing pressure is y. s2 The result is the overall upward and downward trend of the parameter. 0 indicates a normal state, 1 indicates an abnormal increase, 2 indicates an abnormal decrease, and 'a' is the discrimination threshold. The well switching status includes: well switching normal, well switching data missing, and well switching time too short; "Well opening and closing normally" means that the well opening and closing cycle is normal. Missing well control data means that there is no status data for the well control system. Too short a well opening / closing time refers to a well opening time of less than 10 minutes; The plunger status includes: normal plunger, plunger at the bottom of the well for a long time, plunger at the wellhead for a long time, and plunger mismatch with the well opening / closing condition. A normal plunger operation means that the plunger is functioning normally. The plunger remaining at the bottom of the well indicates that the plunger has not reached its destination. The plunger being at the wellhead for an extended period means that the plunger is always in the "reach" state. Piston mismatch with well opening / closing refers to a mismatch in the piston lifting process; the piston is not showing the arrival status when opening the well, and the piston is not at the bottom of the well when closing the well. The hydraulic pressure status includes: normal hydraulic pressure, hydraulic pressure communication failure, abnormal constant hydraulic pressure, approximately constant hydraulic pressure, abnormal increase in hydraulic pressure, abnormal decrease in hydraulic pressure, and hydraulic pressure exceeding the normal range. Normal oil pressure means that the oil pressure is in line with the normal operating condition of the plunger. Hydraulic communication failure refers to hydraulic failure caused by communication problems; Abnormal constant oil pressure refers to oil pressure being a constant value; The approximate constant oil pressure refers to a segmented constant value less than 0.

7. An abnormal rise in oil pressure refers to an increase in the average slope of the oil pressure cycle greater than 0.

07. An abnormal drop in oil pressure refers to a decrease in the average slope of the oil pressure cycle value greater than 0.

05. Oil pressure exceeding the normal range means that the oil pressure exceeds the normal oil pressure range of the gas well, and the 3σ extreme value is identified as 1; The pressure status includes: normal pressure status, pressure communication failure, abnormal constant pressure, near constant pressure, abnormal increase in pressure, abnormal decrease in pressure, and exceeding the normal range. Normal sleeve pressure means that the sleeve pressure meets the normal operating conditions of the plunger. A pressure-fitting communication failure refers to a pressure-fitting failure caused by a communication problem. Abnormally constant casing pressure refers to a casing pressure that is a constant value. The approximate constant value of the casing pressure refers to a segmented constant value less than 0.7; An abnormal increase in casing pressure refers to an increase in the average slope of the casing pressure cycle greater than 0.

07. An abnormal increase in casing pressure refers to a decrease in the average slope of the casing pressure cycle value greater than 0.

05. Casing pressure exceeding the normal range refers to casing pressure exceeding the normal casing pressure range of a gas well; the 3σ extreme value is identified as 1. The oil-casing pressure difference includes: normal oil-casing pressure difference, abnormal misalignment of oil-casing pressure difference, excessive oil-casing pressure difference, and excessively large oil-casing pressure difference. Normal oil-casing pressure differential means that the oil-casing pressure is less than 3 MPa. Abnormal misalignment of oil-casing pressure difference refers to a negative oil-casing pressure difference. Excessive oil-jacket pressure difference refers to an oil-jacket pressure difference greater than 3 MPa and less than or equal to 5 MPa. Excessive oil-casing pressure difference refers to an oil-casing pressure difference greater than 5 MPa.

2. The method for identifying abnormal operating conditions of plunger gas lift based on single-parameter analysis according to claim 1, characterized in that, The acquisition of production data related to the plunger lift system includes: Acquire well status data, plunger status data, oil pressure data, casing pressure data, and oil-casing pressure differential data.

Images