Gas well working condition diagnosis system and method

Abstract

The invention discloses a gas well working condition diagnosis system and method, and belongs to the technical field of plunger gas lift, and the method comprises the following steps: S1, sorting and constructing original data required by diagnosis, and carrying out the recognition and restoration of the original data, and obtaining diagnosis data; and S2, comparing the diagnostic data with running data trends of three stages of plunger ascending, follow current production and shut-in pressure recovery in a plunger gas lift period under a normal condition, and performing working condition diagnosis according to a running data trend comparison result. According to the method, the working condition of gas well operation is diagnosed and identified according to the running trend and form reasonability of three stages of plunger rising, follow current production and shut-in pressure recovery in the plunger gas lift period, and intelligent, rapid and accurate diagnostic analysis can be carried out on the running plunger gas lift well.

Description

Technical Field

[0001] The invention belongs to the technical field of plunger gas lift, and in particular relates to a gas well working condition diagnosis system and method. Background Art

[0002] Plunger gas lift drainage gas production is an efficient drainage gas production technology. A plunger tool is placed in the wellbore. The plunger forms an isolation interface between the gas and liquid in the wellbore, effectively reducing the slip loss between the gas and liquid. Under the impetus of the formation or the injected gas energy, periodic drainage is carried out to achieve stable production of the gas well. This technology is currently widely used. During the operation of the plunger gas lift technology, as the gas well production progresses, the amount of liquid accumulation and lifting energy in the gas well change. It is necessary to optimize the plunger lift operation system to achieve the optimal operation of the plunger gas lift process parameters. When the number of applied wells increases, in order to improve the plunger gas lift parameter adjustment operation efficiency, an intelligent optimization technology has been formed.

[0003] In the application of plunger gas lift technology, the operating conditions are complex, so there are various fault problems, including failure of equipment such as oil casing pressure sensors and control valves, abnormal data transmission, process errors, abnormal operation of liquid accumulation, etc. The causes of the problems are also diverse. Failures will have a serious impact on the normal operation and optimization of plunger gas lift technology, making the intelligent optimization method invalid and the plunger lift ineffective. In severe cases, it will cause liquid accumulation in the gas well and stop production, affecting the gas well production capacity.

[0004] In order to improve the stability and reliability of plunger gas lift technology, it is necessary to identify, screen and handle the faults in operation. The existing fault identification is mainly based on manual analysis, that is, based on a large number of wells in the field, the plunger gas lift operation and device fault characteristics are summarized, and the key production data, operation information, operation curves, etc. of each well are analyzed manually on a regular basis to determine the specific working conditions of the gas well production. When it is normal, the optimization system is continued to be implemented, and manual processing is arranged after the fault is found. When the number of plunger gas lift wells is small, the manual working condition analysis method can basically meet the production application needs of gas wells, but when the number of wells is large, the regular working condition diagnosis and analysis exceeds the limit of manual management and cannot meet the production needs of plunger gas lift wells. At the same time, the experience of management personnel plays an important role in the accurate and rapid identification of gas well working conditions and faults. When the position turnover of technical personnel is large, it will also have a serious impact on the manual analysis method. Therefore, there is an urgent need for intelligent technology that can achieve efficient and accurate diagnosis to solve the above problems. Summary of the invention

[0005] The present invention provides a gas well operating condition diagnosis system and method to improve fault diagnosis efficiency.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A gas well operating condition diagnosis method, characterized in that it comprises the following steps:

[0008] S1. Collect the original data required for working condition diagnosis, identify and repair the original data, and obtain diagnostic data;

[0009] S2. Compare the diagnostic data with the operating data trends of the three stages of plunger rise, continuous flow production, and shut-in pressure recovery during the plunger gas lift cycle under normal circumstances, and perform working condition diagnosis based on the comparison results of the operating data trends.

[0010] Furthermore, in step S2, the oil and casing pressure trend index and the fluid discharge trend index of the three stages of plunger rise, continued production, and shut-in pressure recovery during the plunger gas lift cycle are calculated based on the diagnostic data. Whether there is an operating process failure is determined based on the oil and casing pressure trend index and the fluid discharge trend index; whether there is a hardware failure and whether there is a fluid accumulation failure is determined based on the difference between the oil pressure and the casing pressure.

[0011] Furthermore, the calculation formula of the casing pressure trend index is:

[0012]

[0013] Among them, x qs is the oil pressure upward trend index, oil pressure continuous flow trend index, oil pressure recovery trend index, casing pressure upward trend index, casing pressure continuous flow trend index or casing pressure recovery trend index; n is the total number of samples, xi is the time of the i-th sampling point, xi+1 is the time of the i+1-th sampling point, y i is the oil pressure or casing pressure sampling value at time xi, y i+1 It is the oil pressure or casing pressure sampling value at the moment xi+1.

[0014] Furthermore, the calculation formula of the discharge volume trend index is:

[0015]

[0016] Among them, x p is the slope of the oil pressure value, i.e., the running drainage trend index; n is the total number of samples, xi is the time of the i-th sampling point, xi+1 is the time of the i+1-th sampling point, y i is the sampling value at time xi, y i+1 It is the oil pressure sampling value at time xi+1.

[0017] Furthermore, in step S2, a multivariate nonlinear classification algorithm Logistic Regression identification method is used to perform operating condition diagnosis.

[0018] Further, in step S2, the overall operation index of the gas well is calculated according to the calculation formula of the overall operation index of the gas well, and the working condition diagnosis is performed according to the overall operation index of the gas well; the calculation formula of the overall operation index of the gas well is:

[0019]

[0020] p is the overall operation index, X is the variable, X=a0+a1X1+a2X2+…+a k X k ; X1, X2...X k is the identification parameter, a0 is a constant, a1, a2...a k are the weight coefficients of the identification parameters respectively.

[0021] Furthermore, in step S2, the oil pressure trend index, casing pressure trend index and fluid displacement trend index are calculated based on the diagnostic data, and a radar chart is drawn based on the oil pressure trend index, casing pressure trend index, fluid displacement trend index and the overall operation index of the gas well to display the operating status of the gas well.

[0022] Furthermore, the identification parameters are oil pressure upward trend index, oil pressure continuous flow trend index, oil pressure recovery trend index, casing pressure upward trend index, casing pressure continuous flow trend index, casing pressure recovery trend index, drainage trend index and load factor.

[0023] A gas well operating condition diagnosis system, comprising:

[0024] The data processing module is used to collect the required raw data, identify and repair the raw data, and obtain diagnostic data;

[0025] The working condition diagnosis module is used to compare the diagnostic data with the operating data trends of the three stages of plunger rise, continuous flow production, and shut-in pressure recovery during the plunger gas lift cycle under normal circumstances, and perform working condition diagnosis based on the comparison results of the operating data trends.

[0026] Furthermore, it also includes a diagnostic application module, which is used to screen, analyze and handle the operating results based on the block gas well operating condition diagnosis according to conditions such as operating condition type and regional scope.

[0027] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0028] The present invention discloses a method for diagnosing the working condition of a gas well. The method diagnoses and identifies the working condition of the gas well according to the operating trends and rationality of the shapes of the three stages of plunger rise, continuous flow production and shut-in pressure recovery within the plunger gas lift cycle. The method can realize intelligent, rapid and accurate diagnostic analysis of the operating plunger gas lift well and compare it with manual working condition analysis. The intelligent diagnostic technology effectively saves the workload of manual analysis and identification, greatly improves the timeliness of identification, and realizes cost reduction and efficiency improvement in gas field development. At the same time, it can eliminate management problems such as technology loss caused by job transfers of technical personnel, and provide reliable guarantee for timely fault handling and stable operation of plunger gas lift technology.

[0029] Furthermore, solutions corresponding to different fault types are set in advance, and solutions are automatically output for the diagnosed faults at the same time.

[0030] Furthermore, a radar chart of gas well operation is generated to visualize the analysis results. Through radar chart analysis, the gas well operating conditions can be intuitively reflected, which can assist in guiding the application of gas well operating diagnosis technology.

[0031] Furthermore, the application module of the operating condition diagnosis system can display the operating conditions, operating indexes and radar charts of each well, and can query and analyze the diagnosis results according to different query conditions. It provides solutions for faulty gas wells and can handle and record the faults on the application platform. The statistical module then displays the diagnosis results in the form of bar charts, pie charts and tables. Finally, typical fault cases are pushed to the case library in the application for later technical reference. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the working condition diagnosis system of the plunger gas lift technology.

[0033] Figure 2 It is a logic diagram of the plunger gas lift technology working condition diagnosis system and method application.

[0034] Figure 3 It is the three-stage casing pressure trend and drainage trend during the plunger gas lift cycle.

[0035] Figure 4 It is a well operation curve diagram.

[0036] Figure 5 It is a radar chart of well operation conditions.

[0037] In the attached figure: 1 is a complete cycle of plunger gas lift operation, 2 is the plunger rising stage, 3 is the continuous flow production stage, 4 is the pressure recovery stage, and 5 is the drainage process. DETAILED DESCRIPTION

[0038] In order to make the purpose and technical solution of the present invention clearer and easier to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more. In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0040] Reference Figure 1 , a gas well operating condition diagnosis system comprises:

[0041] The data processing module organizes and constructs the data required for diagnosis, and uses threshold anomaly identification and 3σ extreme value identification and adjacent value repair methods to identify and process abnormal conditions in the diagnosis data, providing detailed and accurate data for accurate diagnosis.

[0042] The operating condition diagnosis module diagnoses and identifies the operating condition of the gas well based on the operating trends and morphological rationality of the three stages of plunger rise, continued flow production, and shut-in pressure recovery during the plunger gas lift cycle. At the same time, it establishes the casing pressure trend index and displacement volume index for different production stages, as well as a production identification radar chart. It can also use machine learning classification algorithms such as random forests and decision trees to realize intelligent identification of operating conditions and establish fault handling countermeasures.

[0043] The diagnostic application module completes the diagnosis of the working conditions of the gas wells in the block, and screens, statistically analyzes and processes the working condition results according to the working condition category and regional scope. It can directly push the intelligent optimization terminal and export different results.

[0044] The working condition statistics module conducts statistical analysis on the diagnosis results according to different production units and different working condition diagnosis result types, and displays the working condition diagnosis results in the form of bar charts and pie charts for overall analysis and guidance of working conditions.

[0045] The working condition case library module establishes a working condition case library, stores and classifies typical diagnostic working conditions in the form of data and curves. The data includes the oil pressure, casing pressure, plunger gas lift arrival state, load factor, discharge volume and oil-casing pressure difference, oil trend index and casing pressure trend index of the gas well at each stage during the plunger gas lift cycle. It can be queried and compared according to the well number and working condition type, which can guide the self-learning application of diagnostic technology and improve the accuracy of working condition diagnosis. It also includes the operating data and curves of each gas well under normal conditions.

[0046] 1) The data processing module of the present invention is based on data mainly including original and constructed parameters such as gas well production oil pressure, casing pressure, plunger gas lift arrival state (whether it has arrived), load coefficient, discharge volume and oil-casing pressure difference.

[0047] The data processing module of the present invention adopts a threshold anomaly identification method to determine whether there is abnormal data in the gas well identification. The parameter threshold range is set according to the regular characteristics of the production data. Each parameter is judged before application. When an abnormality exists, it needs to be repaired. For wells with too large data anomaly rate, effective diagnosis and identification of gas wells cannot be achieved, and they are directly pushed as diagnostic data abnormalities and cannot be diagnosed.

[0048] The data processing module of the present invention adopts 3σ extreme value recognition and adjacent value filling processing methods to repair abnormal data, remove abnormal data, and form continuous and effective diagnostic data.

[0049] 2) The working condition diagnosis module of the present invention diagnoses and identifies the working condition of the gas well according to the trend and rationality of the three stages of operation of the plunger's rise, continuous flow production, and shut-in pressure recovery during the plunger gas lift cycle. When the production and construction parameters of the plunger gas lift movement process conform to the periodic cycle law and change according to the three stages of plunger upward movement, continuous flow production, and shut-in pressure recovery, it is a normal working condition; when it is different from the three-stage change law, it is an abnormal working condition.

[0050] The production characteristics of the three stages of normal conditions are:

[0051] During the plunger upward phase, when the wellhead oil and casing pressure recovers to a certain level, the well is opened for production, and the plunger moves upward to the wellhead along with the gas and liquid. At this time, the oil pressure and casing pressure continue to decrease. When the plunger reaches the wellhead, the liquid is discharged, which is reflected in the production data curve as the oil pressure and casing pressure continuously decreasing. During this period, the oil pressure has a short upward oscillation, indicating that there is liquid discharge. The oil pressure rise and oscillation can determine the plunger gas lift liquid discharge condition.

[0052] In the continuous production stage, the plunger lifts the liquid to the wellhead, and the liquid is discharged to the production pipeline to continue the well production. At this time, the bottom hole liquid accumulation begins to increase, and the bottom hole flow pressure continues to rise, which is reflected in the curve of production data as relatively stable or slow changes in oil pressure and casing pressure.

[0053] In the shut-in pressure recovery phase, the well is shut down after the continuous production phase ends, and the plunger begins to fall. At this time, the wellhead casing pressure and wellhead oil pressure begin to gradually recover. When the well opening conditions are met, the well opening enters the next cycle, which is reflected in the curve of production data as the oil pressure and casing pressure continue to rise to a stable level.

[0054] The working condition diagnosis module of the present invention determines whether the operation process of the gas well is normal and whether there is a working condition of liquid discharge by establishing the oil casing pressure trend index and the liquid discharge trend index in the production stage of the gas well.

[0055] The oil and casing pressure trend index characterizes the trend of oil pressure and casing pressure changes in the three stages of plunger upward movement, continued flow production and shut-in pressure recovery during plunger gas lift operation, including trend indices such as oil pressure upward trend index, oil pressure continued flow trend index, oil pressure recovery trend index, casing pressure upward trend index, casing pressure continued flow trend index and casing pressure recovery trend index.

[0056] The identification method is:

[0057] Calculate the oil pressure and casing pressure trend index according to formula (1):

[0058]

[0059]

[0060] Among them, x qs It is the oil pressure slope in the plunger upward stage, the oil pressure slope in the continuous flow production stage, the oil pressure slope in the shut-in pressure recovery stage, the casing pressure slope in the plunger upward stage, the casing pressure slope in the continuous flow production stage or the casing pressure slope in the shut-in pressure recovery stage, that is, the oil pressure upward trend index, the oil pressure continuous flow trend index, the oil pressure recovery trend index, the casing pressure upward trend index, the casing pressure continuous flow trend index or the casing pressure recovery trend index;

[0061] n is the total number of samples, xi is the time of the i-th sampling point, xi+1 is the time of the i+1-th sampling point, y i is the oil pressure or casing pressure sampling value at time xi, yi+1 It is the sampling value of oil pressure or casing pressure at the moment xi+1. The sampling values ​​of oil pressure or casing pressure are the oil pressure in the plunger upward stage, the oil pressure in the continuous flow production stage and the oil pressure in the shut-in pressure recovery stage, the casing pressure in the plunger upward stage, the casing pressure in the continuous flow production stage and the casing pressure in the shut-in pressure recovery stage.

[0062] a is x qs The corresponding recognition threshold;

[0063] y qs is the result of identification, when y qs When y is 0, there is no fluctuation. qs When y is 1, it is an upward trend. qs A value of 2 indicates a downward trend.

[0064] When the trend index in the plunger gas lift operation stage is contrary to the set judgment value, the diagnosis result is: the gas well operating condition is abnormal.

[0065] The displacement trend index uses the oscillation of oil pressure during the plunger's ascent to reflect the plunger's gas lift displacement. The identification method is:

[0066]

[0067]

[0068] x p is the slope of the oil pressure value, i.e., the operating drainage trend index;

[0069] n is the total number of samples, xi is the time of the i-th sampling point, xi+1 is the time of the i+1-th sampling point, y i is the sampling value at time xi, y i+1 It is the oil pressure sampling value at time xi+1.

[0070] t is the discharge identification threshold;

[0071] y p is the identification result, 0 means no discharge, 1 means discharge.

[0072] The plunger gas lift drainage trend index determines whether drainage is performed during plunger operation and the drainage effect. The larger the drainage trend index, the more obvious the drainage. The index is 0 when there is no drainage.

[0073] In order to realize intelligent identification of gas well working conditions, the working condition diagnosis module of the present invention uses machine learning classification algorithms such as random forest, decision tree, K nearest neighbor, support vector machine, bagging or neural network or logistic regression to identify the working conditions and obtain the overall operation index of the gas well.

[0074] The working condition diagnosis module of the present invention adopts the multivariate nonlinear classification algorithm Logistic Regression identification method to obtain the overall operation index of the gas well. The identification formula is:

[0075] logit(p)=a0+a1X1+a2X2+…+a k X k … (5)

[0076] X1, X2...X k are the identification parameters, see Table 1 for details.

[0077] Table 1

[0078]

[0079] a0 is a constant, a1, a2, ... a k are the weight coefficients of the discrimination parameters respectively;

[0080] The working condition diagnosis module of the present invention also adopts the sigmoid function, and uses formula 6 to convert the nonlinear logic identification logit (p) into a linear result, and outputs an index value (0-1), which is defined as the operating condition index. The closer the index is to 1, the more the operating state of the periodic plunger meets the optimal standard, and the better the working condition is. The closer it is to 0, the worse it is. Formula 6 is:

[0081]

[0082] p is the overall operation index, X is the variable, X=a0+a1X1+a2X2+…+a k X k ;

[0083] Combining multiple plunger gas lift cycle operating condition indexes, it provides guidance for evaluating the operating condition of gas wells.

[0084] The working condition diagnosis module of the present invention develops a radar chart of the working condition of the gas well according to the oil casing pressure trend index, the drainage trend index and the operating condition index, and vividly displays the working condition of the gas well.

[0085] The working condition diagnosis module of the present invention finally outputs the gas well working condition name, operation status index and working condition radar chart. When a fault occurs, a fault handling countermeasure will be automatically formulated, as shown in Table 2.

[0086] Table 2 Fault handling measures

[0087]

[0088] A gas well operating condition diagnosis method comprises the following steps:

[0089] (1) For gas well diagnosis, the computer automatically collects and constructs information such as oil pressure, casing pressure, well opening and closing status, plunger arrival, load factor, oil-casing pressure difference, etc. during the operation cycle;

[0090] (2) Using threshold anomaly identification and 3σ extreme value identification and adjacent value filling processing methods to identify and repair gas well data;

[0091] (3) Using the trend and drainage index analysis method, the average oil trend index, casing pressure trend index and average drainage volume trend index of the three stages of plunger rise, continuous production and shut-in pressure recovery within the target plunger gas lift well identification period are analyzed;

[0092] (4) Using machine learning methods to identify the target well trend index and the operating case library, combined with the construction of identification parameters for comparison, the target well operating type is determined;

[0093] (5) Draw a radar chart of the operating condition based on the oil pressure trend index, casing pressure trend index, drainage trend index and overall gas well operation index, score and analyze the overall operating condition, and qualitatively analyze the operating condition of the gas well;

[0094] (6) According to the identified working condition type and fault handling countermeasures table, formulate the corresponding handling method for the working condition;

[0095] (7) Display and apply the diagnosis results and treatment methods on the application end;

[0096] (8) Setting a working condition diagnosis cycle and repeating steps (1) to (7) to achieve continuous and regular effective diagnosis and application of gas well working conditions;

[0097] (9) Perform computer automatic diagnosis and analysis on all gas wells in the gas management area that require working condition diagnosis according to the processes (1) to (8) to obtain diagnosis and fault handling countermeasures;

[0098] (10) Use the working condition application module to query and analyze the working conditions;

[0099] (11) When it is necessary to diagnose according to the specific operation conditions of the well in the application, the manual setting method can be used to execute the diagnostic command;

[0100] (12) In the application of working condition diagnosis, when it is determined that the well is representative of the case, the case can be added to the working condition case library to facilitate later call-up and analysis.

[0101] Preferably, in step (4), further working condition diagnosis is performed in combination with the oil-casing pressure difference, the oil pressure rise and fall frequency ratio, the casing pressure rise and fall frequency ratio, and the well opening and closing time.

[0102] Example 1

[0103] Figure 1is the standard operation curve of plunger gas lift. In the figure, 1 is a complete cycle of plunger gas lift operation, 2 is the plunger rising stage, 3 is the continuous flow production stage, 4 is the pressure recovery stage, and 5 is the drainage process. A complete cycle 1 includes three stages: plunger rising 2, continuous flow production 3 and pressure recovery 4. The characteristic of drainage in the plunger rising stage is 5.

[0104] like Figure 2 As shown, a plunger gas lift technology working condition diagnosis system includes modules such as data processing, working condition diagnosis, diagnostic application, working condition statistics and case library.

[0105] The data processing module is the basis for working condition diagnosis. It organizes the data required for diagnosis, including oil pressure, casing pressure, plunger gas lift arrival, load factor, drainage, oil-casing pressure difference, etc. At the same time, it identifies and processes abnormal data, and identifies and screens gas wells that cannot be diagnosed due to data problems, providing basic support for working condition diagnosis.

[0106] The working condition diagnosis is the core module of the present invention. According to the three-stage characteristics of the plunger gas lift technology, the working condition of the plunger well is accurately identified in combination with the construction parameters. The working condition diagnosis applies innovative technologies such as the oil casing pressure trend index, the displacement trend index, the machine learning method, the gas well operating condition index analysis after nonlinear logic linearization processing, and the production of the operating condition radar map, so as to realize the intelligent, efficient and accurate diagnosis of the working condition of the plunger well.

[0107] The diagnostic application module is the target result achieved by the working condition diagnostic technology. Through this module, the operating status of the target plunger well group can be effectively monitored and efficiently managed.

[0108] The operating condition statistics module is a display window for operating condition diagnosis results. It displays the operating condition diagnosis results by category in the form of bar charts, pie charts and detailed data tables, making it easy to analyze and apply the diagnosis results.

[0109] The case library module is used to collect and store typical working condition cases to provide support for diagnostic method optimization and application learning.

[0110] When applied, the data processing module first collects and organizes the data required for diagnosis, makes abnormal judgments and repairs the data, and screens out gas wells that do not meet the diagnostic requirements, and then provides the data to the diagnostic module; the diagnostic module uses three-stage trend index, drainage index, oil-casing pressure difference, production time, machine learning methods and other means to complete the diagnosis of gas well conditions, and then pushes the diagnostic results to the application module; the application module displays the operating conditions, operating indexes and radar charts of each well, and can query and analyze the diagnostic results according to different query conditions. For faulty gas wells, solutions are provided, and the faults can be handled and recorded on the application platform; the statistical module then displays the diagnostic results in the form of bar charts, pie charts and tables; finally, typical fault cases are pushed to the case library in the application for later technical reference.

[0111] like Figure 3 As shown, the application process of a plunger gas lift technology working condition diagnosis system and method is described as follows:

[0112] (1) For plunger gas lift wells, the computer automatically collects and constructs information such as oil pressure, casing pressure, well opening and closing status, plunger arrival, load factor and oil-casing pressure difference during the operation cycle. The data required for diagnosis are identified and repaired using threshold abnormality identification and 3σ extreme value identification and adjacent value filling processing methods, and gas wells that do not meet the diagnosis conditions are determined;

[0113] (2) Calculate the periodic oil pressure trend index, casing pressure trend index and drainage trend index of the gas well;

[0114] (3) Use machine learning methods to diagnose the operating conditions of plunger wells, determine the operating condition type, form an overall gas well operation index, and develop solutions for faulty wells;

[0115] (4) Draw an operating condition radar chart based on the oil casing pressure, drainage trend index and overall operating index of the gas well diagnosis, output the fault name, operating index, radar chart and fault handling suggestions, and push the diagnosis results to the operating condition application platform;

[0116] (5) The diagnostic results are analyzed on the working condition application platform, which can realize functions such as working condition query processing, working condition statistics and working condition case library push.

[0117] (6) Perform periodic diagnostic inspections on a single well in accordance with the procedures (1) to (5) to ensure continuous monitoring and normal operation of the gas well; then perform operating condition diagnosis and treatment on different gas wells in accordance with the procedures (1) to (5) to ensure the normal operation of the plunger wells in the gas zone;

[0118] Example 2

[0119] like Figure 4 is the plunger gas lift operation curve of example well A, Figure 5 It is a radar diagram for diagnosing the working condition of a gas well. Taking the gas well as an example, a system and method for diagnosing the working condition of a plunger gas lift technology according to the present invention are described.

[0120] The data of 20 operation cycles of plunger gas lift were selected, and the abnormal data were analyzed and processed to form standard operation data. The data of the well met the analysis conditions. The working condition diagnosis method was used to diagnose and analyze the gas well, and the diagnosis results were shown in Table 1.

[0121] Table 1 Gas well operating condition diagnosis results

[0122]

[0123] The diagnosis result of the well is normal (the oil-casing pressure difference is reasonable) with drainage, the operation status index is 0.74, which is excellent production, the drainage index is 0.4, the drainage is general, the plunger state is that the plunger does not match the switch well, and the arrival is unstable. Since the gas well is operating normally, the working condition treatment recommendation is to continue to maintain. Comparing the diagnosis result with the operation curve, the oil-casing pressure trend, drainage and analysis results of the plunger gas lift operation cycle can correspond. In the middle of the gas well operation, the oil-casing pressure increases, causing the pressure difference to increase. In the later operation, the oil-casing pressure difference returns to normal. Combined with 20 cycles, the overall operation trend of the well is 0.74, which is consistent with the actual situation; in the plunger state curve, there are multiple cycles where the plunger does not arrive, so the diagnosis result is that the arrival does not match the open pipe well, and the diagnosis result is also consistent with the actual situation.

[0124] The gas well operation radar chart is produced according to the working condition diagnosis results. The fuller the radar chart is, the better the operating status is. Through the radar chart analysis, the gas well oil casing pressure trend is excellent, the overall operating status is excellent, and the drainage index is medium. It can intuitively reflect the working conditions of the gas well and can assist in guiding the application of gas well working condition diagnosis technology.

[0125] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A gas well operating condition diagnosis method, characterized in that: The following steps are involved: S1. Collect the original data required for working condition diagnosis, identify and repair the original data, and obtain diagnostic data; S2. Compare the diagnostic data with the operating data trends of the three stages of plunger rise, continuous flow production, and shut-in pressure recovery during the plunger gas lift cycle under normal circumstances, and perform working condition diagnosis based on the comparison results of the operating data trends.

2. A gas well operating condition diagnosis method according to claim 1, characterized in that: In step S2, the oil and casing pressure trend index and the displacement volume trend index of the three stages of plunger rise, continuous production, and shut-in pressure recovery during the plunger gas lift cycle are calculated based on the diagnostic data, and whether there is an operation process failure is determined based on the oil and casing pressure trend index and the displacement volume trend index; whether there is a hardware failure and whether there is a fluid accumulation failure is determined based on the difference between the oil pressure and the casing pressure.

3. A gas well operating condition diagnosis method according to claim 2, characterized in that: The calculation formula of the casing pressure trend index is: Among them, x qs is the oil pressure upward trend index, oil pressure continuous flow trend index, oil pressure recovery trend index, casing pressure upward trend index, casing pressure continuous flow trend index or casing pressure recovery trend index; n is the total number of samples, xi is the time of the i-th sampling point, xi+1 is the time of the i+1-th sampling point, y i is the oil pressure or casing pressure sampling value at time xi, y i+1 It is the oil pressure or casing pressure sampling value at the moment xi+1.

4. A gas well operating condition diagnosis method according to claim 1, characterized in that: The calculation formula of the discharge volume trend index is: Among them, x p is the slope of the oil pressure value, i.e., the running drainage trend index; n is the total number of samples, xi is the time of the i-th sampling point, xi+1 is the time of the i+1-th sampling point, y i is the sampling value at time xi, y i+1 It is the oil pressure sampling value at time xi+1.

5. A gas well operating condition diagnosis method according to claim 1, characterized in that: In step S2, a multivariate nonlinear classification algorithm Logistic Regression identification method is used to perform operating condition diagnosis.

6. A gas well operating condition diagnosis method according to claim 1 or 5, characterized in that: In step S2, the overall operation index of the gas well is calculated according to the calculation formula of the overall operation index of the gas well, and the working condition diagnosis is performed according to the overall operation index of the gas well; the calculation formula of the overall operation index of the gas well is: p is the overall operation index, X is the variable, X=a0+a1X1+a2X2+…+a k X k ; X1, X2...X k is the identification parameter, a0 is a constant, a1, a2...a k are the weight coefficients of the identification parameters respectively.

7. A gas well operating condition diagnosis method according to claim 6, characterized in that: In step S2, the oil pressure trend index, casing pressure trend index and fluid displacement trend index are calculated according to the diagnostic data, and a radar chart is drawn according to the oil pressure trend index, casing pressure trend index, fluid displacement trend index and the overall operation index of the gas well to display the working status of the gas well.

8. A gas well operating condition diagnosis method according to claim 6, characterized in that: The identification parameters are oil pressure upward trend index, oil pressure continuous flow trend index, oil pressure recovery trend index, casing pressure upward trend index, casing pressure continuous flow trend index, casing pressure recovery trend index, drainage trend index and load coefficient.

9. A gas well operating condition diagnosis system, characterized in that: include: The data processing module is used to collect the required raw data, identify and repair the raw data, and obtain diagnostic data; The working condition diagnosis module is used to compare the diagnostic data with the operating data trends of the three stages of plunger rise, continuous flow production, and shut-in pressure recovery during the plunger gas lift cycle under normal circumstances, and perform working condition diagnosis based on the comparison results of the operating data trends.

10. A gas well operating condition diagnosis system according to claim 9, characterized in that: It also includes a diagnostic application module, which is used to screen, analyze and handle the operating results based on the block gas well operating condition diagnosis according to conditions such as operating condition type and regional scope.

Images