CN114790885A - Method and device for measuring output of oil pumping well - Google Patents
Method and device for measuring output of oil pumping well Download PDFInfo
- Publication number
- CN114790885A CN114790885A CN202110022441.1A CN202110022441A CN114790885A CN 114790885 A CN114790885 A CN 114790885A CN 202110022441 A CN202110022441 A CN 202110022441A CN 114790885 A CN114790885 A CN 114790885A
- Authority
- CN
- China
- Prior art keywords
- electric power
- obtaining
- diagram
- well
- indicator diagram
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 94
- 238000005086 pumping Methods 0.000 title claims abstract description 66
- 238000010586 diagram Methods 0.000 claims abstract description 167
- 238000004519 manufacturing process Methods 0.000 claims abstract description 68
- 238000006243 chemical reaction Methods 0.000 claims abstract description 44
- 238000005259 measurement Methods 0.000 claims abstract description 21
- 239000007788 liquid Substances 0.000 claims abstract description 19
- 239000003129 oil well Substances 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000000306 recurrent effect Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 16
- 238000004891 communication Methods 0.000 description 14
- 239000012530 fluid Substances 0.000 description 13
- 238000012545 processing Methods 0.000 description 11
- 238000013135 deep learning Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 239000000872 buffer Substances 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Business, Economics & Management (AREA)
- Geology (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Marine Sciences & Fisheries (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- Agronomy & Crop Science (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The application provides a method and a device for measuring the output of an oil pumping well, wherein the method comprises the following steps: acquiring an electric power curve of a target pumping well; obtaining the corresponding effective stroke of the target pumping well according to a preset power-indicator diagram conversion model, a five-point curvature method and the electric power curve; and obtaining the liquid production amount of the target pumping well by using the effective stroke and the pre-obtained leakage coefficient. The method and the device can avoid actually measured indicator diagram data distortion and improve the accuracy and efficiency of output measurement of the rod-pumped well.
Description
Technical Field
The application relates to the technical field of oil field mechanical oil extraction, in particular to a method and a device for measuring the output of an oil pumping well.
Background
Metering of well production is an important task in the daily production of oil fields. The method has the advantages of accurate and timely measurement of the oil well yield, and important guiding significance for mastering the oil reservoir condition, developing dynamic analysis and making a production scheme. The oil measurement is mainly carried out in each oil field by using a volume method, a mass method and other methods, and the problems of multiple application devices, long process flow, high investment, untimely measurement and the like exist.
With the popularization of oil well digitization and automation, digital metering becomes a new development trend with small investment, high efficiency and the like, the technology of calculating the oil well yield by utilizing the indicator diagram of the pumping well is gradually applied and developed, the indicator diagram on the ground of the pumping well can be obtained by a load sensor, and the problems of high cost, low popularization rate, easy data drift and distortion and the like exist.
Disclosure of Invention
The method and the device for measuring the output of the rod-pumped well are used for solving at least one problem in the prior art, the data distortion of an actually measured indicator diagram can be avoided, and the accuracy and the efficiency of the output measurement of the rod-pumped well can be improved.
In order to solve the technical problem, the present application provides the following technical solutions:
in a first aspect, the present application provides a method for measuring output of a rod-pumped well, comprising:
acquiring an electric power curve of a target pumping well;
obtaining the corresponding effective stroke of the target pumping well according to a preset power-work diagram conversion model, a five-point curvature method and the electric power curve;
and obtaining the liquid production amount of the target pumping well by using the effective stroke and the pre-obtained leakage coefficient.
Further, the obtaining of the effective stroke corresponding to the target rod-pumped well according to a preset power-to-diagram conversion model, a five-point curvature method and the electric power curve includes:
obtaining an indicator diagram corresponding to the electric power curve according to the electric power curve and a preset power-indicator diagram conversion model;
obtaining a pump indicator diagram corresponding to the indicator diagram according to a three-dimensional wave equation, a finite difference algorithm and the indicator diagram;
and obtaining the corresponding effective stroke of the target pumping well according to the pump work diagram and a five-point curvature method.
Further, before obtaining the effective stroke corresponding to the target rod-pumped well according to the preset power-work diagram conversion model, the five-point curvature method and the electric power curve, the method further includes:
training the power-indicator diagram conversion model by applying a plurality of historical electric power curves and the actually measured indicator diagram corresponding to each historical electric power curve;
wherein, the power-diagram conversion model sequentially comprises: a restrictive boltzmann machine, a sparse self-encoder, and a Softmax mapping layer.
Further, before the step of obtaining the fluid production of the target rod-pumped well by applying the effective stroke and the pre-obtained loss-through coefficient, the method further comprises the following steps:
collecting historical data of an oil well;
and determining a model by using the historical data of the oil well and a preset leakage coefficient to obtain the leakage coefficient.
Further, the preset leakage coefficient determination model is obtained by training a recurrent neural network in advance.
In a second aspect, the present application provides a pumped well production metering device comprising:
the acquisition module is used for acquiring an electric power curve of the target pumping well;
the stroke determining module is used for obtaining the corresponding effective stroke of the target pumping well according to a preset power-work diagram conversion model, a five-point curvature method and the electric power curve;
and the liquid production amount determining module is used for applying the effective stroke and the pre-acquired leakage coefficient to obtain the liquid production amount of the target pumping well.
Further, the stroke determination module includes:
obtaining an indicator diagram unit, configured to obtain an indicator diagram corresponding to the electric power curve according to the electric power curve and a preset power-indicator diagram conversion model;
obtaining a pump diagram unit, which is used for obtaining a pump diagram corresponding to the indicator diagram according to a three-dimensional wave equation, a finite difference algorithm and the indicator diagram;
and the stroke determining unit is used for obtaining the corresponding effective stroke of the target pumping well according to the pump work diagram and the five-point curvature method.
Further, the oil pumping well production metering device further comprises:
the training module is used for applying a plurality of historical electric power curves and actual measurement indicator diagrams corresponding to the historical electric power curves to train the power-indicator diagram conversion model;
wherein, the power-diagram conversion model sequentially comprises: a restrictive boltzmann machine, a sparse autoencoder, and a Softmax mapping layer.
Further, the oil pumping well production metering device further comprises:
the acquisition module is used for acquiring historical data of an oil well;
and the leakage coefficient obtaining module is used for determining a model by applying the historical data of the oil well and a preset leakage coefficient to obtain the leakage coefficient.
Further, the preset leakage coefficient determination model is obtained by training a recurrent neural network in advance.
In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for measuring output of a rod pumped well when executing the program.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon computer instructions that, when executed, implement the method for rod-pumped well throughput.
According to the technical scheme, the method and the device for measuring the output of the rod-pumped well are provided. Wherein, the method comprises the following steps: acquiring an electric power curve of a target pumping well; obtaining the corresponding effective stroke of the target pumping well according to a preset power-work diagram conversion model, a five-point curvature method and the electric power curve; the effective stroke and the pre-acquired leakage coefficient are applied to obtain the liquid production amount of the target pumping well, so that the data distortion of an actually measured indicator diagram can be avoided, and the accuracy and the efficiency of the output measurement of the pumping well can be improved; particularly, the liquid production amount metering cost can be reduced, the intelligent degree of liquid production amount metering can be improved, rapid and accurate online metering is realized, and the method has a wide application prospect.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for measuring the output of a rod-pumped well according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for measuring output from a rod-pumped well according to another embodiment of the present application;
FIG. 3 is a schematic flow chart of training and recognition of a power-diagram conversion model in an application example of the present application;
FIG. 4 is a logic diagram of sample library establishment in an application example of the present application;
FIG. 5 is a diagram illustrating a relationship between a pump diagram and an indicator diagram in an application example of the present application;
FIG. 6 is a schematic flow chart of a method for measuring output from a rod-pumped well according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a flow meter for a pumped well according to an exemplary embodiment of the present invention;
fig. 8 is a schematic block diagram of a system configuration of an electronic device 9600 according to the embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Along with the application of internet of things in the oil gas well production field, can collect a large amount of actual measurement electrical parameters, indicator diagram data on the scene, cover all kinds of complicated operating modes of different types of oil wells, use conventional mathematics physical model and electrical parameter to indirectly obtain the indicator diagram, there is the hypothesis constraint condition many, the on-the-spot unable effective application scheduling problem, if: the oil pumping unit is supposed to be completely balanced, the structural parameters of the oil pumping unit are required to be input completely, zero division is carried out on an upper dead point and a lower dead point, and the like. Based on this, this application considers and utilizes the degree of deep learning technique means, turns into the indicator diagram with the electric power curve, utilizes the effective stroke method to calculate oil well liquid production volume, can adapt to complicated operating mode, avoids actual measurement indicator diagram data distortion, can improve the accuracy and the efficiency of oil pumping motor-pumped well output measurement.
Based on this, in order to avoid actually measuring the indicator diagram data distortion, improve the accuracy and the efficiency of beam-pumping unit well output measurement, the embodiment of the present application provides a beam-pumping unit well output measurement device, the device may be a server or a client device, and the client device may include a smart phone, a tablet electronic device, a network set top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, an intelligent wearable device, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch and intelligent bracelet etc..
In practice, the metering of the production from the rod-pumped well may be performed in part on the server side as described above, or all operations may be performed at the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. The client device may further include a processor if all operations are performed in the client device.
The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.
The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of the present application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.
The following examples are intended to illustrate the details.
In order to avoid the distortion of the actually measured indicator diagram data and improve the accuracy and efficiency of the output measurement of the rod-pumped well, the present embodiment provides a method for measuring the output of the rod-pumped well, in which the main execution body is a rod-pumped well output measuring device, the rod-pumped well output measuring device includes, but is not limited to, a server, as shown in fig. 1, and the method specifically includes the following contents:
step 100: and acquiring an electric power curve of the target pumping well.
In particular, the electrical power curve may be a measured electrical power curve.
Step 200: and obtaining the corresponding effective stroke of the target pumping well according to a preset power-indicator diagram conversion model, a five-point curvature method and the electric power curve.
Step 300: and obtaining the liquid production amount of the target pumping well by using the effective stroke and the pre-obtained leakage loss coefficient.
In one embodiment of the present application, referring to fig. 2, step 200 comprises:
step 201: and obtaining an indicator diagram corresponding to the electric power curve according to the electric power curve and a preset power-indicator diagram conversion model.
Specifically, the electrical parameters are the most basic operating parameters of the oil well, the method has the advantages of high popularization rate, low acquisition cost, stable data and the like, the indicator diagram of the oil pumping well is indirectly obtained through the electrical parameters, then online measurement of the oil well is carried out, low-cost and high-efficiency oil well digital processing can be achieved, and the electric power in the embodiment is one electrical parameter.
Step 202: and obtaining a pump diagram corresponding to the indicator diagram according to the three-dimensional wave equation, the finite difference algorithm and the indicator diagram.
Specifically, the relation between the ground indicator diagram and the underground pump diagram can be established through a three-dimensional wave equation, the three-dimensional wave equation is solved through a finite difference algorithm, and the ground indicator diagram is converted into the underground pump diagram.
Step 203: and obtaining the corresponding effective stroke of the target pumping well according to the pump diagram and the five-point curvature method.
Specifically, a traveling valve closing point a, a fixed valve opening point B, a fixed valve closing point C and a traveling valve opening point D in the pump diagram can be determined by a five-point curvature method, and the smaller of AD and BC is taken as an effective stroke, that is, an effective stroke of the plunger.
As can be seen from the above description, in the method for measuring the output of the rod-pumped well according to the embodiment, the indicator diagram corresponding to the electric power curve is obtained according to the electric power curve and the preset power-indicator diagram conversion model; obtaining a pump indicator diagram corresponding to the indicator diagram according to a three-dimensional wave equation, a finite difference algorithm and the indicator diagram; obtaining the corresponding effective stroke of the target pumping well according to the pump diagram and a five-point curvature method; the problems that the load sensor is high in cost and data are prone to drifting and distorting in the process of obtaining the indicator diagram can be avoided, meanwhile, the load sensor can adapt to various complex working conditions of different types of oil wells, and accuracy and efficiency of liquid production amount metering can be improved.
In order to improve the reliability of the power-indicator diagram conversion model and the accuracy of the fluid production measurement, in an embodiment of the present application, before step 200, the method further includes:
step 021: training the power-diagram conversion model by applying a plurality of historical electric power curves and the actually measured indicator diagrams corresponding to the historical electric power curves; wherein, the power-diagram conversion model sequentially comprises: a restrictive boltzmann machine, a sparse self-encoder, and a Softmax mapping layer.
Specifically, the normalized electric power parameter corresponding to the historical electric power curve may be used as a sample, and the indicator diagram parameter of the actually measured indicator diagram corresponding to the historical electric power curve may be used as a label to train the power-indicator diagram conversion model.
In order to improve the accuracy of the fluid production quantity measurement, the method may determine the current leakage coefficient by using a deep learning model in consideration of the influence of time factors in the process of determining the leakage coefficient, and in an embodiment of the present application, before step 300, further includes:
step 031: and collecting historical data of the oil well.
Specifically, the well history data may include: fluid data (sand content, viscosity, bottom hole temperature, bubble point pressure, volume factor, etc.), historical pump inspection operations (hours of operation, pump-rig initial clearance values), and production data (production, stroke, pump-in, pump-out depth, rod-string combination, gas-oil ratio, bottom hole pressure, etc.).
Step 032: and determining a model by using the historical data of the oil well and a preset leakage coefficient to obtain the leakage coefficient.
Specifically, the preset leakage coefficient determination model may be obtained by training a recurrent neural network in advance; the historical data of the oil well can be input into the preset leakage coefficient determination model, and the output result of the preset leakage coefficient determination model is used as the leakage coefficient.
To further illustrate the present solution, the present application provides an example of an application of a method for measuring the output of a rod-pumped well, which is specifically described as follows:
1) electric power curve conversion indicator diagram based on deep learning method
(1) Collecting field power and load data, and establishing a sample library
The construction of the Internet of things of the oil field in China has been achieved primarily, data such as the power of an oil pumping unit, the load of a suspension point, the displacement and the like can be directly uploaded to a background database through a sensor, the database is called to collect actually measured electric power curves and corresponding indicator diagram parameters of typical oil wells under different working conditions in a period of time from the site, and a sample library is established. The sample library mainly comprises power parameters and indicator diagram parameters, can contain more than 5 ten thousand data, and relates to the main working conditions of normality, insufficient liquid supply, gas influence, valve loss and the like. The purpose is to establish the conversion relation between the power parameters and the indicator diagram parameters, and finally realize the direct conversion of the indicator diagram through the electric power curve, so that the indicator diagram parameters do not need to be collected on site, and the cost of the Internet of things of the oil field can be reduced.
(2) Eigenvalue extraction
Extracting a test point of an electric power curve in a period from an upper stroke as a characteristic value X, wherein the electric power curve is formed by continuous periodic functions, identifying the position of a bottom dead center of the curve, extracting the electric power curve of the period from the bottom dead center, and taking a power parameter after normalization processing as an input characteristic.
And generating a binary image with a standard size by using the actually measured indicator diagram, wherein the background color and the indicator diagram shape are respectively expressed by two colors, and then extracting pixel points of the indicator diagram curve in the image as characteristic values.
(3) Inversion indicator diagram based on deep learning
The method comprises the steps of utilizing deep learning technologies such as a restrictive Boltzmann machine, sparse self-coding and Softmax mapping, building a deep learning model framework based on TensorFlow, automatically analyzing the incidence relation between electric power and an indicator diagram through the deep learning technology, building a power-indicator diagram conversion model M, seeking the highest model conversion precision through a genetic algorithm, and training to obtain a correlation coefficient.
As shown in fig. 3, the deep learning model training and recognition process specifically includes:
inputting the normalized electrical parameter characteristic value X' into a power-diagram conversion model M; the power-diagram conversion model M performs characteristic value transformation 1 and 2 on X' through a restrictive Boltzmann machine, performs characteristic composition analysis 1 and 2 through a sparse self-encoder, and outputs a final result through Softmax mapping; the power-to-work graph conversion model M may be optimized according to the final result and the normalized load characteristic value Y'.
The training process is as follows:
firstly, data records corresponding to the power-work diagram are collected.
Secondly, extracting the characteristics of the power, and forming a characteristic vector according to the time sequence in the period.
And thirdly, extracting power data, and forming a curve image according to the coordinates and the load data.
And fourthly, carrying out closed filling on the curve image, and extracting the filled pixels as features to form a vector.
Normalizing the power characteristic and the power diagram characteristic according to rows and mapping the power characteristic and the power diagram characteristic to a range from 0 to 1; the steps (i) to (v) may be equivalent to the process of establishing the sample library.
In an example, the process of establishing the sample library may be as shown in fig. 4, obtaining an electric power curve and a corresponding indicator diagram, that is, obtaining field power-indicator diagram sample data; extracting a characteristic X from the electric power curve, namely extracting the characteristic of the power to obtain power values arranged in time sequence; normalizing the power value to be between 0 and 1 to obtain a normalized electrical parameter characteristic value X', namely normalized power characteristics; filling the indicator diagram; extracting pixel characteristics Y from the filled indicator diagram; and normalizing the pixel characteristics to be between 0 and 1 to obtain a normalized load characteristic value Y', namely normalized indicator diagram characteristics.
And sixthly, taking the normalized power characteristic as input and the normalized power diagram characteristic as output, and training the deep learning model.
(4) Indicator diagram output
The inverted indicator diagram is a black and white image with uniform size, and all the closed space is black.
2) Oil well production calculation
(1) Pump diagram solving
And converting the ground indicator diagram into a downhole pump diagram by solving the three-dimensional wave equation.
(2) Effective stroke solution
As shown in fig. 5, a traveling valve closing point a, a fixed valve opening point B, a fixed valve closing point C and a traveling valve opening point D in the pump diagram are solved by a five-point curvature method, and the smaller one of AD and BC is taken as the effective stroke of the plunger.
Specifically, the maximum curvature change point of the pump diagram curve is the valve opening/closing point.
(3) Solution of leakage coefficients
The leakage coefficient is related to fluid data (sand content, viscosity, bottom hole temperature, bubble point pressure, volume coefficient and the like), historical pump detection operation (operation time, oil well pump initial gap value) and production data (yield, stroke frequency, pump well, pump down depth, rod column combination, gas-oil ratio, bottom hole pressure and the like), and the like, the fluid data, the historical pump detection operation data and the production data are used as input, the leakage coefficient is used as a target function, a recurrent neural network is built based on TensorFlow, and a multi-parameter time series leakage coefficient calculation model, namely the leakage coefficient determination model, is built by using a recurrent neural network method. Historical data of the oil well including fluid data, historical pump inspection operation data and production data can be input into a multi-parameter time series leakage coefficient calculation model, and an output result is used as a current leakage coefficient.
The recurrent neural network can be used for describing the output of continuous states in time and has a memory function, the leakage just changes along with the time, the recurrent neural network memorizes the previous leakage coefficient and applies the previous leakage coefficient to the calculation of the current output, and the neural network nodes not only comprise the production data of the current time, but also comprise the fluid data and the operation data of the previous period of time, thereby carrying out the trend prediction on the leakage situation of the future period of time.
(4) Calculation of fluid production
Based on a deep learning algorithm, converting an electric power curve into a ground indicator diagram, further converting the ground indicator diagram into a downhole pump diagram by solving a three-dimensional wave equation, and finally obtaining the oil well yield by an effective stroke method, namely obtaining the single-well liquid production by applying the following formula:
wherein Q represents the amount of fluid produced, unit: m is 3 /d；D p Represents the pump diameter, unit: m; eta L Represents the pump loss coefficient; n represents stroke, unit: min(s) -1 ；S pump Represents the effective stroke of the plug, in units: m; b is 1 Representing the well fluid volume factor.
According to the description, the method for measuring the yield of the pumping well provided by the application example comprises the steps of establishing a deep learning sample base by collecting field power-indicator diagram sample data, training the sample base by using a big data method, establishing a power-indicator diagram conversion model, realizing electric power curve inversion of a ground indicator diagram, solving a pump indicator diagram through a three-dimensional wave equation, accurately obtaining an effective stroke and a leakage coefficient, and finally solving the yield of the oil well by using an effective stroke method; specifically, the electric power curve is used for calculating the yield, only the electric power curve of the pumping well needs to be tested, the indicator diagram is inverted by using the big data deep learning and the effective stroke method, the yield of the oil well is calculated, the indicator diagram does not need to be actually measured, online measurement is performed quickly and accurately, the inverted indicator diagram and the yield calculation result can be obtained, the traditional load sensor can be replaced, the cost is reduced, the accuracy and the popularization rate are improved, and the digital popularization of the oil field can be promoted.
To further illustrate the present solution, the present application provides an application example of a method for measuring output of a rod-pumped well, as shown in fig. 6, which specifically includes:
acquiring a ground indicator diagram; applying a wave equation and a finite difference algorithm to obtain a downhole pump diagram corresponding to the ground indicator diagram; solving the valve switch position by applying a five-point curvature method, and obtaining an effective stroke according to a small-scale method; constructing a sample library, namely constructing a trend model, namely the multi-parameter time sequence leakage coefficient calculation model by using a recurrent neural network to obtain a leakage coefficient; and obtaining the oil well yield according to the effective stroke and the leakage coefficient.
In terms of software, in order to avoid the distortion of the actually measured indicator diagram data and improve the accuracy and efficiency of the oil pumping well production metering, the present application provides an embodiment of the oil pumping well production metering device for implementing all or part of the content of the oil pumping well production metering method, referring to fig. 7, the oil pumping well production metering device specifically includes the following contents:
and the acquisition module 10 is used for acquiring an electric power curve of the target pumping well.
And a stroke determining module 20, configured to obtain an effective stroke corresponding to the target rod-pumped well according to a preset power-to-work diagram conversion model, a five-point curvature method, and the electric power curve.
And a fluid production rate determining module 30, configured to apply the effective stroke and the pre-obtained leakage coefficient to obtain a fluid production rate of the target rod-pumped well.
In one embodiment of the present application, the stroke determining module includes:
and the indicator diagram unit is used for obtaining an indicator diagram corresponding to the electric power curve according to the electric power curve and a preset power-indicator diagram conversion model.
And obtaining a pump diagram unit, which is used for obtaining a pump diagram corresponding to the indicator diagram according to the three-dimensional wave equation, the finite difference algorithm and the indicator diagram.
And the stroke determining unit is used for obtaining the corresponding effective stroke of the target pumping well according to the pump work diagram and the five-point curvature method.
In an embodiment of the present application, the oil pumping well production metering device further includes:
and the training module is used for applying a plurality of historical electric power curves and the actual measurement indicator diagram corresponding to each historical electric power curve to train the power-indicator diagram conversion model.
Wherein, the power-diagram conversion model sequentially comprises: a restrictive boltzmann machine, a sparse autoencoder, and a Softmax mapping layer.
In an embodiment of the present application, the production metering device for a rod-pumped well further includes:
and the acquisition module is used for acquiring historical data of the oil well.
And the leakage coefficient obtaining module is used for determining a model by applying the historical data of the oil well and a preset leakage coefficient to obtain the leakage coefficient.
The preset leakage coefficient determination model may be obtained by training a recurrent neural network in advance.
The embodiment of the rod-pumped well production metering device provided in this specification can be specifically used for executing the processing flow of the embodiment of the rod-pumped well production metering method, and the functions thereof are not described herein again, and reference can be made to the detailed description of the embodiment of the rod-pumped well production metering method.
According to the description, the method and the device for measuring the output of the rod-pumped well can avoid the data distortion of the actually measured indicator diagram and improve the accuracy and the efficiency of the output measurement of the rod-pumped well; particularly, the liquid production amount metering cost can be reduced, the intelligent degree of liquid production amount metering can be improved, rapid and accurate online metering is realized, and the method has a wide application prospect.
In terms of hardware, in order to avoid distortion of actually measured indicator diagram data and improve accuracy and efficiency of oil pumping well production metering, the present application provides an embodiment of an electronic device for implementing all or part of the contents of the method for measuring oil pumping well production, wherein the electronic device specifically includes the following contents:
a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission between the oil pumping well yield metering device, a user terminal and other related equipment; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to the embodiment for implementing the method for measuring the output of the rod-pumped well and the embodiment for implementing the device for measuring the output of the rod-pumped well in the embodiments, and the contents thereof are incorporated herein, and repeated details are not repeated herein.
Fig. 8 is a schematic block diagram of a system configuration of an electronic device 9600 according to the embodiment of the present application. As shown in fig. 8, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is noted that this fig. 8 is exemplary; other types of structures may also be used in addition to or in place of the structures to implement telecommunications or other functions.
In one or more embodiments of the present application, the rod-pumped well production metering function may be integrated into the central processor 9100. The central processor 9100 may be configured to control as follows:
step 100: and acquiring an electric power curve of the target pumping well.
Step 200: and obtaining the corresponding effective stroke of the target pumping well according to a preset power-work diagram conversion model, a five-point curvature method and the electric power curve.
Step 300: and obtaining the liquid production amount of the target pumping well by using the effective stroke and the pre-obtained leakage coefficient.
From the above description, the electronic device provided in the embodiment of the present application can avoid actually measured indicator diagram data distortion, and can improve the accuracy and efficiency of oil pumping well production metering.
In another embodiment, the pumping well production metering device can be configured separately from the central processor 9100, for example, the pumping well production metering device can be configured as a chip connected to the central processor 9100, and the pumping well production metering function can be realized by the control of the central processor.
As shown in fig. 8, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worthy to note that the electronic device 9600 also does not necessarily include all of the components shown in fig. 8; in addition, the electronic device 9600 may further include components not shown in fig. 8, which may be referred to in the prior art.
As shown in fig. 8, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.
The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.
The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.
The memory 9140 may be a solid-state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage part 9142, the application/function storage part 9142 being used to store application programs and function programs or a flow for executing the operation of the electronic device 9600 by the central processing unit 9100.
The memory 9140 can also include a data store 9143, the data store 9143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).
The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132 to implement general telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.
According to the description, the electronic equipment provided by the embodiment of the application can avoid actually measured indicator diagram data distortion and improve the accuracy and efficiency of oil pumping well yield metering.
Embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the rod-pumped well production method in the above embodiments, where the computer-readable storage medium stores thereon a computer program, and the computer program when executed by a processor implements all the steps of the rod-pumped well production method in the above embodiments, for example, the processor implements the following steps when executing the computer program:
step 100: and acquiring an electric power curve of the target pumping well.
Step 200: and obtaining the corresponding effective stroke of the target pumping well according to a preset power-work diagram conversion model, a five-point curvature method and the electric power curve.
Step 300: and obtaining the liquid production amount of the target pumping well by using the effective stroke and the pre-obtained leakage loss coefficient.
From the above description, it can be seen that the computer-readable storage medium provided in the embodiments of the present application can avoid data distortion of an actually measured indicator diagram, and improve accuracy and efficiency of output measurement of a rod-pumped well.
In the present application, each embodiment of the method is described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. Reference is made to the description of the method embodiments.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the present application are explained by applying specific embodiments in the present application, and the description of the above embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (12)
1. A method for measuring the output of a rod-pumped well, comprising:
acquiring an electric power curve of a target pumping well;
obtaining the corresponding effective stroke of the target pumping well according to a preset power-indicator diagram conversion model, a five-point curvature method and the electric power curve;
and obtaining the liquid production amount of the target pumping well by using the effective stroke and the pre-obtained leakage coefficient.
2. The method for measuring the output of the rod-pumped well according to claim 1, wherein the obtaining the effective stroke corresponding to the target rod-pumped well according to the preset power-work diagram conversion model, the five-point curvature method and the electric power curve comprises:
obtaining an indicator diagram corresponding to the electric power curve according to the electric power curve and a preset power-indicator diagram conversion model;
obtaining a pump diagram corresponding to the indicator diagram according to a three-dimensional wave equation, a finite difference algorithm and the indicator diagram;
and obtaining the corresponding effective stroke of the target pumping well according to the pump diagram and the five-point curvature method.
3. The method for measuring the output of the rod-pumped well according to claim 1, wherein before obtaining the corresponding effective stroke of the target rod-pumped well according to the preset power-work diagram transformation model, the five-point curvature method and the electric power curve, the method further comprises:
training the power-indicator diagram conversion model by applying a plurality of historical electric power curves and the actually measured indicator diagram corresponding to each historical electric power curve;
wherein, the power-diagram conversion model sequentially comprises: a restrictive boltzmann machine, a sparse self-encoder, and a Softmax mapping layer.
4. The method for measuring the production capacity of a rod-pumped well according to claim 1, further comprising, before said applying the effective stroke and the pre-obtained loss-through coefficient to obtain the production capacity of the target rod-pumped well:
collecting historical data of an oil well;
and determining a model by using the historical data of the oil well and a preset leakage coefficient to obtain the leakage coefficient.
5. The rod-pumped well production volume measuring method according to claim 4, wherein the predetermined leakage coefficient determination model is obtained by pre-training a recurrent neural network.
6. A production metering device for a rod-pumped well is characterized by comprising:
the acquisition module is used for acquiring an electric power curve of the target pumping well;
the stroke determining module is used for obtaining the corresponding effective stroke of the target pumping well according to a preset power-work diagram conversion model, a five-point curvature method and the electric power curve;
and the liquid production amount determining module is used for applying the effective stroke and the pre-acquired leakage coefficient to obtain the liquid production amount of the target pumping well.
7. The pumped well production metering device of claim 6, wherein the stroke determining module comprises:
the indicator diagram obtaining unit is used for obtaining an indicator diagram corresponding to the electric power curve according to the electric power curve and a preset power-indicator diagram conversion model;
obtaining a pump diagram unit, which is used for obtaining a pump diagram corresponding to the indicator diagram according to a three-dimensional wave equation, a finite difference algorithm and the indicator diagram;
and the stroke determining unit is used for obtaining the corresponding effective stroke of the target pumping well according to the pump work diagram and the five-point curvature method.
8. The pumped well production metering device of claim 6, further comprising:
the training module is used for applying a plurality of historical electric power curves and actual measurement indicator diagrams corresponding to the historical electric power curves to train the power-indicator diagram conversion model;
wherein, the power-diagram conversion model sequentially comprises: a restrictive boltzmann machine, a sparse autoencoder, and a Softmax mapping layer.
9. The pumped well production metering device of claim 6, further comprising:
the acquisition module is used for acquiring historical data of an oil well;
and the leakage coefficient obtaining module is used for determining a model by applying the historical data of the oil well and a preset leakage coefficient to obtain the leakage coefficient.
10. The rod pumped well production gauging apparatus according to claim 9, wherein said predetermined leakage factor determining model is pre-trained to the recurrent neural network.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of rod-pumped well production volume according to any of claims 1 to 5.
12. A computer readable storage medium having stored thereon computer instructions, wherein the instructions when executed perform the method of rod-pumped well production volume according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110022441.1A CN114790885A (en) | 2021-01-08 | 2021-01-08 | Method and device for measuring output of oil pumping well |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110022441.1A CN114790885A (en) | 2021-01-08 | 2021-01-08 | Method and device for measuring output of oil pumping well |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114790885A true CN114790885A (en) | 2022-07-26 |
Family
ID=82460427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110022441.1A Pending CN114790885A (en) | 2021-01-08 | 2021-01-08 | Method and device for measuring output of oil pumping well |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114790885A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436319A (en) * | 2023-12-20 | 2024-01-23 | 中国石油大学(华东) | Oil pumping well production gas-oil ratio calculation method based on ground indicator diagram |
-
2021
- 2021-01-08 CN CN202110022441.1A patent/CN114790885A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436319A (en) * | 2023-12-20 | 2024-01-23 | 中国石油大学(华东) | Oil pumping well production gas-oil ratio calculation method based on ground indicator diagram |
| CN117436319B (en) * | 2023-12-20 | 2024-03-19 | 中国石油大学(华东) | Oil pumping well production gas-oil ratio calculation method based on ground indicator diagram |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6873519B1 (en) | Trajectory prediction method and system | |
| CN109379240B (en) | Internet of vehicles flow prediction model construction method and device and electronic equipment | |
| CN111379555B (en) | Fault diagnosis method and device for oil pumping well | |
| CN111768231A (en) | Product information recommendation method and device | |
| Chung et al. | Adaptive cloud offloading of augmented reality applications on smart devices for minimum energy consumption | |
| CN114790885A (en) | Method and device for measuring output of oil pumping well | |
| CN114492211A (en) | Residual oil distribution prediction method based on autoregressive network model | |
| CN108319749A (en) | A kind of method and device of determining indicator card | |
| CN111175817B (en) | Micro-seismic data-assisted compact oil and gas reservoir fracture distribution inversion method | |
| CN113627093A (en) | Underwater mechanism cross-scale flow field characteristic prediction method based on improved Unet network | |
| CN105683494A (en) | Pseudo phase production simulation: a signal processing approach to assess quasi-multiphase flow production via successive analogous step-function relative permeability controlled models in reservoir flow simulation in order to rank multiple petro-physical realizations | |
| CN115222583A (en) | Model training method and device, image processing method, electronic device and medium | |
| CN110486009B (en) | Automatic parameter reverse solving method and system for infinite stratum | |
| CN110486008B (en) | Parameter interpretation method and system for radial composite oil reservoir | |
| CN113255770B (en) | Training method of compound attribute prediction model and compound attribute prediction method | |
| CN115457598A (en) | Acupuncture point identification method and acupuncture point identification network | |
| CN110765680A (en) | Intelligent damage identification method and device for engineering structure and electronic equipment | |
| CN116008379B (en) | Automatic titration system, method and device based on model fitting and machine learning | |
| Zhao et al. | Research and Application of Rod Pump Working Condition Diagnosis and Virtual Production Metering Based on Electric Parameters | |
| CN111999331A (en) | Capillary pressure determination method and device based on nuclear magnetic test | |
| US20240133281A1 (en) | Calculation systems for predicting proppant embedding depth based on shale softening effect | |
| CN112541607B (en) | Volcanic oil reservoir productivity prediction method and device | |
| Chen et al. | Research and Application of Big Data Production Measurement Method for SRP Wells Based on Electrical Parameters | |
| CN117672378A (en) | Protein solubility prediction method, device, equipment and medium | |
| CN113624797A (en) | Method and device for detecting fluid in tight rock core |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |