CN113553539A - Oil well working condition identification and diagnosis system - Google Patents
Oil well working condition identification and diagnosis system Download PDFInfo
- Publication number
- CN113553539A CN113553539A CN202110839864.2A CN202110839864A CN113553539A CN 113553539 A CN113553539 A CN 113553539A CN 202110839864 A CN202110839864 A CN 202110839864A CN 113553539 A CN113553539 A CN 113553539A
- Authority
- CN
- China
- Prior art keywords
- module
- working condition
- pump
- diagram
- data acquisition
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 44
- 239000003129 oil well Substances 0.000 title claims abstract description 24
- 238000010586 diagram Methods 0.000 claims abstract description 77
- 238000004364 calculation method Methods 0.000 claims abstract description 36
- 239000007788 liquid Substances 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000005086 pumping Methods 0.000 claims abstract description 17
- 238000005259 measurement Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims abstract description 6
- 238000004519 manufacturing process Methods 0.000 claims description 39
- 238000012544 monitoring process Methods 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000006073 displacement reaction Methods 0.000 claims description 21
- 230000000694 effects Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 238000013461 design Methods 0.000 claims description 11
- 239000012530 fluid Substances 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000013016 damping Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 239000000725 suspension Substances 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000013135 deep learning Methods 0.000 abstract description 3
- 230000005284 excitation Effects 0.000 abstract description 2
- 239000000463 material Substances 0.000 abstract description 2
- 238000013178 mathematical model Methods 0.000 abstract description 2
- 230000004044 response Effects 0.000 abstract description 2
- 239000003921 oil Substances 0.000 description 12
- 238000000605 extraction Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- 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
-
- 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
- E21B47/008—Monitoring of down-hole pump systems, e.g. for the detection of "pumped-off" conditions
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Geology (AREA)
- Theoretical Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Geophysics (AREA)
- Marketing (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Pure & Applied Mathematics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Fluid Mechanics (AREA)
- Environmental & Geological Engineering (AREA)
- Geochemistry & Mineralogy (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides an oil well working condition identification and diagnosis system which comprises a comprehensive diagnosis system and a data acquisition end, wherein the data acquisition end acquires working condition information and transmits the working condition information to the comprehensive diagnosis system, and the comprehensive diagnosis system is processed and then visually displayed to a user; the data acquisition end comprises a ground indicator diagram and a ground data acquisition module. The invention establishes a mechanics and mathematical model of a pumping system of a sucker rod pump of a directional well, the model can calculate the pump diagram response of a given system under the excitation of different well head indicator diagrams, analyze the pump diagram, determine the effective stroke of the pump, further calculate the effective discharge capacity of ground conversion, and establish the calculation of key variables in the artificial lifting process of a pumping well with high precision and high operation speed by using the technologies of big data, deep learning and the like, including daily liquid yield prediction and 10 typical working condition identification, thereby reducing the consumption of a large amount of manpower, material resources and financial resources in the traditional artificial judgment and measurement, improving the oil field exploitation efficiency and saving the artificial cost.
Description
Technical Field
The invention relates to the technical field of oil wells, in particular to an oil well working condition identification and diagnosis system.
Background
In the mechanical oil extraction process, the sucker-rod pump oil extraction mode occupies an important position in the crude oil extraction in China. The current oil field widely adopts a maintenance strategy for the oil pumping well, namely, the oil pumping well is maintained when a certain fault causes the oil well not to be normally produced. Frequent pump detection not only causes yield loss, but also increases operation cost, and sometimes causes long operation waiting time of part of oil wells due to the reasons of service life, the limitation of the number of operation teams and the like, seriously affects the yield of the oil wells, and causes huge economic loss.
At present, under traditional management mode, oil well operating mode is judged and is measured by artifical judgement with the measurement, consumes a large amount of manpowers and financial resources, for the efficient improvement work efficiency more and practice thrift the cost of labor, according to current computer technology and big data statistics algorithm, carries out the high-efficient prediction of oil well liquid production volume and the high-efficient judgement overall plan of oil well operating mode. The existing indicator diagram oil measuring technology of the oil well: the comprehensive diagnosis method is based on the diagnosis of the working condition of the oil well and combines factors such as pump loss, pump fullness, gas influence and the like.
Disclosure of Invention
The invention aims to provide an oil well working condition identification and diagnosis system which can realize daily liquid yield prediction and oil well working condition diagnosis based on a single well and a single period and finally visually display monitoring data or a model calculation output result to a user.
In order to achieve the above purpose, the invention provides the following technical scheme: an oil well working condition identification and diagnosis system comprises a comprehensive diagnosis system and a data acquisition end, wherein the data acquisition end acquires working condition information and transmits the working condition information to the comprehensive diagnosis system, and the comprehensive diagnosis system is processed and then visually displayed to a user;
the data acquisition end comprises a ground indicator diagram and a ground data acquisition module;
the comprehensive diagnosis system comprises a working condition monitoring system, a remote video monitoring subsystem, a network browsing subsystem and a metering, analyzing and optimizing subsystem, wherein the working condition monitoring system comprises a data acquisition remote control module, information acquired by the ground indicator diagram and the ground acquisition data module is sent to the data acquisition remote control module, the remote video monitoring subsystem is respectively connected with the working condition monitoring system and the network browsing subsystem, and the metering, analyzing and optimizing subsystem is connected with the working condition monitoring system;
the metering, analyzing and optimizing subsystem comprises a dynamic model of the rod pumping system, and the dynamic model of the rod pumping system comprises a liquid production amount calculation flow module, a liquid production amount calculation data set module, a liquid production amount calculation model design module, a liquid production amount calculation model training and optimizing module, a liquid production amount calculation model prediction effect module, a working condition diagnosis data set module, a working condition diagnosis model design module, a working condition diagnosis training and optimizing module, a working condition diagnosis effect module and a model self-adaptive online learning module; the metering, analyzing and optimizing subsystem carries out fluid production amount calculation, fluid production amount analysis, pressure analysis, load analysis, pump efficiency analysis, system efficiency analysis, macroscopic control chart display, working condition analysis and optimization design, and the metering, analyzing and optimizing subsystem transmits the processed data to the network browsing subsystem;
the network browsing subsystem receives the measurement and analysis optimization subsystem to display the processed data to the user visually after processing.
Further, in the invention, the ground indicator diagram and the ground data acquisition module comprise data acquisition point equipment and a primary instrument, the data acquisition point equipment comprises a load sensor, a displacement sensor, a data acquisition controller, a data processing module, a communication module, a main control box, a data transmission radio and a high-gain antenna which are arranged at the wellhead of the pumping unit, and the primary instrument comprises a fixed load sensor, an angular displacement sensor, a motor monitoring module, a temperature sensor and a pressure sensor;
the ground indicator diagram and ground data acquisition module further comprises an RTU cabinet, an antenna feeder line and a cable.
Further, in the invention, the RTU cabinet comprises an RTU module, a data transmission radio station, a switch power supply, a wiring terminal and a case;
the antenna feeder comprises an omnidirectional antenna, a feeder, a crossover sub and a lightning arrester.
Further, in the invention, the calculation and processing of the downhole pump indicator diagram obtains the downhole pump supply diagram by solving the ground indicator diagram and the fluctuation equation;
and (3) establishing and solving a wave equation:
the propagation process of the stress wave in the sucker rod string can be described by the wave equation:
wherein U (x, t) -displacement of any section (x) of the sucker rod string at any time t; a-the propagation velocity of the stress wave in the sucker rod string; c-damping coefficient;
using suspension point dynamic load function D (T) and polish rod displacement function U (T) expressed by truncated Fourier series as boundary conditions:
the equation is solved by a separation variable method, and the change of the displacement of the X section of the sucker rod string at any depth along with the time can be obtained:
the change of the dynamic load function of the sucker rod string on the section of any depth x along with the time is as follows:
and (3) damping coefficient calculation:
further, in the present invention, the method further comprises a pump diagram quantitative processing, and the curvature model is established:
since the pump diagram curve is composed of a series of discrete points, the analytical function cannot be obtained, and the curvature of any point on the pump diagram cannot be directly obtained by the above formula. Approximating the circular arcs of the adjacent three points to a continuous curve to obtain the curvature K of each discrete point of the pump indicator diagram;
analyzing the effect condition of the quantitative processing pump for image supply, and establishing an adaptive data model support foundation for the model;
plunger effective stroke, downhole displacement and valve opening and closing point position determination in a pump indicator diagram:
calculating the coordinate average value of each point by using a five-point averaging method, namely:
secondly, respectively solving the maximum value Xmax and the minimum value Xmin of the abscissa and the maximum value Ymax and the minimum value Ymin of the ordinate of the discrete point of the pump diagram;
normalizing the discrete points, wherein the normalized expression is as follows:
expanding the normalized pump diagram along the plunger stroke, and changing the pump diagram from a closed curve to a single-value curve;
calculating the curvature value Ki of each discrete point according to a curvature calculation formula;
according to deltai=|Ki+1-KiL, solving the curvature of any discrete pointKi and the curvature variation delta i of the curvature Ki +1 of the subsequent discrete point;
to increase the accuracy of the algorithm according toCalculating the average value of the curvature change quantity by adopting a five-point method;
searching two points with the maximum curvature variation as the opening and closing points of the valve in the up and down strokes respectively, converting the effective stroke of the plunger by using a curvature pump model diagram, and integrating data to convert the downhole output;
and finally converting the liquid outlet quantity of the well head.
The beneficial effects are that the technical scheme of this application possesses following technological effect:
the invention establishes a mechanics and mathematical model of a directional well rod pump oil pumping system, the model can calculate the pump diagram response of a given system under the excitation of different well head indicator diagrams, analyze the pump diagram, determine the effective stroke of a pump, further calculate the effective discharge capacity of ground conversion, and establish the calculation of key variables in the artificial lifting process of an oil pumping well with high precision and high operation speed by using the technologies of big data, deep learning and the like, including daily liquid yield prediction and 10 typical working condition identification, thereby reducing the consumption of a large amount of manpower, material resources and financial resources for the traditional artificial judgment and measurement, further improving the oil field exploitation efficiency and saving the labor cost.
It should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below are contemplated as being part of the inventive subject matter of this disclosure unless such concepts are mutually inconsistent.
The foregoing and other aspects, embodiments and features of the present teachings can be more fully understood from the following description taken in conjunction with the accompanying drawings. Additional aspects of the present invention, such as features and/or advantages of exemplary embodiments, will be apparent from the description which follows, or may be learned by practice of specific embodiments in accordance with the teachings of the present invention.
Drawings
The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the present invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a schematic flow chart of the system of the present invention.
FIG. 2 is a diagram of the integrated diagnostic system of the present invention.
FIG. 3 is a table illustrating an example of data according to the present invention.
FIG. 4 is a schematic diagram of the oil measuring model of the present invention.
FIG. 5 is a diagram of a fusion construct of the present invention.
FIG. 6 is a graph showing the effect of calculating the amount of fluid produced according to the present invention.
FIG. 7 is a graph showing the effect of predicting the amount of fluid produced in a portion of a sample according to the present invention.
FIG. 8 is an exemplary graph of operating condition data according to the present invention.
FIG. 9 is an exemplary diagram of a condition diagnosis model according to the present invention.
FIG. 10 is a diagram of network structure and parameter configuration according to the model of the present invention.
FIG. 11 is a diagram illustrating the diagnostic effect of the model according to the present invention.
FIG. 12 is an exemplary diagram of the model online learning mechanism of the present invention.
Fig. 13 is an illustration of a well indicator diagram of the present invention.
FIG. 14 is a diagram illustrating the pump power supply measurement and conversion according to the present invention.
Fig. 15 is a graph for solving the curvature K.
Fig. 16 is a schematic diagram of the residual module and the bottleeck module of the present invention.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings. In this disclosure, aspects of the present invention are described with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily defined to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in greater detail below, may be implemented in any of numerous ways, as the disclosed concepts and embodiments are not limited to any implementation. In addition, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
The oil well working condition identification and diagnosis system shown in fig. 1-2 comprises a comprehensive diagnosis system and a data acquisition end, wherein the data acquisition end acquires working condition information and transmits the working condition information to the comprehensive diagnosis system, and the comprehensive diagnosis system is processed and then visually displayed to a user.
The data acquisition end comprises a ground indicator diagram and a ground data acquisition module.
The comprehensive diagnosis system comprises a working condition monitoring system, a remote video monitoring subsystem, a network browsing subsystem and a metering, analyzing and optimizing subsystem, wherein the working condition monitoring system comprises a data acquisition remote control module, information acquired by the ground indicator diagram and the ground acquisition data module is sent to the data acquisition remote control module, the remote video monitoring subsystem is respectively connected with the working condition monitoring system and the network browsing subsystem, and the metering, analyzing and optimizing subsystem is connected with the working condition monitoring system;
the metering, analyzing and optimizing subsystem comprises a dynamic model of the rod pumping system, and the dynamic model of the rod pumping system comprises a liquid production amount calculation flow module, a liquid production amount calculation data set module, a liquid production amount calculation model design module, a liquid production amount calculation model training and optimizing module, a liquid production amount calculation model prediction effect module, a working condition diagnosis data set module, a working condition diagnosis model design module, a working condition diagnosis training and optimizing module, a working condition diagnosis effect module and a model self-adaptive online learning module; the metering, analyzing and optimizing subsystem carries out fluid production amount calculation, fluid production amount analysis, pressure analysis, load analysis, pump efficiency analysis, system efficiency analysis, macroscopic control chart display, working condition analysis and optimization design, and the metering, analyzing and optimizing subsystem transmits the processed data to the network browsing subsystem;
the network browsing subsystem receives the measurement and analysis optimization subsystem to display the processed data to the user visually after processing.
In this embodiment, the ground indicator diagram and the ground data acquisition module include data acquisition point equipment and a primary instrument, the data acquisition point equipment includes a load sensor, a displacement sensor, a data acquisition controller, a data processing module, a communication module, a main control box, a data transmission radio station and a high-gain antenna, which are installed at a wellhead of the pumping unit, and the primary instrument includes a fixed load sensor, an angular displacement sensor, a motor monitoring module, a temperature sensor and a pressure sensor;
the ground indicator diagram and ground data acquisition module further comprises an RTU cabinet, an antenna feeder line and a cable.
In this embodiment, the RTU cabinet includes an RTU module, a data transmission station, a switching power supply, a terminal and a chassis;
the antenna feeder comprises an omnidirectional antenna, a feeder, a crossover sub and a lightning arrester. Dynamic model of sucker rod pumping system.
Wherein:
the liquid production amount calculating process module comprises the following steps:
firstly, data acquisition and pretreatment;
establishing an oil well liquid production amount calculation model according to the load and displacement data and by combining other related production data (stroke and stroke) of the oil well, realizing the daily liquid production amount prediction of a single well in a single period based on the sequence and providing real-time production condition information;
and thirdly, based on the average data of the single well per day, calculating the daily liquid production of the single well by using a liquid production calculation model.
A fluid production calculation dataset module, the dataset of which comprises:
data attribute: ground displacement, ground load, stroke and stroke frequency of a single well in a single day;
data label: the daily liquid yield;
data specification: the ground displacement and the ground load are 144 sequence points respectively, and the stroke frequency are scalar quantities;
data set: about 2 ten thousand data from 283 wells. An example table of data is shown in fig. 3.
Liquid production volume calculation model design module:
the main body of the liquid production amount calculation model is composed of a gate control cycle unit (GRU), belongs to one type of a cycle neural network (RNN), and the rear end fuses the time sequence characteristics extracted by the GRU with stroke frequency and stroke information through a full connection layer, so that the liquid production amount is calculated. Such as the architecture diagram of the oil metering model of fig. 4 and the fusion structure diagram of fig. 5.
The liquid production amount calculation model training and optimizing module comprises:
and adopting 10-fold cross validation to ensure the reliability of the experimental result. The learning rate for the training was set to 0.0001, the number of iterations was 500, and the batch size was set to 128. The model adopts Mean Squared Error (MSE for short) as an optimization target:
where n represents the number of samples and f represents the network model.
The network model parameter optimization algorithm adopts an adaptive moment estimation Adam method.
The liquid production amount calculation model prediction effect module:
dividing the test data into 3 intervals according to the size of the liquid production amount: [10, + ∞), [5, 10), (0, 5). The test results show that the predicted decision coefficients of the liquid production amounts of the 3 interval data are 0.942, 0.926 and 0.892 respectively. The comprehensive coefficient of decision of all interval data is 0.938, and a relatively high accuracy is achieved. The effect graph of the fluid production amount calculation of fig. 6 and the effect of the prediction of the fluid production amount of the partial sample of fig. 7 are shown.
A working condition diagnostic data set module: the data set includes:
data attribute: a ground indicator diagram image;
data label: 10 working conditions;
data specification: 224 x 224 pixels;
data set: about 22 thousand pieces of data. Such as the example plot of operating condition data of fig. 8.
A working condition diagnosis model design module:
the input of the model is a ground indicator diagram, and the output is a corresponding working condition code. And (3) constructing a working condition diagnosis model by using a Resnet50 residual error network. Because of the large volume of data sets, the use of residuals and the Bottlenet technique speeds up training and reduces parameters. Such as the example graph of the condition diagnostic model of fig. 9.
As shown in fig. 16, for the working condition diagnosis training and optimizing module, which includes a residual module and a bottletec k module, the residual structure of the model can effectively solve the problems of gradient disappearance and network degradation in deep learning. The model has four groups of residual error structures, each group is respectively provided with 3, 4, 6 and 3 Bottleneck modules, each B ottlneck module contains three convolution layers, and the sizes and the numbers of convolution kernels are different. Such as the model network structure and parameter setting diagram of fig. 10.
The working condition diagnosis effect module:
the test result shows that the model prediction accuracy reaches 92.4%. Such as the model diagnostic effect example of fig. 11. The model self-adaptive online learning module: such as the model online learning mechanism example diagram of fig. 12.
A downhole pumping diagram.
(1) Calculating a pump diagram:
sucker rod string-the conducting wire of downhole dynamic signal.
Oil pump-transmitter.
The working condition of the pump (load change on the plunger) is transmitted to the ground along the sucker rod string in the form of stress wave, and is received by the dynamometer as a receiver, so that the required indicator diagram of each section of the sucker rod and the pump can be obtained. And solving a downhole pump supply diagram through a ground indicator diagram-wave equation. As illustrated in the well indicator diagram of fig. 13.
(2) And (3) establishing and solving a wave equation:
the propagation process of the stress wave in the sucker rod string can be described by the wave equation:
wherein U (x, t) -displacement of any section (x) of the sucker rod string at any time t; a-the propagation velocity of the stress wave in the sucker rod string; c-damping coefficient.
Using suspension point dynamic load function D (T) and polish rod displacement function U (T) expressed by truncated Fourier series as boundary conditions:
the equation is solved by a separation variable method, and the change of the displacement of the X section of the sucker rod string at any depth along with the time can be obtained:
the change of the dynamic load function of the sucker rod string on the section of any depth x along with the time is as follows:
and (3) damping coefficient calculation:
4. and (5) quantitatively processing the pump diagram.
(1) Establishing a curvature model:
curvature K is defined as the rate of change of the included angle α to the radian S:
since the pump diagram curve is composed of a series of discrete points, the analytical function cannot be obtained, and the curvature of any point on the pump diagram cannot be directly obtained by the above formula. Approximating the circular arcs of the adjacent three points to a continuous curve to obtain the curvature K of each discrete point of the pump indicator diagram, such as the curvature K solving diagram of fig. 15:
and analyzing the effect condition of the quantitative processing pump for image supply, and establishing an adaptive data model support foundation for the model.
5. Plunger active stroke, downhole displacement.
(1) Determining the position of a valve opening and closing point in a pump indicator diagram:
calculating the coordinate average value of each point by using a five-point averaging method, namely:
secondly, respectively solving the maximum value Xmax and the minimum value Xmin of the abscissa and the maximum value Ymax and the minimum value Ymin of the ordinate of the discrete point of the pump diagram;
normalizing the discrete points, wherein the normalized expression is as follows:
expanding the normalized pump diagram along the plunger stroke, and changing the pump diagram from a closed curve to a single-value curve;
calculating the curvature value Ki of each discrete point according to a curvature calculation formula;
according to deltai=|Ki+1-KiCalculating the curvature variation of the curvature Ki of any discrete point and the curvature Ki +1 of the next discrete pointδi;
To increase the accuracy of the algorithm according toCalculating the average value of the curvature variation by adopting a five-point method;
and searching two points with the maximum curvature variation as the opening and closing points of the valve in the up and down strokes. The pump supply diagram calculation conversion diagram shown in fig. 14 is used, a curvature pump model diagram is used, the effective stroke of the plunger is converted, and the data is integrated to convert the downhole discharge capacity. And finally converting the liquid outlet quantity of the well head.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention should be determined by the appended claims.
Claims (5)
1. An oil well working condition identification and diagnosis system is characterized in that: the comprehensive diagnosis system comprises a comprehensive diagnosis system and a data acquisition end, wherein the data acquisition end acquires working condition information and transmits the working condition information to the comprehensive diagnosis system, and the comprehensive diagnosis system is processed and then visually displayed to a user;
the data acquisition end comprises a ground indicator diagram and a ground data acquisition module;
the comprehensive diagnosis system comprises a working condition monitoring system, a remote video monitoring subsystem, a network browsing subsystem and a metering, analyzing and optimizing subsystem, wherein the working condition monitoring system comprises a data acquisition remote control module, the ground indicator diagram and the ground acquisition data module acquire information and send the information to the data acquisition remote control module, the remote video monitoring subsystem is respectively connected with the working condition monitoring system and the network browsing subsystem, and the metering, analyzing and optimizing subsystem is connected with the working condition monitoring system;
the metering, analyzing and optimizing subsystem comprises a dynamic model of the rod pumping system, and the dynamic model of the rod pumping system comprises a liquid production amount calculation flow module, a liquid production amount calculation data set module, a liquid production amount calculation model design module, a liquid production amount calculation model training and optimizing module, a liquid production amount calculation model prediction effect module, a working condition diagnosis data set module, a working condition diagnosis model design module, a working condition diagnosis training and optimizing module, a working condition diagnosis effect module and a model self-adaptive online learning module; the metering, analyzing and optimizing subsystem carries out fluid production amount calculation, fluid production amount analysis, pressure analysis, load analysis, pump efficiency analysis, system efficiency analysis, macro control chart display, working condition analysis and optimization design, and the metering, analyzing and optimizing subsystem transmits the processed data to the network browsing subsystem;
the network browsing subsystem receives the measurement and analysis optimization subsystem to display the processed data to the user visually after processing.
2. The system for identifying and diagnosing the working conditions of the oil well as claimed in claim 1, wherein: the ground indicator diagram and ground data acquisition module comprises data acquisition point equipment and a primary instrument, wherein the data acquisition point equipment comprises a load sensor, a displacement sensor, a data acquisition controller, a data processing module, a communication module, a main control box, a data transmission radio and a high-gain antenna which are arranged at the wellhead of the oil pumping unit, and the primary instrument comprises a fixed load sensor, an angular displacement sensor, a motor monitoring module, a temperature sensor and a pressure sensor;
the ground indicator diagram and ground data acquisition module further comprises an RTU cabinet, an antenna feeder line and a cable.
3. The system for identifying and diagnosing the working conditions of the oil well as claimed in claim 2, wherein: the RTU cabinet comprises an RTU module, a data transmission radio station, a switching power supply, a wiring terminal and a case;
the antenna feeder comprises an omnidirectional antenna, a feeder, a crossover sub and a lightning arrester.
4. The system for identifying and diagnosing the working conditions of the oil well as claimed in claim 1, wherein: the underground pump power supply diagram is obtained by calculating and processing the underground pump power diagram through solving the ground power diagram and the wave equation;
and (3) establishing and solving a wave equation:
the propagation process of the stress wave in the sucker rod string can be described by the wave equation:
wherein U (x, t) -displacement of any section (x) of the sucker rod string at any time t; a-the propagation velocity of the stress wave in the sucker rod string; c-damping coefficient;
using suspension point dynamic load function D (T) and polish rod displacement function U (T) expressed by truncated Fourier series as boundary conditions:
the equation is solved by a separation variable method, and the change of the displacement of the X section of the sucker rod string at any depth along with the time can be obtained:
the change of the dynamic load function of the sucker rod string on the section of any depth x along with the time is as follows:
and (3) damping coefficient calculation:
5. the system for identifying and diagnosing the working conditions of the oil well as claimed in claim 4, wherein: the method further comprises the steps of pump diagram quantitative processing and curvature model establishment:
since the pump diagram curve is composed of a series of discrete points, the analytical function cannot be obtained, and the curvature of any point on the pump diagram cannot be directly obtained by the above formula. Approximating the circular arcs of the adjacent three points to a continuous curve to obtain the curvature K of each discrete point of the pump indicator diagram;
analyzing the effect condition of the quantitative processing pump for image supply, and establishing an adaptive data model support foundation for the model;
plunger effective stroke, downhole displacement and valve opening and closing point position determination in a pump indicator diagram:
calculating the coordinate average value of each point by using a five-point averaging method, namely:
secondly, respectively solving the maximum value Xmax and the minimum value Xmin of the abscissa and the maximum value Ymax and the minimum value Ymin of the ordinate of the discrete point of the pump diagram;
normalizing the discrete points, wherein the normalized expression is as follows:
expanding the normalized pump diagram along the plunger stroke, and changing the pump diagram from a closed curve to a single-value curve;
calculating the curvature value Ki of each discrete point according to a curvature calculation formula;
according to deltai=|Ki+1-KiSolving the curvature Ki of any discrete point and the curvature variation delta i of the curvature Ki +1 of the next discrete point;
to increase the accuracy of the algorithm according toCalculating the average value of the curvature variation by adopting a five-point method;
searching two points with the maximum curvature variation as the opening and closing points of the valve in the up and down strokes respectively, converting the effective stroke of the plunger by using a curvature pump model diagram, and integrating data to convert the downhole output;
and finally converting the liquid outlet quantity of the well head.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110839864.2A CN113553539A (en) | 2021-07-24 | 2021-07-24 | Oil well working condition identification and diagnosis system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110839864.2A CN113553539A (en) | 2021-07-24 | 2021-07-24 | Oil well working condition identification and diagnosis system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113553539A true CN113553539A (en) | 2021-10-26 |
Family
ID=78104432
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110839864.2A Pending CN113553539A (en) | 2021-07-24 | 2021-07-24 | Oil well working condition identification and diagnosis system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113553539A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114382447A (en) * | 2021-12-31 | 2022-04-22 | 大庆富兴达石油科技有限公司 | Intelligent control method and device for intermittent pumping of pumping unit |
-
2021
- 2021-07-24 CN CN202110839864.2A patent/CN113553539A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114382447A (en) * | 2021-12-31 | 2022-04-22 | 大庆富兴达石油科技有限公司 | Intelligent control method and device for intermittent pumping of pumping unit |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106761681B (en) | Electric pump well fault real-time diagnosis system and method based on time sequence data analysis | |
CN106761668B (en) | Oil well failure intelligent analysis decision system and method | |
Li et al. | A novel prediction method for down-hole working conditions of the beam pumping unit based on 8-directions chain codes and online sequential extreme learning machine | |
CN107305601B (en) | Method for analyzing efficiency factors of oil pumping well system | |
CN106682815B (en) | Monitoring system and monitoring method for pumping well | |
CN107977749A (en) | A kind of prediction analysis method of oilfield development indexes | |
Zheng et al. | Sucker rod pump working state diagnosis using motor data and hidden conditional random fields | |
CN104213904A (en) | Method for monitoring efficiency of rod oil pumping system in real time | |
CN113553539A (en) | Oil well working condition identification and diagnosis system | |
CN110288257A (en) | A kind of depth transfinites indicator card learning method | |
CN113137211B (en) | Oil well production parameter self-adaptive control method based on fuzzy comprehensive decision | |
CN109441548A (en) | Intelligent fully-mechanized mining equipment | |
CN102268989A (en) | Method and system for acquiring online real-time data of working fluid level of pumping well | |
CN112664184A (en) | Pumping unit well pump detection period prediction method based on support vector regression algorithm | |
CN112664185A (en) | Indicator diagram-based rod-pumped well working condition prediction method | |
Zhang et al. | A real-time diagnosis method of reservoir-wellbore-surface conditions in sucker-rod pump wells based on multidata combination analysis | |
CN112836856A (en) | Polynomial regression algorithm-based pumping unit water drive well pump detection period prediction method | |
CN111271049B (en) | Method for identifying filling degree of sucker rod pumping well | |
CN115929279B (en) | Plate analysis method for judging interference intensity under mining balance | |
CN206722821U (en) | Electric pump well fault real-time diagnosis system based on time series data analysis | |
CN114810037A (en) | Oil pumping well fault discrimination method based on data driving | |
CN113627069A (en) | Well testing dynamic yield evaluation method and system for fracture-cavity type oil reservoir oil and gas well | |
CN115726764A (en) | Electric pump well fault diagnosis system and method based on fuzzy logic | |
CN110428095A (en) | A kind of offshore oilfield long-medium term power load forecasting method | |
CN110043228A (en) | A kind of oil pumping unit well field intelligent management work station |
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 |