CN116822086A - Method for intelligently converting working fluid level by pump diagram - Google Patents
Method for intelligently converting working fluid level by pump diagram Download PDFInfo
- Publication number
- CN116822086A CN116822086A CN202310782845.XA CN202310782845A CN116822086A CN 116822086 A CN116822086 A CN 116822086A CN 202310782845 A CN202310782845 A CN 202310782845A CN 116822086 A CN116822086 A CN 116822086A
- Authority
- CN
- China
- Prior art keywords
- diagram
- working fluid
- fluid level
- pump work
- plunger
- 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
- 238000010586 diagram Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 39
- 239000012530 fluid Substances 0.000 title claims abstract description 38
- 239000007788 liquid Substances 0.000 claims abstract description 38
- 239000003129 oil well Substances 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 4
- 239000000725 suspension Substances 0.000 claims description 48
- 238000006073 displacement reaction Methods 0.000 claims description 45
- 230000014509 gene expression Effects 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000013016 damping Methods 0.000 claims description 14
- 238000007637 random forest analysis Methods 0.000 claims description 12
- 238000005086 pumping Methods 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 10
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method for intelligently converting a working fluid level by a pump diagram, which is characterized by comprising the following steps of: s1: collecting an indicator diagram of an oil well; s2: preprocessing the indicator diagram; s3: establishing a pump work diagram model, and acquiring the converted working fluid level data of the pump work diagram; s4: performing error calibration processing on the converted dynamic liquid level data to obtain a new pump work diagram; s5: and carrying out working condition identification on the new pump work diagram to obtain the converted working fluid level data of the final oil well. According to the application, the electric diagram of the oil well is converted into the pump diagram, and then error calibration is carried out, so that deviation caused by unbalanced data of the pump diagram is reduced, and stable and accurate converted working fluid level data is obtained.
Description
Technical Field
The application relates to the field of digital and oil extraction processes, and discloses a method for intelligently converting a working fluid level by using an electric diagram.
Background
At present, the oil field is deepened along with the continuous construction of the Internet of things, a large amount of data is monitored and analyzed based on a system platform of the Internet of things, the comprehensive perception of a production well is basically realized, the continuous accumulation of the data is complete, and the oil field construction is advanced from a digital oil field to an intelligent oil field.
The traditional method has the advantages that the oil well measuring working fluid level is tested through the artificial echo instrument, the operation workload is large, the period is long, the method is not suitable for the real-time analysis requirement of the digital oil field, so that most oil fields currently adopt the indicator diagram to measure the working fluid level, but the indicator diagram is not more accurate than the pump indicator diagram, so that along with the continuous popularization of the Internet of things for oil and gas production, the application value of the Internet of things data is further excavated, the production dynamic management level is improved, and the method for intelligently converting the working fluid level by the pump indicator diagram is needed to be researched.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the present application proposes a technical solution of the present application, comprising:
s1: collecting an indicator diagram of an oil well;
s2: preprocessing the indicator diagram;
s3: establishing a pump work diagram model, and acquiring the converted working fluid level data of the pump work diagram;
s4: performing error calibration processing on the converted dynamic liquid level data to obtain a new pump work diagram;
s5: and carrying out working condition identification on the new pump work diagram to obtain the converted working fluid level data of the final oil well.
Preferably, the preprocessing of S2 includes: dividing the indicator diagram into binary images of 26 multiplied by 52 grids, setting the grid assignment of the curve to be 1, and setting the network assignment of the curve which does not pass to be 0.
Preferably, the creating the pump diagram model of S3 includes: and establishing a sucker rod column mechanical model to obtain a sucker rod column mathematical model, establishing a sucker rod column motion differential equation, obtaining plunger displacement and plunger liquid load through the sucker rod column motion differential equation, and drawing a pump work diagram by taking the plunger displacement as an abscissa and the plunger liquid load as an ordinate.
Preferably, the sucker rod string is reduced to a mass-spring-damping system, the mass nodes are connected to each other by springs, the upper ends are connected at the pumping unit suspension points, the lower ends are excited by the plunger liquid load, and are limited to longitudinal vibration in the vertical plane.
Preferably, the establishing a differential equation of motion of the sucker rod string comprises: taking the displacement x of the mass node of the sucker rod from the balance position as a generalized coordinate, and adopting the following formula:
{x}＝[x 1 ，x 2 ，…，x j ] T
the formula of the plunger liquid load applied to the mass node of the sucker rod is as follows:
{P}＝[0，0，…，P P () T
and then establishing a sucker rod string motion differential equation through a sucker rod string mechanical model, wherein the equation is as follows:
in the formula Is a structural total node acceleration array under generalized coordinates, < +.>The method is characterized in that the method is a structural total node speed array under the generalized coordinates, { m } is a structural total node mass array under the generalized coordinates, and { c } is a structural total node oil damping array under the generalized coordinates.
Preferably, the plunger displacement comprises: the differential equation of the sucker rod string motion contains static coupling and dynamic coupling, and the principal coordinates are converted into regular coordinates, so that { x } = [ U ]]{ θ } is substituted into the equation, the equation can be decoupled and multiplied by [ U ]] T The orthogonality of the mass matrix and the stiffness matrix is utilized to divide the equation into r single-degree-of-freedom motion differential equations which are not coupled with each other, and the matrix form is as follows:
in the formula ,acceleration array for total node, +.>Velocity array for summary points, { θ } for summary point displacement array, [ C ] N ]Regular diagonal matrix for damping oil liquid>The diagonal matrix which is the square of the natural frequency, { e } is a preset value, and the Fourier coefficient constant term and [ U ] in the liquid load expression of the plunger are used for calculating the characteristic frequency of the plunger]Corresponding to the elements in the two groups;
and obtaining plunger displacement according to the single-degree-of-freedom motion differential equation, wherein the formula is as follows:
where { q } is the actual displacement of each node of the sucker rod string, [ U ]]Is a regular vibration matrix, and { θ } is the displacement of each node,The last element of the suspension displacement, { q }, is the plunger displacement.
Preferably, the plunger liquid load comprises: and (3) providing a Fourier series expression of the suspension point load according to the known data of the suspension point load at different operation moments of the pumping unit in combination with a Fourier series method, wherein the Fourier series expression is as follows:
wherein ,
calculating a suspension point load by the displacement of the first node of the sucker rod string and the known suspension point displacement, making the fitted suspension point load equal to the calculated suspension point load, and obtaining various Fourier coefficients in a plunger liquid load expression, thereby obtaining a Fourier series expression of the plunger liquid load, and calculating the suspension point load:
PRL＝k e (x A -q 1 )+G’ rod
in the formula ,G’rod ＝(ρ i -ρ f )A i L i g、G’ rod Is the dead weight of the pole column in the oil liquid and ρ f Is the oil density.
Preferably, the error calibration process of S4 includes: correcting the converted working fluid level data of the pump work diagram through ADASYN, firstly distributing different sampling multiplying powers according to data samples of the pump work diagram, and synthesizing different numbers of samples around samples with different characteristics, wherein the formula is as follows:
m i ＝x i +γ(x si -x i )
in the formula ,xi For the sample to be synthesized, x si For the neighbor samples of the sample to be synthesized, γ is a preset constant,
γ∈[0，1]。
preferably, the S5 includes: and taking the data of the new pumping diagram as the data of the working condition identification model based on the random forest classification of the gray matrix, extracting the characteristic value of the data, and classifying the data by adopting the random forest classification to obtain the converted working fluid level data of the final oil well.
Preferably, the random forest classification includes: in the random forest classification method, the number mtry of the attributes in classification in the network model is set to be 5, and the number ntree of the decision trees is set to be 150.
The beneficial effects are that:
the method for intelligently converting the working fluid level of the pump work diagram is based on the real-time indicator work diagram and the basic data of the oil well sucker rod string, converts the basic data into the pump work diagram according to a theoretical formula, calculates the converted working fluid level, and then calculates the accurate working fluid level through the calibration of special working condition treatment, and the method is simple and easy to implement, does not increase the existing development cost, and is a new method for calculating the working fluid level of the oil well.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the present application;
FIG. 2 is a schematic diagram of the preprocessing of an indicator diagram in accordance with a preferred embodiment of the present application;
FIG. 3 is a schematic view of a mechanical model of a preferred embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a node force analysis according to a preferred embodiment of the present application;
FIG. 5 is a schematic diagram of an error calibration process according to a preferred embodiment of the present application;
FIG. 6 is a schematic diagram illustrating the condition recognition according to a preferred embodiment of the present application.
Detailed Description
The following examples of the present application are described in detail, and are given by way of illustration of the present application, but the scope of the present application is not limited to the following examples.
The application designs a method for intelligently converting a working fluid level by a pump work diagram, which comprises the following steps, as shown in fig. 1, of:
s1: collecting an indicator diagram of an oil well;
s2: preprocessing the indicator diagram;
s3: establishing a pump work diagram model, and acquiring the converted working fluid level data of the pump work diagram;
s4: performing error calibration processing on the converted dynamic liquid level data to obtain a new pump work diagram;
s5: and (3) identifying the working condition of the new pump diagram to obtain the converted working fluid level data of the final oil well.
Specifically, an indicator diagram is acquired through intelligent acquisition equipment arranged at a wellhead (the indicator diagram is a curve diagram of displacement-suspension point load pair drawn by reciprocating motion at a suspension point when the rod-type pumping unit works, and the shape indirectly reflects the working condition of an oil well).
Preprocessing the indicator diagram data, dividing the indicator diagram into binary images of 26 multiplied by 52 grids as shown in fig. 2, assigning 1 to the grids passing through the curve, and assigning 0 to the grids not passing through the curve; for better implementation of the representation and analysis of the indicator diagram.
And converting the displacement and load time sequence of the indicator diagram into Fourier series, then assuming the plunger liquid load as Fourier series containing undetermined coefficients, simplifying the vertical well sucker rod string into a mass-spring-damping system, establishing a differential equation of the motion of the sucker rod string, obtaining the plunger displacement and the plunger liquid load, and drawing the pump diagram by taking the plunger displacement as an abscissa and the plunger liquid load as an ordinate. .
Specifically, as shown in fig. 3, the dynamic analysis is performed on the mass node, a multi-degree-of-freedom motion differential equation set of the vertical column is built, and then the corresponding fourier expression is built on the suspension point displacement, the suspension point speed, the suspension point acceleration and the plunger liquid load by using the fourier series method. Wherein each node is subjected to the elastic force of two adjacent springs, the oil damping force and the tension of the suspension point, and only the lowest node is subjected to the plunger liquid load. (assuming equal damping coefficient of oil throughout the rod string, isotropy of the rod string, neglecting slip of the ground motor)
x A The displacement (m) of the suspension point at any moment; k (k) e Equivalent spring rate (N/m) for suspension system; l (L) 1 Length (m) of the first stage pole; l (L) 2 Is the length of the second-stage pole; l (L) 3 Is the third stage stem length (m); e (E) 1 ，A 1 The first-stage column elastic modulus (Pa) and the cross-sectional area (m) 2 )；E 2 ，A 2 The second-stage column elastic modulus (Pa) and the cross-sectional area (m) 2 )；E 3 ，A 3 The third-stage column elastic modulus (Pa) and the cross-sectional area (m) 2 )。
The sucker rod string is then simplified into a mass-spring-damping system, the mass nodes are connected to each other by springs, the upper ends are connected to the suspension point of the pumping unit, the lower ends are excited by the liquid load of the plunger, and the sucker rod string is limited to longitudinally vibrating on a vertical plane, and the displacement x of the mass nodes from the balance position is taken as a generalized coordinate, and the formula is as follows:
{x}＝[x 1 ，x 2 ，…，x j ] T
except for the lowest node, each node receives 4 forces, namely the elastic force acted by two adjacent springs of the node, the oil damping force and the suspension point tension, wherein the formula of the plunger liquid load received by each node is as follows:
{P}＝[0，0，…，P P () T
as shown in fig. 4, the multi-degree-of-freedom motion differential of the sucker rod string can be obtained according to the stress analysis of a single node as follows:
in the formula Is a structural total node acceleration array under generalized coordinates, < +.>The method is characterized in that the method is a structural total node speed array under the generalized coordinates, { m } is a structural total node mass array under the generalized coordinates, and { c } is a structural total node oil damping array under the generalized coordinates.
The known data of the suspension point displacement at different running moments of the pumping unit are utilized, the Fourier series expression of the suspension point displacement can be given by combining the Fourier series method, the Fourier series expression of the suspension point displacement can be obtained by respectively solving the first derivative and the second derivative of the time of the Fourier series expression of the suspension point displacement, the suspension point speed and the suspension point acceleration can be obtained, the plunger liquid load data is unknown, and the plunger liquid load expression can be assumed by utilizing the Fourier series method. The fourier series expressions of the suspension point displacement, suspension point speed, suspension point acceleration and plunger liquid load are as follows:
suspension point displacement, suspension point speed and suspension point acceleration Fourier series expressionFourier coefficient a of (a) n 、b n As shown in the following formula, (Fourier coefficient e in Fourier series expression of plunger liquid load) n 、f n Will be found in the above formula):
wherein T is the operation period(s) and omega of the pumping unit 0 Is the average angular velocity (rad/s) of crank rotation,Is the number of truncated fourier series.
m i，j A mass (kg) of a j-th node of the i-th column; x is x i，j A relative displacement (m) of a j-th node of the i-th stage column; c i，j An oil damping coefficient (1/s) of a j-th node of the i-th pole; k (k) i，j Spring rate (N/m) for the j-th node of the i-th stage post; p (P) P(t) Is the plunger load (N).
The differential equation of the sucker rod string motion contains static coupling and dynamic coupling, and the principal coordinates are converted into regular coordinates, so that { x } = [ U ]]{ θ } is substituted into the equation, the equation can be decoupled and multiplied by [ U ]] T The orthogonality of the mass matrix and the rigidity matrix is utilized to divide the equation into r single-degree-of-freedom motion differential equations which are not coupled with each other, and the matrix form is as follows:
wherein ,
in the formula ,acceleration array for total node, +.>Velocity array for summary points, { θ } for summary point displacement array, [ C ] N ]Regular diagonal matrix for damping oil liquid>The diagonal matrix which is the square of the natural frequency, { e } is a preset value, and the Fourier coefficient constant term and [ U ] in the liquid load expression of the plunger are used for calculating the characteristic frequency of the plunger]Corresponding to the elements in the two groups;
the plunger displacement is obtained according to a single degree of freedom motion differential equation, and the formula is as follows:
where { q } is the actual displacement of each node of the sucker rod string, [ U ]]Is a regular vibration matrix, and { θ } is the displacement of each node,The last element of the suspension displacement, { q }, is the plunger displacement.
And then, a Fourier series expression of the suspension point load is given by combining the known data of the suspension point load at different running moments of the pumping unit with a Fourier series method, wherein the Fourier series expression is as follows:
wherein ,
calculating a suspension point load by the displacement of the first node of the sucker rod string and the known suspension point displacement, making the fitted suspension point load equal to the calculated suspension point load, and obtaining various Fourier coefficients in a plunger liquid load expression, thereby obtaining a Fourier series expression of the plunger liquid load, and calculating the suspension point load:
PRL＝k e (x A -q 1 )+G’ rod
wherein ,G’rod ＝(ρ i -ρ f )A i L i g; in the formula, G' rod Is the dead weight (N) and ρ of the pole in the oil f Is oil density (kg/m) 3 )。
Characteristic working condition error calibration: as shown in fig. 5, the working fluid level data of the pump work diagram is corrected by ADASYN to reduce the deviation caused by unbalanced data, firstly, different sampling multiplying powers are allocated according to the data samples of the pump work diagram, and different numbers of samples are synthesized around the samples with different characteristics, wherein the formula is as follows:
m i ＝x i +γ(x si -x i )
in the formula ,xi For the sample to be synthesized, x si For the neighbor samples of the sample to be synthesized, gamma is a preset constant, gamma is 0,1]；
As shown in fig. 6, the pump diagram data after the working fluid level error is calibrated is used as the data of the working condition identification model based on the random forest classification of the gray matrix, the characteristic value is extracted, then the random forest classification (the random forest classification method uses the number mtry of the attributes in the classification attribute in the random forest working condition identification network model to be set as 5, and the number ntree of the decision tree to be set as 150) is adopted to classify the working condition identification model, the result of the characteristic working condition identification is obtained, and the result can be output after the technical scheme is completed, so that the calculation is completed.
The foregoing describes in detail preferred embodiments of the present application. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the application without requiring creative effort by one of ordinary skill in the art. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by a person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (10)
1. The method for intelligently converting the working fluid level of the pump work diagram is characterized by comprising the following steps of:
s1: collecting an indicator diagram of an oil well;
s2: preprocessing the indicator diagram;
s3: establishing a pump work diagram model, and acquiring the converted working fluid level data of the pump work diagram;
s4: performing error calibration processing on the converted dynamic liquid level data to obtain a new pump work diagram;
s5: and carrying out working condition identification on the new pump work diagram to obtain the converted working fluid level data of the final oil well.
2. The method for intelligently converting the working fluid level of a pump work diagram according to claim 1, wherein the pretreatment of the step S2 comprises the following steps:
dividing the indicator diagram into binary images of 26 multiplied by 52 grids, setting the grid assignment of the curve to be 1, and setting the network assignment of the curve which does not pass to be 0.
3. The method for intelligently converting the working fluid level into the pump work diagram according to claim 1, wherein the step of establishing the pump work diagram model in the step of S3 comprises the following steps:
and establishing a mechanical model of the sucker rod column to obtain a mathematical model of the sucker rod column, obtaining plunger displacement and plunger liquid load through a differential equation of motion of the sucker rod column, and drawing a pump work diagram by taking the plunger displacement as an abscissa and the plunger liquid load as an ordinate.
4. A method for intelligently converting a working fluid level in a pump diagram according to claim 3, comprising:
the sucker rod string is simplified into a mass-spring-damping system, mass nodes are connected with each other by springs, the upper ends of the mass nodes are connected at the suspension point of the pumping unit, the lower ends of the mass nodes are excited by the liquid load of the plunger, and the mass nodes are limited to longitudinally vibrating on a vertical plane.
5. A method for intelligently converting a pump work pattern into a working fluid according to claim 3, wherein said establishing a differential equation of motion of the sucker rod string comprises:
taking the displacement x of the mass node of the sucker rod from the balance position as a generalized coordinate, and adopting the following formula:
{x}＝[x 1 ，x 2 ，…，x j ] T
the formula of the plunger liquid load applied to the mass node of the sucker rod is as follows:
{P}＝[0，0，…，P P () T
and then establishing a sucker rod string motion differential equation through a sucker rod string mechanical model, wherein the equation is as follows:
in the formula Is a structural total node acceleration array under generalized coordinates, < +.>The method is characterized in that the method is a structural total node speed array under the generalized coordinates, { m } is a structural total node mass array under the generalized coordinates, and { c } is a structural total node oil damping array under the generalized coordinates.
6. A method of intelligently translating a working fluid level for a pump work pattern according to claim 3 wherein said plunger displacement comprises:
the differential equation of the sucker rod string motion contains static coupling and dynamic coupling, and the principal coordinates are converted into regular coordinates, so that { x } = [ U ]]{ θ } is substituted into the equation, the equation can be decoupled and multiplied by [ U ]] T The orthogonality of the mass matrix and the stiffness matrix is utilized to divide the equation into r single-degree-of-freedom motion differential equations which are not coupled with each other, and the matrix form is as follows:
in the formula ,acceleration array for total node, +.>Velocity array for summary points, { θ } for summary point displacement array, [ C ] N ]Regular diagonal matrix for damping oil liquid>The diagonal matrix which is the square of the natural frequency, { e } is a preset value, and the Fourier coefficient constant term and [ U ] in the liquid load expression of the plunger are used for calculating the characteristic frequency of the plunger]Corresponding to the elements in the two groups;
and obtaining plunger displacement according to the single-degree-of-freedom motion differential equation, wherein the formula is as follows:
where { q } is the actual displacement of each node of the sucker rod string, [ U ]]Is a regular vibration matrix, and { θ } is the displacement of each node,The last element of the suspension displacement, { q }, is the plunger displacement.
7. A method of intelligently translating a working fluid level for a pump work pattern according to claim 3 wherein said plunger fluid load comprises:
and (3) providing a Fourier series expression of the suspension point load according to the known data of the suspension point load at different operation moments of the pumping unit in combination with a Fourier series method, wherein the Fourier series expression is as follows:
wherein ,
calculating a suspension point load by the displacement of the first node of the sucker rod string and the known suspension point displacement, making the fitted suspension point load equal to the calculated suspension point load, and obtaining various Fourier coefficients in a plunger liquid load expression, thereby obtaining a Fourier series expression of the plunger liquid load, and calculating the suspension point load:
PRL＝k e (x A -q 1 )+G’ rod
in the formula ,G’rod ＝(ρ i -ρ f )A i L i g、G’ rod Is the dead weight of the pole column in the oil liquid and ρ f Is the oil density.
8. The method for intelligently converting a working fluid level into a pump diagram according to claim 1, wherein the error calibration process of S4 comprises:
correcting the converted working fluid level data of the pump work diagram through ADASYN, firstly distributing different sampling multiplying powers according to data samples of the pump work diagram, and synthesizing different numbers of samples around samples with different characteristics, wherein the formula is as follows:
m i ＝x i +γ(x si -x i )
in the formula ,xi For the sample to be synthesized, x si For the neighbor samples of the sample to be synthesized, gamma is a preset constant, gamma is 0,1]。
9. The method for intelligently converting a working fluid level into a pump diagram according to claim 1, wherein S5 comprises:
and taking the data of the new pumping diagram as the data of the working condition identification model based on the random forest classification of the gray matrix, extracting the characteristic value of the data, and classifying the data by adopting the random forest classification to obtain the converted working fluid level data of the final oil well.
10. The method for intelligently converting a pump work pattern into a working fluid according to claim 9, wherein said random forest classification comprises:
in the random forest classification method, the number mtry of the attributes in classification in the network model is set to be 5, and the number ntree of the decision trees is set to be 150.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310782845.XA CN116822086A (en) | 2023-06-29 | 2023-06-29 | Method for intelligently converting working fluid level by pump diagram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310782845.XA CN116822086A (en) | 2023-06-29 | 2023-06-29 | Method for intelligently converting working fluid level by pump diagram |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116822086A true CN116822086A (en) | 2023-09-29 |
Family
ID=88112271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310782845.XA Pending CN116822086A (en) | 2023-06-29 | 2023-06-29 | Method for intelligently converting working fluid level by pump diagram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822086A (en) |
-
2023
- 2023-06-29 CN CN202310782845.XA patent/CN116822086A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105257277B (en) | Dlagnosis of Sucker Rod Pumping Well underground failure prediction method based on Multi-variable Grey Model | |
| CN111946329B (en) | Method for solving working fluid level of oil well | |
| CN112417954A (en) | Bearing fault mode diagnosis method and system for small sample data set | |
| CN104481496B (en) | Fault diagnosis method of sucker-rod pump well | |
| CN112985671B (en) | Damage judgment method based on full-cable-system cable force test and error adaptive analysis | |
| CN106930751A (en) | A kind of Dlagnosis of Sucker Rod Pumping Well fault separating method | |
| CN109613611A (en) | The determination method and system of input-to-state stabilization for earthquake-resistant structure time-history analysis | |
| CN107024271A (en) | Mechanical oscillation signal compression reconfiguration method and system | |
| CN106121622A (en) | A kind of Multiple faults diagnosis approach of Dlagnosis of Sucker Rod Pumping Well based on indicator card | |
| CN114216682B (en) | Service life prediction method and device of rolling bearing based on TCN and BLS | |
| CN108240215B (en) | Finite difference method-based pumping well plunger effective stroke determination method | |
| CN106351645A (en) | Method and device for continuously measuring working fluid level of rod-pumped well | |
| CN111475989A (en) | Method for acquiring water content of crude oil based on oil well indicator diagram | |
| CN116822086A (en) | Method for intelligently converting working fluid level by pump diagram | |
| CN110260914B (en) | Engineering safety monitoring system region division method based on measuring point space-time characteristics | |
| CN108376192B (en) | Method for determining number of vibration modes required by acceleration reaction calculated by modal superposition method | |
| CN104807661B (en) | A kind of high-rise and tall and slender structure Dynamic testing evaluation on bearing capacity method | |
| CN111626324A (en) | Seabed observation network data heterogeneous analysis integration method based on edge calculation | |
| CN113255035B (en) | Method for fusing monitoring data of small and medium-sized bridges | |
| CN110486009A (en) | A kind of automatic reverse method of parameter and system on infinity stratum | |
| CN112392466A (en) | Energy calculation working fluid level method based on oil well indicator diagram | |
| CN108763289A (en) | A kind of analytic method of magnanimity heterogeneous sensor formatted data | |
| CN107202661A (en) | A kind of inhaul cable vibration frequency rank recognition methods based on pseudo- greatest common divisor | |
| CN114282577A (en) | Industrial robot fault diagnosis method based on current signal analysis | |
| CN108661623B (en) | Pump diagram calculation method and device based on pumping unit suspension point load fluctuation analysis |
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 |