A prediction method of dynamometer diagram based on electrical parameters
By obtaining sample data of the pumping well, inverting the relationship between the suspension load and the motor input power, and combining the displacement factor to predict the power diagram, the problem of insufficient prediction accuracy of the power diagram in the prior art is solved, and the pumping well is improved digital and intelligent application level.
Patent Information
- Application Number
- CN202210188218.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-02-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-02-28
AI Technical Summary
The existing power diagram prediction technology based on current and power has problems such as insufficient accuracy and limited application scope in oil pump wells, which cannot meet the needs of production management.
By obtaining the sample motor input power, speed and suspension load of the pump well, inverting the relationship between the suspension load and the motor input power, calculating the real-time suspension load, and predicting the power diagram with displacement factors, using comprehensive efficiency Parameters improve prediction accuracy.
It has achieved higher prediction accuracy of power diagrams, reduced the cost of IoT construction and operation and maintenance of oil fields, and improved the level of digital and intelligent application of oil well production.
Smart Images

Figure CN114517673B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of deep integration of petroleum engineering, artificial intelligence and the Internet of Things, and in particular to a dynamometer diagram prediction method based on electrical parameters. Background Art
[0002] The dynamometer diagram is the key data for production monitoring and working condition diagnosis of pumping wells. In the era of digital oilfields, load and displacement sensors or load-displacement integrated dynamometers used to obtain dynamometer diagrams have become standard for IoT-based pumping wells in digital oilfields. For oilfields with a huge number of pumping wells and low single-well production, a set of dynamometer diagram test equipment for each well not only requires huge investment, but also has high subsequent operation and maintenance costs. In order to reduce the cost of digital oilfields, the industry has developed technology to predict dynamometer diagrams based on electrical parameters including current and power.
[0003] At present, the technology has been developed to a certain extent, and there are two main technical routes: one is the physical model based on the relationship between the indicator diagram-torque-load, using the theoretical model for calculation; the other is to use artificial intelligence algorithms to establish a data model between the electric participation and the load based on historical data. These two technical routes have their own advantages and disadvantages. Generally speaking, due to the neglect of some key parameters of the pumping well, their scope of application is limited and the accuracy is difficult to meet the needs of production management. Summary of the invention
[0004] In view of the above problems, an embodiment of the present invention is proposed to provide a method for predicting a dynamometer diagram based on electrical parameters, which overcomes the above problems or at least partially solves the above problems.
[0005] In order to solve the above problems, a method for predicting a dynamometer diagram based on electrical parameters is provided according to the present invention. The method comprises:
[0006] Obtaining a sample motor input power, a sample motor speed and a sample suspension point load of a pumping well at a preset crank angle;
[0007] Inverting a plurality of comprehensive efficiency parameters in the relationship according to the sample motor input power, the sample motor speed, the sample suspension point load, and the relationship between the suspension point load and the motor input power;
[0008] Calculating the real-time suspension point load of the pumping well according to the plurality of comprehensive efficiency parameters, the relationship and the real-time motor input power of the pumping well; comparing the real-time suspension point load with the predicted theoretical suspension point load;
[0009] If the deviation between the real-time suspension point load and the theoretical suspension point load is within a preset deviation range, then calculating the displacement at the angle corresponding to the real-time suspension point load;
[0010] According to the real-time suspension point load and the corresponding displacement, a public diagram of the pumping well is predicted in a unified coordinate system.
[0011] Preferably, the step of calculating the relationship includes: generating the relationship according to the net torque output by the reduction box at different crank angles, the balance torque, the torque factor and the unbalanced weight of the pumping well.
[0012] Preferably, the relationship is expressed as:
[0013]
[0014] Wherein, W(θ) represents the suspension point load at different crank angles, θ represents the crank angle, represents the net torque, a, b, c, d and e represent multiple comprehensive efficiency parameters, ηm represents the motor load rate, N(θ) represents the motor input power at different crank angles, n(θ) represents the motor speed at different crank angles, 9.8(W b R b X+2W c R c )sin(θ+τ) represents the balance torque, the W b Indicates the balance weight of each crank, the R b represents the crank balance radius, X represents the number of balance weights, and W c represents the deadweight of each crank, the R c represents the crank center of gravity radius, τ represents the crank balance phase angle, TF represents the torque factor, and Bu represents the unbalanced weight.
[0015] Preferably, the calculating the displacement at the angle corresponding to the real-time suspension point load includes: calculating the displacement according to a displacement factor and a stroke.
[0016] Preferably, the displacement is expressed as: POS = S * PR = A (ψ max -ψ); wherein, POS represents the displacement, S represents the stroke, PR represents the displacement factor, A represents the length of the forearm of the walking beam, B represents the length of the rear arm of the walking beam, K represents the distance from the center of the crankshaft to the center of the walking beam shaft, L represents the distance from the center of the crossbeam shaft to the center of the crankpin, R represents the crank radius, Ψ=ξ+ρ, J represents the distance from the crankpin center to the beam bearing center, and ρ represents the crankpin beam center crank center angle.
[0017] Compared with the prior art, the technical solution provided by the embodiment of the present invention has the following advantages:
[0018] The embodiment of the present invention provides a method for predicting a dynamometer diagram based on electrical parameters. According to the sample motor input power, sample motor speed, sample suspension point load, and the relationship between the suspension point load and the motor input power, multiple comprehensive efficiency parameters in the relationship are inverted, and then the real-time suspension point load of the pumping well is calculated according to the multiple comprehensive efficiency parameters, the relationship, and the real-time motor input power of the pumping well. Combined with the predicted theoretical suspension point load, when the deviation between the real-time suspension point load and the theoretical suspension point load is small, the displacement at the corresponding angle of the real-time suspension point load is calculated. Finally, according to the real-time suspension point load and the corresponding displacement, the public diagram of the pumping well is predicted in a unified coordinate system.
[0019] The embodiment of the present invention inverts multiple comprehensive efficiency parameters in the relationship between the suspension point load and the motor input power, uses the comprehensive efficiency parameters and the relationship to calculate the real-time suspension point load corresponding to the real-time motor input power, and then combines it with the theoretical suspension point load. Finally, when the deviation between the real-time suspension point load and the theoretical suspension point load is small, the dynamometer diagram is predicted according to the real-time suspension point load and the corresponding displacement. This not only avoids simply relying on theoretical models or artificial intelligence algorithms to predict the dynamometer diagram, but also makes full use of the comprehensive efficiency parameters, thereby achieving the purpose of reducing the construction and operation and maintenance costs of the oilfield Internet of Things, improving the accuracy of the dynamometer diagram converted from electrical parameters, and enhancing the level of digitalization and intelligent application of oil well production. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 It is a flowchart of the steps of the method for predicting a dynamometer diagram based on electrical parameters according to an embodiment of the present invention;
[0021] Figure 2 It is a schematic diagram of the geometric structure of the oil pump. DETAILED DESCRIPTION
[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0023] Reference Figure 1 and Figure 2 ,in, Figure 1 The flowchart of a method for predicting a power diagram based on electrical parameters according to an embodiment of the present invention is shown. The method for predicting a power diagram based on electrical parameters can be applied to a terminal or a server. The method for predicting a power diagram based on electrical parameters can specifically include the following steps:
[0024] Step S101, obtaining a sample motor input power, a sample motor speed and a sample suspension point load of a pumping well at a preset crank angle.
[0025] In an embodiment of the present invention, in order to obtain multiple comprehensive efficiency parameters through subsequent inversion, multiple groups of sample motor input power, sample motor speed and sample suspension point load can be obtained. Theoretically, multiple comprehensive efficiency parameters can be inverted through 5 groups of sample motor input power, sample motor speed and sample suspension point load. However, the embodiment of the present invention can obtain as many groups of sample motor input power, sample motor speed and sample suspension point load as possible, for example, 180 groups. Then, the least squares method is used to obtain the final sample data, and then the sample data is used to invert more accurate comprehensive efficiency parameters.
[0026] Step S102, inverting a plurality of comprehensive efficiency parameters in the relationship according to the sample motor input power, the sample motor speed, the sample suspension point load, and the relationship between the suspension point load and the motor input power.
[0027] When the motor input power, motor speed and suspension point load are measured at a given crank angle, the relationship between the unknown coefficients a, b, c, d, and e can be obtained. In oil wells equipped with electrical parameter acquisition devices, the above relationship can be obtained through power diagram calibration tests. In theory, only more than 5 different measurement points are needed to determine a, b, c, d, and e. For the sake of accuracy, each power diagram test can take more than 180 points, and the least squares method can be used to obtain a more accurate comprehensive efficiency relationship.
[0028] In an embodiment of the present invention, the step of calculating the relationship includes:
[0029] The relationship is generated according to the net torque output by the reduction box at different crank angles, the balance torque, the torque factor and the unbalanced weight of the pumping well.
[0030] Specifically, the comprehensive efficiency index from the motor input end to the gearbox output end is defined as η. Under normal working conditions, it is regarded as a function of the motor load rate and is expressed as follows:
[0031] Motor load rate:
[0032] η m =(N(θ)f 0 ) / (N n f) (1)
[0033] Formula (1) takes into account the conversion of motor load factor under variable frequency conditions.
[0034] Overall efficiency:
[0035]
[0036] a, b, c, d, e are unknown coefficients
[0037] The net torque output by the reduction gearbox at different crank angles can be expressed as:
[0038] M(θ)=9550*η*N(θ) / n(θ) (3)
[0039] n(θ) is the motor speed at different crank angles,
[0040] N(θ) is the motor input power at different crank angles,
[0041] N n Motor rated power, f Motor actual operating frequency, f 0 Power frequency
[0042] According to the torque balance relationship
[0043] M(θ)=M o (θ)-M c (θ) (4)
[0044] Load torque M o (θ):M o (θ)=TF[W(θ)-9.8Bu] (5)
[0045] Balance torque Mc(θ): M c (θ)=9.8(W b R b X+2W c R c )sin(θ+τ) (6)
[0046] From formula 1-6, we can get: the relationship between the suspension point load and the motor input power
[0047]
[0048] Except a, b, c, d, and e which are unknown coefficients, the other parameters are mainly test data and pumping unit design parameters.
[0049] The meaning of each term in the above formula is:
[0050] W(θ), suspension point load at different crank angles, N
[0051] Bu, unbalanced weight of the pumping unit, kg, independent of angle
[0052] TF, torque factor, m
[0053]
[0054] ɑ, the angle between the connecting rod and the crank
[0055] ɑ=2π-(θ x+ψ+β) (9)
[0056] θ x =θ+ψ (10)
[0057] When the donkey head is on the left, the crank rotates counterclockwise θ to take a positive value, and the crank rotates clockwise θ to take a negative value.
[0058]
[0059]
[0060]
[0061] A, B, J, L, K, R, and H are the geometric size parameters of the oil pump, as shown in the figure below.
[0062] Mc-crank balance torque, Nm;
[0063] Wb-mass of each crank counterweight, kg;
[0064] Rb-crank balance radius, m;
[0065] X-number of balancing weights;
[0066] Wc-weight of each crank, kg;
[0067] Rc-crank center of gravity radius, m;
[0068] θ-crank angle, rad;
[0069] τ-crank balance phase angle, rad.
[0070] Specifically, the relationship is expressed as:
[0071]
[0072] Wherein, W(θ) represents the suspension point load at different crank angles, θ represents the crank angle, represents the net torque, a, b, c, d and e represent a plurality of comprehensive efficiency parameters, η m represents the motor load rate, N(θ) represents the motor input power at different crank angles, n(θ) represents the motor speed at different crank angles, and 9.8(W b R b X+2W c R c )sin(θ+τ) represents the balance torque, the W b Indicates the balance weight of each crank, the R b represents the crank balance radius, X represents the number of balance weights, and Wc represents the deadweight of each crank, the R c represents the crank center of gravity radius, τ represents the crank balance phase angle, TF represents the torque factor, and Bu represents the unbalanced weight.
[0073] Step S103, calculating the real-time suspension point load of the pumping well according to the plurality of comprehensive efficiency parameters, the relationship and the real-time motor input power of the pumping well.
[0074] By inverting the relationship, we can get the relationship between input power and suspension point load. Under the condition of testing real-time power, we can use this relationship to calculate the suspension point load.
[0075] Step S104, comparing the real-time suspension point load with the predicted theoretical suspension point load; if the deviation between the real-time suspension point load and the theoretical suspension point load is within a preset deviation range, calculating the displacement at the corresponding angle of the real-time suspension point load.
[0076] The predicted theoretical suspension point load includes the maximum and minimum loads; in the embodiment of the present invention, the theoretical maximum and minimum load predictions include:
[0077]
[0078]
[0079] W l ′=A P L rod ρ L g
[0080] q′ r =q r *(ρ r -ρ l ) / ρ r
[0081] Among them, P max_th - Maximum load of the theoretical suspension point indicator diagram, KN;
[0082] P min_th -Minimum load of the theoretical suspension point indicator diagram, KN;
[0083] W r ′-the sucker rod string load acting on the suspension point during the downstroke, N;
[0084] Wr-upstroke sucker rod load, N;
[0085] W l ′-Liquid column load acting on the plunger during the upward stroke, N;
[0086] R-crank rotation radius, m;
[0087] L rod - connecting rod length, m;
[0088] s-stroke, real-time test data, m;
[0089] n-strokes, real-time test data, min-1;
[0090] q r -Mass of sucker rod per meter, kg / m;
[0091] A P - Cross-sectional area of plunger, m 2 ;
[0092] L- sucker rod length, m
[0093] ρ L -Average density of liquid in the tube, kg / m 3
[0094] Limit the range of loads predicted by subsequent power diagrams.
[0095] In an embodiment of the present invention, calculating the displacement at the angle corresponding to the real-time suspension point load includes:
[0096] The displacement is calculated based on the displacement factor and the stroke.
[0097] The displacement is expressed as:
[0098] POS=S*PR=A(ψ max -ψ);
[0099] Wherein, POS represents the displacement, S represents the stroke, PR represents the displacement factor, A represents the length of the forearm of the walking beam, B represents the length of the rear arm of the walking beam, K represents the distance from the center of the crankshaft to the center of the walking beam shaft, L represents the distance from the center of the crossbeam shaft to the center of the crankpin, R represents the crank radius, Ψ=ξ+ρ, J represents the distance from the crankpin center to the beam bearing center, and ρ represents the crankpin beam center crank center angle.
[0100] When sinθ is greater than 0, ρ is positive, and when sinθ is less than 0, ρ is negative. Plotting the displacement and the corresponding load in a unified coordinate system gives the oil well indicator diagram.
[0101] Step S105, predicting and obtaining a public diagram of the pumping well in a unified coordinate system according to the real-time suspension point load and the corresponding displacement.
[0102] The dynamometer diagram prediction method based on electrical parameters provided by the embodiment of the present invention is based on the sample motor input power, sample motor speed, sample suspension point load and the relationship between the suspension point load and the motor input power, and then the real-time suspension point load of the pumping well is calculated based on the multiple comprehensive efficiency parameters, the relationship and the real-time motor input power of the pumping well. Combined with the predicted theoretical suspension point load, when the deviation between the real-time suspension point load and the theoretical suspension point load is small, the displacement at the corresponding angle of the real-time suspension point load is calculated. Finally, based on the real-time suspension point load and the corresponding displacement, the public diagram of the pumping well is predicted in a unified coordinate system.
[0103] The embodiment of the present invention inverts multiple comprehensive efficiency parameters in the relationship between the suspension point load and the motor input power, uses the comprehensive efficiency parameters and the relationship to calculate the real-time suspension point load corresponding to the real-time motor input power, and then combines it with the theoretical suspension point load. Finally, when the deviation between the real-time suspension point load and the theoretical suspension point load is small, the dynamometer diagram is predicted according to the real-time suspension point load and the corresponding displacement. This not only avoids simply relying on theoretical models or artificial intelligence algorithms to predict the dynamometer diagram, but also makes full use of the comprehensive efficiency parameters, thereby achieving the purpose of reducing the construction and operation and maintenance costs of the oilfield Internet of Things, improving the accuracy of the dynamometer diagram converted from electrical parameters, and enhancing the level of digitalization and intelligent application of oil well production.
[0104] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
[0105] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0106] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.
[0107] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0108] The above is a detailed introduction to a dynamometer diagram prediction method based on electrical parameters provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A method for predicting a dynamometer diagram based on electrical parameters, characterized in that: The method comprises: Obtaining a sample motor input power, a sample motor speed and a sample suspension point load of a pumping well at a preset crank angle; Inverting a plurality of comprehensive efficiency parameters in the relationship according to the sample motor input power, the sample motor speed, the sample suspension point load, and the relationship between the suspension point load and the motor input power; Calculating the real-time suspension point load of the pumping well according to the plurality of comprehensive efficiency parameters, the relationship and the real-time motor input power of the pumping well; comparing the real-time suspension point load with the predicted theoretical suspension point load; If the deviation between the real-time suspension point load and the theoretical suspension point load is within a preset deviation range, then calculating the displacement at the angle corresponding to the real-time suspension point load; According to the real-time suspension point load and the corresponding displacement, predicting and obtaining the indicator diagram of the pumping well in a unified coordinate system; The calculation step of the relationship includes: The relationship is generated according to the net torque output by the reduction box at different crank angles, the balance torque, the torque factor and the unbalanced weight of the pumping well; The relationship is expressed as: Wherein, W(θ) represents the suspension point load at different crank angles, θ represents the crank angle, represents the net torque, a, b, c, d and e represent a plurality of comprehensive efficiency parameters, η m represents the motor load rate, N(θ) represents the motor input power at different crank angles, n(θ) represents the motor speed at different crank angles, and 9.8(W b R b X+2W c R c )sin(θ+τ) represents the balance torque, the W b Indicates the balance weight of each crank, the R b represents the crank balance radius, X represents the number of balance weights, and W c represents the deadweight of each crank, the R c represents the crank center of gravity radius, τ represents the crank balance phase angle, TF represents the torque factor, and Bu represents the unbalanced weight.
2. The method according to claim 1, characterized in that The calculating the displacement at the angle corresponding to the real-time suspension point load comprises: The displacement is calculated based on the displacement factor and the stroke.
3. The method according to claim 2, characterized in that The displacement is expressed as: Pos=S*PR=A(ψ max -ψ); Wherein, Pos represents the displacement, S represents the stroke, PR represents the displacement factor, A represents the length of the forearm of the walking beam, B represents the length of the rear arm of the walking beam, K represents the distance from the center of the crankshaft to the center of the walking beam shaft, L represents the distance from the center of the crossbeam shaft to the center of the crankpin, R represents the crank radius, Ψ=ξ+ρ, J represents the distance from the crankpin center to the beam bearing center, and ρ represents the crankpin beam center crank center angle.
