Ultra-long stroke pumping unit downhole working condition diagnosis method and system based on electrical parameters

Abstract

The invention discloses an electric parameter-based ultra-long stroke pumping unit downhole working condition diagnosis method and system, and belongs to the field of oil well mechanical oil extraction. By collecting parameters such as data of an ultra-long stroke pumping unit, the load and the displacement stroke of the polished rod lower end suspension point are obtained, an oil well ground indicator diagram is further obtained, and therefore the underground working condition is visually and accurately diagnosed. Converting and solving the ground indicator diagram through a wave equation to obtain a pump indicator diagram, analyzing the pump indicator diagram, determining multi-parameter characteristic parameters, establishing an indicator diagram fault sample library, and performing real-time diagnosis on the working condition of the oil well by utilizing a pump indicator diagram characteristic value and a BP (Back Propagation) neural network method. The problem that the pump condition of a long-stroke oil production well is difficult to diagnose is solved, the situation of operation false detection caused by unclear working condition analysis is avoided, and the intelligent management level of an ultra-long-stroke oil pumping unit is improved.

Description

Technical Field

[0001] The invention belongs to the field of mechanical oil production of oil wells, and relates to a method and system for diagnosing downhole working conditions of an ultra-long stroke oil pump based on electrical parameters. Background Art

[0002] With the development of mechanical oil production technology, the low efficiency, high energy consumption and severe wellbore wear of conventional pumping systems used in low-yield and low-efficiency wells have gradually become a problem restricting the improvement of oil field quality and efficiency.

[0003] The flexible polished rod ultra-long stroke lifting system is a new lifting technology in recent years. Its structure and working mode are quite different from those of the traditional beam pumping unit. The system consists of key equipment such as ultra-long stroke beamless pumping unit, flexible polished rod, and ultra-long combined pump barrel pump. The transmission system of the ultra-long stroke pumping unit transmits the forward and reverse motion of the motor to the drum, which drives the pumping rod and the pump plunger connected to the flexible polished rod to reciprocate up and down to produce oil. The study found that the pumping unit has technical advantages such as high lifting efficiency, significant energy saving and consumption reduction, and high system stability.

[0004] The upper part of the long-stroke oil well is a flexible sucker rod, and the load sensor cannot be installed. Therefore, the conventional pumping well dynamometer tester cannot be used. When diagnosing the working condition of the downhole oil pump, we can only rely on field experience to check the changes in the operating current to roughly analyze the downhole working conditions. The diagnostic results vary from person to person, the on-site compliance rate is low, and there is a lack of intelligent management methods for oil wells. It is urgent to solve the problem of downhole working condition diagnosis of ultra-long-stroke pumping units. Summary of the invention

[0005] The purpose of the present invention is to solve the problem in the prior art that the upper part of a long-stroke oil production well is a flexible sucker rod, the load sensor cannot be installed, and the conventional pumping well dynamometer tester cannot be used, resulting in low diagnostic accuracy, and to provide an ultra-long-stroke pumping unit downhole working condition diagnosis method and system based on electrical parameters.

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

[0007] The present invention proposes a method for diagnosing downhole working conditions of an ultra-long stroke oil pump based on electrical parameters, comprising the following steps:

[0008] Obtain the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod, and determine the ground dynamometer diagram according to the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod;

[0009] Obtaining the damping coefficient, obtaining the displacement stroke at the oil well pump and the load at the oil well pump according to the indicator diagram, the damping coefficient and the wave equation, and determining the pump diagram according to the displacement stroke at the oil well pump and the load at the oil well pump;

[0010] The oil well working condition is diagnosed in real time according to the pump performance diagram and BP neural network, realizing the downhole working condition diagnosis of ultra-long stroke pumping units.

[0011] Preferably, the damping coefficient obtained includes the damping coefficient of the sucker rod with a coupling and the damping coefficient of the flexible sucker rod without a coupling;

[0012] Damping coefficient of the entire rod with coupling

[0013] The damping coefficient of the flexible sucker rod without coupling is as follows:

[0014]

[0015] in, d r is the diameter of the sucker rod; d t is the inner diameter of the oil pipe; r is the rod density; η is the fluid dynamic viscosity coefficient; A r is the sucker rod area; L o is the length of the oil pipe; L j is the coupling length; d j is the diameter of the sucker rod coupling; f(m) is the damping factor.

[0016] Preferably, the load at the hanging point at the lower end of the polished rod is obtained as follows:

[0017]

[0018] Where, U(t) is the instantaneous line voltage; I(t) is the instantaneous line current; is the instantaneous power factor; P O is the motor no-load power; N is the rated efficiency of the motor; P N is the rated power of the motor; β is the instantaneous power utilization rate of the motor; f 光杆 (t) is the polished rod load; v 光杆 (t) is the polished rod speed;

[0019] The displacement stroke of the lower end suspension point of the polished rod is obtained as follows:

[0020] S(t)=ω(t)r·t

[0021] Among them, S(t) is the displacement of the suspension point at the lower end of the polished rod; ω(t) is the rotation speed of the roller shaft; r is the winding radius of the flexible polished rod; and t is time.

[0022] Preferably, the displacement stroke at the oil well pump is obtained as follows:

[0023]

[0024] Among them, γ0 is the speed of the suspension point, w is the angular velocity of the drum, τ i are the coefficients of the loading Fourier series.

[0025] Preferably, σ i and τ i The calculation method is as follows:

[0026]

[0027] Preferably, the load at the oil well pump is obtained as follows:

[0028]

[0029] Where, E is the elastic modulus of the sucker rod; f r is the cross-sectional area of ​​the sucker rod string; γ0 is the movement speed of the suspension point.

[0030] Preferably, the coefficient O in the displacement function i (x) and the coefficient P in the load function i The calculation method of (x) is as follows:

[0031] O i (x)=(x i chβ i x+δ i shβ i x)sinα i x+(μ i shβ i x+γ i chβ i x)cosα i x

[0032] P i (x)=(x i Shβ i x+δ i chβ i x)sinα i x+(μ i chβ i x+γ i shβ i x)cosα i x

[0033] Where: α i , β i 、x i , μ i All are special constants.

[0034] The present invention proposes an electrical parameter-based downhole working condition diagnosis system for an ultra-long stroke oil pump, comprising:

[0035] A dynamometer diagram acquisition module, the dynamometer diagram acquisition module is used to acquire the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod, and determine the ground dynamometer diagram according to the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod;

[0036] A pump work diagram acquisition module, the pump work diagram acquisition module is used to acquire the damping coefficient, acquire the displacement stroke at the oil pump and the load at the oil pump according to the indicator diagram, the damping coefficient and the wave equation, and determine the pump work diagram according to the displacement stroke at the oil pump and the load at the oil pump;

[0037] The working condition data processing module is used to perform real-time diagnosis of the oil well working condition according to the pump performance diagram and the BP neural network, so as to realize downhole working condition diagnosis of the ultra-long stroke oil pumping unit.

[0038] A computer device comprises a memory and a processor, wherein the memory stores a computer program and the processor implements the steps of a method for diagnosing downhole working conditions of an ultra-long stroke pumping unit based on electrical parameters when executing the computer program.

[0039] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for diagnosing downhole working conditions of an ultra-long stroke pumping unit based on electrical parameters.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention proposes a method for diagnosing the downhole working condition of an ultra-long stroke oil pump based on electrical parameters. By collecting parameters such as ultra-long stroke oil pump data, the load at the lower end suspension point of the light rod and the displacement stroke at the lower end suspension point of the light rod are obtained, and then the surface indicator diagram of the oil well is obtained, so as to intuitively and accurately diagnose the downhole working condition. The surface indicator diagram is then converted and solved by the wave equation to obtain the pump power diagram, and the pump power diagram is analyzed to determine the multi-parameter characteristic parameters, and a power diagram fault sample library is established. The characteristic value of the pump power diagram and the BP neural network method are used to perform real-time diagnosis of the oil well working condition. The problem of difficult diagnosis of the pump condition of long-stroke oil wells is solved, the situation of misdetection of operations caused by unclear working condition analysis is avoided, and the intelligent management level of ultra-long stroke oil pumps is improved. Therefore, the diagnostic method proposed by the present invention can solve the problems existing in the prior art.

[0042] The present invention proposes an ultra-long stroke pumping unit downhole working condition diagnosis system based on electrical parameters, which realizes the downhole working condition diagnosis of the ultra-long stroke pumping unit by dividing the system into a dynamometer diagram acquisition module, a pump dynamometer diagram acquisition module and a working condition data processing module. The modularization concept is adopted to make each module independent of each other, which is convenient for unified management of each module. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 The present invention is a flow chart of the downhole working condition diagnosis method of the ultra-long stroke oil pump based on electrical parameters.

[0045] Figure 2 It is a curve diagram of acceleration change of the suspension point of the ultra-long stroke oil pumping unit of the present invention.

[0046] Figure 3 It is a curve diagram of the speed change of the suspension point of the ultra-long stroke oil pumping unit of the present invention.

[0047] Figure 4 It is a displacement variation curve of the suspension point of the ultra-long stroke oil pumping unit of the present invention.

[0048] Figure 5 It is a pump performance diagram combined with a BP neural network diagnostic diagram of the present invention.

[0049] Figure 6 This is a diagram of the downhole working condition diagnosis system of the ultra-long stroke oil pumping unit based on electrical parameters of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0051] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0053] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0054] In addition, if the term "horizontal" appears, it does not mean that the component is required to be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0055] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0056] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0057] The present invention proposes a method for diagnosing downhole working conditions of ultra-long stroke oil pumping units based on electrical parameters, such as Figure 1 As shown, the following steps are included:

[0058] S1, obtaining the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod, and determining the ground dynamometer diagram according to the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod;

[0059] S2, obtaining a damping coefficient, obtaining a displacement stroke at the oil well pump and a load at the oil well pump according to the indicator diagram, the damping coefficient and the wave equation, and determining a pump diagram according to the displacement stroke at the oil well pump and the load at the oil well pump;

[0060] S3. Perform real-time diagnosis of oil well working conditions based on pump performance diagram and BP neural network to realize downhole working condition diagnosis of ultra-long stroke pumping units.

[0061] The specific steps are as follows:

[0062] Step 1: Get the ground dynamometer diagram

[0063] By installing an electric energy test module at the motor port of the ultra-long stroke oil pump, the three-phase current and voltage of the ultra-long stroke oil pump motor are collected through the voltage and current acquisition circuit every 10 minutes. The instantaneous output active power of the motor is calculated through the three-phase power quality, and the power curve that changes with time within a stroke cycle is obtained.

[0064] The drum speed acquisition module is installed on the drum shaft. The speed sensor is used to test the speed of the drum shaft. According to the winding radius of the flexible polished rod, the displacement curve of the flexible polished rod over time in a stroke cycle can be calculated. The drum speed acquisition module is installed on the motor shaft, and the drum speed is obtained by testing the motor speed.

[0065] V1=rω

[0066] Wherein, V1 is the linear velocity of the flexible polished rod, m / s; ω is the rotation speed of the roller shaft; r is the winding radius of the flexible polished rod, m.

[0067] The suspension point displacement can be calculated from the linear velocity of the polished rod:

[0068] S=V1t

[0069] Where: t is time, s.

[0070] The power test module and the calculation module are both installed in the control cabinet of the ultra-long stroke oil pump. The power test module sends the power signal to the calculation module through the cable, and the drum speed acquisition module sends the displacement signal to the calculation module through the cable. The calculation module calculates the load value according to the power curve and the suspension point displacement according to the speed, thereby drawing the ground indicator diagram.

[0071] The ultra-long stroke pumping unit adopts a permanent magnet synchronous motor and a planetary reducer direct drive mode to replace the original transmission chain drive mode. As the load on the polished rod changes within a stroke, the output power of the drive motor also changes periodically. According to the energy balance principle, when the polished rod of the pumping unit is at a certain position within a stroke, the following relationship is established:

[0072] The relationship between the instantaneous output power of the motor and the instantaneous power of the bare rod is as follows: P 电参 (t) = P 光杆 (t)

[0073] Motor instantaneous output power:

[0074] Instantaneous power of the bare rod: P 光杆 (t) = f 光杆 (t)v 光杆 (t)

[0075] The mathematical model for calculating the load value using the real-time collected electrical parameter data is as follows:

[0076] Polished rod load:

[0077] Where, U(t) is the instantaneous line voltage, V; I(t) is the instantaneous line current, V; is the instantaneous power factor; P O is the motor no-load power, kW; η N is the rated efficiency of the motor, %; P N is the rated power of the motor, kW; β is the instantaneous power utilization rate of the motor; v 光杆 (t) is the polished rod speed, m / S;

[0078] Step 2: Convert the ground dynamometer diagram to the pump dynamometer diagram

[0079] The surface dynamometer diagram is different from the pump dynamometer diagram. The surface dynamometer diagram can be used to preliminarily diagnose the working condition of the well, but the pump dynamometer diagram is required to accurately diagnose the working condition of the oil well. The pump dynamometer diagram is obtained from the surface dynamometer diagram through the wave equation.

[0080] The rod pumping system is regarded as a three-dimensional vibration system of sucker rod, tubing and liquid column. Under certain boundary conditions and certain initial conditions (such as periodic conditions), it affects the external excitation (surface power diagram) (pump power diagram). The transformation of the downhole pump power diagram is the basis of working condition diagnosis. The downhole pump power diagram transformation technology is based on the suspension point power diagram. By solving the wave equation of the sucker rod string, the load and displacement of the downhole pump are obtained, and the pump power diagram is drawn.

[0081] The traditional method of solving the pump performance diagram using a fixed damping coefficient is changed. According to the wellbore structure of the pumping well, the temperature and pressure distribution of the wellbore is calculated using a multiphase flow model. Then, the influence of changes in temperature, pressure, viscosity, etc. at each section of the well depth on the damping forces in the rod, pipe and well fluid is considered, and the damping coefficient calculation method for the entire well section is obtained, making the solution of the pump performance diagram more accurate.

[0082] When the suspension point indicator diagram is converted into a downhole pump indicator diagram, the basic differential equation describing the dynamics of the sucker rod is the following wave equation with viscous damping:

[0083]

[0084] in, is the acceleration variation of the sucker rod section at any depth x over time; is the velocity variation of the sucker rod section at any depth x over time; is the displacement of the section x at any depth of the sucker rod changing with time; t is time, s; a is the stress propagation speed, m / s, x is the cross-sectional depth of the sucker rod, m; E is the elastic modulus of the sucker rod, ρ is the density of the sucker rod, and c is the damping coefficient of the sucker rod.

[0085] Boundary conditions: Boundary conditions are required to solve the above wave equation. Here, the suspension point load D(t) and the suspension point displacement U(t) are used as boundary conditions, and the relationship is as follows:

[0086]

[0087] Continuity condition: For multi-stage rod strings, the forces and displacements of two adjacent rod strings at the connection surface are equal, and the relationship is as follows:

[0088]

[0089] but

[0090]

[0091] Where: F(x,t) is the change of dynamic load on the section of the sucker rod at any depth x over time; D(t) and U(t) are expanded into Fourier series respectively: σ0、σ i , τ i is the coefficient of the Fourier series of the load; D(t) is the suspension point load, N; w is the angular velocity of the roller, rad / s. γ0, γ i ,δ i is the coefficient of the displacement Fourier series; γ0 is the speed of the suspension point; U(t) is the suspension point displacement, m.

[0092] The wave equation with viscous damping does not contain the gravity term, so the suspension point dynamic load cannot be directly used as the boundary condition of the force. The weight of the rod column needs to be subtracted from the suspension point load to obtain the dynamic load function D(t) that does not include the rod weight. The coefficient σ of the Fourier series of the suspension point load and the suspension point displacement is i , τ i and γ i ,δ i The calculation method is as follows:

[0093]

[0094]

[0095] Wherein, (i=0,1,2,...,n), n is the number of truncated terms of the Fourier series.

[0096] In actual solution, the suspension point load and displacement are both discrete data, so the coefficients of the above Fourier series can be calculated by numerical integration.

[0097] Taking the above suspension point load and suspension point displacement as boundary conditions, using the separation of variables method, by solving the equation, the displacement of a certain depth x section of the column can be obtained as

[0098]

[0099] Where: E is the elastic modulus of the sucker rod, N / m 2 ;f r is the cross-sectional area of ​​the sucker rod string, m 2 ;γ0 is the speed of the suspension point, m / s.

[0100] From Hooke's law Then the dynamic load on the section at any depth x of the sucker rod string changes with time: At time t, the total load on section x is equal to F(x,t) plus the weight of the sucker rod string below section x. i is the coefficient in the displacement function, P i is the coefficient in the loading function.

[0101] O i (x)=(x i chβ i x+δ i shβ i x)sinα i x+(μ i shβ i x+γ i chβ i x)cosα i x

[0102] P i (x)=(x i Shβ i x+δ i chβ i x)sinα i x+(μ i chβ i x+γ i shβ i x)cosα i x

[0103] Where: α i , β i 、x i , μ i They are all special constants, and their expressions are as follows:

[0104]

[0105]

[0106]

[0107]

[0108] Because the structure of the ultra-long stroke pumping unit is different from that of the conventional pumping unit, under certain stroke conditions, the suspension point speed, acceleration, and displacement are quite different from those of the conventional pumping unit. According to the starting characteristics of the motor, the acceleration mode of the motor is set to a cosine curve. Therefore, the change process of the suspension point load of this pumping unit changes with the change of the motor acceleration. The specific acceleration change curve. The movement law of the suspension point of the drum winch structure is as follows: Figures 2 to 4 As shown:

[0109] The super-long pumping unit sucker rod is composed of a conventional steel rod and a wire rope polished rod. The two parts have different structures and materials, so the damping coefficient needs to be calculated separately:

[0110] Damping coefficient of sucker rod with coupling

[0111] Considering that when the fluid passes through the coupling, it flows from the large diameter into the small diameter, and then flows from the small diameter into the large diameter, the friction resistance of the two is combined, and the damping coefficient of the entire rod with coupling is calculated as:

[0112]

[0113] Among them, the coefficient of variation d r is the diameter of the sucker rod (mm); d t is the inner diameter of the oil pipe (mm); ρ r is the rod density; η is the fluid dynamic viscosity coefficient Pa·s; A r is the sucker rod area mm 2 ; L o is the length of the oil pipe, m; L j is the coupling length, m; d j is the diameter of the sucker rod coupling (mm).

[0114] Damping coefficient of flexible sucker rod without coupling

[0115]

[0116] Where f(m) is the damping factor, dimensionless.

[0117] Table 1 List of damping coefficients of sucker rods with different rod diameters and materials

[0118]

[0119]

[0120] The elastic modulus of the sucker rod of the ultra-long stroke pumping unit is 2.1*10 11 Pa of conventional steel rods and elastic modulus of 1.5*10 11 Pa flexible wire rope rod.

[0121] Step 3:

[0122] The pump performance diagram is analyzed, multi-parameter characteristic parameters are determined, and a performance diagram fault sample library is established. The oil well operating condition is diagnosed in real time using methods such as pump performance diagram characteristic value + BP neural network, load difference verification, CNN deep learning, and expert diagnosis method.

[0123] Based on the pump performance diagram + BP neural network, it can diagnose wax deposition, sand production, pump collision, pump collision, sucker rod breakage, gas impact, insufficient fluid supply, fixed valve leakage, floating valve leakage and tubing leakage. Its core algorithm: using the pump performance diagram characteristic value K, combined with BP neural network technology for diagnosis.

[0124] According to the application status of long-stroke pumping units, several indicators are established to identify specific fault types. The characteristic value is represented by K (K1, K2, K3, K4, K5, K6, K7).

[0125] K1 area-to-perimeter ratio: The first type is that the K1 of the fault is greater than the normal value, such as wax deposition and sand production; the second type is that the K1 of the fault remains basically unchanged, such as pump up and pump down collision; the last type is that the K1 of the fault is less than the normal value, such as sucker rod breakage, gas influence, insufficient fluid supply, fixed valve leakage, floating valve leakage and oil pipe leakage.

[0126] K2 partial upstroke data standard deviation: A significant difference between wax deposition and sand production is that the upper and lower stroke lines of the sand production indicator diagram have dense jitter. Therefore, the indicator is set - partial upstroke data standard deviation K2. The standard deviation indicates the degree of data dispersion. The larger the standard deviation, the more severe the jitter of the indicator diagram. Eliminate the influence of the loading line data and select 80% of the data after the entire upstroke to calculate the K2 value.

[0127] K3 upper stroke line before and after data ratio: The characteristic of the upper stroke indicator diagram is that there is an obvious upward convex part in the upper right corner of the indicator diagram. In order to identify this convex part, the data before and after the upper stroke line can be used as a quotient. The K3 value of the normal indicator diagram and the pump lower impact indicator diagram is approximately equal to 1, while the K3 value of the pump upper impact indicator diagram is greater than 1. The left picture is a pump upper impact.

[0128] K4 downstroke line data ratio: The characteristic of the downstroke indicator diagram is that there is an obvious downward bulge in the lower left corner of the indicator diagram. In order to identify this bulge, the data before and after the downstroke line are used as the quotient. The specific data range for the quotient is: the sum of the data of the 10% after the downstroke part is magnified four times and divided by the sum of the data in the 50% to 90% area in the middle and rear part of the upper stroke part. The K4 value of the normal indicator diagram is approximately equal to 1, and the K4 value of the pump downstroke indicator diagram is less than 1.

[0129] K5 left half area ratio: For the remaining five fault types that need to be identified, establish the indicator K5 - the left half area ratio of the graph. That is, use the midpoint of the horizontal axis as a vertical line to divide the indicator diagram into two parts, the left half area ratio of the entire graph area. In order to normalize the K5 value, it needs to be magnified by one. The K5 value of the floating valve leakage fault is less than 1; the K5 value of the fixed valve leakage and insufficient liquid supply is greater than 1; the K5 value of gas influence and oil pipe leakage is approximately equal to 1.

[0130] Slope of the lower right corner of K6 graph: Under the combined effect of K1 and K5, insufficient fluid supply and fixed valve leakage are identified. Although the K5 values ​​of insufficient fluid supply and fixed valve leakage faults in the same pumping well are significantly different, a new characteristic value indicator K6 is introduced - the slope of the lower right corner of the graph. A parallelogram is missing in the lower right corner of the insufficient fluid supply indicator diagram, while a triangle is missing in the lower right corner of the fixed valve leakage indicator diagram. Therefore, calculating the slope of the lower right corner of the indicator diagram, that is, the beginning of the downstroke, can distinguish these two types of faults.

[0131] K7 graph loading line slope: Under the combined effect of K1 and K5, gas impact and tubing leakage can also be identified. However, it is impossible to accurately distinguish between gas impact faults and tubing leakage faults based on the existing eigenvalues. Therefore, a new eigenvalue component K7, graph loading line slope, is introduced. By analyzing the dynamometer diagrams of the two fault types, it is found that the slopes on the left side of their graphs are significantly different. The K7 value of gas impact is approximately equal to 1, while the K7 value of tubing leakage is greater than 2.

[0132] like Figure 5 As shown in the figure, a three-layer BP neural network is selected. The input layer is the eigenvalue of the pumping unit indicator diagram, and the eigenvalue has seven components, so the number of neurons in the input layer is 7. The types of working conditions that need to be judged are: normal working conditions, fixed valve leakage fault, floating valve leakage fault, oil pipe leakage fault, sucker rod break fault, pump upper collision fault, pump lower collision fault, gas impact fault, insufficient liquid supply, wax deposition, sand production, etc., so the number of neurons in the output layer is 11.

[0133] Table 2 Oil well operating condition characteristic values

[0134]

[0135]

[0136] The present invention proposes a downhole working condition diagnosis system of an ultra-long stroke oil pump based on electrical parameters, such as Figure 6 As shown, it includes a dynamometer diagram acquisition module, a pump dynamometer diagram acquisition module and a working condition data processing module;

[0137] The dynamometer diagram acquisition module is used to acquire the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod, and determine the ground dynamometer diagram according to the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod;

[0138] The pump work diagram acquisition module is used to acquire the damping coefficient, acquire the displacement stroke at the oil pump and the load at the oil pump according to the indicator diagram, the damping coefficient and the wave equation, and determine the pump work diagram according to the displacement stroke at the oil pump and the load at the oil pump;

[0139] The working condition data processing module is used to perform real-time diagnosis of the oil well working condition according to the pump performance diagram and the BP neural network, so as to realize downhole working condition diagnosis of the ultra-long stroke oil pumping unit.

[0140] The terminal device provided in an embodiment of the present invention comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0141] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to accomplish the present invention.

[0142] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0143] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0144] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0145] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0146] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for downhole working condition diagnosis of ultra-long stroke pumping unit based on electrical parameters, characterized in that: The steps include: Obtain the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod, and determine the ground dynamometer diagram according to the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod; Obtaining the damping coefficient, obtaining the displacement stroke at the oil well pump and the load at the oil well pump according to the indicator diagram, the damping coefficient and the wave equation, and determining the pump diagram according to the displacement stroke at the oil well pump and the load at the oil well pump; The oil well working condition is diagnosed in real time according to the pump performance diagram and BP neural network, realizing the downhole working condition diagnosis of ultra-long stroke pumping units.

2. The method for downhole working condition diagnosis of ultra-long stroke oil pumping unit based on electrical parameters according to claim 1, characterized in that: Obtaining the damping coefficient includes the damping coefficient of the sucker rod with coupling and the damping coefficient of the flexible sucker rod without coupling; Damping coefficient of the entire rod with coupling The damping coefficient of the flexible sucker rod without coupling is as follows: in, d r is the diameter of the sucker rod; d t is the inner diameter of the oil pipe; r is the rod density; η is the fluid dynamic viscosity coefficient; A r is the sucker rod area; L o is the length of the oil pipe; L j is the coupling length; d j is the diameter of the sucker rod coupling; f(m) is the damping factor.

3. The method for downhole working condition diagnosis of ultra-long stroke pumping unit based on electrical parameters according to claim 1, characterized in that: The load at the lower end suspension point of the polished rod is obtained as follows: Where, U(t) is the instantaneous line voltage; I(t) is the instantaneous line current; is the instantaneous power factor; P O is the motor no-load power; N is the rated efficiency of the motor; P N is the rated power of the motor; β is the instantaneous power utilization rate of the motor; f 光杆 (t) is the polished rod load; v 光杆 (t) is the polished rod speed; The displacement stroke at the lower end suspension point of the polished rod is obtained as follows: S(t)=ω(t)r·t Among them, S(t) is the displacement of the suspension point at the lower end of the polished rod; ω(t) is the rotation speed of the roller shaft; r is the winding radius of the flexible polished rod; and t is time.

4. The method for downhole working condition diagnosis of ultra-long stroke oil pumping unit based on electrical parameters according to claim 1, characterized in that: The displacement stroke at the oil well pump is obtained as follows: Among them, γ0 is the speed of the suspension point, w is the angular velocity of the drum, τ i are the coefficients of the loading Fourier series.

5. The method for downhole working condition diagnosis of ultra-long stroke pumping unit based on electrical parameters according to claim 4, characterized in that: σ i and τ i The calculation method is as follows:

6. The method for downhole working condition diagnosis of ultra-long stroke pumping unit based on electrical parameters according to claim 1, characterized in that: The load at the oil well pump is obtained as follows: Where, E is the elastic modulus of the sucker rod; f r is the cross-sectional area of ​​the sucker rod string; γ0 is the movement speed of the suspension point.

7. The method for downhole working condition diagnosis of ultra-long stroke pumping unit based on electrical parameters according to claim 6 is characterized in that: The coefficient O in the displacement function i (x) and the coefficient P in the load function i The calculation method of (x) is as follows: O i (x)=(x i chβ i x+δ i shβ i x)sinα i x+(μ i shβ i x+γ i chβ i x)cosα i x P i (x)=(x i Shβ i x+δ i chβ i x)sinα i x+(μ i chβ i x+γ i shβ i x)cosα i x Where: α i , β i 、x i , μ i All are special constants.

8. An ultra-long stroke pumping unit downhole working condition diagnosis system based on electrical parameters, characterized in that: include: A dynamometer diagram acquisition module, the dynamometer diagram acquisition module is used to acquire the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod, and determine the ground dynamometer diagram according to the load at the hanging point at the lower end of the polished rod and the displacement stroke at the hanging point at the lower end of the polished rod; A pump work diagram acquisition module, the pump work diagram acquisition module is used to acquire the damping coefficient, acquire the displacement stroke at the oil pump and the load at the oil pump according to the indicator diagram, the damping coefficient and the wave equation, and determine the pump work diagram according to the displacement stroke at the oil pump and the load at the oil pump; The working condition data processing module is used to perform real-time diagnosis of the oil well working condition according to the pump performance diagram and the BP neural network, so as to realize downhole working condition diagnosis of the ultra-long stroke oil pumping unit.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for diagnosing downhole working conditions of an ultra-long stroke pumping unit based on electrical parameters as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for diagnosing downhole working conditions of an ultra-long stroke pumping unit based on electrical parameters as described in any one of claims 1 to 7 are implemented.

Images