CN116595440A - Underground working condition fault diagnosis method and device - Google Patents
Underground working condition fault diagnosis method and device Download PDFInfo
- Publication number
- CN116595440A CN116595440A CN202310607837.1A CN202310607837A CN116595440A CN 116595440 A CN116595440 A CN 116595440A CN 202310607837 A CN202310607837 A CN 202310607837A CN 116595440 A CN116595440 A CN 116595440A
- Authority
- CN
- China
- Prior art keywords
- working condition
- sucker rod
- stroke
- influence factor
- pump
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 71
- 239000000725 suspension Substances 0.000 claims abstract description 76
- 230000005856 abnormality Effects 0.000 claims abstract description 24
- 239000012530 fluid Substances 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 27
- 239000003129 oil well Substances 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 2
- 235000013619 trace mineral Nutrition 0.000 claims description 2
- 239000011573 trace mineral Substances 0.000 claims description 2
- 238000010586 diagram Methods 0.000 abstract description 16
- 238000000605 extraction Methods 0.000 abstract description 10
- 238000010801 machine learning Methods 0.000 abstract description 6
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract description 4
- 239000003921 oil Substances 0.000 description 33
- 239000004576 sand Substances 0.000 description 14
- 230000006870 function Effects 0.000 description 9
- 238000013461 design Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0499—Feedforward networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a method and a device for diagnosing faults of underground working conditions, and belongs to the field of safety diagnosis of tubular columns. And (3) classifying factors influencing disconnection of the sucker rod into a pump working condition influence factor and a shaft working condition influence factor, integrating the two influence factors into an existing mechanical model, enabling the maximum suspension point load of the up-down stroke to be matched with the on-site working condition through adjusting parameters, examining deviation conditions of the influence factors, and judging what kind of abnormality specifically occurs underground. The diagnosis method can diagnose the breaking reason of the sucker rod according to the ground key parameters, and can diagnose not only the abnormality of the pump, but also the abnormality of the friction resistance of the shaft. Meanwhile, the intelligent diagnosis is performed by the diagnosis model trained by machine learning based on the BP neural network, so that the influence factors of the actual reaction conditions can be estimated better, the method has the advantages of high diagnosis efficiency and good prediction accuracy, has very important reference significance for the field application of the sucker-rod pump oil extraction system, and overcomes the defect that most of China depends on the prediction diagnosis of the indicator diagram at present.
Description
Technical Field
The invention relates to the technical field of pipe column safety diagnosis, in particular to a method and a device for diagnosing underground working condition faults.
Background
The oil extraction by a sucker rod pump is one of the traditional mechanical oil extraction modes in China at present, and occupies 80% of the production wells of various oil fields in China. At present, most of oil fields in China enter a high water content stage, so that not only is the oil extraction cost increased, but also the possibility of breaking off and breaking down of the sucker rod (abnormal underground working conditions) is greatly increased. And once the sucker rod is disconnected, the fishing operation is required, and the problems of farmland damage and pay, rod pump re-well entering and the like possibly caused by the fishing operation cost, the production stopping effect and the large-scale equipment approach operation are considered, so that great economic loss is brought to the oil field. In order to avoid the influence caused by breaking and disengaging faults of the sucker rod, the underground working condition faults should be predicted and diagnosed before the problems occur as much as possible. The traditional diagnosis method mostly depends on analysis of the indicator diagram, so that whether the pump has problems or not is diagnosed, but friction influence cannot be diagnosed.
Therefore, how to provide a more comprehensive fault diagnosis method for the underground working condition is a problem to be solved at present.
Disclosure of Invention
The invention provides a method and a device for diagnosing underground working condition faults, which are time-saving and labor-saving, high in diagnosis efficiency and good in prediction precision, and make up for the defect that the prediction diagnosis is mostly dependent on an indicator diagram in China at present. The specific scheme is as follows:
In a first aspect, the application discloses a method for diagnosing faults of underground working conditions, which comprises the following steps:
establishing a mechanical theoretical model of the sucker rod, wherein the theoretical model is used for calculating theoretical values of maximum suspension point loads of the upper stroke and the lower stroke of the sucker rod of a target oil well;
acquiring actual values of the maximum suspension point loads of the up stroke and the down stroke of the sucker rod of the target oil well acquired on site;
introducing a pump working condition influence factor and a shaft working condition influence factor into the theoretical model, and establishing a mapping relation between the pump working condition influence factor and the shaft working condition influence factor and the maximum suspension point loads of the upper stroke and the lower stroke of the sucker rod;
initializing values of a pump working condition influence factor and a shaft working condition influence factor, and introducing the actual values into a fault diagnosis prediction model to obtain the pump working condition influence factor and the shaft working condition influence factor matched with the actual values;
and comparing the matching result with the initialized value, and judging the situation of underground abnormality through the deviation situation of the influence factors.
Optionally, the step of calculating the theoretical value of the maximum suspension point load of the up stroke and the down stroke of the sucker rod of the target oil well specifically includes:
and carrying out sectional calculation on the sucker rod by adopting a micro-element method to obtain the theoretical value of the maximum suspension point load of the upper stroke and the lower stroke of the sucker rod.
Alternatively, in the theoretical model,
the related factors of the pump working condition influence factors comprise resistance generated by the well fluid passing through the traveling valve, friction force between the plunger of the oil pump and the liner, and pump port pressure;
the related factors of the wellbore working condition influence factors comprise contact force of the oil pipe on the sucker rod, equivalent friction resistance of the well fluid on the sucker rod and friction force between the well fluid and the oil pipe.
Optionally, introducing a pump working condition influence factor and a shaft working condition influence factor into the theoretical model, and establishing a mapping relation between the pump working condition influence factor and the shaft working condition influence factor and the maximum suspension point load of the upper stroke and the lower stroke of the sucker rod, which specifically comprises the following steps:
after the influence factors are integrated into the theoretical model, the calculation formula of the micro-element stress of the upstroke sucker rod is as follows:
the calculation formula of the micro-element stress of the down stroke sucker rod is as follows:
wherein F is s(j) 、F x(j) Axial force f at j-position of upper, lower and stroke sucker rod trace element nodes r Is the buoyancy force exerted by the sucker rod in unit length, q r Is the gravity of the sucker rod in unit length, f Ir Is the inertial force of the sucker rod in unit length, f mz Is the friction resistance of the well fluid applied to the sucker rod in unit length, f lss 、f lsx The acting force of the up-stroke well fluid flow and the down-stroke well fluid flow on the sucker rod in unit length is respectively shown as f, the friction coefficient of the oil pipe and the sucker rod is shown as f, the supporting force of the oil pipe on the micro element of the sucker rod is shown as N, and m r Is the micro-element mass of the sucker rod, a s 、a x Acceleration of the upper stroke sucker rod and the lower stroke sucker rod are respectively the minor elements;
the boundary condition calculating method comprises the following steps:
wherein K is r K is the pump working condition influencing factor w Is the working condition influence factor of a shaft，F s(0) F is the force acting on the sucker rod bottom end plunger in the upstroke x(0) To force on the plunger at the bottom end of the sucker rod during the downstroke, w ls For liquid column load on the plunger, f cp F is the friction force between the pump plunger and the liner tl F is the friction force between the well fluid and the oil pipe hu F for the influence of the back pressure of the upstroke wellhead Il For inertial loading of liquid column, p P For the load of the gas in the pump on the plunger, f v Resistance to passage of well fluid through the travelling valve bore, f hd Is the wellhead back pressure effect.
Optionally, initializing values of the pump working condition influencing factors and the shaft working condition influencing factors, and bringing the actual values into a fault diagnosis prediction model to obtain the pump working condition influencing factors and the shaft working condition influencing factors matched with the actual values, which specifically comprises the following steps:
assigning an initial value of 1 to both the pump working condition influencing factor and the shaft working condition influencing factor;
inputting the actual value into a fault diagnosis prediction model;
the fault diagnosis prediction model adjusts the values of the pump working condition influence factors and the shaft working condition influence factors, so that the maximum suspension point loads of the up stroke and the down stroke of the sucker rod calculated by the adjusted pump working condition influence factors and the shaft working condition influence factors are matched with the actual values;
And outputting the regulated chemical pump working condition influence factors and the well bore working condition influence factors.
Optionally, the training method of the fault diagnosis prediction model includes:
the pump working condition influence factors and the shaft working condition influence factors are respectively valued and combined in a (0, 1) interval at certain intervals to obtain a plurality of influence factor groups;
respectively bringing each influence factor group into the theoretical model, and calculating to obtain the maximum suspension point load value of the up and down strokes of the sucker rod corresponding to each influence factor group;
combining an influence factor group and corresponding maximum suspension point load values of the upper stroke and the lower stroke of the sucker rod to obtain a data group;
dividing a plurality of data groups obtained according to a plurality of influence factor groups into a test set and a verification set, and carrying out learning training through a BP neural network model; the maximum suspension point load value of the up stroke and the down stroke of the sucker rod is used as the input of a training model, and the influence factor group is used as the output of the training model.
Optionally, comparing the matching result with the initialized value, and judging the situation of the underground abnormality by the deviation situation of the influencing factors, which specifically includes:
respectively comparing the deviation degree of the pump working condition influence factor and the shaft working condition influence factor which are output by the fault diagnosis prediction model with an initial value 1;
The higher the deviation degree between the influence factor and the initial value 1 is, the higher the probability of working condition faults caused by corresponding reasons is judged.
In a second aspect, the application discloses a downhole operating condition fault diagnosis device, comprising:
the model building unit is used for building a theoretical model of sucker rod force, and the theoretical model is used for calculating theoretical values of maximum suspension point loads of the up stroke and the down stroke of the sucker rod of the target oil well;
the data acquisition unit is used for acquiring actual values of the maximum suspension point load of the up stroke and the down stroke of the sucker rod of the target oil well acquired on site;
the factor introducing unit is used for introducing a pump working condition influence factor and a shaft working condition influence factor into the theoretical model and establishing a mapping relation between the pump working condition influence factor and the shaft working condition influence factor and the maximum suspension point load of the upper stroke and the lower stroke of the sucker rod;
the prediction calculation unit is used for initializing the values of the pump working condition influence factors and the shaft working condition influence factors, and bringing the actual values into a fault diagnosis prediction model to obtain the pump working condition influence factors and the shaft working condition influence factors matched with the actual values;
and the fault diagnosis unit is used for comparing the matching result with the initialized value and judging the situation of underground abnormality through the deviation situation of the influence factors.
In a third aspect of an embodiment of the present invention, there is provided an electronic device, including:
one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to perform the method of the first aspect.
In a fourth aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored therein program code which is callable by a processor to perform the method according to the first aspect.
In summary, the invention provides a method and a device for diagnosing a fault under an underground working condition, which are used for classifying factors influencing disconnection of a sucker rod into a pump working condition influence factor and a shaft working condition influence factor, integrating the two influence factors into an existing mechanical model, and supposing that a theoretical calculation model is an ideal working condition model, reducing the influence factors when the underground working condition deviates from a design or the underground environment is deteriorated. The maximum suspension point load of the up-down stroke is matched with the on-site working condition by adjusting parameters, and the deviation condition of the influence factors is examined, so that the specific occurrence of the abnormality in the underground can be primarily judged. The diagnosis method can diagnose the breaking reason of the sucker rod according to the ground key parameters, and can diagnose not only the abnormality of the pump, but also the abnormality of the friction resistance of the shaft. Meanwhile, the method combines a diagnosis model trained by machine learning based on the BP neural network, can better estimate the influence factors of the actual reaction conditions, has the advantages of high diagnosis efficiency and good prediction accuracy, and has very important reference significance for the field application of the sucker-rod pump oil extraction system.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for diagnosing downhole operating conditions according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a micro-element configuration of a sucker rod in an inclined well according to an embodiment of the present invention;
FIG. 3 is a graph of an analysis of the force applied to an upstroke sucker rod according to an embodiment of the present invention;
FIG. 4 is a graph of a down stroke sucker rod stress analysis of an embodiment of the present invention;
FIG. 5 is a graph showing the theoretical and actual values of the load at the maximum suspension point of the upstroke according to the embodiment of the invention;
FIG. 6 is a graph showing a theoretical value of the down-stroke maximum suspension point load versus an actual value in accordance with an embodiment of the present invention;
FIG. 7 is a graph showing a comparison of a theoretical value and an actual value of a maximum suspension point load of an up-stroke after matching according to an embodiment of the present invention;
FIG. 8 is a graph showing a comparison of a theoretical value and an actual value of a post-match downstroke maximum suspension point load in accordance with an embodiment of the present invention;
FIG. 9 is a functional block diagram of a downhole operating condition fault diagnostic apparatus according to an embodiment of the present application;
FIG. 10 is a block diagram of an electronic device for performing a method of downhole operating condition fault diagnosis according to an embodiment of the present application;
FIG. 11 is a block diagram of a computer readable storage medium storing or carrying program code for implementing a method for downhole operating condition fault diagnosis according to an embodiment of the application.
Icon:
a model building unit 110; a data acquisition unit 120; a factor introduction unit 130; a prediction calculation unit 140; a fault diagnosis unit 150; an electronic device 300; a processor 310; a memory 320; a computer-readable storage medium 400; program code 410.
Detailed Description
The oil extraction by a sucker rod pump is one of the traditional mechanical oil extraction modes in China at present, and occupies 80% of the production wells of various oil fields in China. At present, most of oil fields in China enter a high water content stage, so that not only is the oil extraction cost increased, but also the possibility of breaking off and breaking down of the sucker rod (abnormal underground working conditions) is greatly increased. And once the sucker rod is disconnected, the fishing operation is required, and the problems of farmland damage and pay, rod pump re-well entering and the like possibly caused by the fishing operation cost, the production stopping effect and the large-scale equipment approach operation are considered, so that great economic loss is brought to the oil field. In order to avoid the influence caused by breaking and disengaging faults of the sucker rod, the underground working condition faults should be predicted and diagnosed before the problems occur as much as possible. The traditional diagnosis method mostly depends on analysis of the indicator diagram, so that whether the pump has problems or not is diagnosed, but friction influence cannot be diagnosed.
Conventional downhole condition prediction and diagnosis methods often require a significant amount of manpower. Machine learning has been widely used today in a variety of engineering applications and in complex problems in the scientific field. Machine learning has been in the brand-new angle in the petroleum field in recent years, and has been excellent in terms of improving work efficiency, reducing work costs, providing safety measures, and the like.
Therefore, how to provide a more comprehensive fault diagnosis method for the underground working condition is a problem to be solved at present.
Based on the problems, the invention designs the neural network underground working condition fault prediction diagnosis method based on the ground parameters, namely the maximum suspension point load of the top dead center and the bottom dead center, and the method can directly perform prediction diagnosis on underground faults through the on-site collected rod pipe pump parameters, can diagnose the abnormality of the pump and the friction of a shaft, saves time and labor, and has practical significance and good application prospect.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "top", "bottom", "inner", "outer", etc., are directions or positional relationships based on those shown in the drawings, or those that are conventionally put in use, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
As shown in FIG. 1, the method for diagnosing the fault of the underground working condition comprises the following steps:
step S101, a mechanical theoretical model of the sucker rod is established, and the theoretical model is used for calculating theoretical values of maximum suspension point loads of the upper stroke and the lower stroke of the sucker rod of the target oil well.
Based on the specific conditions of the underground working conditions, a mechanical theoretical model of the sucker rod is established, and the dynamic characteristics and mechanical behaviors of the system can be analyzed by solving the model. By establishing a mathematical model of the relevant key factors and applying appropriate analytical techniques, forces, stresses, deformations and vibrations of the sucker rod system under different conditions can be predicted.
After the theoretical model is established, as a preferred implementation mode, when calculating the theoretical value of the maximum suspension point load of the up stroke and the down stroke of the sucker rod of the target oil well, the sectional calculation can be carried out on the sucker rod by adopting a micro-element method, wherein the micro-element form of the sucker rod in a common inclined well is shown as figure 2, and the sucker rod in a working state has bending deformation along with the track shape of a well.
The specific calculation mode is as follows:
in a common inclined well, a section (a micro-element of the sucker rod) on the sucker rod is intercepted for stress analysis, and Newton's second law of motion is applied to the micro-element section, and then the method comprises the following steps:
in the formula (1):
m r -sucker rod infinitesimal mass, kg;
a-the micro-acceleration of the sucker rod, N.kg < -1 >;
-sum of the micro forces of the sucker rod, N.
The stress condition of the sucker rod is shown in fig. 3 and 4, and based on the stress condition, the sucker rod is obtained according to the balance principle by combining the formula (1):
the micro-element stress of the upstroke sucker rod is as follows:
(F s(j+1) -F s(j) )-Δx·(q r -f r )cosα-Δx·(f Tr +f 1ss )-f·N＝m r ·a s (2-a)
the infinitesimal stress of the down stroke sucker rod is as follows:
(F x(j) -F x(j+1) )+Δx·(q r -f r )cosα-Δx·(f Tr +f mz +f 1sx )-f·N＝m r ·a x (2-b)
wherein:
F s(j) ，F x(j) -axial force, N, at the micro-element node j of the sucker rod for up and down strokes, respectively;
F s(j+1) ，F x(j+1) -axial force, N, at the micro-element node j+1 of the up-down stroke sucker rod, respectively;
f r -buoyancy exerted by the sucker rod per unit length, n·m -1 ；
q r -weight of sucker rod per unit length, n.m -1 ；
f Ir -inertial force of sucker rod per unit length, n.m -1 ；
f mz -friction resistance of the well fluid to which the sucker rod is subjected per unit length, n·m -1 ；
f lss ，f lsx -force of up-down stroke well stream on sucker rod unit length, n·m -1 ；
f-friction coefficient between the oil pipe and the sucker rod;
the supporting force of the N-oil pipe to the micro-element of the sucker rod, N;
m r -sucker rod infinitesimal mass, kg.
a s 、a x Acceleration of the upper and lower stroke sucker rod primordia, n.kg -1 。
Therefore, the axial force at the up and down stroke sucker rod node j+1 is:
F s(j+1) ＝F s(j) +Δx·(q r -f r )cosα+Δx·(f Tr +f 1ss )+f·N+m r ·a s (3-a)
F x(j+1) ＝F x(j) +Δx·(q r -f r )cosα-Δx·(f Tr +f mz +f 1sx )-f·N-m r ·a x (3-b)
the formula (3-a) and the formula (3-b) are the micro-element stress model of the sucker rod.
Defining the connection point of the sucker rod and the plunger as a node 0, and obtaining F according to the related boundary conditions s(0) And F x(0) Substituting the above formula, and adopting an iterative algorithm to obtain the axial force born by each node on the sucker rod.
The boundary condition calculating method comprises the following steps:
F s(0) ＝w 1s +f cp +f t1 +f hu +f 1 -p p (4-a)
F x(0) ＝-(f v +f cp +f hd ) (4-b)
wherein:
F s(0) the force acting on the plunger at the bottom end of the sucker rod during the upstroke, positive, typically pulling, N;
F x(0) the force acting on the plunger at the bottom end of the sucker rod during the downstroke, negative, typically pressure, N;
w ls -a liquid column load on the column, N;
f cp -friction between the pump plunger and the liner, N;
f t1 -friction between the well fluid and the tubing, N;
f hu -upstroke wellhead back pressure effect, N;
f I1 -liquid column inertial load, N;
p P -the load of the gas in the pump on the plunger, N;
f v -resistance created by the passage of well fluid through the travelling valve orifice, N;
f hd wellhead back pressure effect, N.
Wherein the calculation of 12 forces in the formula (4-a) and the formula (3-b) is shown in the table (1):
table (1) summary of mechanical calculation model table
Wherein:
ρ r sucker rod material density, kg/m 3 ；
ρ s Density of collar material, kg/m 3 ；
ρ f Centralizer material density, kg/m 3 ；
The total length of the L-sucker rod, the coupling and the centralizer is m;
L r -total sucker rod length, m;
L s -total length of coupling, m;
L f -total centralizer length, m;
k-the coefficient of influence of the rod string vibration to increase the resistance of the traveling valve;
Δp o equal to the pressure drop produced by the passage of the well fluid through the travelling valve, N/m 2 ；
Δp i -the pressure drop of the well fluid passing through the fixed valve is approximately equal to the pressure drop of the well fluid passing through the travelling valve, N/m 2 ；
H-pump hanging deep, m;
H c -depth of submergence in vertical direction, m;
A r sucker rod cross-sectional area, m 2 ；
A s Coupling cross-sectional area, m 2 ；
A f Centralizer cross-section area, m 2 ；
A p Plunger cross-sectional area, m 2 ；
A t -oil tube cross-sectional area, m 2 ；
ρ l Oil density, kg/m 3 ；
L f -total centralizer length, m;
F lss -the force of the well stream flow on the whole string, N, on the upstroke;
F lsx -the force exerted by the well stream on the whole string on the downstroke, N;
a-sucker rod string acceleration, m/s 2 ；
Epsilon-considers the oil column acceleration reduction coefficient caused by the expansion of the flow section of the oil pipe;
p h -wellhead back pressure, pa;
n y -number of traveling valves;
g-gravitational acceleration, N/kg;
d p -plunger diameter, m;
a gap m between the delta-oil pump plunger and the bushing in the radial direction;
S p -pumping unit effective stroke, m;
S y -level in pump, m;
R s -ground gas-oil ratio, m 3 /m 3 ；
Alpha-solubility coefficient, m 3 /(m 3 MPa)；
p p -gas pressure in pump, pa;
p 0 -standard pressure, pa;
b 0 -crude oil volume coefficient;
f w -water content, decimal;
t-pump inlet temperature, K;
T 0 -ground temperature, K;
y-natural gas compression factor.
f r1 -friction resistance of the well fluid against the sucker rod per unit length, N/m;
f s1 -frictional resistance of the well fluid to the collar per unit length, N/m;
f f1 -frictional resistance of the well fluid to the centralizer per unit length, N/m;
f mz -equivalent friction of the well fluid against the sucker rod string of unit length, N/m;
substituting the formulas in table 1 into corresponding positions for solving, and combining boundary conditions, iterating upwards from the bottom end of the sucker rod to the wellhead to obtain the suspension point loads of the sucker rod in the upstroke and the downstroke, and further respectively obtaining the maximum suspension point loads of the sucker rod in the upstroke and the downstroke on the basis.
Through the steps, the calculation of the theoretical value of the maximum suspension point load of the upper stroke and the lower stroke of the sucker rod can be realized based on the theoretical model. And carrying corresponding parameter values for different target wells, and calculating theoretical values of maximum suspension point loads of the up and down strokes of the sucker rod for different target wells.
It should be noted that, as other implementations of the embodiments of the present invention, the calculation of the theoretical value of the maximum suspension point load of the up-stroke and the down-stroke of the sucker rod may be performed by using any one of the disclosed models or algorithms, or may be performed by using an improved or optimized model or algorithm, which is not limited herein specifically.
Step S102, obtaining actual values of maximum suspension point loads of the upper and lower strokes of the sucker rod of the target oil well acquired on site.
And aiming at a target oil well needing fault diagnosis and prediction, on-site collecting actual values of maximum suspension point loads of the upper and lower strokes of the sucker rod of the target oil well for subsequent matching.
It should be noted that the method for acquiring the actual values of the maximum suspension point loads of the up and down strokes of the sucker rod of the target oil well is not particularly limited herein.
Step S103, introducing a pump working condition influence factor and a shaft working condition influence factor into the theoretical model, and establishing a mapping relation between the pump working condition influence factor and the shaft working condition influence factor and the maximum suspension point loads of the upper stroke and the lower stroke of the sucker rod.
The pump working condition influencing factor K is introduced into a theoretical model r And a well bore condition affecting factor K w Wherein the pump condition affects factor K r Corresponding to the condition of pump working condition and the well bore working condition influence factor K w Corresponding to the working condition of the shaft.
In particular, the pump operating conditions are for the twelve forces referred to in Table 1Influence factor K r The related factors of (1) include the resistance F generated by the well fluid passing through the traveling valve v Friction force F between plunger and liner of oil pump cp Pump port pressure P p The method comprises the steps of carrying out a first treatment on the surface of the The shaft working condition influence factor K w The related factors of (a) include the contact force f of the oil pipe to the sucker rod rt Equivalent friction resistance f of well fluid to sucker rod mz Friction force F between well fluid and oil pipe t1 。
After the influence factors are integrated into the sucker rod force theory model, the calculation formula of the micro-element stress of the upstroke sucker rod is as follows:
the calculation formula of the micro-element stress of the down stroke sucker rod is as follows:
the boundary condition calculation method after the influence factors are integrated is as follows:
by integrating the influence factors into the calculation formulas of the micro-element stress of the sucker rod in the up and down strokes, the mapping relation between the influence factors and the maximum suspension point loads in the up and down strokes of the sucker rod is established, namely, the theoretical values of the corresponding maximum suspension point loads in the up and down strokes of the sucker rod can be calculated through the theoretical model based on the acquired ground key parameters and the values of the influence factors.
Step S104, initializing values of a pump working condition influence factor and a shaft working condition influence factor, and bringing the actual values into a fault diagnosis prediction model to obtain the pump working condition influence factor and the shaft working condition influence factor matched with the actual values.
According to the mapping relation between the influence factors and the maximum suspension point loads of the upper and lower strokes of the sucker rod, the fault diagnosis prediction model can correspondingly determine pump working condition influence factors and shaft working condition influence factors matched with the actual values according to the actual values of the maximum suspension point loads of the upper and lower strokes of the sucker rod acquired on site. The method flow corresponding to step S104 specifically includes:
assigning an initial value of 1 to both the pump working condition influencing factor and the shaft working condition influencing factor;
inputting the actual value into a fault diagnosis prediction model;
the fault diagnosis prediction model adjusts the values of the pump working condition influence factors and the shaft working condition influence factors, so that the maximum suspension point loads of the up stroke and the down stroke of the sucker rod calculated by the adjusted pump working condition influence factors and the shaft working condition influence factors are matched with the actual values;
and outputting the regulated chemical pump working condition influence factors and the well bore working condition influence factors.
The impact factor decreases as the downhole conditions deviate from design or the downhole environment deteriorates. The suspension point load is matched with the on-site working condition by adjusting parameters, and the deviation condition of the influence factors is examined, so that the specific occurrence of the abnormality in the underground can be primarily judged.
On the basis of the above, as a preferred implementation manner of the embodiment of the present invention, in order to improve the accuracy of calculation of the fault diagnosis prediction model, a BP neural network model is adopted for learning training, and a specific training method includes:
The pump working condition influence factors and the shaft working condition influence factors are respectively valued and combined in a (0, 1) interval at certain intervals to obtain a plurality of influence factor groups;
respectively bringing each influence factor group into the theoretical model, and calculating to obtain the maximum suspension point load value of the up and down strokes of the sucker rod corresponding to each influence factor group;
combining an influence factor group and corresponding maximum suspension point load values of the upper stroke and the lower stroke of the sucker rod to obtain a data group;
dividing a plurality of data groups obtained according to a plurality of influence factor groups into a test set and a verification set, and carrying out learning training through a BP neural network model; the maximum suspension point load value of the up stroke and the down stroke of the sucker rod is used as the input of a training model, and the influence factor group is used as the output of the training model.
When the test set and the verification set for training are constructed, two influence factors (0, 1) are valued at intervals of 0.01 and are combined with each other to obtain ten thousand influence factor groups, then ten thousand influence factor groups are respectively brought into the theoretical model, the maximum suspension point load values of the upper stroke and the lower stroke of the sucker rod corresponding to the ten thousand influence factor groups are calculated and obtained, ten thousand data groups are obtained through combination, finally, the ten thousand data groups are divided into two parts of the test set and the verification set, a BP neural network model is selected for learning, and the ten thousand data groups obtained by a target well are put into the BP neural network model for learning.
The BP neural network model is used for learning training, and a large number of data sets can be used for enabling the generated fault diagnosis prediction model to more accurately estimate the influence factor set corresponding to the actual value. According to the theoretical model introduced with the influence factors, the influence factors with different values are substituted, and the corresponding maximum suspension point load values of the up stroke and the down stroke of the sucker rod can be calculated by combining the related parameter values acquired on site. In actual fault prediction diagnosis, the fault diagnosis prediction model is required to calculate and estimate an influence factor group with the highest possibility of corresponding to the actual value according to the actual value of the maximum suspension point load of the oil rod up and down stroke acquired on site, and the influence factor group is used as output. Therefore, when learning and training are performed, the larger the data set is, the higher the accuracy is, and the more accurate the obtained fault diagnosis prediction model estimates the influence factor group.
Step S105, comparing the matching result with the initialized value, and judging the situation of underground abnormality through the deviation situation of the influence factors.
The impact factor decreases as the downhole conditions deviate from design or the downhole environment deteriorates. Therefore, based on the influence factor group output by the fault diagnosis prediction model, respectively comparing the deviation degree of the pump working condition influence factor and the shaft working condition influence factor output by the fault diagnosis prediction model from an initial value 1; the higher the deviation degree between the influence factor and the initial value 1 is, the higher the probability of working condition faults caused by corresponding reasons is judged. The two working conditions can be judged simultaneously by comparing the working conditions of the pump and the working conditions of the shaft which are respectively corresponding to the two influencing factors.
The following describes a method for diagnosing the fault of the underground working condition by using a specific case:
the application of the underground working condition fault diagnosis method is respectively carried out by taking 16 fault wells of a certain block as target wells, and the specific flow is as follows:
(1) Firstly, a mechanical theoretical model of the sucker rod is established, and the theoretical values of the maximum suspension point load of the up stroke and the down stroke of the sucker rod of the target well are calculated respectively, wherein the calculation results are shown in fig. 5 and 6.
(2) And (3) comparing the theoretical value calculated in the step (1) with the actual value of the up-stroke and down-stroke maximum suspension point load acquired on site, wherein the comparison result is shown in fig. 5 and 6. As can be seen from the figure, the theoretical value of the maximum suspension point load of the upper stroke is generally lower than the calculated value of the maximum suspension point load of the upper stroke, and the theoretical value of the maximum suspension point load of the lower stroke is generally higher than the calculated value of the maximum suspension point load of the lower stroke.
(3) Introducing pump working condition influencing factor K r And a well bore condition affecting factor K w 。
(4) And 3) merging the two influencing factors in the step 3) into the existing mechanical model, and giving the initial parameter of the model to be 1 under the assumption that the theoretical calculation model is an ideal working condition model, wherein the influencing factors are reduced when the underground working condition deviates from the design or the underground environment is deteriorated. And obtaining an influence factor group which enables the calculated values of the maximum suspension point loads of the up stroke and the down stroke to be matched with the actual values acquired on site through a fault diagnosis prediction model, wherein specific prediction results are shown in fig. 7 and 8. The deviation condition of the obtained influence factor group is examined, and the specific occurrence of the abnormality in the underground can be primarily judged.
The results of the determination for 16 faulty wells are shown in table (2):
TABLE (2) influence factor match results Table
| Sequence number | Well number | Well bore condition influencing factor K w | Pump condition influencing factor K r | Diagnosis of abnormality cause |
| 1 | Sand 23-14 | 0.46 | 1.00 | Working condition of shaft |
| 2 | Sand 7-3 | 0.40 | 0.95 | Working condition of shaft |
| 3 | Sand 23-1 | 1.00 | 0.16 | Pump condition |
| 4 | Sand 19-58 | 0.55 | 0.20 | Pump condition |
| 5 | Sand 19-45 | 0.21 | 0.91 | Working condition of shaft |
| 6 | Hair 2-23 | 0.51 | 0.94 | Working condition of shaft |
| 7 | Sand 23-21 | 0.01 | 0.67 | Working condition of shaft |
| 8 | Sand 19-12 | 0.19 | 0.96 | Working condition of shaft |
| 9 | Sand 36-3 | 0.20 | 1.00 | Working condition of shaft |
| 10 | Sand 18-12 | 0.57 | 0.01 | Pump condition |
| 11 | Sand 26-24 | 0.27 | 0.31 | Pump condition and wellbore condition |
| 12 | Sand 19-85 | 0.4 | 0.5 | Pump condition and wellbore condition |
| 13 | Sand 20-79 | 0.3 | 0.1 | Pump condition and wellbore condition |
| 14 | Sand 75A | 0.86 | 0.01 | Pump condition |
| 15 | Hair X10 | 0.49 | 0.01 | Pump condition and wellbore condition |
| 16 | Sand 19-44A | 1.00 | 0.06 | Pump condition |
It can be seen from the data in table (2) that the lower the number of influencing factors, the higher the probability of operating mode failure due to the corresponding cause. Generally, when the value of a certain influence factor is lower than 0.5, the corresponding reason is indicated to cause the working condition to be faulty.
In order to further explain the underground working condition fault diagnosis method provided by the invention, a specific fault well is taken as an example, and the specific application steps are as follows:
1) Establishing a mechanical theoretical model of the sucker rod, and respectively calculating the maximum suspension point load theoretical values of the upstroke and the downstroke of the sucker rod of the target well: the target well has an upstroke maximum suspension point load of 55949; the target well has a downstroke maximum suspension point load of 39468.
2) Comparing the value obtained in the step 1) with the actual value of the up-and-down stroke maximum suspension point load acquired on site: as can be seen from the field detection data, the on-site value of the maximum suspension point load of the target well is 60640; the target downhole stroke maximum suspension point load field value is 36650.
3) Introducing pump working condition influencing factor K r And a well bore condition affecting factor K w 。
4) And (3) placing the two influence factors between 0 and 1 into a mechanical model at intervals of 0.01 for calculation to obtain ten thousand data sets consisting of the influence factor sets and the up-stroke and down-stroke maximum suspension point loads. And dividing ten thousand data components into a test set and a verification set, and selecting a BP neural network model for learning.
5) The on-site value of the maximum suspension point load of the up-stroke and the down-stroke of the target well is put into a fault diagnosis prediction model to be predicted, and the influence factor K of the working condition of the shaft is obtained w The predicted result was 0.51; to the pump working condition influencing factor K r The prediction result is that0.94. The results indicate that the cause of the failure of the target downhole conditions is associated with the wellbore.
6) The on-site working nodule of the target well observes that the sucker rod has the phenomena of wax deposition, scaling and eccentric wear, which indicates that the failure cause of the down-hole working condition of the target well is related to the working condition of the shaft, and further proves that the predictive diagnosis method is effective.
In summary, according to the underground working condition fault diagnosis method provided by the embodiment of the invention, factors influencing disconnection of the sucker rod are classified into the pump working condition influence factor and the shaft working condition influence factor, the two influence factors are integrated into the existing mechanical model, the theoretical calculation model is assumed to be an ideal working condition model, and when the underground working condition deviates from the design or the underground environment is deteriorated, the influence factors are reduced. The maximum suspension point load of the up-down stroke is matched with the on-site working condition by adjusting parameters, and the deviation condition of the influence factors is examined, so that the specific occurrence of the abnormality in the underground can be primarily judged. The diagnosis method can diagnose the breaking reason of the sucker rod according to the ground key parameters, and can diagnose not only the abnormality of the pump, but also the abnormality of the friction resistance of the shaft. Meanwhile, the intelligent diagnosis is performed by combining a diagnosis model trained by machine learning based on the BP neural network, the influence factors of the actual reaction conditions can be estimated better, the diagnosis efficiency is high, the prediction accuracy is good, and the intelligent diagnosis method has very important reference significance for the field application of the sucker-rod pump oil extraction system. The method is time-saving and labor-saving, has high diagnosis efficiency, and overcomes the defect that most of China depends on the prediction diagnosis of the indicator diagram at present.
As shown in fig. 9, the device for diagnosing a fault in a downhole working condition provided by the embodiment of the invention comprises:
a model building unit 110 for building a theoretical model of sucker rod mechanics for calculating theoretical values of maximum suspension point loads of up and down strokes of the sucker rod of the target oil well;
the data acquisition unit 120 is used for acquiring actual values of the maximum suspension point load of the up stroke and the down stroke of the sucker rod of the target oil well acquired on site;
a factor introducing unit 130, configured to introduce a pump working condition influence factor and a wellbore working condition influence factor into the theoretical model, and establish a mapping relationship between the pump working condition influence factor and the wellbore working condition influence factor and the maximum suspension point loads of the up and down strokes of the sucker rod;
the prediction calculation unit 140 is configured to initialize values of a pump working condition influence factor and a wellbore working condition influence factor, and bring the actual values into a fault diagnosis prediction model to obtain the pump working condition influence factor and the wellbore working condition influence factor that are matched with the actual values;
the fault diagnosis unit 150 is configured to compare the matching result with the initialized value, and determine that an abnormality occurs in the well by affecting the deviation of the factors.
The downhole working condition fault diagnosis device provided by the embodiment of the invention is used for realizing the downhole working condition fault diagnosis method, so that the specific implementation mode is the same as the method and is not repeated here.
As shown in fig. 10, an embodiment of the present application provides a block diagram of an electronic device 300. The electronic device 300 may be a smart phone, tablet, electronic book, etc. capable of running an application program of the electronic device 300. The electronic device 300 of the present application may include one or more of the following components: a processor 310, a memory 320, and one or more application programs, wherein the one or more application programs may be stored in the memory 320 and configured to be executed by the one or more processors 310, the one or more program(s) configured to perform the method as described in the foregoing method embodiments.
Processor 310 may include one or more processing cores. The processor 310 utilizes various interfaces and lines to connect various portions of the overall electronic device 300, perform various functions of the electronic device 300, and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 320, and invoking data stored in the memory 320. Alternatively, the processor 310 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 310 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 310 and may be implemented solely by a single communication chip.
The Memory 320 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Memory 320 may be used to store instructions, programs, code sets, or instruction sets. The memory 320 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described below, etc. The storage data area may also store data created by the terminal in use (such as phonebook, audio-video data, chat-record data), etc.
As shown in fig. 11, an embodiment of the present invention provides a block diagram of a computer-readable storage medium 400. The computer readable medium has stored therein a program code 410, said program code 410 being callable by a processor for performing the method described in the above method embodiments.
The computer readable storage medium 400 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 400 comprises a non-volatile computer readable medium (non-transitory computer-readable storage medium). The computer readable storage medium 400 has storage space for program code 410 that performs any of the method steps described above. These program code 410 can be read from or written to one or more computer program products. Program code 410 may be compressed, for example, in a suitable form.
In summary, the invention provides a method and a device for diagnosing a fault under an underground working condition, which are used for classifying factors influencing disconnection of a sucker rod into a pump working condition influence factor and a shaft working condition influence factor, integrating the two influence factors into an existing mechanical model, and supposing that a theoretical calculation model is an ideal working condition model, reducing the influence factors when the underground working condition deviates from a design or the underground environment is deteriorated. The maximum suspension point load of the up-down stroke is matched with the on-site working condition by adjusting parameters, and the deviation condition of the influence factors is examined, so that the specific occurrence of the abnormality in the underground can be primarily judged. The diagnosis method can diagnose the breaking reason of the sucker rod according to the ground key parameters, and can diagnose not only the abnormality of the pump, but also the abnormality of the friction resistance of the shaft. Meanwhile, the intelligent diagnosis is performed by combining a diagnosis model trained by machine learning based on the BP neural network, the influence factors of the actual reaction conditions can be estimated better, the diagnosis efficiency is high, the prediction accuracy is good, and the intelligent diagnosis method has very important reference significance for the field application of the sucker-rod pump oil extraction system. The method is time-saving and labor-saving, has high diagnosis efficiency, and overcomes the defect that most of China depends on the prediction diagnosis of the indicator diagram at present.
In the several embodiments disclosed herein, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Claims (10)
1. A method for diagnosing a fault in a downhole condition, comprising:
Establishing a mechanical theoretical model of the sucker rod, wherein the theoretical model is used for calculating theoretical values of maximum suspension point loads of the upper stroke and the lower stroke of the sucker rod of a target oil well;
acquiring actual values of the maximum suspension point loads of the up stroke and the down stroke of the sucker rod of the target oil well acquired on site;
introducing a pump working condition influence factor and a shaft working condition influence factor into the theoretical model, and establishing a mapping relation between the pump working condition influence factor and the shaft working condition influence factor and the maximum suspension point loads of the upper stroke and the lower stroke of the sucker rod;
initializing values of a pump working condition influence factor and a shaft working condition influence factor, and introducing the actual values into a fault diagnosis prediction model to obtain the pump working condition influence factor and the shaft working condition influence factor matched with the actual values;
and comparing the matching result with the initialized value, and judging the situation of underground abnormality through the deviation situation of the influence factors.
2. The method for diagnosing a fault in a downhole operation according to claim 1, wherein the step of calculating a theoretical value of a maximum suspension point load of an up-stroke and a down-stroke of a sucker rod of a target oil well comprises:
and carrying out sectional calculation on the sucker rod by adopting a micro-element method to obtain the theoretical value of the maximum suspension point load of the upper stroke and the lower stroke of the sucker rod.
3. The downhole operation fault diagnosis method according to claim 2, wherein, in the theoretical model,
the related factors of the pump working condition influence factors comprise resistance generated by the well fluid passing through the traveling valve, friction force between the plunger of the oil pump and the liner, and pump port pressure;
the related factors of the wellbore working condition influence factors comprise contact force of the oil pipe on the sucker rod, equivalent friction resistance of the well fluid on the sucker rod and friction force between the well fluid and the oil pipe.
4. The method for diagnosing a fault in a downhole operation condition according to claim 3, wherein the step of introducing a pump operation condition influence factor and a well bore operation condition influence factor into the theoretical model and establishing a mapping relationship between the pump operation condition influence factor and the well bore operation condition influence factor and the maximum suspension point load of the up and down stroke of the sucker rod specifically comprises the steps of:
after the influence factors are integrated into the theoretical model, the calculation formula of the micro-element stress of the upstroke sucker rod is as follows:
the calculation formula of the micro-element stress of the down stroke sucker rod is as follows:
wherein F is s(j) 、F x(j) Axial force f at j-position of upper, lower and stroke sucker rod trace element nodes r Is the buoyancy force exerted by the sucker rod in unit length, q r Is the gravity of the sucker rod in unit length, f Ir Is the inertial force of the sucker rod in unit length, f mz Is the friction resistance of the well fluid applied to the sucker rod in unit length, f lss 、f lsx The acting force of the up-stroke well fluid flow and the down-stroke well fluid flow on the sucker rod in unit length is respectively shown as f, the friction coefficient of the oil pipe and the sucker rod is shown as f, the supporting force of the oil pipe on the micro element of the sucker rod is shown as N, and m r Is the micro-element mass of the sucker rod, a s 、a x Acceleration of the upper stroke sucker rod and the lower stroke sucker rod are respectively the minor elements;
the boundary condition calculating method comprises the following steps:
wherein K is r K is the pump working condition influencing factor w F is the well bore condition influencing factor s(0) F is the force acting on the sucker rod bottom end plunger in the upstroke x(0) To force on the plunger at the bottom end of the sucker rod during the downstroke, w ls For liquid column load on the plunger, f cp F is the friction force between the pump plunger and the liner tl F is the friction force between the well fluid and the oil pipe hu F for the influence of the back pressure of the upstroke wellhead Il For inertial loading of liquid column, p P For the load of the gas in the pump on the plunger, f v Resistance to passage of well fluid through the travelling valve bore, f hd Is the wellhead back pressure effect.
5. The method for diagnosing a fault in a downhole operation according to claim 4, wherein initializing values of a pump operation influence factor and a well bore operation influence factor, and bringing the actual values into a fault diagnosis prediction model to obtain the pump operation influence factor and the well bore operation influence factor matched with the actual values, comprises the following steps:
Assigning an initial value of 1 to both the pump working condition influencing factor and the shaft working condition influencing factor;
inputting the actual value into a fault diagnosis prediction model;
the fault diagnosis prediction model adjusts the values of the pump working condition influence factors and the shaft working condition influence factors, so that the maximum suspension point loads of the up stroke and the down stroke of the sucker rod calculated by the adjusted pump working condition influence factors and the shaft working condition influence factors are matched with the actual values;
and outputting the regulated chemical pump working condition influence factors and the well bore working condition influence factors.
6. The downhole operating mode fault diagnosis method according to claim 5, wherein the training method of the fault diagnosis prediction model comprises:
the pump working condition influence factors and the shaft working condition influence factors are respectively valued and combined in a (0, 1) interval at certain intervals to obtain a plurality of influence factor groups;
respectively bringing each influence factor group into the theoretical model, and calculating to obtain the maximum suspension point load value of the up and down strokes of the sucker rod corresponding to each influence factor group;
combining an influence factor group and corresponding maximum suspension point load values of the upper stroke and the lower stroke of the sucker rod to obtain a data group;
dividing a plurality of data groups obtained according to a plurality of influence factor groups into a test set and a verification set, and carrying out learning training through a BP neural network model; the maximum suspension point load value of the up stroke and the down stroke of the sucker rod is used as the input of a training model, and the influence factor group is used as the output of the training model.
7. The method for diagnosing a fault in an underground condition according to claim 6, wherein the step of comparing the matching result with the initialized value and determining the occurrence of an abnormality in the underground condition by influencing the deviation of the factors comprises:
respectively comparing the deviation degree of the pump working condition influence factor and the shaft working condition influence factor which are output by the fault diagnosis prediction model with an initial value 1;
the higher the deviation degree between the influence factor and the initial value 1 is, the higher the probability of working condition faults caused by corresponding reasons is judged.
8. A downhole operating condition fault diagnostic apparatus, comprising:
the model building unit is used for building a theoretical model of sucker rod force, and the theoretical model is used for calculating theoretical values of maximum suspension point loads of the up stroke and the down stroke of the sucker rod of the target oil well;
the data acquisition unit is used for acquiring actual values of the maximum suspension point load of the up stroke and the down stroke of the sucker rod of the target oil well acquired on site;
the factor introducing unit is used for introducing a pump working condition influence factor and a shaft working condition influence factor into the theoretical model and establishing a mapping relation between the pump working condition influence factor and the shaft working condition influence factor and the maximum suspension point load of the upper stroke and the lower stroke of the sucker rod;
The prediction calculation unit is used for initializing the values of the pump working condition influence factors and the shaft working condition influence factors, and bringing the actual values into a fault diagnosis prediction model to obtain the pump working condition influence factors and the shaft working condition influence factors matched with the actual values;
and the fault diagnosis unit is used for comparing the matching result with the initialized value and judging the situation of underground abnormality through the deviation situation of the influence factors.
9. An electronic device, comprising:
one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to perform the method of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program code, which is callable by a processor for executing the method according to claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310607837.1A CN116595440A (en) | 2023-05-26 | 2023-05-26 | Underground working condition fault diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310607837.1A CN116595440A (en) | 2023-05-26 | 2023-05-26 | Underground working condition fault diagnosis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116595440A true CN116595440A (en) | 2023-08-15 |
Family
ID=87611392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310607837.1A Pending CN116595440A (en) | 2023-05-26 | 2023-05-26 | Underground working condition fault diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595440A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117539155A (en) * | 2024-01-09 | 2024-02-09 | 深圳市威诺达工业技术有限公司 | Optimized control method of electric submersible pump |
-
2023
- 2023-05-26 CN CN202310607837.1A patent/CN116595440A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117539155A (en) * | 2024-01-09 | 2024-02-09 | 深圳市威诺达工业技术有限公司 | Optimized control method of electric submersible pump |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107288617B (en) | Method and system for improving oil measuring precision of indicator diagram of pumping well | |
| US10060247B2 (en) | Hydrocarbon well performance monitoring system | |
| Zheng et al. | Diagnosis of sucker rod pump based on generating dynamometer cards | |
| CN109272123B (en) | Sucker-rod pump working condition early warning method based on convolution-circulation neural network | |
| CN105257277B (en) | Dlagnosis of Sucker Rod Pumping Well underground failure prediction method based on Multi-variable Grey Model | |
| CN106951662B (en) | Method for diagnosing underground working condition of sucker-rod pump oil well based on valve working point | |
| CN116595440A (en) | Underground working condition fault diagnosis method and device | |
| CN108319738A (en) | A kind of shale gas well yield prediction technique | |
| CN105257279A (en) | Method for measuring working fluid level of pumping well | |
| CN111946329B (en) | Method for solving working fluid level of oil well | |
| CN104405365A (en) | Pumping unit indicator diagram liquid production capacity measurement technology | |
| CN104234695A (en) | Oil well fault diagnosis method based on neural network | |
| CN111734396B (en) | Friction determination method, device and equipment | |
| CN112330038A (en) | Method, device and equipment for determining stress condition of tubular column | |
| Lv et al. | Quantitative diagnosis method of the sucker rod pump system based on the fault mechanism and inversion algorithm | |
| Zhang et al. | A real-time diagnosis method of reservoir-wellbore-surface conditions in sucker-rod pump wells based on multidata combination analysis | |
| CN106593415A (en) | Oil well dynamic liquid surface metering method based on improved multiphase flow algorithm | |
| Langbauer et al. | Sucker rod antibuckling system: development and field application | |
| RU2492357C1 (en) | Method to diagnose operation of sucker rod pumping unit | |
| Milovzorov et al. | Diagnostics of the condition of sucker-rod pumping units after the analysis of dynamogram cards | |
| CN114707270A (en) | Oil-gas well pipe column strength design method based on pipe plasticity failure criterion | |
| CN116084921A (en) | Working fluid level prediction method, device, apparatus, and readable storage medium | |
| CN114458274A (en) | Rock capacity expansion method | |
| CN112683712B (en) | Method for determining corrosion life of sucker rod | |
| Jegbefume et al. | Rod-Guide Placement Based on High-Resolution Tortuosity Analysis of Production Tubing |
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 |