CN106121622B - A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card - Google Patents
A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card Download PDFInfo
- Publication number
- CN106121622B CN106121622B CN201610597512.XA CN201610597512A CN106121622B CN 106121622 B CN106121622 B CN 106121622B CN 201610597512 A CN201610597512 A CN 201610597512A CN 106121622 B CN106121622 B CN 106121622B
- Authority
- CN
- China
- Prior art keywords
- invariant
- moment
- fault
- corrected
- value
- 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.)
- Expired - Fee Related
Links
- 238000005086 pumping Methods 0.000 title claims abstract description 21
- 238000003745 diagnosis Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000004519 manufacturing process Methods 0.000 claims abstract description 16
- 238000010586 diagram Methods 0.000 claims description 102
- 239000013598 vector Substances 0.000 claims description 61
- 238000010606 normalization Methods 0.000 claims description 11
- 238000002474 experimental method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 4
- 238000005314 correlation function Methods 0.000 claims description 3
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 239000003208 petroleum Substances 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 239000003129 oil well Substances 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 239000007788 liquid Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/008—Monitoring of down-hole pump systems, e.g. for the detection of "pumped-off" conditions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a kind of Multiple faults diagnosis approach of Dlagnosis of Sucker Rod Pumping Well based on indicator card, are related to Petroleum Production technical field.The surface dynamometer card of acquisition is converted into underground pump dynagraoph, according to oil field produce in existing indicator card data establish the standard feature library of each fault type, for the characteristic value of each invariant curve Character eigenvector, it is indicated by the form of interval censored data, then the degree of association of each fault type in institute's collecting sample and standard feature library is calculated, judge the fault type that institute's collecting sample may have, improves the credibility of fault diagnosis.The combination that the fault type that institute's collecting sample may have finally is carried out to various multiple failures determines possessed multiple faults type by calculating each combined F index value.This method principle is simple, and computational complexity is small, easy to accomplish, and the accuracy of diagnosis is high.
Description
Technical Field
The invention relates to the technical field of petroleum production, in particular to a multi-fault diagnosis method of a sucker-rod pump pumping well based on an indicator diagram.
Background
The sucker-rod pumping well is a main production mode of oil fields at home and abroad, realizes continuous, stable and efficient operation, and is an important measure for improving the production efficiency of the oil well, reducing the production cost and reducing the potential safety hazard of production. Because the oil well pump works in the underground of thousands of meters and the working environment is severe, the underground working condition is extremely complex, faults occur sometimes, the well is stopped to influence production if the faults occur, and safety accidents occur if the faults occur seriously, so that the accurate fault diagnosis of the underground working condition of the sucker rod pump oil well is a problem which is always concerned by oil field enterprises.
With the continuous development of computer information technology, communication technology, electronic technology and the like, the realization of fault diagnosis of downhole working conditions of pumping wells by using computers has been paid more and more attention. The computer diagnosis mode replaces manual diagnosis, large-scale data can be processed efficiently, a diagnosis conclusion can be obtained in a short time, and convenience is provided for a management department to make reasonable production measures according to real-time working conditions.
However, the existing diagnosis method generally only considers the occurrence situation of one fault condition, and the situation that multiple faults occur simultaneously in actual production is common, so when multiple fault conditions occur simultaneously in a well, the existing method cannot make accurate analysis to provide effective technical guidance.
Disclosure of Invention
The embodiment of the invention provides a multi-fault diagnosis method of a sucker-rod pump pumping well based on an indicator diagram, which is used for solving the problems in the prior art.
A multi-fault diagnostic method for a sucker-rod pumping well based on an indicator diagram, comprising:
collecting a ground indicator diagram, and converting the ground indicator diagram into a downhole pump indicator diagram;
normalizing the underground pump work diagram, wherein the normalization interval is [0,1], extracting invariant moment characteristic vectors of the normalized underground pump work diagram, and correcting the extracted invariant moment characteristic vectors;
establishing a matter element model of the underground pump work diagram by the corrected invariant moment characteristic vector, wherein the matter element model comprises the following steps:
wherein, delta1,δ2,...,δ7Respectively 7 of the corrected invariant moment eigenvectors, v1,v2,...,v7Respectively 7 of the correctionThe value of the invariant curve moment feature vector;
establishing a standard characteristic library from the recorded ground indicator diagram samples of different known fault types in oilfield production, and establishing a matter element model of each fault type as follows:
where j 1,2, T represents the number of known fault types, WjIndicating a jth fault type; [ v ] ofj1a,vj1b]Representing the value range of the 1 st corrected invariant curve moment feature vector under the jth fault type in the standard feature library, [ v [ [ v ] v [ ]j2a,vj2b]Representing the value range of the 2 nd corrected invariant curve moment feature vector under the jth fault type in the standard feature library; by analogy, [ v ]j7a,vj7b]Representing the value range of the 7 th corrected invariant curve moment feature vector under the jth fault type in the standard feature library;
and calculating the correlation degree of the underground pump work diagram and each fault type in the standard feature library, wherein the calculation formula is as follows:
wherein k is 1,2kA value, v, representing the k-th corrected invariant moment eigenvector of the downhole pump diagramjkRepresenting the value of the k modified invariant curve moment feature vector under the j fault type in the standard feature library, vjkaAnd vjkbRespectively representing the kth corrected fault type in the standard feature library under the jth fault typeThe minimum value and the maximum value of the constant curve moment characteristic vector value, | vjkL represents the value range of the k-th corrected invariant moment feature vector under the j-th fault type in the standard feature library; node region X ═ 0,20]；λ(Wj) Representing the degree of association, epsilon (v), between the underground pump work diagram and the jth fault type in the standard feature libraryk,vjk) Indicating the distance, xi, between the kth corrected invariant moment eigenvector of the downhole pump diagram and the kth corrected invariant moment eigenvector of the jth fault type in the standard feature libraryjk(vk) A correlation function representing the jth fault type in the standard feature library, epsilon (v) of the downhole pump diagram under the kth corrected invariant moment feature vectorkAnd X) represents the distance between the k-th corrected invariant moment characteristic vector of the downhole pump diagram and the section domain;
for lambda (W)j) Classifying the fault types of more than or equal to 0 by multi-fault combination, regarding a group of multi-fault combination as one type, and each multi-fault combination at least comprises lambda (W)j) A maximum fault type and the downhole pumping diagram;
for lambda (W)j) Carrying out mean value estimation based on interval data of unbiased conversion on each corrected invariant curve moment feature vector of the fault type of more than or equal to 0, and calculating an unbiased estimation value of the mean value estimation;
calculating an F index value of each group of combination of multiple faults according to the unbiased estimation value of the mean value estimation and the following formula, and determining that the multiple fault combination with the minimum F index value is the multiple fault type of the underground pump work diagram:
wherein k is 1, 2.,. num, num represents the number of fault types in each group of multiple fault combinations; exptkThe number of experiments carried out under the kth fault type is shown, namely the number of the corrected invariant curve moment characteristic vectors under the kth fault type, exptk＝7，expt is the number of all experiments under different fault types, including: indicates the kth fault typeAn unbiased estimated value of the mean estimate of the interval data of the modified invariant moment eigenvector, an average value of unbiased estimated values representing mean estimates of interval data of all the modified invariant moment eigenvectors for the kth fault type is: the total average of unbiased estimates of the mean estimates of the interval data representing all modified invariant moment eigenvectors for all fault types is:sum1to representAndthe sum of the differences of (a) and (b) is:Sum2to representAndthe sum of the differences of (a) and (b) is:
preferably, the step of extracting the invariant moment feature vector of the normalized downhole pump diagram, and the step of correcting the extracted invariant moment feature vector specifically includes:
the normalized downhole pumping diagram is composed of N discrete data points (x)i,yi) A curve composed of (i ═ 1, 2.. N), and whose order p + q is defined as a curve moment cpqComprises the following steps:
wherein,(p, q ═ 0,1,2,3) is the linear distance between two adjacent discrete data points;
the corresponding p + q order central moment is defined as:
wherein,dotThe gravity center coordinates of the normalized underground pump work diagram curve are obtained;
the central moments of the orders are calculated as follows:
φ00＝c00，φ10＝0，φ01＝0，
and carrying out normalization processing on the obtained central moments of each order by adopting a normalization formula as follows:
calculating 7 constant curve moment feature vectors as follows:
and 7 constant curve moment characteristic vectors are corrected, wherein the correction formula is as follows:
δi＝|lg|γi|| (17)
where, i is 1,2, 7, and 7 corrected invariant moment eigenvectors are obtained.
Preferably, step pair λ (W)j) The mean value estimation of the interval data based on the unbiased conversion is performed on each corrected invariant curve moment feature vector of the fault type of more than or equal to 0, and the calculation of the unbiased estimation value of the mean value estimation specifically includes:
assuming that the mean value of the interval data is estimated to be alpha, the value is a non-negative random variable, and is represented by [ va,vb]An interval form showing the value of the corrected invariant moment eigenvector, [ v [ [ v ]a,vb]Is a random vector independent of alpha, let [ v ] bea,vb]Satisfies a certain continuous data distribution, represented by g (·,), considering that g (·,) satisfies uniform distribution, and the corrected invariant curve moment characteristic vector value interval [ v ·)a,vb]Is represented by the following formula:
suppose thatAndare respectively (v)a,vb) And a, assuming that (v) was observed in the experimentas,vbs,τ1s,τ2s,τ3s) Wherein: i denotes an illustrative function, r denotes the number of independent identically distributed samples, let:
wherein, tausRepresents an observed value of the s independent identically distributed sample;
order:
wherein,represents the unbiased estimate, θ, of the s-th independent identically distributed sample1(·,·)、θ2(. phi.) and theta3(-) is a continuous function independent of the distribution of α, and θ1(·,·)、θ2(. phi.) and theta3(-) satisfies the following condition:
calculating interval data [ v ]a,vb]The unbiased estimate of the mean estimate of (a) is as follows:
the invention has the beneficial effects that:
1. the graphic characteristics of the pump diagram can reflect the underground working conditions of the sucker-rod pumping well, and the extraction of the characteristic vector capable of accurately describing the graphic characteristics is an effective basis for fault diagnosis. The invention adopts 7 invariant curve moment characteristic vectors extracted by an invariant moment theory, wherein each order moment has a specific physical meaning phi00Length of the curve representing the pump diagram; phi is a10And phi01Can be used to determine the gray scale center of gravity of the pump diagram curve; phi is a20、φ11And phi02The pump power diagram curve measuring device is used for measuring the size and the direction of the pump power diagram curve; phi is a30And phi03Showing asymmetry of the pump diagram, phi30Represents a measure of asymmetry, φ, of the pump diagram curve about a vertical axis03Curve representing pump diagram about horizontal axisA measure of asymmetry of the line.
2. The invention establishes a standard characteristic library of each fault type according to the existing indicator diagram data in oil field production, and expresses the characteristic value of each invariant moment characteristic vector by the form of interval data, thereby solving the problem that the traditional method only considers the single-value form of the characteristic vector but can not quantitatively reflect the data change difference, then calculating the association degree of the collected sample and each fault type in the standard characteristic library, judging the possible fault type of the collected sample by a quantitative analysis mode, and improving the credibility of fault diagnosis.
3. The multi-fault diagnosis method for the underground working condition of the sucker-rod pump oil well, which is established by the invention, combines various multiple faults with the possible fault types of the collected sample, and determines the multiple fault types by calculating the F index value of each combination, wherein the smaller the F index value is, the smallest difference among the fault types in the combination is shown, and the highest possibility of simultaneous occurrence of the fault types is shown. The method has the advantages of simple principle, small calculation complexity, easy realization and high diagnosis accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating the steps of a method for diagnosing multiple faults in a sucker rod pumping well based on an indicator diagram according to an embodiment of the present invention;
FIG. 2 is a ground indicator diagram collected by the wireless remote collection system of the ground indicator diagram of the sucker rod pump well;
FIG. 3 is a downhole pump diagram converted from the surface indicator diagram of FIG. 2.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides an indicator diagram-based multi-fault diagnosis method for a sucker-rod pumping well, including:
step 100, acquiring a ground indicator diagram by indicator diagram digital acquisition equipment installed on an oil pumping unit of an oil well, transmitting the acquired ground indicator diagram to an operation area data management server located in an operation area through a wireless network by an indicator diagram acquisition control module, and receiving the ground indicator diagram by an underground working condition fault diagnosis system of the oil pumping unit.
And 200, converting the ground indicator diagram into a downhole pump diagram.
Step 300, performing normalization processing on the downhole pump work diagram, wherein the normalization interval is [0,1], and then performing feature vector extraction on the normalized downhole pump work diagram, wherein the specific extraction steps are as follows:
in substep 310, the normalized downhole pumping diagram is formed from N discrete data points (x)i,yi) A curve composed of (i ═ 1, 2.. N), and whose order p + q is defined as a curve moment cpqComprises the following steps:
wherein,(p, q ═ 0,1,2,3) is the linear distance between two adjacent discrete data points.
The corresponding p + q order central moment is defined as:
wherein,dotThe coordinates of the center of gravity of the normalized downhole pump diagram curve are obtained.
The central moments of the orders are calculated as follows:
φ00＝c00，φ10＝0，φ01＝0，
substep 320, performing normalization processing on the obtained central moments of each order, and adopting the following normalization formula:
substep 330, calculating 7 invariant moment eigenvectors as follows:
substep 340, correcting 7 invariant moment eigenvectors, wherein the correction formula is as follows:
δi＝|lg|γi|| (11)
where, i is 1,2, 7, and 7 corrected invariant moment eigenvectors are obtained.
Step 400, establishing a material element model of the underground pump diagram by the corrected invariant moment characteristic vector obtained by calculation, wherein the material element model comprises the following steps:
wherein v is1,v2,...,v7And 7 corrected values of the constant curve moment characteristic vector are respectively obtained.
Step 500, establishing a standard characteristic library by the ground indicator diagram samples of different known fault types recorded in the oilfield production, and obtaining a matter element model of each fault type according to the steps 200-400 as follows:
where j 1,2, T represents the number of known fault types, WjIndicating a jth fault type; [ v ] ofj1a,vj1b]Representing the value range of the 1 st corrected invariant curve moment feature vector under the jth fault type in the standard feature library, [ v [ [ v ] v [ ]j2a,vj2b]Indicating the 2 nd corrected fault type in the j fault type in the standard feature libraryThe value range of the constant curve moment characteristic vector; by analogy, [ v ]j7a,vj7b]And representing the value range of the 7 th corrected invariant curve moment feature vector under the jth fault type in the standard feature library.
Step 600, calculating the correlation degree between the underground pump work diagram and each fault type in the standard feature library, wherein the calculation formula is as follows:
wherein k is 1,2kA value, v, representing the k-th corrected invariant moment eigenvector of the downhole pump diagramjkRepresenting the value of the k-th corrected invariant curve moment feature vector under the j-th fault type in the standard feature library, vjkaAnd vjkbRespectively representing the minimum value and the maximum value of the k-th corrected invariant curve moment characteristic vector value under the j fault type in the standard characteristic library, | vjkL represents the value range of the k-th corrected invariant moment feature vector under the jth fault type in the standard feature library; node region X ═ 0,20]；λ(Wj) Representing the correlation degree of the collected underground pump work diagram and the jth fault type in the standard feature library, epsilon (v)k,vjk) Indicating the distance, xi, between the kth corrected invariant moment eigenvector of the downhole pump diagram and the kth corrected invariant moment eigenvector of the jth fault type in the standard feature libraryjk(vk) A correlation function representing the jth fault type in the standard feature library, epsilon (v) of the downhole pump diagram under the kth corrected invariant moment feature vectorkAnd X) represents the distance between the k th corrected invariant moment characteristic vector of the downhole pump diagram and the node region。
When lambda (W)j) If the fault is less than 0, the fault indicates that the fault of the type does not occur in the underground pump work diagram; when lambda (W)j) And when the value is more than or equal to 0, the downhole pump work diagram can generate the fault of the type, and the larger the value is, the higher the occurrence degree is.
Step 700, for λ (W)j) Classifying the fault types more than or equal to 0 by multi-fault combination, and considering lambda (W)j) The largest fault of this type is bound to occur, and a group of a plurality of faults is regarded as a class, and each group at least comprises the lambda (W)j) The maximum fault type and the downhole pumping diagram.
In step 800, since the value of the corrected invariant moment eigenvector of each fault type in the standard feature library is an interval value, λ (W) obtained in step 700 is calculatedj) Carrying out mean value estimation based on unbiased conversion interval data on each corrected invariant curve moment feature vector of the fault type of more than or equal to 0, and calculating an unbiased estimation value of the mean value estimation, wherein the specific steps are as follows:
substep 810, assuming that the mean value of the interval data is estimated to be α, is a non-negative random variable, consisting of [ v ]a,vb]An interval form showing the value of the corrected invariant moment eigenvector, [ v [ [ v ]a,vb]Is a random vector independent of α, which may be in the interval va,vb]In the interval [ v ] is also possiblea,vb]On the left side of, or in the interval [ v ]a,vb]To the right of (a). Suppose [ v ]a,vb]Satisfies a certain continuous data distribution, represented by g (·,), which is considered to satisfy uniform distribution in the embodiment, and the modified invariant curve moment eigenvector value range [ v ·)a,vb]Is represented by the following formula:
substep 820, assumeAndare respectively (v)a,vb) And a, assuming that (v) was observed in the experimentas,vbs,τ1s,τ2s,τ3s) Wherein: i denotes an illustrative function, r denotes the number of independent identically distributed samples, let:
wherein, tausRepresents the observed value of the s independent identically distributed sample.
Substep 830, let:
wherein,represents the unbiased estimate, θ, of the s-th independent identically distributed sample1(·,·)、θ2(. phi.) and theta3(-) is a continuous function independent of the distribution of α, and θ1(·,·)、θ2(. phi.) and theta3(-) satisfies the following condition:
substep 840, interval data v is then calculateda,vb]The unbiased estimate of the mean estimate of (a) is as follows:
and 900, calculating the F index value of each group of the plurality of fault combinations, wherein the plurality of fault combinations with the minimum F index value are the multiple fault types of the collected underground pump work diagram. The method specifically comprises the following steps:
sub-step 910, calculating F index values for each of a plurality of fault combinations using the following formula,
wherein k is 1, 2.,. num, num represents the number of fault types in each group of multiple fault combinations; exptkThe number of experiments performed under the kth fault type is shown, namely the number of the corrected invariant curve moment feature vectors under the kth fault type, in the embodiment, exptkWhen the failure type is 7, expt is the number of all experiments under different failure types, including: indicates the kth fault typeAn unbiased estimated value of the mean estimate of the interval data of the modified invariant moment eigenvector, an average value of unbiased estimated values representing mean estimates of interval data of all the modified invariant moment eigenvectors for the kth fault type is: the total average of unbiased estimates of the mean estimates of the interval data representing all modified invariant moment eigenvectors for all fault types is:sum1to representAndthe sum of the differences of (a) and (b) is:Sum2to representAndthe sum of the differences of (a) and (b) is:
and a substep 920 of analyzing the F index values for each of the plurality of fault combinations. The smaller the F index value is, the smaller the distance between each fault type in the group of the fault type combinations is, the smaller the difference between each fault type is, and the multiple fault combinations with the minimum F index value are determined to be the multiple fault types of the collected underground pump work diagram.
The invention is described in detail below with reference to a specific example:
1. the ground indicator diagram is acquired by a wireless remote acquisition system for the ground indicator diagram of the sucker-rod pumping well, as shown in figure 2.
2. The collected surface indicator diagram is converted into a downhole pump diagram, as shown in fig. 3.
3. And (3) carrying out normalization processing on the converted underground pump diagram to an interval [0,1], then carrying out feature extraction, and extracting 7 invariant moment feature vectors according to formulas (1) - (11), wherein the 7 invariant moment feature vectors are shown in a table 1.
7 invariant moment characteristic values of downhole pump diagram collected in table 1
4. According to the formula (12), establishing an object model of the acquired underground pump work diagram by the calculated invariant moment eigenvector, wherein the object model comprises the following steps:
5. establishing a standard feature library from the ground indicator diagram samples of different known fault types recorded in the oilfield production to obtain a matter element model of each fault type, as shown in table 2, wherein: the standard feature library established contains 11 fault types, which are respectively: "Normal", "gas influence", "insufficient liquid supply", "broken sucker rod", "thick oil", "leakage of traveling valve", "bump on pump", "bump under pump", "leakage of fixed valve", "sand production from oil well", "plunger coming out of working cylinder", composed of W1-W11And (4) showing.
TABLE 2 invariant curve moment eigenvector value intervals for each fault type in the standard feature library
6. And calculating the relevance of the collected underground pump work diagram and each fault type in the standard feature library according to the formulas (14) to (16), as shown in the table 3.
TABLE 3 correlation between the downhole pump diagram and each fault type in the standard feature library
According to Table 3The collected downhole pump diagram and W2、W3、W4And W6The relevance of the fault types is more than or equal to 0, which indicates that the fault types possibly possessed by the collected underground pump diagram are 'gas influence', 'insufficient liquid supply', 'sucker rod breakage' and 'traveling valve leakage'.
7. For lambda (W)j) And classifying various types of faults more than or equal to 0 by multi-fault combination, and according to the conclusion in the table 3, the following steps are carried out: lambda (W)3)＞λ(W2)＞λ(W6)＞λ(W4) > 0, lambda (W) is considered to have a maximum value3) The corresponding fault of the type is inevitable, and the fault of the type is as follows: "insufficient liquid supply". The method comprises the following steps of carrying out combined classification on a plurality of faults, wherein the steps are as follows: { W3，β}，{W3，W2，β}，{W3，W4，β}，{W3，W6，β}，{W3，W2，W4，β}，{W3，W2，W6，β}，{W3，W4，W6，β}，{W3，W2，W4，W6β, where β is the collected downhole pump diagram sample. The combination of a group of a plurality of faults is regarded as a class, and is respectively represented by Z1-Z8And (4) showing.
8. According to formulas (17) to (22), Z is calculated1-Z8As shown in table 4, wherein: theta1(va,vb)＝0、θ3(va,vb)＝(vb-va)·(2-vb)·e-α。
TABLE 4Z1-Z8F index value for each combination classification
| Z1 | Z2 | Z3 | Z4 | Z5 | Z6 | Z7 | Z8 | |
| F index value | 22.5 | 14.2 | 19.7 | 22.6 | 21.3 | 25.2 | 23.4 | 20.8 |
Z2Classification combination { W3，W2Beta is minimum, which indicates the W-th index value in the collected underground pump work diagram and the standard characteristic library2And W3The difference between the types of the faults is small, and the collected underground pump work diagram is determined to have two faults of 'liquid supply deficiency' and 'gas influence'.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (2)
1. A multi-fault diagnosis method for a sucker-rod pumping well based on an indicator diagram is characterized by comprising the following steps:
collecting a ground indicator diagram, and converting the ground indicator diagram into a downhole pump indicator diagram;
normalizing the underground pump work diagram, wherein the normalization interval is [0,1], extracting invariant moment characteristic vectors of the normalized underground pump work diagram, and correcting the extracted invariant moment characteristic vectors;
establishing a matter element model of the underground pump work diagram by the corrected invariant moment characteristic vector, wherein the matter element model comprises the following steps:
wherein, delta1,δ2,...,δ7Respectively 7 of the corrected invariant moment eigenvectors, v1,v2,...,v7Respectively taking the values of 7 corrected invariant curve moment eigenvectors;
establishing a standard characteristic library from the recorded ground indicator diagram samples of different known fault types in oilfield production, and establishing a matter element model of each fault type as follows:
where j 1,2, T represents the number of known fault types, WjIndicating a jth fault type; [ v ] ofj1a,vj1b]Representing the value range of the 1 st corrected invariant curve moment feature vector under the jth fault type in the standard feature library, [ v [ [ v ] v [ ]j2a,vj2b]Representing the value range of the 2 nd corrected invariant curve moment feature vector under the jth fault type in the standard feature library; by analogy, [ v ]j7a,vj7b]Representing the value range of the 7 th corrected invariant curve moment feature vector under the jth fault type in the standard feature library;
and calculating the correlation degree of the underground pump work diagram and each fault type in the standard feature library, wherein the calculation formula is as follows:
wherein k is 1,2kA value, v, representing the k-th corrected invariant moment eigenvector of the downhole pump diagramjkRepresenting the value of the k modified invariant curve moment feature vector under the j fault type in the standard feature library, vjkaAnd vjkbRespectively representing the minimum value and the maximum value of the k-th corrected invariant curve moment characteristic vector value under the j-th fault type in the standard characteristic library, | vjkL represents the value range of the k-th corrected invariant moment feature vector under the j-th fault type in the standard feature library; node region X ═ 0,20]；λ(Wj) Representing the degree of association, epsilon (v), between the underground pump work diagram and the jth fault type in the standard feature libraryk,vjk) Represents a kth correction of the downhole pump diagramThe distance, xi, between the invariant moment feature vector and the kth corrected invariant moment feature vector under the jth fault type in the standard feature libraryjk(vk) A correlation function representing the jth fault type in the standard feature library, epsilon (v) of the downhole pump diagram under the kth corrected invariant moment feature vectorkAnd X) represents the distance between the k-th corrected invariant moment characteristic vector of the downhole pump diagram and the section domain;
for lambda (W)j) Classifying the fault types of more than or equal to 0 by multi-fault combination, regarding a group of multi-fault combination as one type, and each multi-fault combination at least comprises lambda (W)j) A maximum fault type and the downhole pumping diagram;
for lambda (W)j) Carrying out mean value estimation based on interval data of unbiased conversion on each corrected invariant curve moment feature vector of the fault type of more than or equal to 0, and calculating an unbiased estimation value of the mean value estimation;
calculating an F index value of each group of combination of multiple faults according to the unbiased estimation value of the mean value estimation and the following formula, and determining that the multiple fault combination with the minimum F index value is the multiple fault type of the underground pump work diagram:
wherein k is 1, 2.,. num, num represents the number of fault types in each group of multiple fault combinations; exptkThe number of experiments carried out under the kth fault type is shown, namely the number of the corrected invariant curve moment characteristic vectors under the kth fault type, exptkWhen the failure type is 7, expt is the number of all experiments under different failure types, including: indicates the kth fault typeAn unbiased estimated value of the mean estimate of the interval data of the modified invariant moment eigenvector, an average value of unbiased estimated values representing mean estimates of interval data of all the modified invariant moment eigenvectors for the kth fault type is: the total average of unbiased estimates of the mean estimates of the interval data representing all modified invariant moment eigenvectors for all fault types is:sum1to representAndthe sum of the differences of (a) and (b) is:Sum2to representAndthe sum of the differences of (a) and (b) is:
step pair λ (W)j) The mean value estimation of the interval data based on the unbiased conversion is performed on each corrected invariant curve moment feature vector of the fault type of more than or equal to 0, and the calculation of the unbiased estimation value of the mean value estimation specifically includes:
assuming that the mean value of the interval data is estimated to be alpha, the value is a non-negative random variable, and is represented by [ va,vb]An interval form showing the value of the corrected invariant moment eigenvector, [ v [ [ v ]a,vb]Is a random vector independent of alpha, let [ v ] bea,vb]Satisfies a certain continuous data distribution, represented by g (·,), considering that g (·,) satisfies uniform distribution, and the corrected invariant curve moment characteristic vector value interval [ v ·)a,vb]Is represented by the following formula:
suppose thatAndare respectively (v)a,vb) And a, assuming that (v) was observed in the experimentas,vbs,τ1s,τ2s,τ3s) Wherein:i denotes an illustrative function, r denotes the number of independent identically distributed samples, let:
wherein,τsrepresents an observed value of the s independent identically distributed sample;
order:
wherein,represents the unbiased estimate, θ, of the s-th independent identically distributed sample1(·,·)、θ2(. phi.) and theta3(-) is a continuous function independent of the distribution of α, and θ1(·,·)、θ2(. phi.) and theta3(-) satisfies the following condition:
calculating interval data [ v ]a,vb]The unbiased estimate of the mean estimate of (a) is as follows:
2. the method of claim 1, wherein the step of extracting invariant moment features of the normalized downhole pump diagram and modifying the extracted invariant moment features specifically comprises:
the normalized downhole pumping diagram is composed of N discrete data points (x)i,yi) A curve composed of (i ═ 1, 2.. N), and whose order p + q is defined as a curve moment cpqComprises the following steps:
wherein,(p, q ═ 0,1,2,3) is the linear distance between two adjacent discrete data points;
the corresponding p + q order central moment is defined as:
wherein,dotThe gravity center coordinates of the normalized underground pump work diagram curve are obtained;
the central moments of the orders are calculated as follows:
φ00＝c00，φ10＝0，φ01＝0，
and carrying out normalization processing on the obtained central moments of each order by adopting a normalization formula as follows:
calculating 7 constant curve moment feature vectors as follows:
and 7 constant curve moment characteristic vectors are corrected, wherein the correction formula is as follows:
δi＝|lg|γi|| (22)
where, i is 1,2, 7, and 7 corrected invariant moment eigenvectors are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610597512.XA CN106121622B (en) | 2016-07-27 | 2016-07-27 | A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610597512.XA CN106121622B (en) | 2016-07-27 | 2016-07-27 | A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106121622A CN106121622A (en) | 2016-11-16 |
| CN106121622B true CN106121622B (en) | 2019-10-25 |
Family
ID=57290183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610597512.XA Expired - Fee Related CN106121622B (en) | 2016-07-27 | 2016-07-27 | A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106121622B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106677761B (en) * | 2016-12-27 | 2020-01-31 | 东软集团股份有限公司 | fault prediction method and device |
| CN106951662B (en) * | 2017-04-12 | 2020-03-20 | 东北大学 | Method for diagnosing underground working condition of sucker-rod pump oil well based on valve working point |
| CN106930751B (en) * | 2017-04-20 | 2020-02-11 | 东北大学 | Fault separation method for sucker-rod pump pumping well |
| CN107165615B (en) * | 2017-05-10 | 2020-04-24 | 东北大学 | Pumping well semi-supervised fault diagnosis method based on curvelet transform and nuclear sparseness |
| CN109255134B (en) * | 2017-07-12 | 2021-08-31 | 中国石油天然气股份有限公司 | Method for acquiring fault condition of pumping well |
| CN110878692B (en) * | 2018-09-05 | 2023-10-27 | 北京国双科技有限公司 | Fault alarm method and device |
| CN109508473B (en) * | 2018-09-29 | 2020-12-08 | 北京国双科技有限公司 | Pumping well fault determination method based on case diagram, pumping well fault case diagram establishment method and related device |
| CN112884068A (en) * | 2021-03-15 | 2021-06-01 | 大庆油田有限责任公司 | Fault diagnosis method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102011576A (en) * | 2010-11-24 | 2011-04-13 | 河海大学 | Method for hierarchically diagnosing fault of rod-comprising oil pumping system based on indicator diagram |
| CN102094626A (en) * | 2010-12-20 | 2011-06-15 | 中国石油天然气股份有限公司 | Real-time early warning method and system for oil well fault |
| CN104481496A (en) * | 2014-09-16 | 2015-04-01 | 渤海大学 | Fault diagnosis method of sucker-rod pump well |
| CN204347530U (en) * | 2015-01-13 | 2015-05-20 | 天津仪控科技有限公司 | A kind of walking-beam pumping unit well production status diagnostic device |
| CN105257277A (en) * | 2015-05-15 | 2016-01-20 | 渤海大学 | Method for predicating underground fault of sucker-rod pump oil pumping well on basis of multivariable grey model |
| CN105672988A (en) * | 2015-12-30 | 2016-06-15 | 中国石油天然气股份有限公司 | Oil pumping unit indicator diagram diagnosis system and method |
-
2016
- 2016-07-27 CN CN201610597512.XA patent/CN106121622B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102011576A (en) * | 2010-11-24 | 2011-04-13 | 河海大学 | Method for hierarchically diagnosing fault of rod-comprising oil pumping system based on indicator diagram |
| CN102094626A (en) * | 2010-12-20 | 2011-06-15 | 中国石油天然气股份有限公司 | Real-time early warning method and system for oil well fault |
| CN104481496A (en) * | 2014-09-16 | 2015-04-01 | 渤海大学 | Fault diagnosis method of sucker-rod pump well |
| CN204347530U (en) * | 2015-01-13 | 2015-05-20 | 天津仪控科技有限公司 | A kind of walking-beam pumping unit well production status diagnostic device |
| CN105257277A (en) * | 2015-05-15 | 2016-01-20 | 渤海大学 | Method for predicating underground fault of sucker-rod pump oil pumping well on basis of multivariable grey model |
| CN105672988A (en) * | 2015-12-30 | 2016-06-15 | 中国石油天然气股份有限公司 | Oil pumping unit indicator diagram diagnosis system and method |
Non-Patent Citations (1)
| Title |
|---|
| 有杆泵抽油系统井下工况诊断的物元分析方法;李琨等;《东北大学学报（自然科学版）》;20130531;第34卷(第5期);第613-617页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106121622A (en) | 2016-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106121622B (en) | A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card | |
| CN112508105B (en) | Fault detection and retrieval method for oil extraction machine | |
| WO2020019681A1 (en) | Fault diagnosis method and apparatus for oil production equipment | |
| Zheng et al. | Sucker rod pumping diagnosis using valve working position and parameter optimal continuous hidden Markov model | |
| CN106930751A (en) | A kind of Dlagnosis of Sucker Rod Pumping Well fault separating method | |
| CN108435819B (en) | Energy consumption abnormity detection method for aluminum profile extruder | |
| CN112766301A (en) | Similarity judgment method for indicator diagram of oil extraction machine | |
| CN104234695A (en) | Oil well fault diagnosis method based on neural network | |
| CN103886339A (en) | Oil pumping device indicator diagram dynamic identification method and device based on BP neural network | |
| CN114266289A (en) | Complex equipment health state assessment method | |
| CN109840671A (en) | Operational development effect calculates equipment, operational development effect calculation method and recording medium | |
| CN104405374A (en) | Method for measuring stress sensitivity of tight gas reservoir | |
| CN104866940A (en) | Stochastic simulation method for geologic risk evaluation | |
| WO2016138805A1 (en) | Method and system for determining and locating distributed data transaction | |
| CN109613109A (en) | A kind of Pipeline Magnetic Flux Leakage Inspection automatic data analysis system | |
| CN114021620B (en) | BP neural network feature extraction-based electric submersible pump fault diagnosis method | |
| CN110514366B (en) | Method for detecting weak leakage of pipeline under small sample condition | |
| Leonzio et al. | Water Leak Detection and Localization using Convolutional Autoencoders | |
| WO2022134579A1 (en) | Method and apparatus for detecting abnormalities of service transaction data, and computer device | |
| CN113092083A (en) | Machine pump fault diagnosis method and device based on fractal dimension and neural network | |
| CN116990865A (en) | Microseism event detection method and system based on deep migration learning | |
| CN109210268B (en) | Big data processing method based on ultralow-power electromagnetic valve | |
| CN114912372B (en) | High-precision filling pipeline fault early warning method based on artificial intelligence algorithm | |
| CN102938068A (en) | Bridge structure multi-system damage identification method | |
| CN114138535A (en) | Fault diagnosis method and device of storage system, electronic equipment, medium and product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191025 Termination date: 20200727 |