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 PDF

Info

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
fault type
indicate
revised
value
invariant curve
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.)
Active
Application number
CN201610597512.XA
Other languages
Chinese (zh)
Other versions
CN106121622A (en
Inventor
李琨
韩莹
佘东生
魏泽飞
杨一柳
于震
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bohai University
Original Assignee
Bohai University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Bohai University filed Critical Bohai University
Priority to CN201610597512.XA priority Critical patent/CN106121622B/en
Publication of CN106121622A publication Critical patent/CN106121622A/en
Application granted granted Critical
Publication of CN106121622B publication Critical patent/CN106121622B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • EFIXED CONSTRUCTIONS
    • E21EARTH DRILLING; MINING
    • E21BEARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B44/00Automatic 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
    • EFIXED CONSTRUCTIONS
    • E21EARTH DRILLING; MINING
    • E21BEARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B47/00Survey of boreholes or wells
    • E21B47/008Monitoring of down-hole pump systems, e.g. for the detection of "pumped-off" conditions
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16ZINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00Subject matter not provided for in other main groups of this subclass

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

A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card
Technical field
The present invention relates to Petroleum Production technical field, in particular to the mostly event of a kind of Dlagnosis of Sucker Rod Pumping Well based on indicator card Hinder diagnostic method.
Background technique
Dlagnosis of Sucker Rod Pumping Well is the main production method in domestic and international oil field, realizes its continuous, stable and efficient operation, is Oil well production efficiency is improved, production cost is reduced and reduces the important measures of production safety hidden danger.Since oil pumping pump work is in number The underground of km, working environment is severe, so that underground working is extremely complex, failure happens occasionally, and gently then stopping well influences production, weight Safety accident then occurs, therefore, the exact failure diagnosis to Dlagnosis of Sucker Rod Pumping Well underground working is that oilfield enterprise pays close attention to always Problem.
With the continuous development of computer information technology, the communication technology, electronic technology etc., pumpingh well is realized using computer The fault diagnosis of underground working is increasingly taken seriously.Computer diagnosis mode replaces Artificial Diagnosis, can be handled with high efficiency Large-scale data obtains diagnosis in a relatively short period of time, formulates reasonable production according to real-time working condition for administrative department and arranges Offer convenience is provided.
But existing diagnostic method generally only considers a kind of fault condition there is a situation where and in actual production at present The simultaneous situation of various faults be it is generally existing, therefore, when the multiple fault conditions in underground simultaneously occur when, existing side Method can not make accurate analysis to provide effective technological guidance.
Summary of the invention
The embodiment of the invention provides a kind of Multiple faults diagnosis approach of Dlagnosis of Sucker Rod Pumping Well based on indicator card, to solve Certainly problems of the prior art.
A kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card, comprising:
Surface dynamometer card is acquired, and converts underground pump dynagraoph for the surface dynamometer card;
The underground pump dynagraoph is normalized, normalization section is [0,1], the down-hole pump after extracting normalization The invariant curve Character eigenvector of function figure, and the invariant curve Character eigenvector of extraction is modified;
The matter-element model of the underground pump dynagraoph is established by revised invariant curve Character eigenvector, as follows:
Wherein, δ12,...,δ7The respectively 7 revised invariant curve Character eigenvectors, v1,v2,...,v7Point Not Wei 7 revised invariant curve Character eigenvectors value;
As oil field produce recorded in the surface dynamometer card sample of known different faults type establish standard feature library, and The matter-element model of each fault type is established, as follows:
Wherein, j=1,2 ..., T, T indicate the quantity of known fault type, WjIndicate jth kind fault type;[vj1a, vj1b] indicate taking for the 1st revised invariant curve Character eigenvector in the standard feature library under jth kind fault type It is worth section, [vj2a,vj2b] indicate the 2nd revised invariant curve square in the standard feature library under jth kind fault type The value interval of feature vector;And so on, [vj7a,vj7b] indicate in the standard feature library under jth kind fault type the 7th The value interval of a revised invariant curve Character eigenvector;
The degree of association of each fault type in the underground pump dynagraoph and the standard feature library is calculated, calculation formula is as follows:
Wherein, k=1,2 ..., 7, vkIndicate described k-th of underground pump dynagraoph revised invariant curve Character eigenvector Value, vjkIndicate in the standard feature library under jth kind fault type k-th of revised invariant curve Character eigenvector Value, vjkaAnd vjkbIt is special to respectively indicate in the standard feature library k-th of revised invariant curve square under jth kind fault type The minimum value and maximum value of vector value are levied, | vjk| it indicates in the standard feature library under jth kind fault type after k-th of amendment Invariant curve Character eigenvector value range size;It saves domain X=[0,20];λ(Wj) indicate the underground pump dynagraoph and institute State the degree of association of jth kind fault type in standard feature library, ε (vk,vjk) indicate it is described k-th of underground pump dynagraoph it is revised not K-th of revised invariant curve moment characteristics under jth kind fault type in varied curve Character eigenvector and the standard feature library The distance of vector, ξjk(vk) indicate the underground pump dynagraoph and the mark under k-th of revised invariant curve Character eigenvector The correlation function of jth kind fault type, ε (v in quasi- feature databasek, X) indicate it is described k-th of underground pump dynagraoph it is revised constant Curve Character eigenvector is at a distance from section domain;
To λ (WjEach fault type of) >=0 carries out the classification of multiple faults combination, regards the combination of one group of multiple failure as one Class includes at least λ (W in the combination of each the multiple failurej) maximum fault type and the underground pump dynagraoph;
To λ (WjEach revised invariant curve Character eigenvector of the fault type of) >=0 is carried out based on " unbiased transformation " Interval censored data Estimation of Mean, and calculate the unbiased estimator of the Estimation of Mean;
Referred to according to the combined F that the unbiased estimator of the Estimation of Mean and following formula calculate each group of multiple failures Scale value, and determine that multiple failure groups with minimum F index value are combined into multiple faults type possessed by the underground pump dynagraoph:
Wherein, k=1,2 ..., num, num indicate the number of fault type in each group of multiple failure combinations;exptkTable Show the number tested under k-th of fault type, revised invariant curve Character eigenvector under as k-th of fault type Number, exptk=7, expt are the number of all experiments under different faults type, are had: It indicates under k-th of fault typeThe Estimation of Mean of the interval censored data of a revised invariant curve Character eigenvector it is unbiased Estimated value, Indicate under k-th of fault type all revised invariant curve moment characteristics to The average value of the unbiased estimator of the Estimation of Mean of the interval censored data of amount, has: It indicates The unbiased esti-mator of the Estimation of Mean of the interval censored data of all revised invariant curve Character eigenvectors under all fault types The overall average of value, has:sum1It indicatesWithThe sum of difference, have:Sum2It indicatesWithThe sum of difference, have:
Preferably, step extracts the invariant curve Character eigenvector of the underground pump dynagraoph after normalization, and not to extraction Varied curve Character eigenvector, which is modified, to be specifically included:
Underground pump dynagraoph after normalization is by N number of discrete data point (xi,yi), (i=1,2 ... N) composition curve, Define its p+q rank Curve Moment cpqAre as follows:
Wherein,(p, q=0,1,2,3) is between two neighboring discrete data point Linear distance;
Corresponding p+q rank central moment is defined as:
Wherein,PointIt is sat for the center of gravity of the underground pump dynagraoph curve after normalization Mark;
It is as follows to calculate each rank central moment:
φ00=c00, φ10=0, φ01=0,
Standardization processing is carried out to obtained each rank central moment, using following normalizing:
It is as follows to calculate 7 invariant curve Character eigenvectors:
7 invariant curve Character eigenvectors are modified, correction formula is as follows:
δi=| lg | γi|| (17)
Wherein, i=1,2 ..., 7 obtains 7 revised invariant curve Character eigenvectors.
Preferably, step is to λ (WjEach revised invariant curve Character eigenvector of the fault type of) >=0 is based on The Estimation of Mean of the interval censored data of " unbiased transformation ", and the unbiased estimator for calculating the Estimation of Mean specifically includes:
Assuming that the value of the Estimation of Mean of the interval censored data is α, it is a non-negative stochastic variable, by [va,vb] indicate amendment The range format of the value of invariant curve Character eigenvector afterwards, [va,vb] be and the independent random vector of α, it is assumed that [va,vb] Meet the distribution of certain continuous data, indicated by g (), it is believed that g (), which meets, to be uniformly distributed, revised invariant curve Character eigenvector value interval [va,vb] be uniformly distributed and indicated by following formula:
Assuming thatWithIt is (v respectivelya,vb) and α independent same distribution sample, it is assumed that (v has been observed in experimentas,vbs1s2s3s), in which: I indicates that indicative function, r indicate independent same distribution sample size, enables:
Wherein, τsIndicate the observation of s-th of independent same distribution sample;
It enables:
Wherein,Indicate the unbiased estimator of s-th of independent same distribution sample, θ1(·,·)、θ2() and θ3 () is the continuous function unrelated with the distribution of α, and θ1(·,·)、θ2() and θ3() meets following condition:
Computation interval data [va,vb] Estimation of Mean unbiased estimator it is as follows:
The beneficial effects of the present invention are:
1, the graphic feature of pump dynagraoph can reflect the underground working of Dlagnosis of Sucker Rod Pumping Well, and extraction being capable of accurate description figure The feature vector of feature is to carry out effective foundation of fault diagnosis.The present invention is using the theoretical extracted 7 constant songs of not bending moment Line Character eigenvector, each rank square therein all have specific physical significance, φ00Indicate pump dynagraoph length of a curve;φ10With φ01It may be used to determine the grey scale centre of gravity of pump dynagraoph curve;φ20、φ11And φ02For measuring size and the side of pump dynagraoph curve To;φ30And φ03Indicate the asymmetry of pump dynagraoph figure, φ30Indicate pump dynagraoph curve about vertical axis asymmetry degree Amount, φ03Indicate asymmetry measurement of the pump dynagraoph curve about horizontal axis.
2, the present invention 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 is indicated by the form of interval censored data, is solved conventional method and is only considered The monodrome form of feature vector, and it is unable to the problem of quantification embodies data variation difference, then calculate institute's collecting sample and mark The degree of association of each fault type in quasi- feature database, the failure that collecting sample may have by way of quantitative analysis to judge Type improves the credibility of fault diagnosis.
3, the Multiple faults diagnosis approach of Dlagnosis of Sucker Rod Pumping Well underground working established by the present invention, may by institute's collecting sample The fault type having carries out the combination of various multiple failures, is determined by calculating each combined F index value possessed Multiple faults type, the smaller difference illustrated in the combination between each fault type of F index value is minimum, and each fault type is sent out simultaneously A possibility that giving birth to highest.This method principle is simple, and computational complexity is small, easy to accomplish, and the accuracy of diagnosis is high.
Detailed description of the invention
It, below will be to embodiment in order to illustrate more clearly of inventive embodiments of the present invention or technical solution in the prior art Or attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only It is some embodiments that the present invention invents, for those of ordinary skill in the art, in the premise not made the creative labor Under, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card provided in an embodiment of the present invention Flow chart of steps;
Fig. 2 is by the collected surface dynamometer card of Dlagnosis of Sucker Rod Pumping Well surface dynamometer card wireless remote acquisition system;
Fig. 3 is the underground pump dynagraoph that surface dynamometer card converts in Fig. 2.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.
Referring to Fig.1, the embodiment of the invention provides a kind of multi-fault Diagnosis sides of Dlagnosis of Sucker Rod Pumping Well based on indicator card Method, which comprises
Step 100, surface dynamometer card is acquired using the indicator card digital collection equipment being mounted on pumping unit of well, by The collected surface dynamometer card is passed through wireless network transmissions to the operation for being located at operation area by indicator card acquisition control module Then area's data management server receives the surface dynamometer card by pumpingh well underground working fault diagnosis system.
Step 200, underground pump dynagraoph is converted by the surface dynamometer card.
Step 300, the underground pump dynagraoph is normalized, normalization section is [0,1], then to normalization Underground pump dynagraoph afterwards carries out characteristic vector pickup, specific extraction step are as follows:
Sub-step 310, the underground pump dynagraoph after normalization are by N number of discrete data point (xi,yi), (i=1,2 ... N) group At curve, define its p+q rank Curve Moment cpqAre as follows:
Wherein,(p, q=0,1,2,3) is between two neighboring discrete data point Linear distance.
Corresponding p+q rank central moment is defined as:
Wherein,PointIt is sat for the center of gravity of the underground pump dynagraoph curve after normalization Mark.
It is as follows to calculate each rank central moment:
φ00=c00, φ10=0, φ01=0,
Sub-step 320 carries out standardization processing to obtained each rank central moment, using following normalizing:
It is as follows to calculate 7 invariant curve Character eigenvectors for sub-step 330:
Sub-step 340 is modified 7 invariant curve Character eigenvectors, and correction formula is as follows:
δi=| lg | γi|| (11)
Wherein, i=1,2 ..., 7 obtains 7 revised invariant curve Character eigenvectors.
Step 400, the object of the underground pump dynagraoph is established by the revised invariant curve Character eigenvector being calculated Meta-model, as follows:
Wherein, v1,v2,...,v7The value of the respectively 7 revised invariant curve Character eigenvectors.
Step 500, as oil field produce recorded in the surface dynamometer card sample of known different faults type establish standard Feature database, the matter-element model for obtaining each fault type according to step 200~400 are as follows:
Wherein, j=1,2 ..., T, T indicate the quantity of known fault type, WjIndicate jth kind fault type;[vj1a, vj1b] indicate taking for the 1st revised invariant curve Character eigenvector in the standard feature library under jth kind fault type It is worth section, [vj2a,vj2b] indicate the 2nd revised invariant curve square in the standard feature library under jth kind fault type The value interval of feature vector;And so on, [vj7a,vj7b] indicate in the standard feature library under jth kind fault type the 7th The value interval of a revised invariant curve Character eigenvector.
Step 600, the degree of association of each fault type in the underground pump dynagraoph and standard feature library is calculated, calculation formula is such as Under:
Wherein, k=1,2 ..., 7, vkIndicate described k-th of underground pump dynagraoph revised invariant curve Character eigenvector Value, vjkIndicate in standard feature library under jth kind fault type taking for k-th of revised invariant curve Character eigenvector Value, vjkaAnd vjkbRespectively indicate in standard feature library k-th of revised invariant curve Character eigenvector under jth kind fault type The minimum value and maximum value of value, | vjk| k-th of revised invariant curve under jth kind fault type in expression standard feature library The size of Character eigenvector value range;It saves domain X=[0,20];λ(Wj) indicate underground pump dynagraoph collected and standard feature The degree of association of jth kind fault type, ε (v in libraryk,vjk) indicate that described k-th of underground pump dynagraoph revised invariant curve square is special Vector is levied at a distance from k-th of revised invariant curve Character eigenvector under jth kind fault type in the standard feature library, ξjk(vk) indicate under k-th of revised invariant curve Character eigenvector in the underground pump dynagraoph and the standard feature library the The correlation function of j kind fault type, ε (vk, X) indicate k-th of the underground pump dynagraoph revised invariant curve moment characteristics to Amount is at a distance from section domain.
As λ (Wj) < 0 when, indicate that there is no the failures of the type for the underground pump dynagraoph;As λ (WjWhen) >=0, indicate The failure of the type may occur for the underground pump dynagraoph, and numerical value is bigger, and the degree of generation is higher.
Step 700, to λ (WjEach fault type of) >=0 carries out the classification of multiple faults combination, it is believed that λ (Wj) it is maximum such The failure of type necessarily occurs, and regards the combination of one group of multiple failure as one kind, includes at least the λ in each grouping (Wj) maximum fault type and the underground pump dynagraoph.
Step 800, due to the revised invariant curve Character eigenvector of each fault type in standard feature library Value is all interval value, therefore to λ (W obtained in step 700jEach revised invariant curve of the fault type of) >=0 Character eigenvector carries out the Estimation of Mean of the interval censored data based on " unbiased transformation ", and calculates the unbiased esti-mator of the Estimation of Mean Value, the specific steps are as follows:
Sub-step 810, it is assumed that the value of the Estimation of Mean of interval censored data is α, is a non-negative stochastic variable, by [va,vb] table Show the range format of the value of revised invariant curve Character eigenvector, [va,vb] be and the independent random vector of α, α possibility In section [va,vb] in, it is also possible in section [va,vb] left side, or in section [va,vb] right side.Assuming that [va,vb] meet The distribution of certain continuous data is indicated by g (), is thought that g () meets in the present embodiment and is uniformly distributed, it is revised not Varied curve Character eigenvector value interval [va,vb] be uniformly distributed and indicated by following formula:
Sub-step 820, it is assumed thatWithIt is (v respectivelya,vb) and α independent same distribution sample This, it is assumed that (v has been observed in an experimentas,vbs1s2s3s), in which: I indicates that indicative function, r indicate independent same distribution sample size, enables:
Wherein, τsIndicate the observation of s-th of independent same distribution sample.
Sub-step 830 enables:
Wherein,Indicate the unbiased estimator of s-th of independent same distribution sample, θ1(·,·)、θ2() and θ3 () is the continuous function unrelated with the distribution of α, and θ1(·,·)、θ2() and θ3() meets following condition:
Sub-step 840, then computation interval data [va,vb] Estimation of Mean unbiased estimator it is as follows:
Step 900, the F index value of each group of multiple failure combinations, and multiple failure groups with minimum F index value are calculated It is combined into multiple faults type possessed by underground pump dynagraoph collected.Specifically include following methods:
Sub-step 910 calculates the F index value of each group of multiple failure combinations using following formula,
Wherein, k=1,2 ..., num, num indicate the number of fault type in each group of multiple failure combinations;exptkTable Show the number tested under k-th of fault type, revised invariant curve Character eigenvector under as k-th of fault type Number, expt in embodimentk=7, expt are the number of all experiments under different faults type, are had: It indicates under k-th of fault typeThe area of a revised invariant curve Character eigenvector Between data Estimation of Mean unbiased estimator, It indicates all under k-th of fault type to repair The average value of the unbiased estimator of the Estimation of Mean of the interval censored data of invariant curve Character eigenvector after just, has: Indicate all revised invariant curve moment characteristics under all fault types to The overall average of the unbiased estimator of the Estimation of Mean of the interval censored data of amount, has:sum1 It indicatesWithThe sum of difference, have:Sum2It indicatesWith's The sum of difference has:
Sub-step 920 analyzes the F index value of each group of multiple failure combinations.F index value is smaller, illustrates the group The distance between each fault type in multiple fault type combinations is smaller, and the difference between each fault type is small, and determination has Multiple failure groups of minimum F index value are combined into multiple faults type possessed by underground pump dynagraoph collected.
The present invention is specifically described below with reference to a specific example:
1, surface dynamometer card is acquired by Dlagnosis of Sucker Rod Pumping Well surface dynamometer card wireless remote acquisition system, as shown in Figure 2.
2, underground pump dynagraoph is converted by collected surface dynamometer card, as shown in Figure 3.
3, the underground pump dynagraoph after conversion is normalized, normalizes to section [0,1], then carried out feature and mention It takes, extracts its 7 invariant curve Character eigenvectors according to formula (1)-(11), as shown in table 1.
7 invariant curve moment characteristics values of pump dynagraoph under 1 production wells of table
4, according to formula (12), underground pump dynagraoph collected is established by the invariant curve Character eigenvector being calculated Matter-element model, as follows:
5, as oil field produce recorded in the surface dynamometer card sample of known different faults type establish standard feature library, The matter-element model of each fault type is obtained, as shown in table 2, in which: the standard feature library established includes 11 kinds of failure classes Type, be respectively as follows: " normal ", " gases affect ", " feed flow insufficient ", " sucker rod is disconnected to be fallen ", " oil is thick ", " travelling valve leakage ", " on pump Touch ", " being touched under pump ", " fixed valve leakage ", " sand production ", " plunger abjection seating nipple ", by W1-W11It indicates.
The invariant curve Character eigenvector value interval of the 2 each fault type in standard feature library of table
6, the pass of each fault type in underground pump dynagraoph collected and standard feature library is calculated according to formula (14)-(16) Connection degree, as shown in table 3.
The degree of association of pump dynagraoph and each fault type in standard feature library under 3 production wells of table
According to table 3, underground pump dynagraoph and W collected2、W3、W4And W6The degree of association of kind fault type is more than or equal to 0, Illustrate that the fault type that underground pump dynagraoph collected is possible to have is " gases affect ", " feed flow is insufficient ", " sucker rod is disconnected Fall " and " travelling valve leakage ".
7, to λ (WjThe classification that all types of failures of) >=0 carry out multiple faults combination has according to 3 conclusion of table: λ (W3) > λ (W2) > λ (W6) > λ (W4) > 0, it is believed that the λ (W with maximum value3) corresponding to the failure of the type necessarily occur, should Type fault are as follows: " feed flow is insufficient ".Multiple failures are combined classification, are respectively 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, W6, β }, wherein β is collected Underground pump work pattern sheet.Regard the combination of one group of multiple failure as one kind, respectively by Z1-Z8It indicates.
8, according to formula (17)-(22), Z is calculated1-Z8F index value, as shown in table 4, in which: θ1(va,vb)=0,θ3(va,vb)=(vb-va)·(2-vb)·e
Table 4Z1-Z8The F index value of each assembled 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
Z2Sort merge { W3, W2, β } F index value it is minimum, illustrate in underground pump dynagraoph collected and standard feature library W2And W3Difference between kind fault type is small, determines that underground pump dynagraoph collected has " feed flow is insufficient " and " gas shadow Two kinds of failures of sound ".
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more, The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies Within, then the present invention is also intended to include these modifications and variations.

Claims (2)

1. a kind of Multiple faults diagnosis approach of the Dlagnosis of Sucker Rod Pumping Well based on indicator card characterized by comprising
Surface dynamometer card is acquired, and converts underground pump dynagraoph for the surface dynamometer card;
The underground pump dynagraoph is normalized, normalization section is [0,1], the underground pump dynagraoph after extracting normalization Invariant curve Character eigenvector, and the invariant curve Character eigenvector of extraction is modified;
The matter-element model of the underground pump dynagraoph is established by revised invariant curve Character eigenvector, as follows:
Wherein, δ12,...,δ7The respectively 7 revised invariant curve Character eigenvectors, v1,v2,...,v7Respectively The value of 7 revised invariant curve Character eigenvectors;
As oil field produce recorded in the surface dynamometer card sample of known different faults type establish standard feature library, and establish The matter-element model of each fault type, as follows:
Wherein, j=1,2 ..., T, T indicate the quantity of known fault type, WjIndicate jth kind fault type;[vj1a,vj1b] table Show the value interval of the 1st revised invariant curve Character eigenvector in the standard feature library under jth kind fault type, [vj2a,vj2b] indicate the 2nd revised invariant curve Character eigenvector in the standard feature library under jth kind fault type Value interval;And so on, [vj7a,vj7b] indicate the 7th amendment in the standard feature library under jth kind fault type after Invariant curve Character eigenvector value interval;
The degree of association of each fault type in the underground pump dynagraoph and the standard feature library is calculated, calculation formula is as follows:
Wherein, k=1,2 ..., 7, vkIndicate taking for k-th of the underground pump dynagraoph revised invariant curve Character eigenvector Value, vjkIndicate in the standard feature library under jth kind fault type taking for k-th of revised invariant curve Character eigenvector Value, vjkaAnd vjkbRespectively indicate in the standard feature library k-th of revised invariant curve moment characteristics under jth kind fault type The minimum value and maximum value of vector value, | vjk| indicate in the standard feature library under jth kind fault type k-th it is revised The size of invariant curve Character eigenvector value range;It saves domain X=[0,20];λ(Wj) indicate the underground pump dynagraoph with it is described The degree of association of jth kind fault type, ε (v in standard feature libraryk,vjk) indicate it is described k-th of underground pump dynagraoph it is revised constant In curve Character eigenvector and the standard feature library under jth kind fault type k-th of revised invariant curve moment characteristics to The distance of amount, ξjk(vk) indicate the underground pump dynagraoph and the standard under k-th of revised invariant curve Character eigenvector The correlation function of jth kind fault type, ε (v in feature databasek, X) and indicate k-th of the underground pump dynagraoph revised constant song Line Character eigenvector is at a distance from section domain;
To λ (WjEach fault type of) >=0 carries out the classification of multiple faults combination, regards the combination of one group of multiple failure as one kind, often λ (W is included at least in the combination of one the multiple failurej) maximum fault type and the underground pump dynagraoph;
To λ (WjEach revised invariant curve Character eigenvector of the fault type of) >=0 carries out the section based on " unbiased transformation " The Estimation of Mean of data, and calculate the unbiased estimator of the Estimation of Mean;
The combined F index of each group of multiple failures is calculated according to the unbiased estimator of the Estimation of Mean and following formula Value, and determine that multiple failure groups with minimum F index value are combined into multiple faults type possessed by the underground pump dynagraoph:
Wherein, k=1,2 ..., num, num indicate the number of fault type in each group of multiple failure combinations;exptkIndicate kth The number tested under a fault type, of revised invariant curve Character eigenvector under as k-th of fault type Number, exptk=7, expt are the number of all experiments under different faults type, are had: Indicate k-th of event Hinder the under typeThe unbiased estimator of the Estimation of Mean of the interval censored data of a revised invariant curve Character eigenvector, Indicate the interval censored data of all revised invariant curve Character eigenvectors under k-th of fault type The average value of the unbiased estimator of Estimation of Mean, has: Indicate all under all fault types The overall average of the unbiased estimator of the Estimation of Mean of the interval censored data of revised invariant curve Character eigenvector, has:sum1It indicatesWithThe sum of difference, have:Sum2Table ShowWithThe sum of difference, have:
Step is to λ (WjEach revised invariant curve Character eigenvector of the fault type of) >=0 is carried out based on " unbiased transformation " The Estimation of Mean of interval censored data, and the unbiased estimator for calculating the Estimation of Mean specifically includes:
Assuming that the value of the Estimation of Mean of the interval censored data is α, it is a non-negative stochastic variable, by [va,vb] indicate revised The range format of the value of invariant curve Character eigenvector, [va,vb] be and the independent random vector of α, it is assumed that [va,vb] meet The distribution of certain continuous data is indicated by g (), it is believed that g (), which meets, to be uniformly distributed, and revised invariant curve square is special Levy vector value interval [va,vb] be uniformly distributed and indicated by following formula:
Assuming thatWithIt is (v respectivelya,vb) and α independent same distribution sample, it is assumed that observe in an experiment (vas,vbs1s2s3s), in which:I indicates indicative function, R indicates independent same distribution sample size, enables:
Wherein, τsIndicate the observation of s-th of independent same distribution sample;
It enables:
Wherein,Indicate the unbiased estimator of s-th of independent same distribution sample, θ1(·,·)、θ2() and θ3(·,·) It is the continuous function unrelated with the distribution of α, and θ1(·,·)、θ2() and θ3() meets following condition:
Computation interval data [va,vb] Estimation of Mean unbiased estimator it is as follows:
2. the method as described in claim 1, which is characterized in that step extracts the invariant curve of the underground pump dynagraoph after normalization Character eigenvector, and the invariant curve Character eigenvector of extraction is modified and is specifically included:
Underground pump dynagraoph after normalization is by N number of discrete data point (xi,yi), (i=1,2 ... N) composition curve, definition Its p+q rank Curve Moment cpqAre as follows:
Wherein,The straight line of (p, q=0,1,2,3) between two neighboring discrete data point away from From;
Corresponding p+q rank central moment is defined as:
Wherein,PointFor the barycentric coodinates of the underground pump dynagraoph curve after normalization;
It is as follows to calculate each rank central moment:
φ00=c00, φ10=0, φ01=0,
Standardization processing is carried out to obtained each rank central moment, using following normalizing:
It is as follows to calculate 7 invariant curve Character eigenvectors:
7 invariant curve Character eigenvectors are modified, correction formula is as follows:
δi=| lg | γi|| (22)
Wherein, i=1,2 ..., 7 obtains 7 revised invariant curve Character eigenvectors.
CN201610597512.XA 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 Active CN106121622B (en)

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 Active 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 (5)

* Cited by examiner, † Cited by third party
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
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

Citations (6)

* Cited by examiner, † Cited by third party
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 fault early warning method and system of oil well
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 diagnosis method

Patent Citations (6)

* Cited by examiner, † Cited by third party
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 fault early warning method and system of oil well
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 diagnosis method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
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
CN104061445B (en) A kind of pipeline leakage detection method based on neutral net
Helbich et al. Comparative spatial analysis of positional accuracy of OpenStreetMap and proprietary geodata
CN101907681B (en) Analog circuit dynamic online failure diagnosing method based on GSD-SVDD
CN101902470B (en) Form feature-based Web security vulnerability dynamic testing method
Li et al. Using the curve moment and the PSO-SVM method to diagnose downhole conditions of a sucker rod pumping unit
CN106090621B (en) It is a kind of based on pressure signal analysis water supply network leakage, plugging fault diagnosis and localization method
CN104897403A (en) Self-adaption fault diagnosis method based on permutation entropy (PE) and manifold-based dynamic time warping (MDTW)
Häckell et al. Monitoring a 5 MW offshore wind energy converter—Condition parameters and triangulation based extraction of modal parameters
CN105042339B (en) One kind is based on nondimensional leakage of finished oil pipeline amount estimating system and method
CN105206057B (en) Detection method and system based on Floating Car resident trip hot spot region
CN107153843B (en) Ground settlement prediction system and method based on support vector machine
CN102841835B (en) The method and system of hardware performance evaluation and test
CN102235575A (en) Data processing method and system for checking pipeline leakage
CN104766175A (en) Power system abnormal data identifying and correcting method based on time series analysis
CN106195646B (en) Leak is distributed estimating device, deduction system and presumption method
KR102006206B1 (en) Diagnosis method for Detecting Leak of Water Supply Pipe using Deep Learning by Acoustic Signature
CN102750413B (en) Data processing and mapping method of topographic surveying of electric transmission line tower positions
CN102680825A (en) Interference source identification method in system-grade electromagnetic compatibility fault diagnosis
CN105373700A (en) Method for mechanical fault diagnosis based on information entropies and evidence theory
CN107941537B (en) A kind of mechanical equipment health state evaluation method
CN103139007A (en) Method and system for detecting application server performance
CN103336901B (en) The relevant accelerated life test statistical analysis technique of a kind of competing failure
CN105608326B (en) A kind of mountain area complex topography wind field large eddy simulation entrance boundary condition entry method
CN108051035B (en) The pipe network model recognition methods of neural network model based on gating cycle unit
CN104533400B (en) Method for reconstructing logging curve

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
GR01 Patent grant