CN104481508B - Oilfield rod-pumping well fault diagnosis method by combining comentropy and gray level incidence matrix - Google Patents
Oilfield rod-pumping well fault diagnosis method by combining comentropy and gray level incidence matrix Download PDFInfo
- Publication number
- CN104481508B CN104481508B CN201410455797.4A CN201410455797A CN104481508B CN 104481508 B CN104481508 B CN 104481508B CN 201410455797 A CN201410455797 A CN 201410455797A CN 104481508 B CN104481508 B CN 104481508B
- Authority
- CN
- China
- Prior art keywords
- matrix
- potential energy
- indicator card
- gray
- indicator
- 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
Links
- 239000011159 matrix material Substances 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000005086 pumping Methods 0.000 title claims abstract description 15
- 238000003745 diagnosis Methods 0.000 title claims abstract description 14
- 238000005381 potential energy Methods 0.000 claims abstract description 35
- 238000010586 diagram Methods 0.000 claims abstract description 17
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 4
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003129 oil well Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000002360 preparation method Methods 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
- E21B47/00—Survey of boreholes or wells
- E21B47/008—Monitoring of down-hole pump systems, e.g. for the detection of "pumped-off" conditions
Landscapes
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Geophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an oilfield rod-pumping well fault diagnosis method by combining comentropy and a gray level incidence matrix. The method comprises the following steps of: generating a complete indicator diagram in one stoke of a well pump; generating a standard indicator diagram gray level matrix according to the indicator diagram; perform profile identification on the standard indicator diagram gray level matrix by using image potential energy, calculating indicator diagram profile potential energy, filling a potential energy data matrix, and generating profile characteristics based on the image potential energy; calculating six statistical characteristics of the profile data matrix; pre-process data by using a section method; calculating the gray relational degree by combining the comentropy; and diagnosing fault types. According to the method, the comentropy is used for calculating amount of information included in each characteristic factor, and the weighted valve can be determined according to the contribution of each characteristic factor in a correlation process. By the grey correlation fault diagnosis method, error diagnosis and error identification of fault operation can be obviously reduced, diagnostic accuracy is improved, and the risk factor of well pump fault operation can be greatly reduced.
Description
Technical field：
The present invention relates to signal processing and automatic control technology field, refer in particular to one kind comentropy and associate with reference to gray scale
The method that matrix realizes oilfield pumping well fault diagnosis.
Background technology：
With year by year growth of the people to petroleum resources demand, oil becomes the resource for concerning quality of life, and takes out
Oil machine well system structure is huge, and working environment is complicated, while pump for pumping well itself is expensive, if event can not be found in time
Economic loss is also brought in oil supply field by barrier, handling failure information, and accurately oil well fault diagnosis has in oilfield production in real time
Vital effect.Wider fault diagnosis of pumping wells system is applied at present, and based on intelligent algorithm, these algorithms are equal
It is complex, while the situation that rod-pumped well normally runs is significantly larger than situation about breaking down, accomplish the failure of real-time complexity
Diagnosis, for computer system has larger challenge.
The content of the invention：
The invention provides a kind of side for realizing oilfield pumping well fault diagnosis with comentropy with reference to gray scale incidence matrix
Method.
The technical scheme is that：With reference to gray scale incidence matrix, one kind comentropy realizes that oilfield pumping well failure is examined
Disconnected method, comprises the steps：Generate indicator card complete in one stroke of pump for pumping well；Standard is generated according to indicator card to show
Work(figure gray matrix；Outline identification is carried out to standard indicator diagram gray matrix using image potential energy, calculates indicator card profile potential energy
And potential energy data matrix is filled, generate the contour feature based on image potential energy；Six statistics for calculating outline data matrix are special
Levy, including gray average, gray variance, the gray scale degree of bias, gray scale kurtosis, gray scale energy, gray level entropy；Data are carried out using interval method
Pretreatment；The grey relational grade of calculations incorporated comentropy；Fault type is diagnosed.
The detailed process of described generation standard indicator diagram gray matrix is to call indicator card, carries out gray scale to indicator card
Process, generated and the full image of the tangent indicator card in four side of indicator card curve using the method for boundary rectangle, gone unless indicator card figure
As the redundancy that part is brought to gray matrix, preliminary indicator card gray matrix is obtained；The matrix that gray proces are obtained carries out two
Value is processed, and forms original indicator card gray matrix；The gray matrix is compressed into process, non-zero unit in the new matrix is searched for
8 values adjacent in element are 0 value, are replaced with 0；The matrix for obtaining is carried out into binary conversion treatment, the standard of obtaining shows work(
Figure gray matrix.
The detailed process of described calculating indicator card profile potential energy is to define indicator card profile for potential energy zero, indicator card
Contoured interior pixel potential energy by potential energy zero gradually increases, indicator card profile exterior pixel from potential energy zero start potential energy by
It is decrescence few, potential energy assignment is carried out to each element, until each element of standard grayscale matrix is traversed.
The invention has the beneficial effects as follows：The present invention instead of the intelligent algorithm of existing complexity, be calculated using comentropy
The quantity of information included by each characterization factor, determines its according to the size of the contribution of each characterization factor in association process
Weighted value.The gray relative method for diagnosing faults can significantly reduce the not identified erroneous judgement that operates with failure but, improve diagnosis
Degree of accuracy, substantially reduces the danger coefficient that pump for pumping well is run in spite of illness.
Description of the drawings：
The indicator card of the embodiment that Fig. 1 is provided for the present invention；
The generation standard indicator diagram matrix part flow chart of the embodiment that Fig. 2 is provided for the present invention；
The indicator card outline identification result figure of the embodiment that Fig. 3 is provided for the present invention；
The indicator card potential energy data filling partial process view of the embodiment that Fig. 4 is provided for the present invention；
The indicator card potential energy data matrix filling result figure of the embodiment that Fig. 5 is provided for the present invention.
Specific embodiment：
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
The present invention specific implementation step be：
First, generate the measured indicator diagram of pump for pumping well：
As the working environment of pump for pumping well, the course of work have certain complexity and Unpredictability, therefore, sensing
The aspects such as the quantity of device returned data, yardstick, dimension have differences, and in order to keep the feature of indicator card, host computer are not passed back
Data amount check accepted or rejected, and carry out the process of dimensionless normalizing yardstick, reduce geographical position institute's band different with survey tool
The error come.Indicator card is drawn according to the data after process, as shown in Figure 1.The pumpingh well physical fault is that feed flow is not enough.
2nd, the standard grayscale matrix of indicator card is generated, concrete steps are as shown in Figure 2：
Step 201：Enter every trade compression.If original gradation matrix is M ' × N ', by M '/32 matrix unit successively in each column
Value sum is put in new 64 × 32 matrix.
Step 202：Enter ranks compression.Similar to row compression, difference is that successively every row is carried out.
Step 203：Give up the non-zero element that cannot form closed curve with other elements.Search for non-zero element in the new matrix
In 8 adjacent values be 0 value, be replaced with 0, because such matrix element can not form envelope with other matrix elements
Closed curve, therefore give up such value, give up other values that so cannot form closed curve with other non-zero matrix elements in the same manner.
Step 204：Matrix to obtaining carries out binary conversion treatment.
Step 205：Generate standard indicator diagram gray matrix.
3rd, outline identification is carried out to indicator card matrix using image potential energy, recognition result is as shown in Figure 3；To indicator card wheel
Wide data matrix carries out the calculating of profile potential energy and the filling of data matrix, and the flow chart of filling process is as shown in figure 4, concrete walk
Suddenly it is described as follows：
Step 401：Two values matrix is carried out into pretreatment, the element that pixel value therein is 0 is replaced with into 100, it is to avoid
There is obscuring for initial 0 element and element that potential energy is 0 during potential energy assignment.
Step 402：A nw matrix is defined, it is onesize with standard indicator diagram gray matrix, show work(for labelling standard
The positional information of figure gray matrix each pixel.Represent that when nw is 0 the pixel is the pixel on indicator card curve, also
It is described profile point, for the pixel on the outside of closing indicator card, nw is entered as into -1, for the picture inside closing indicator card
Vegetarian refreshments, is entered as 1.
Step 403：Initializing variable.
Step 404：Carry out potential energy assignment.
Step 405：Change assignment point.
Step 406：The element value of assignment point is added certainly.
Step 407：The element of assignment point is judged.
Step 408：When the element of assignment point is 0, return to step 405 re-starts assignment.
Step 409：When the element of assignment point is not 0, the assignment point assignment terminates.
Fig. 5 is referred to, is indicator card potential energy matrix data filling result.
The information weighting entropy of each factor of failure is calculated, is normalized.
Gray average, gray variance, the gray scale degree of bias, gray scale peak value, gray scale energy and the gray scale of tracing trouble is treated in calculating
The fault feature vector constituted by entropy.
The vector and standard failure vector are carried out into contrast association analysiss, this are calculated using ABO incidence formulas and are treated diagnosis event
The grey relational grade of barrier and other standards failure.
Diagnosed using grey relational grade, because the quantity of information fully taken into account contained by the different characteristic factor is different,
So that treating that tracing trouble and the relating value of normal operation become big, diminish with the relating value of other failures, make result more accurate.
The present invention instead of the intelligent algorithm of existing complexity, calculate what each characterization factor was included using comentropy
Quantity of information, determines its weighted value according to the size of the contribution of each characterization factor in association process.The gray relative failure
Diagnostic method can significantly reduce the not identified erroneous judgement that operates with failure but, improve the degree of accuracy of diagnosis, substantially reduce and take out
The danger coefficient that oil pump is run in spite of illness.
Claims (1)
1. a kind of method for realizing oilfield pumping well fault diagnosis with reference to gray scale incidence matrix with comentropy, walks including following
Suddenly：Generate indicator card complete in one stroke of pump for pumping well；Standard indicator diagram gray matrix is generated according to indicator card；Using figure
As potential energy carries out outline identification to standard indicator diagram gray matrix, calculate indicator card profile potential energy and fill potential energy data matrix,
Generate the contour feature based on image potential energy；Six statistical natures of outline data matrix are calculated, including gray average, gray scale side
Difference, the gray scale degree of bias, gray scale kurtosis, gray scale energy, gray level entropy；Data prediction is carried out using interval method；Calculations incorporated comentropy
Grey relational grade；Fault type is diagnosed；
The detailed process of described generation standard indicator diagram gray matrix is to call indicator card, carries out gray proces to indicator card,
Generated and the full image of the tangent indicator card in four side of indicator card curve using the method for boundary rectangle, gone unless indicator card image section
To the redundancy that gray matrix brings, preliminary indicator card gray matrix is obtained；The matrix that gray proces are obtained is carried out at binaryzation
Reason, forms original indicator card gray matrix；The gray matrix is compressed into process, phase in non-zero element is searched in the new matrix
8 adjacent values are 0 value, are replaced with 0；The matrix for obtaining is carried out into binary conversion treatment, standard indicator diagram gray scale is obtained
Matrix；
The detailed process of described calculating indicator card profile potential energy is to define indicator card profile for potential energy zero, indicator card profile
Interior pixels potential energy by potential energy zero gradually increases, and indicator card profile exterior pixel starts potential energy from potential energy zero and gradually subtracts
It is few, potential energy assignment is carried out to each element, until each element of standard grayscale matrix is traversed；
In said method, the concrete grammar for generating indicator card complete in one stroke of pump for pumping well is that host computer is passed back
Total data carries out the process of dimensionless normalizing yardstick, draws indicator card according to the data after process；
In said method, to comprising the following steps that indicator card outline data matrix is filled：
Step 401：Two values matrix is carried out into pretreatment, the element that pixel value therein is 0 is replaced with into 100；
Step 402：A nw matrix is defined, it is onesize with standard indicator diagram gray matrix, for labelling standard indicator diagram ash
The positional information of each pixel of matrix is spent, represents that when nw is 0 the pixel is the pixel on indicator card curve, that is,
Nw, for the pixel on the outside of closing indicator card, is entered as -1 by described profile point, for the pixel inside closing indicator card
Point, is entered as 1；
Step 403：Initializing variable；
Step 404：Carry out potential energy assignment；
Step 405：Change assignment point；
Step 406：The element value of assignment point is added certainly；
Step 407：The element of assignment point is judged；
Step 408：When the element of assignment point is 0, return to step 405 re-starts assignment；
Step 409：When the element of assignment point is not 0, the assignment point assignment terminates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410455797.4A CN104481508B (en) | 2014-09-10 | 2014-09-10 | Oilfield rod-pumping well fault diagnosis method by combining comentropy and gray level incidence matrix |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410455797.4A CN104481508B (en) | 2014-09-10 | 2014-09-10 | Oilfield rod-pumping well fault diagnosis method by combining comentropy and gray level incidence matrix |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104481508A CN104481508A (en) | 2015-04-01 |
| CN104481508B true CN104481508B (en) | 2017-03-22 |
Family
ID=52756100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410455797.4A Active CN104481508B (en) | 2014-09-10 | 2014-09-10 | Oilfield rod-pumping well fault diagnosis method by combining comentropy and gray level incidence matrix |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104481508B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107526784A (en) * | 2017-07-27 | 2017-12-29 | 上海电力学院 | A kind of method for diagnosing faults based on matrix fill-in |
| CN108952673B (en) * | 2018-06-22 | 2023-09-26 | 中国石油天然气股份有限公司 | Method and device for checking working condition of oil pumping well |
| CN108915668A (en) * | 2018-07-17 | 2018-11-30 | 东北大学 | A kind of Diagnosing The Faults of Sucker Rod Pumping System method based on gray level co-occurrence matrixes |
| CN111584088B (en) * | 2020-06-15 | 2023-05-30 | 四川中电启明星信息技术有限公司 | Power grid constructor altitude sickness risk judging method based on disease source information entropy |
| CN114494791B (en) * | 2022-04-06 | 2022-07-08 | 之江实验室 | Attention selection-based transformer operation simplification method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1093772A (en) * | 1993-04-17 | 1994-10-19 | 石油大学(华东) | Universal intelligent diagnostic instrument for deepwell pump oil-production well condition |
| RU2125716C1 (en) * | 1997-02-26 | 1999-01-27 | Волгоградский государственный технический университет | Gear for vibroacoustic diagnostics of machines |
| CN101624908A (en) * | 2009-08-11 | 2010-01-13 | 李桂江 | Method for detecting working condition of pumping well |
| CN102184414A (en) * | 2011-05-16 | 2011-09-14 | 中国石油天然气股份有限公司 | Method and system for identifying and judging pump indicator diagram |
| CN103510940A (en) * | 2013-09-27 | 2014-01-15 | 中国石油天然气股份有限公司 | Comprehensive diagnosis and analysis method and device for mechanical oil production well working condition |
| CN103670373A (en) * | 2012-09-26 | 2014-03-26 | 中国石油天然气股份有限公司 | Method and system for diagnosing faults of oil pumping unit |
-
2014
- 2014-09-10 CN CN201410455797.4A patent/CN104481508B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1093772A (en) * | 1993-04-17 | 1994-10-19 | 石油大学(华东) | Universal intelligent diagnostic instrument for deepwell pump oil-production well condition |
| RU2125716C1 (en) * | 1997-02-26 | 1999-01-27 | Волгоградский государственный технический университет | Gear for vibroacoustic diagnostics of machines |
| CN101624908A (en) * | 2009-08-11 | 2010-01-13 | 李桂江 | Method for detecting working condition of pumping well |
| CN102184414A (en) * | 2011-05-16 | 2011-09-14 | 中国石油天然气股份有限公司 | Method and system for identifying and judging pump indicator diagram |
| CN103670373A (en) * | 2012-09-26 | 2014-03-26 | 中国石油天然气股份有限公司 | Method and system for diagnosing faults of oil pumping unit |
| CN103510940A (en) * | 2013-09-27 | 2014-01-15 | 中国石油天然气股份有限公司 | Comprehensive diagnosis and analysis method and device for mechanical oil production well working condition |
Non-Patent Citations (2)
| Title |
|---|
| 基于信息熵与灰关联的抽油井泵示功图诊断技术研究;王秀芳等;《化工自动化及仪表》;20131130(第11期);第1370-1373页 * |
| 基于图像势能理论的目标轮廓特征提取方法;陈雪松等;《计算机科学》;20110630(第6期);第270-274页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104481508A (en) | 2015-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104481508B (en) | Oilfield rod-pumping well fault diagnosis method by combining comentropy and gray level incidence matrix | |
| CN109615019B (en) | Abnormal behavior detection method based on space-time automatic encoder | |
| CN111160440B (en) | Deep learning-based safety helmet wearing detection method and device | |
| CN111832484B (en) | Loop detection method based on convolution perception hash algorithm | |
| CN110705376A (en) | Abnormal behavior detection method based on generative countermeasure network | |
| CN114332639B (en) | Satellite attitude vision measurement method of nonlinear residual error self-attention mechanism | |
| CN113284107B (en) | Attention mechanism-introduced improved U-net concrete crack real-time detection method | |
| CN112801972A (en) | Bridge defect detection method, device, system and storage medium | |
| CN114022770A (en) | Mountain crack detection method based on improved self-attention mechanism and transfer learning | |
| CN109522831B (en) | Real-time vehicle detection method based on micro-convolution neural network | |
| CN112560587A (en) | Dynamic early warning method and system for convolutional neural network slope crack change | |
| CN104574351A (en) | Parking space detection method based on video processing | |
| CN114445420A (en) | Image segmentation model with coding and decoding structure combined with attention mechanism and training method thereof | |
| CN115345859A (en) | Intelligent detection method, device and equipment for tunnel leakage water image and storage medium | |
| CN114937023A (en) | Defect identification method and device for pressure-bearing equipment | |
| CN114972882A (en) | Wear surface damage depth estimation method and system based on multi-attention machine system | |
| CN112861135B (en) | Malicious code detection method based on attention mechanism | |
| CN117726322A (en) | Intelligent management method and system for probe test equipment | |
| CN116912645A (en) | Three-dimensional target detection method and device integrating texture and geometric features | |
| CN109854227A (en) | A kind of New well drilling fault finding system | |
| KR20230043419A (en) | Ai-based building defect inspection system | |
| CN114495263A (en) | Alarm pre-control device for preventing personal injury | |
| CN207636505U (en) | A kind of shoes mould surface damage detection device | |
| CN116229399B (en) | Feature extraction method, system and medium for point cloud data for automatic driving image processing | |
| CN118505166B (en) | Power transmission line unplanned operation checking method and system based on image analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |