CN117372945A - Hydropower unit large-axis peristaltic detection method based on image recognition technology - Google Patents
Hydropower unit large-axis peristaltic detection method based on image recognition technology Download PDFInfo
- Publication number
- CN117372945A CN117372945A CN202311171332.1A CN202311171332A CN117372945A CN 117372945 A CN117372945 A CN 117372945A CN 202311171332 A CN202311171332 A CN 202311171332A CN 117372945 A CN117372945 A CN 117372945A
- Authority
- CN
- China
- Prior art keywords
- axis
- peristaltic
- pure black
- industrial camera
- black point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002572 peristaltic effect Effects 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000005516 engineering process Methods 0.000 title claims abstract description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000005259 measurement Methods 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 11
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 4
- 239000003550 marker Substances 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 238000009434 installation Methods 0.000 abstract description 2
- 238000012806 monitoring device Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009532 heart rate measurement Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008855 peristalsis Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Multimedia (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a large-axis peristaltic detection method of a hydroelectric generating set based on an image recognition technology, which comprises the following steps: transmitting the shot image to an image processing device through an industrial camera, and obtaining a unit pixel length scale factor of the industrial camera by the image processing device according to the number of pixel points occupied by the large axis of the water turbine and the width of the large axis of the water turbine under the view angle of the industrial camera; calculating the included angle between the pure black point and the center line of the large axis; obtaining the deviation angle range of the pure black point according to the set large-axis peristaltic alarm angle, obtaining the limit deviation distance of the pure black point from the large-axis central line through the limit deviation angle of the pure black point, finally obtaining the limit deviation pixel number of the pure black point, and alarming after the pixel number of the pure black point deviated in the industrial camera image reaches the limit deviation pixel number. The invention has the advantages of reducing the manufacturing and installation cost of the detection equipment, reducing the overhaul interference on the water turbine and improving the detection precision.
Description
Technical Field
The invention relates to the technical field of large-axis peristaltic detection, in particular to a large-axis peristaltic detection method of a hydroelectric generating set based on an image recognition technology.
Background
The large-shaft creep phenomenon of the hydroelectric generating set refers to the phenomenon that the generating set is stopped, and in the guide vane fully-closed state, water leakage occurs between the guide vanes due to the fact that the guide vanes are not tightly closed, and when the water leakage amount is increased, the large shaft of the generating set slowly rotates. When large shaft creep occurs in the hydroelectric generating set, if the large shaft creep cannot be found in time, a potential major safety accident can occur, and long-time large shaft creep can cause dry friction to burn the bearing bush. At present, two methods of non-contact type electric pulse mode detection and mechanical friction mode detection are mainly adopted for large-axis creep detection of the hydroelectric generating set.
Non-contact electrical pulse measurement mode: a toothed belt is arranged on the periphery of a large shaft of the unit, a photoelectric sensor is arranged at a fixed position on the periphery of the toothed belt, when the unit is subject to peristaltic motion, the photoelectric sensor outputs alternating rising edge and falling edge signals to a monitoring device, and the monitoring device sends out peristaltic motion alarm signals when detecting that the signals exceed a set threshold value.
However, this measurement has the following disadvantages: 1. the toothed belt required by the measuring mode is complex to process, and certain requirements are also met on the processing precision; 2. the installation distance between the photoelectric probe and the toothed belt is generally required to be 2+/-0.5 mm, and certain inconvenience is caused to the overhaul and maintenance of the later-stage unit.
Mechanical friction measurement mode: after the machine set is stopped, the friction wheel extends out of the detection device and is contacted with the surface of the large shaft of the machine set, when the large shaft is peristaltic, the friction wheel is driven to deflect by friction force, and after the rotation angle reaches a certain angle, the peristaltic device sends out a peristaltic alarm signal.
However, this measurement has the following disadvantages: because of the contact measurement, when the large-shaft peristaltic monitoring device is thrown and retreated for many times, the device position is deviated, and the phenomenon of poor contact with the large shaft is caused, so that the measurement is inaccurate, even the occurrence of large-shaft peristaltic is not detected, and the large-shaft peristaltic monitoring device has a complex structure and is difficult to install, operate and maintain.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides a large-axis peristaltic detection method for a hydropower station unit based on an image recognition technology, which solves the problems of high preparation cost, reduced detection precision after long-term use and inconvenience in overhauling of the hydropower station unit existing in the prior art.
According to the embodiment of the invention, the large-axis peristaltic detection method of the hydroelectric generating set based on the image recognition technology comprises the following steps of:
s1, sleeving an annular peristaltic measurement mark on a large shaft of a water turbine, equidistantly arranging pure black blocks on the peristaltic measurement mark, shooting and obtaining images of the large shaft of the water turbine and the peristaltic measurement mark through an industrial camera pair, and setting a connecting line of the camera and the center of the large shaft of the water turbine as a center line of the large shaft;
s2, the industrial camera transmits the shot image to an image processing device, and the image processing device obtains a unit pixel length scale factor of the industrial camera according to the number of pixel points occupied by the large axis of the water turbine and the width of the large axis of the water turbine under the view angle of the industrial camera;
s3, obtaining the distance between the position of the pure black point and the central line of the large axis through a unit pixel length scale factor, and calculating the included angle between the pure black point and the central line of the large axis;
s4, obtaining the deviation angle range of the pure black point according to the set large-axis peristaltic alarm angle, obtaining the limit deviation distance of the pure black point from the large-axis central line through the limit deviation angle of the pure black point, finally obtaining the limit deviation pixel point number of the pure black point, and giving an alarm after the deviation pixel point number of the pure black point in the industrial camera image reaches the limit deviation pixel point number.
Preferably, an illumination lamp is arranged above the industrial camera, the illumination lamp facing the peristaltic measurement marker.
Preferably, at least four of the pure black blocks are arranged on the peristaltic measurement markers.
Preferably, in step S2, the industrial camera is mounted perpendicular to the axis of the large axis of the hydraulic turbine, the industrial camera is spaced from the surface of the large axis of the hydraulic turbine by a distance x1, and the radius of the large axis of the hydraulic turbine is R, according to the formula:the actual width x2 of the large axis of the water turbine in the industrial camera view angle can be obtained, and then the total number y of pixels occupied by the large axis width of the water turbine in the image shot by the industrial camera is calculated according to the formula:the unit pixel length scale factor lambda of the industrial camera can be obtained.
Preferably, in step S3, the pure black block is calibrated at a position a, and the number y2 of pixel points between the pixel point where the pure black block is located and the large axis center line in the image shot by the industrial camera is calculated by the formula: x=y2×λ, calculating the actual distance from the large axis centerline at a, and by the formula:calculating an included angle theta between the point A and the central line of the large shaft, and obtaining a peristaltic alarm point A' corresponding to the limit offset angle according to the requirement of the international large shaft peristaltic alarm of 1.5 degrees through the formula: />Calculating the limit distance of the pure black point relative to the center line of the large shaft, and then passing through the formula: obtaining the alarm displacement quantity Deltax of the pure black point by Deltax=x-x', and finally obtaining the displacement of the pure black point in the direction of +.>And a large-axis peristaltic alarm signal is sent out when the pixel points are arranged.
Compared with the prior art, the invention has the following beneficial effects:
1. the image processing device is used for processing the photographed image of the industrial camera through the industrial camera to realize monitoring of the large-axis peristaltic motion of the water turbine, and interference of the monitoring device to overhaul of the water turbine unit is avoided in the remote monitoring mode.
2. And the position shooting and calculation are carried out on the pure black point by taking the pixel point and the center line of the large shaft as references through the shooting of an industrial camera, so that the accuracy of monitoring the large shaft of the water turbine is ensured.
3. The peristaltic measuring sign is simple to manufacture and install and low in production cost.
Drawings
Fig. 1 is a schematic structural diagram of an embodiment of the present invention.
FIG. 2 is a schematic development of a peristaltic measurement marker according to an embodiment of the present invention.
FIG. 3 is a top view of a unit pixel length scale factor calculation in an embodiment of the invention.
Fig. 4 is a plan view of alert displacement calculation in an embodiment of the present invention.
In the above figures: 1. a large shaft of the water turbine; 2. a radiation lamp; 3. an industrial camera; 4. peristaltic measurement markers; 5. a solid black block; 6. an image processing apparatus.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
As shown in fig. 1-4, the large-axis peristaltic monitoring system of the water turbine based on the image recognition technology is efficient and concise in detection method, and the large-axis peristaltic detection device based on the method is easy to install and maintain and more visual in display.
It comprises a large shaft 1 of a water turbine, a peristaltic measuring sign 4, a lighting lamp 2, an industrial camera 3 and an image processing device 6.
The development schematic diagram of the peristaltic measurement marks 4 is shown in fig. 2, the peristaltic measurement marks 4 are developed into strip rectangles, the lengths of the peristaltic measurement marks 4 are the circumferences of the large shafts 1 of the water turbines, and four pure black blocks 5 are uniformly distributed on the peristaltic measurement marks 4.
The industrial camera 3 and the irradiation lamp 2 are arranged on the periphery of the large shaft 1 of the water turbine, the industrial camera 3 is opposite to the large shaft 1 of the water turbine, the irradiation lamp 2 is arranged above the industrial camera 3 at a certain position, and the large shaft 1 of the water turbine is obliquely irradiated downwards, so that the industrial camera 3 can obtain clear and bright images of the large shaft 1 of the water turbine and the peristaltic measuring sign 4.
In the top view of the large axis shown in fig. 3, the camera is installed at a point O perpendicular to the surface of the large axis and distant from the surface x1 of the large axis, the radius R, x2 of the large axis of the water turbine is known as the actual width of the large axis in the image taken by the industrial camera, and the actual width x2 of the large axis in the view angle of the camera is calculated as
The image processing unit calculates the total number y of pixels with the large axial width shot in the camera, and the unit pixel length scale factor lambda is as follows:
in one of the large-axis peristaltic cases, after the machine unit is stopped, a black block of the peristaltic measurement mark is positioned at A, as shown in FIG. 4, the image processing unit calculates the pixel point number y2 of the point A from the center of the large axis in the picture taken by the camera, and multiplies the pixel point number y2 by the unit pixel length scale factor lambda to obtain the actual distance x of the point A from the center of the large axis as
x＝y2×λ
The large shaft radius R of the water turbine is known, and the included angle theta between the point A and the center line of the large shaft is
According to the requirements of 1.5 DEG alarming of large axis peristalsis in national standard, the peristaltic alarming point can be obtained as A ' in the graph, and the actual distance x ' between the A ' point and the center of the large axis is calculated to be
The alarm displacement Deltax is
△x＝x-x'
I.e. when the peristaltic sign is detected to be displaced in the picture taken by the camera in the image processing unitAnd a large-axis peristaltic alarm signal is sent out when the pixel points are arranged.
Claims (5)
1. The large-axis peristaltic detection method for the hydroelectric generating set based on the image recognition technology is characterized by comprising the following steps of:
s1, sleeving an annular peristaltic measurement mark (4) on a large shaft (1) of the water turbine, equidistantly arranging pure black blocks (5) on the peristaltic measurement mark (4), shooting and acquiring images of the large shaft (1) of the water turbine and the peristaltic measurement mark (4) through an industrial camera (3), and setting a connecting line of the camera (3) and the center of the large shaft (1) of the water turbine as a large shaft center line;
s2, the industrial camera (3) transmits the shot image to an image processing device (6), and the image processing device (6) obtains a unit pixel length scale factor of the industrial camera (3) according to the number of pixels occupied by the large axis (1) of the water turbine and the width of the large axis (1) of the water turbine under the view angle of the industrial camera (3);
s3, obtaining the distance between the position of the pure black point (5) and the central line of the large axis through a unit pixel length scale factor, and calculating the included angle between the pure black point (5) and the central line of the large axis;
s4, obtaining an offset angle range of the pure black point (5) according to the set large-axis peristaltic alarm angle, obtaining a limit offset distance of the pure black point (5) from a large-axis central line through a limit offset angle of the pure black point (5), finally obtaining a limit offset pixel point number of the pure black point (5), and giving an alarm after the pixel point number of the pure black point (5) offset in an industrial camera (3) image reaches the limit offset pixel point number.
2. The method for detecting large axis creep of the hydroelectric generating set based on the image recognition technology as claimed in claim 1, wherein the method comprises the following steps: -arranging an illumination lamp (2) above the industrial camera (3), the illumination lamp (2) being directed towards the peristaltic measuring marker (4).
3. The method for detecting large axis creep of the hydroelectric generating set based on the image recognition technology as claimed in claim 1, wherein the method comprises the following steps: -arranging at least four of said pure black blocks (5) on said peristaltic measuring markers (4).
4. The method for detecting large axis creep of the hydroelectric generating set based on the image recognition technology as claimed in claim 1, wherein the method comprises the following steps: in step S2, the industrial camera (3) is mounted perpendicular to the axis of the large turbine shaft (1), the distance of the industrial camera (3) from the surface of the large turbine shaft (1) is x1, the radius of the large turbine shaft (1) is R, and according to the formula:the actual width x2 of the large axis (1) of the water turbine in the view angle of the industrial camera (3) can be obtained, and then the total number y of pixels occupied by the width of the large axis (1) of the water turbine in the image shot by the industrial camera (3) is calculated according to the formula: />The unit pixel length scale factor lambda of the industrial camera (3) can be obtained.
5. The method for detecting large axis creep of the hydroelectric generating set based on the image recognition technology as claimed in claim 1, wherein the method comprises the following steps: in step S3, calibrating the pure black block (5) at a position a, and calculating the number y2 of pixel points between the pixel point where the pure black block (5) is located and the large axis center line in the image shot by the industrial camera (3), where the number y2 is calculated by the formula:
x=y2×λ, calculating the actual distance from the large axis centerline at a, and by the formula:calculating an included angle theta between the point A and the central line of the large shaft, and obtaining a peristaltic alarm point A' corresponding to the limit offset angle according to the requirement of the international large shaft peristaltic alarm of 1.5 degrees through the formula: />Calculating the limit distance of the pure black point (5) relative to the center line of the large shaft, and then passing through the formula: deltax=x-x', obtaining the alarm displacement Deltax of the pure black point (5), and finally obtaining the displacement of the pure black point (5)>And a large-axis peristaltic alarm signal is sent out when the pixel points are arranged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311171332.1A CN117372945A (en) | 2023-09-11 | 2023-09-11 | Hydropower unit large-axis peristaltic detection method based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311171332.1A CN117372945A (en) | 2023-09-11 | 2023-09-11 | Hydropower unit large-axis peristaltic detection method based on image recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117372945A true CN117372945A (en) | 2024-01-09 |
Family
ID=89391893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311171332.1A Pending CN117372945A (en) | 2023-09-11 | 2023-09-11 | Hydropower unit large-axis peristaltic detection method based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117372945A (en) |
-
2023
- 2023-09-11 CN CN202311171332.1A patent/CN117372945A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170260968A1 (en) | Abnormality diagnosing apparatus for rolling bearing, wind turbine, and abnormality diagnosing method for rolling bearing | |
| CN102176329B (en) | Bolt looseness monitoring device for reactor coolant pump and monitoring method thereof | |
| CN106323153A (en) | Pipeline inner bore quality detection mini-sized mobile robot and control method therefor | |
| CN111204566B (en) | Belt deviation monitoring device and method based on machine vision | |
| CN111608731B (en) | Shield tunnel safety state monitoring and early warning device and monitoring and early warning method thereof | |
| CN111380468A (en) | Device and method for measuring rotor eccentricity and phase of steam turbine generator unit | |
| CN117372945A (en) | Hydropower unit large-axis peristaltic detection method based on image recognition technology | |
| CN112729201A (en) | Monitoring device and monitoring method for scouring state of foundation of offshore wind power pile foundation | |
| US20020033052A1 (en) | Rotary shaft axial elongation measuring method and device | |
| WO2023169255A1 (en) | System and method for measuring creep of hydro-generator by using image monitoring | |
| CN104635756A (en) | Measuring method and unit of tracking angle deviation of solar tracker | |
| CN109312719B (en) | Method for monitoring a rotor blade adjustment device | |
| CN212109904U (en) | Turbine generator set rotor eccentricity and phase measuring device thereof | |
| CN113252939B (en) | Peristaltic detection method and device for hydroelectric generating set based on image recognition technology | |
| CN103256904A (en) | Large rotating supporting rolling way abrasion automatic detecting system and arge rotating supporting rolling way abrasion automatic detecting method | |
| CN205642400U (en) | Absolute formula photoelectric encoder's structure | |
| CN113959375B (en) | Image acquisition method of tower flange flatness detection equipment | |
| CN220366826U (en) | Horizontal monitoring device for bearing seat of steam turbine | |
| CN108333383A (en) | Speed measuring system based on smart mobile phone and image procossing | |
| CN113294300A (en) | Method, device and system for measuring blade pitch angle of wind generating set | |
| CN204122478U (en) | The on-line detecting system of cold-strip steel camber | |
| CN113417812A (en) | Wind turbine generator system cabin displacement monitoring system and monitoring method | |
| CN112832957B (en) | Main bearing floating performance monitoring system and method and wind generating set | |
| CN114381596B (en) | Position detecting and positioning device, method and system thereof and positioning method of system | |
| CN219607946U (en) | Deep foundation pit horizontal displacement monitoring device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |