CN113532753A - Wind power plant gear box oil leakage detection method based on machine vision - Google Patents
Wind power plant gear box oil leakage detection method based on machine vision Download PDFInfo
- Publication number
- CN113532753A CN113532753A CN202110803226.5A CN202110803226A CN113532753A CN 113532753 A CN113532753 A CN 113532753A CN 202110803226 A CN202110803226 A CN 202110803226A CN 113532753 A CN113532753 A CN 113532753A
- Authority
- CN
- China
- Prior art keywords
- module
- oil leakage
- infrared imager
- machine vision
- information
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000003709 image segmentation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000011895 specific detection Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000005611 electricity Effects 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000003685 thermal hair damage Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
-
- 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
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radiation Pyrometers (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a wind power plant gear box oil leakage detection method based on machine vision, which comprises a binocular infrared imager, a computer platform and detected equipment, wherein the binocular infrared imager is electrically connected with the computer platform, the computer platform is electrically connected with a power supply, the binocular infrared imager is used as information acquisition hardware equipment in the method, the three-dimensional temperature field of a box-type transformer is reconstructed by a heat conduction method, and the three-dimensional temperature field is subjected to gridding comparison by using a neural network to realize a method for diagnosing regional faults of different temperature-resistant regions of equipment devices.
Description
Technical Field
The invention belongs to the technical field of gear box detection, and particularly relates to a wind power plant gear box oil leakage detection method based on machine vision.
Background
The gear box in the wind generating set is an important mechanical component, the main function of the gear box is to transmit the power generated by the wind wheel under the action of wind power to the generator and enable the generator to obtain corresponding rotating speed, different types of wind generating sets have different requirements, the arrangement form and the structure of the gear box are different, and the horizontal axis wind generating set in the wind power field is most commonly transmitted by a fixed parallel axis gear and a planetary gear;
the infrared imager can image the whole target in real time in a surface mode, the temperature abnormality of an object can be judged through the analysis and the recognition of the image, but an observer cannot acquire the three-dimensional temperature information of the device immediately, and the state is judged by combining the temperature tolerance of different device parts.
Disclosure of Invention
The invention aims to solve the problems in the background art and provides a wind power plant gearbox oil leakage detection method based on machine vision.
The technical scheme adopted by the invention is as follows:
a wind power plant gear box oil leakage detection method based on machine vision comprises a binocular infrared imager, a computer platform and detected equipment, and comprises the following steps:
the method comprises the following steps: before non-detection, image information of the detected equipment in the transformer when oil leakage does not occur is obtained through a binocular infrared imager;
step two: storing the acquired image information in a computer platform as comparison information;
step three: the method comprises the steps of obtaining current image information of detected equipment of the transformer, comparing and processing the image information when oil leakage does not occur with the current image information, and judging whether the oil leakage problem occurs or not.
Further, the specific detection process of the binocular infrared imager is as follows:
the method comprises the following steps: acquiring temperature information of the detected equipment through a binocular infrared imager, performing corner matching and infrared image matching through an SIFT algorithm, and calculating through a space point reconstruction algorithm to obtain three-dimensional surface temperature information;
step two: obtaining the material characteristics and the heat conduction characteristics of the box-type transformer, and calculating to obtain a three-dimensional temperature field model by a finite formula method;
step three: acquiring temperature-resistant threshold values and working ranges of components of the box-type transformer, performing gridding segmentation on a temperature field according to different regions of the components by using an image segmentation algorithm, and acquiring working temperature rise of elements in corresponding grid regions by image identification comparison so as to judge whether the running state of equipment is normal.
Furthermore, the binocular infrared imager obtains oil leakage direction information of a detection area of the detected equipment and color information of the detection area, and judges whether the detection area leaks oil or not based on the oil leakage direction information of the detection area and the color information of the detection area.
Furthermore, the binocular infrared imager is connected with the computer platform through a collecting card.
Further, the binocular infrared imager is used for shooting the detected equipment to acquire three-dimensional surface temperature information.
Furthermore, the binocular infrared imager is composed of an acquisition terminal module, a photosensitive sensor module, an image acquisition module and a data transmission module, wherein the input end of the image acquisition module is respectively the acquisition terminal module and the photosensitive sensor module, and the input end of the data transmission module is the image acquisition module.
Furthermore, the computer platform is composed of a data receiving module, a database module, a server terminal module, a data processing module and an alarm terminal module, wherein one output end of the data receiving module is the database module, the other output end of the data receiving module is the server terminal module, the output end of the server terminal module is the data processing module, and the output end of the data processing module is the alarm terminal module.
Furthermore, the binocular infrared imager is electrically connected with a computer platform, and the computer platform is electrically connected with a power supply.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. according to the method, a binocular infrared imager is used as information acquisition hardware equipment, the three-dimensional temperature field of a box-type transformer is reconstructed through a heat conduction method, and the neural network is used for carrying out gridding comparison on the three-dimensional temperature field so as to realize regional fault diagnosis on different temperature-resistant regions of equipment devices.
2. The three-dimensional temperature field reconstruction method provided by the invention can provide more monitoring information for equipment operation, and is beneficial to monitoring and analyzing the equipment operation state.
Drawings
FIG. 1 is a schematic flow chart of a machine vision-based wind farm gearbox oil leakage detection system of the present invention;
FIG. 2 is a schematic flow diagram of a binocular infrared imager detection system of the present invention;
FIG. 3 is a schematic flow chart of a computer platform inspection system according to the present invention.
The labels in the figure are: 1. a binocular infrared imager; 11. a collection terminal module; 12. a photosensitive sensor module; 13. an image acquisition module; 14. a data transmission module; 2. a computer platform; 21. a data receiving module; 22. a database module; 23. a server terminal module; 24. a data processing module; 25. an alarm terminal module; 3. and (5) detecting the device.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[ example 1 ]
As shown in FIG. 1, the wind power plant gear box oil leakage detection method based on machine vision comprises a binocular infrared imager 1, a computer platform 2 and detected equipment 3, and comprises the following steps:
the method comprises the following steps: before non-detection, image information of the detected equipment 3 in the transformer when oil leakage does not occur is obtained through a binocular infrared imager 1;
step two: storing the acquired image information in the computer platform 2 as comparison information;
step three: and acquiring the current image information of the detected equipment 3 of the transformer, and comparing and processing the image information when oil leakage does not occur with the current image information so as to judge whether the oil leakage problem occurs or not.
[ example 2 ]
As shown in fig. 1, the specific detection process of the binocular infrared imager 1 is as follows:
the method comprises the following steps: acquiring temperature information of a detected device 3 through a binocular infrared imager 1, performing corner matching and infrared image matching through an SIFT algorithm, and calculating through a space point reconstruction algorithm to obtain three-dimensional surface temperature information;
step two: obtaining the material characteristics and the heat conduction characteristics of the box-type transformer, and calculating to obtain a three-dimensional temperature field model by a finite formula method;
step three: acquiring temperature-resistant threshold values and working ranges of components of the box-type transformer, performing gridding segmentation on a temperature field according to different regions of the components by using an image segmentation algorithm, and acquiring working temperature rise of elements in corresponding grid regions by image identification comparison so as to judge whether the running state of equipment is normal.
[ example 3 ]
As shown in fig. 1, the binocular infrared imager 1 obtains oil leakage direction information of a detection area of the detected device 3 and color information of the detection area, and determines whether the detection area leaks oil based on the oil leakage direction information of the detection area and the color information of the detection area.
[ example 4 ]
As shown in fig. 1, the binocular infrared imager 1 is connected to the computer platform 2 via an acquisition card.
When the double-sided infrared imager is used specifically, data collected by the double-sided infrared imager 1 can be received through the computer platform 2.
[ example 5 ]
As shown in fig. 1, the binocular infrared imager 1 is used to photograph the device under test 3 for acquiring three-dimensional surface temperature information.
When the double-sided infrared imager is used specifically, information can be acquired under the action of the double-sided infrared imager 1.
[ example 6 ]
As shown in fig. 2, the binocular infrared imager 1 is composed of an acquisition terminal module 11, a photosensitive sensor module 12, an image acquisition module 13 and a data transmission module 14, wherein the input end of the image acquisition module 13 is the acquisition terminal module 11 and the photosensitive sensor module 12, and the input end of the data transmission module 14 is the image acquisition module 13.
[ example 7 ]
As shown in fig. 3, the computer platform 2 is composed of a data receiving module 21, a database module 22, a server terminal module 23, a data processing module 24 and an alarm terminal module 25, wherein one output end of the data receiving module 21 is the database module 22, the other output end of the data receiving module 21 is the server terminal module 23, the output end of the server terminal module 23 is the data processing module 24, and the output end of the data processing module 24 is the alarm terminal module 25.
[ example 8 ]
As shown in fig. 1, the binocular infrared imager 1 is electrically connected to the computer platform 2, and the computer platform 2 is electrically connected to the power supply.
The working principle is as follows: the binocular infrared imager 1 is calibrated by an angle calibration method and a Zhang calibration method based on sub-pixels, and geometric parameters of the binocular infrared imager 1 are obtained; acquiring temperature information of a detected device 3 through a binocular infrared imager 1, performing corner matching and infrared image matching through an SIFT algorithm, and calculating through a space point reconstruction algorithm to obtain three-dimensional surface temperature information;
then, the acquired image data is sent to a computer platform 2 through an acquisition card, and a dynamic temperature three-dimensional temperature field is drawn by operating a finite formula method model established according to parameter information such as box-type transformer material and structural heat conduction characteristics and combining surface three-dimensional temperature and calculating point information of the three-dimensional space temperature field;
after the three-dimensional temperature field information is obtained, according to a distribution reference model diagram of a transformer device, image identification and marking are carried out through a neural network algorithm, so that cutting and division of the temperature field are achieved, temperature rise of each region is judged and analyzed, and diagnosis of temperature rise fault points and early warning of equipment thermal damage are achieved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. The utility model provides a wind-powered electricity generation field gear case oil leak detection method based on machine vision, includes binocular infrared imager (1), computer platform (2) and detected equipment (3), its characterized in that: the method for detecting the oil leakage of the gearbox of the wind power plant comprises the following steps:
the method comprises the following steps: before non-detection, image information of the detected equipment (3) in the transformer when oil leakage does not occur is obtained through a binocular infrared imager (1);
step two: storing the acquired image information inside a computer platform (2) as comparison information;
step three: and acquiring the current image information of the detected equipment (3) of the transformer, and comparing and processing the image information when oil leakage does not occur with the current image information so as to judge whether the oil leakage problem occurs or not.
2. The machine vision-based wind farm gearbox oil leakage detection method according to claim 1, characterized by: the specific detection process of the binocular infrared imager (1) is as follows:
the method comprises the following steps: temperature information of the detected equipment (3) is obtained through a binocular infrared imager (1), corner matching and infrared image matching are carried out through an SIFT algorithm, and three-dimensional surface temperature information is obtained through calculation of a space point reconstruction algorithm;
step two: obtaining the material characteristics and the heat conduction characteristics of the box-type transformer, and calculating to obtain a three-dimensional temperature field model by a finite formula method;
step three: acquiring temperature-resistant threshold values and working ranges of components of the box-type transformer, performing gridding segmentation on a temperature field according to different regions of the components by using an image segmentation algorithm, and acquiring working temperature rise of elements in corresponding grid regions by image identification comparison so as to judge whether the running state of equipment is normal.
3. The machine vision-based wind farm gearbox oil leakage detection method according to claim 1, characterized by: the binocular infrared imager (1) obtains oil leakage direction information of a detection area of the detected equipment (3) and color information of the detection area, and judges whether the detection area leaks oil or not based on the oil leakage direction information of the detection area and the color information of the detection area.
4. The machine vision-based wind farm gearbox oil leakage detection method according to claim 1, characterized by: the binocular infrared imager (1) is connected with the computer platform (2) through a collecting card.
5. The machine vision-based wind farm gearbox oil leakage detection method according to claim 1, characterized by: the binocular infrared imager (1) is used for shooting the detected equipment (3) to acquire three-dimensional surface temperature information.
6. The machine vision-based wind farm gearbox oil leakage detection method according to claim 1, characterized by: binocular infrared imager (1) comprises acquisition terminal module (11), photosensitive sensor module (12), image acquisition module (13) and data transmission module (14), the input of image acquisition module (13) is acquisition terminal module (11) and photosensitive sensor module (12) respectively, the input of data transmission module (14) is image acquisition module (13).
7. The machine vision-based wind farm gearbox oil leakage detection method according to claim 1, characterized by: computer platform (2) comprises data receiving module (21), database module (22), server terminal module (23), data processing module (24) and alarm terminal module (25), one of them output of data receiving module (21) is database module (22), the other output of data receiving module (21) is server terminal module (23), the output of server terminal module (23) is data processing module (24), the output of data processing module (24) is alarm terminal module (25).
8. The machine vision-based wind farm gearbox oil leakage detection method according to claim 1, characterized by: binocular infrared imager (1) and computer platform (2) electric connection, computer platform (2) and power electric connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110803226.5A CN113532753B (en) | 2021-07-15 | 2021-07-15 | Wind farm gear box oil leakage detection method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110803226.5A CN113532753B (en) | 2021-07-15 | 2021-07-15 | Wind farm gear box oil leakage detection method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113532753A true CN113532753A (en) | 2021-10-22 |
| CN113532753B CN113532753B (en) | 2024-02-20 |
Family
ID=78128200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110803226.5A Active CN113532753B (en) | 2021-07-15 | 2021-07-15 | Wind farm gear box oil leakage detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113532753B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114033617A (en) * | 2021-12-16 | 2022-02-11 | 金麒麟建设科技股份有限公司 | Controllable wind power generation method and system with control parameters adjusted in self-adaptive mode |
| CN114924207A (en) * | 2022-04-20 | 2022-08-19 | 国网上海市电力公司 | Method for detecting intermittent earth fault based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140033944A (en) * | 2012-09-11 | 2014-03-19 | 엘에스전선 주식회사 | System and method for monitoring-diagnose wind power transformer |
| KR101957464B1 (en) * | 2018-10-18 | 2019-03-12 | 대흥전력기술 주식회사 | Method for repairing leak of transformer on live wire state |
| CN111238649A (en) * | 2020-02-28 | 2020-06-05 | 国网山东省电力公司菏泽供电公司 | Oil-immersed transformer operation abnormity judgment system and method based on infrared temperature measurement |
| CN111751762A (en) * | 2020-05-29 | 2020-10-09 | 江苏方天电力技术有限公司 | Power transformer state identification and safety prevention and control system |
| CN112284619A (en) * | 2020-11-06 | 2021-01-29 | 重庆大唐国际彭水水电开发有限公司 | Oil leakage real-time monitoring device and detection method |
-
2021
- 2021-07-15 CN CN202110803226.5A patent/CN113532753B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140033944A (en) * | 2012-09-11 | 2014-03-19 | 엘에스전선 주식회사 | System and method for monitoring-diagnose wind power transformer |
| KR101957464B1 (en) * | 2018-10-18 | 2019-03-12 | 대흥전력기술 주식회사 | Method for repairing leak of transformer on live wire state |
| CN111238649A (en) * | 2020-02-28 | 2020-06-05 | 国网山东省电力公司菏泽供电公司 | Oil-immersed transformer operation abnormity judgment system and method based on infrared temperature measurement |
| CN111751762A (en) * | 2020-05-29 | 2020-10-09 | 江苏方天电力技术有限公司 | Power transformer state identification and safety prevention and control system |
| CN112284619A (en) * | 2020-11-06 | 2021-01-29 | 重庆大唐国际彭水水电开发有限公司 | Oil leakage real-time monitoring device and detection method |
Non-Patent Citations (2)
| Title |
|---|
| 佟文明;舒圣浪;朱高嘉;孙静阳;兰玉华;: "电机三维温度场的有限公式法计算技术", 中国电机工程学报, no. 07, pages 2131 - 2140 * |
| 杨晓;黎琼炜;殷春;陈凯;邱根;薛婷;黄雪刚;: "应用于压力容器红外无损检测的SIFT图像拼接方法", 电子测量与仪器学报, no. 12, pages 31 - 38 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114033617A (en) * | 2021-12-16 | 2022-02-11 | 金麒麟建设科技股份有限公司 | Controllable wind power generation method and system with control parameters adjusted in self-adaptive mode |
| CN114924207A (en) * | 2022-04-20 | 2022-08-19 | 国网上海市电力公司 | Method for detecting intermittent earth fault based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113532753B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108008176B (en) | A kind of photovoltaic array real-time state monitoring and fault location system | |
| KR101275702B1 (en) | Method and apparatus for fault diagnosis and fault detection of gearbox using vibration signal | |
| CN102565625B (en) | Method for intelligently diagnosing thermal defects of high-voltage transmission line based on infrared image | |
| CN103901072B (en) | Method for diagnosing equipment overheating defects by utilizing infrared spectrum analysis | |
| CN113532753B (en) | Wind farm gear box oil leakage detection method based on machine vision | |
| CN107764198B (en) | Engine stator blade axial gap light projection measuring device and method | |
| CN103499382B (en) | A kind ofly to merge and the Diagnosis Method of Transformer Faults of image recognition based on vibration data | |
| CN110567583A (en) | Energy storage battery stack three-dimensional temperature visualization method based on infrared image | |
| CN103984952A (en) | Method for diagnosing surface crack fault of blade of wind turbine generator of electric power system based on machine vision image | |
| CN113418617A (en) | Three-dimensional temperature field measuring and diagnosing method for box type transformer of wind power plant | |
| CN113030723A (en) | Alternating current asynchronous motor state monitoring system | |
| CN106548211A (en) | Transformer station's point for measuring temperature automatic identifying method and device based on infrared image | |
| CN111027565A (en) | Power transmission and transformation equipment report content generation method based on optical vision semantic extraction | |
| CN108491622A (en) | A kind of fault diagnosis method and system of Wind turbines | |
| CN117743794A (en) | Distributed photovoltaic power station fault diagnosis and efficiency loss evaluation system | |
| Yue et al. | The research on auto-recognition method for analogy measuring instruments | |
| CN117372403A (en) | Method and system for detecting defects of visible light and infrared transformer sleeve image of mobile phone | |
| CN114325197B (en) | Electric energy quality disturbance detection method and device | |
| Cipriani et al. | Thermal anomalies detection in a photovoltaic plant using artificial intelligence: Italy case studies | |
| CN116007759A (en) | Battery temperature field generation method and device, equipment and storage medium | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN210221296U (en) | On-spot management and control early warning device of transformer substation | |
| Wu et al. | Fault Diagnosis of Wind Turbine Blades Based on Image Fusion and ResNet | |
| CA3154395A1 (en) | System and method for determining an operating condition of a wind turbine | |
| CN109557467A (en) | It is suitable for the intelligent Fault Diagnose Systems of a variety of motors based on VxWorks platform |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220429 Address after: 751300 guest house of Tongxin County People's government, Wuzhong City, Ningxia Hui Autonomous Region Applicant after: Ningxia Longyuan new energy Co.,Ltd. Applicant after: XI'AN HUAKONG INTELLIGENT SYSTEM ENGINEERING Co.,Ltd. Address before: Room 11703, 17th floor, unit 1, building 1, oak block, 36 Fenghui South Road, high tech Zone, Xi'an City, Shaanxi Province, 710065 Applicant before: XI'AN HUAKONG INTELLIGENT SYSTEM ENGINEERING Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |