CN104865269A - Wind turbine blade fault diagnosis method - Google Patents
Wind turbine blade fault diagnosis method Download PDFInfo
- Publication number
- CN104865269A CN104865269A CN201510170405.4A CN201510170405A CN104865269A CN 104865269 A CN104865269 A CN 104865269A CN 201510170405 A CN201510170405 A CN 201510170405A CN 104865269 A CN104865269 A CN 104865269A
- Authority
- CN
- China
- Prior art keywords
- blade
- fault
- image
- pneumatic equipment
- equipment blades
- 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
Abstract
The invention relates to the technical field of wind turbine fault diagnosis, and especially a wind turbine blade fault diagnosis method. Multiple segmentation is carried out on the wind turbine blade surface through locating points divided, and the differential principle is employed to divide the curved wind turbine blade into an image elements believed to be plane, and the locating point can locate the fault. A camera fixed on the wind turbine tower takes photos the wind turbine blade elements on preset timing for sampling, and the blade element original images are obtained and processed. A blade fault database is designed, and the blade fault diagnosis algorithm is applied to fault diagnosis of wind turbine blades for intelligent fault identification, in order to make judgments. The method solves the problems in the existing diagnosis method that the video monitoring of growth and development of wind turbine blade fault are very complex and the algorithm is low in precision and can not meet production demand. The diagnosis method of the invention is simple, feasible and high in sensitivity, and can enhance the security of the blades of a wind driven generator.
Description
Technical field
The present invention relates to wind energy conversion system fault diagnosis technology field, specifically pneumatic equipment blades method for diagnosing faults.
Background technology
At present, pneumatic equipment blades damage problem be vane design of wind turbines, manufacture, an important content paying close attention in operation.Severe and the whole day of the weather conditions of the residing environment of wind energy conversion system itself is run under being in alternate load, cause fan part ratio to be easier to damage, and the fast development of wind-powered electricity generation industry proposes stricter requirement to fault supervision and diagnostic techniques.
The fault of pneumatic equipment blades has multiple mode classification, is divided into from its form of expression aspect: blade surface has sand holes, blade cracking, blade freezes, blade surface corrosion.Measure of supervision for pneumatic equipment blades fault is divided into damage and non-damage two class, and the non-damage measure of supervision of pneumatic equipment blades fault just has practical significance.The many non-damage monitoring method of pneumatic equipment blades can be divided into contact and contactless two kinds according to the action mode of signal receiving device and blade.Directly contact by measurement mechanism and blade surface the method measuring blade state and be called that contact is monitored, method has vibration monitoring, acoustic emission, stress monitoring, ultrasound wave etc.; And the monitoring method that measurement mechanism discord blade produces contact is called non-contact measurement, method has thermal imaging, x-ray imaging, digital picture correlation analysis etc.
But, in contact measurement method, certain error is inherently caused in the region of being reacted representated by it by the point that sensor is monitored due to it, and touch sensor is often because itself temperature range and installation difficulty also can cause the difficulty used under actual condition; For existing non-contact measurement method, such as x-ray imaging method its principle the technical merit of present stage can only be done heavier, so its present stage can only in laboratory to pneumatic equipment blades diagnosing malfunction.
In computer vision field, there is scholar to computer vision effects on surface Study of Defects, but mostly stationary object is carried out.Because pneumatic equipment blades surface is in camber structure, and wind energy conversion system exists in the course of the work and becomes slurry and driftage, and causing trouble presents three dimensional change, directly cause camera acquisition to epigraph is difficult to distinguish whether twice image is same image.This just causes, and the video surveillance work for the growth of pneumatic equipment blades fault, development is very complicated and arithmetic accuracy is not high can not meet Production requirement.
Chinese invention patent CN102175449A, disclose a kind of blade fault diagnosing method based on the response of wind energy conversion system strain energy, obtain by the strain energy frequency domain response of cabin sensor setting point fault damage position, the fault degree of injury that wind generator set blade fault shape faulted condition eigenwert accurately can find out wind generator set blade, but for contact method for diagnosing faults, due to by monitoring the object reaching and monitor blade integral, so localization of fault accuracy rate is lower to sensor institute installation position signal.
At present, those skilled in the art are necessary to develop a kind of diagnostic method that accurately can judge blade fault.
Summary of the invention
Object of the present invention is exactly the deficiency in order to overcome existing wind energy conversion system fault diagnosis, provide a kind of pneumatic equipment blades method for diagnosing faults, to solve the very complicated and not high problem that can not meet Production requirement of arithmetic accuracy of video surveillance work for the growth of pneumatic equipment blades fault, development.
In order to solve the problems of the technologies described above, the present invention is solved by following technical proposals:
A kind of pneumatic equipment blades method for diagnosing faults, comprises the steps:
(1) extraction of pneumatic equipment blades primitive:
First, by Boundary extracting algorithm, background rejecting is carried out to pneumatic equipment blades; Then, wind energy conversion system blade surface is coated colour band, by colour band, wind energy conversion system blade integral is divided into N number of subregion, wherein N >=1, any one subregion is called blade primitive.
Then take the method that net region divides, every for pneumatic equipment blades sub regions surface is artificially divided marker dots, and round dot divides according to blade surface radian, divides more sparse, the sub-zone dividing comparatively dense that radian is large in straight part.
Finally, found the center of circle of marker dots by hough-circle transform, by four angle points in the center of circle and region, subregion is divided again, grid is split into subregion, make grid inside be approximately at grade; This subregion is carried out secondary and is divided into picture element, use as fault diagnosis image.
(2) video monitoring:
First utilize the picture pick-up device be fixed on windmill tower frame, timing is carried out sampling to pneumatic equipment blades primitive and is taken pictures, and obtains blade primitive original image.
Then, original image is converted to gray-scale map.
It is as follows that original image converts gray-scale map method to:
First, by original figure through gray proces, become gray-scale map from cromogram, obtain the original image of blade primitive.
Then, carry out blade primitive contours extract by contour extraction method to gray level image, obtain the bianry image of blade primitive, this bianry image Leaf primitive is white background, and remainder is black background.
Again, after Morphological scale-space is carried out to bianry image, obtain the two-value denoising image of image, find region the best part in image to be blade place part, take out the bianry image that namely other parts obtain blade.
Finally, find in original image is the image that namely white part extracts whole blade in corresponding blade bianry image.
(3) Judging fault:
First common wind energy conversion system fault blade is collected, then characteristics of image is extracted to wind energy conversion system fault blade, then fault picture is classified, finally design blade fault kind database, by the algorithm application of blade fault diagnosing in pneumatic equipment blades fault diagnosis, carry out Intelligent Recognition fault, if the catastrophic failure of being determined as, inform and need maintenance; If be judged as trickle fault, inform supervision fault progression and Change of types, if blade cracks growth, then inform maintenance.
Adopt the present invention of technique scheme compared with prior art:
Framing point is utilized to carry out primitive division to pneumatic equipment blades, can effectively position blade surface fault, and, due to the curved surface of pneumatic equipment blades is divided into almost plane region, adopt the feature of two dimensional fault plane picture to replace three-dimension curved surface image, greatly can be reduced at the amount of calculation in wind energy conversion system fault identification and computational accuracy.
Find the fault of monitored blade to reach the object of production monitoring by carrying out analyzing and processing to the image of industrial camera collection, to overcome wind energy conversion system working environment be outdoor and ambient light environment is complicated, long the causing of pneumatic equipment blades can not to photograph whole blade, inevitably introduce background information, deficiency due to the change slurry of the blade simple use image processing method such as cause shooting angle fixing in a photo.The equipment that is characterized in is simple, compact, cheap.
Preferred version of the present invention is as follows:
Further to subregion at least twice division, extract blade primitive, by determining that to the fault diagnosis of blade primitive fault happening part or the growing state to fault exercise supervision.
Carry out shooting to picture pick-up device to control, utilize leaf position output signal as the switching signal of shooting, start picture pick-up device when blade reaches desired location and leaf image is gathered.
The monitored area that Switching Condition for picture pick-up device is required to meet blade occupies the major part of image, and adjust the image pickup scope of picture pick-up device, only make a surveyed area all enter image pickup scope at every turn, jointly complete with at least two picture pick-up devices and the entirety of blade is supervised.
In wind energy conversion system operational process, picture pick-up device gathers leaf image and analyzes, what picture pick-up device collected is at least three blades are successively through being caught on camera the ambient image not having blade taken in the image and picture pick-up device viewfinder range that equipment captures, this picture pick-up device can go out the image of pneumatic equipment blades by automatic distinguishing from different images, avoids the erroneous judgement to pneumatic equipment blades fault.
Fault distinguishing is adopted based on dual-tree complex wavelet image feature extraction.
Image data method of descent based on manifold learning is adopted to fault distinguishing.
Image data method of descent based on improving manifold learning arithmetic is adopted to fault distinguishing.
Accompanying drawing explanation
Fig. 1 is blade fault diagnosing process flow diagram of the present invention.
Fig. 2 is blade fault diagnosing schematic diagram of the present invention.
In figure: 1-wind energy conversion system; 2-pneumatic equipment blades; 3-blade primitive; 4-picture pick-up device; 5-windmill tower frame.
explanation of nouns:
Dual-tree complex wavelet refers to that employing two wavelet tree are carried out analyzing and processing and made algorithm have approximate translation invariance Sum decomposition coefficient correspondence and each opposite sex in direction.
Manifold learning refers to the data of sampling from dimensional Euclidean Space and recovers low dimensional manifold structure, obtains simultaneously and embeds mapping accordingly, to realize yojan, the dimensionality reduction or visual of data.
Embodiment
The present invention is further elaborated for the embodiment provided below in conjunction with Fig. 1 to Fig. 2, but embodiment does not form any restriction to the present invention.
A kind of pneumatic equipment blades method for diagnosing faults, comprises the steps:
(1) extraction of pneumatic equipment blades primitive 3:
First, by Boundary extracting algorithm, background rejecting is carried out to pneumatic equipment blades 2; Then, colour band is coated on pneumatic equipment blades 2 surface, by colour band, wind energy conversion system blade integral is divided into N number of subregion, wherein N >=1, any one subregion is called blade primitive 3.Such as: N gets 100; The value got and the imaging of camera and installation site, leaf blade size and blade surface curvature have relation.
Then take the method that net region divides, every for pneumatic equipment blades 2 sub regions surface is artificially divided marker dots, and round dot divides according to blade surface radian, divides more sparse, the sub-zone dividing comparatively dense that radian is large in straight part.
Finally, found the center of circle of marker dots by hough-circle transform, by four angle points in the center of circle and region, subregion is divided again, grid is split into subregion, make grid inside be approximately at grade; This subregion is carried out secondary and is divided into picture element, use as fault diagnosis image.
(2) video monitoring:
First utilize the picture pick-up device 4 be fixed on windmill tower frame 5, timing is carried out sampling to pneumatic equipment blades primitive 3 and is taken pictures, and obtains blade primitive 3 original image.
Then, original image is converted to gray-scale map.
It is as follows that original image converts gray-scale map method to:
First, by original figure through gray proces, become gray-scale map from cromogram, obtain the original image of blade primitive 3.
Then, carry out blade primitive 3 contours extract by contour extraction method to gray level image, obtain the bianry image of blade primitive 3, this bianry image Leaf primitive 3 is white background, and remainder is black background.
Again, after Morphological scale-space is carried out to bianry image, obtain the two-value denoising image of image, find region the best part in image to be blade place part, take out the bianry image that namely other parts obtain blade.
Finally, find in original image is the image that namely white part extracts whole blade 2 in corresponding blade bianry image.
(3) Judging fault:
First common wind energy conversion system fault blade is collected, then characteristics of image is extracted to wind energy conversion system fault blade, then fault picture is classified, finally design blade fault kind database, by the algorithm application of blade fault diagnosing in pneumatic equipment blades 3 fault diagnosis, carry out Intelligent Recognition fault, if the catastrophic failure of being determined as, inform and need maintenance; If be judged as trickle fault, inform supervision fault progression and Change of types, if blade cracks growth, then inform maintenance.
Further to subregion at least twice division, extract blade primitive 3, by determining that to the fault diagnosis of blade primitive 3 fault happening part or the growing state to fault exercise supervision.
Carry out shooting to picture pick-up device to control, utilize leaf position output signal as the switching signal of shooting, start picture pick-up device 4 pairs of leaf images when blade reaches desired location and gather.
The monitored area that Switching Condition for picture pick-up device 4 is required to meet blade occupies the major part of image, and adjust the image pickup scope of picture pick-up device, only make a surveyed area all enter image pickup scope at every turn, jointly complete with at least two picture pick-up devices 4 and the entirety of blade is supervised.
In wind energy conversion system operational process, picture pick-up device 4 pairs of leaf images gather and analyze, what picture pick-up device collected is three blades are successively through being caught on camera the ambient image not having blade taken in the image and picture pick-up device 4 viewfinder range that equipment 4 captures, this picture pick-up device can go out the image of pneumatic equipment blades by automatic distinguishing from different images, avoids the erroneous judgement to pneumatic equipment blades 2 fault.
Blade fault kind database is devised to fault frequent species, by carrying out image characteristics extraction based on dual-tree complex wavelet, manifold learning and improvement manifold learning three kinds of methods to leaf image.
The present embodiment utilizes framing point to carry out primitive division to pneumatic equipment blades, can effectively position blade surface fault, and, due to the curved surface of pneumatic equipment blades is divided into almost plane region, adopt the feature of two dimensional fault plane picture to replace three-dimension curved surface image, be greatly reduced at the amount of calculation in wind energy conversion system fault identification and computational accuracy.
Those skilled in the art do not depart from essence of the present invention and spirit, kinds of schemes is had to realize the present invention, the foregoing is only the better feasible embodiment of the present invention, not thereby interest field of the present invention is limited to, the equivalent structure change that all utilizations instructions of the present invention and accompanying drawing content are done, is all contained within interest field of the present invention.
Claims (8)
1. pneumatic equipment blades method for diagnosing faults, comprises the steps:
(1) extraction of pneumatic equipment blades primitive:
First, by Boundary extracting algorithm, background rejecting is carried out to pneumatic equipment blades; Then, wind energy conversion system blade surface is coated colour band, by colour band, wind energy conversion system blade integral is divided into N number of subregion, wherein N >=1, any one subregion is called blade primitive;
Then take the method that net region divides, every for pneumatic equipment blades sub regions surface is artificially divided marker dots, and round dot divides according to blade surface radian, divides more sparse, the sub-zone dividing comparatively dense that radian is large in straight part;
Finally, found the center of circle of marker dots by hough-circle transform, by four angle points in the center of circle and region, subregion is divided again, grid is split into subregion, make grid inside be approximately at grade; This subregion is carried out secondary and is divided into picture element, use as fault diagnosis image;
(2) video monitoring:
First utilize the picture pick-up device be fixed on windmill tower frame, timing is carried out sampling to pneumatic equipment blades primitive and is taken pictures, and obtains blade primitive original image;
Then, original image is converted to gray-scale map;
It is as follows that original image converts gray-scale map method to:
First, by original figure through gray proces, become gray-scale map from cromogram, obtain the original image of blade primitive;
Then, carry out blade primitive contours extract by contour extraction method to gray level image, obtain the bianry image of blade primitive, this bianry image Leaf primitive is white background, and remainder is black background;
Again, after Morphological scale-space is carried out to bianry image, obtain the two-value denoising image of image, find region the best part in image to be blade place part, take out the bianry image that namely other parts obtain blade;
Finally, find in original image is the image that namely white part extracts whole blade in corresponding blade bianry image;
(3) Judging fault:
First common wind energy conversion system fault blade is collected, then characteristics of image is extracted to wind energy conversion system fault blade, then fault picture is classified, finally design blade fault kind database, by the algorithm application of blade fault diagnosing in pneumatic equipment blades fault diagnosis, carry out Intelligent Recognition fault, if the catastrophic failure of being determined as, inform and need maintenance; If be judged as trickle fault, inform supervision fault progression and Change of types, if blade cracks growth, then inform maintenance.
2. pneumatic equipment blades method for diagnosing faults according to claim 1, it is characterized in that: further to subregion at least twice division, extract blade primitive, by determining that to the fault diagnosis of blade primitive fault happening part or the growing state to fault exercise supervision.
3. pneumatic equipment blades method for diagnosing faults according to claim 1, it is characterized in that: shooting is carried out to picture pick-up device and controls, utilize leaf position output signal as the switching signal of shooting, start picture pick-up device when blade reaches desired location and leaf image is gathered.
4. the pneumatic equipment blades method for diagnosing faults according to claim 1 or 3, it is characterized in that: the monitored area that the Switching Condition for picture pick-up device is required to meet blade occupies the major part of image, and adjust the image pickup scope of picture pick-up device, only make a surveyed area all enter image pickup scope at every turn, jointly complete with at least two picture pick-up devices and the entirety of blade is supervised.
5. pneumatic equipment blades method for diagnosing faults according to claim 4, it is characterized in that: in wind energy conversion system operational process, picture pick-up device gathers leaf image and analyzes, what picture pick-up device collected is at least three blades are successively through being caught on camera the ambient image not having blade taken in the image and picture pick-up device viewfinder range that equipment captures, this picture pick-up device can go out the image of pneumatic equipment blades by automatic distinguishing from different images, avoids the erroneous judgement to pneumatic equipment blades fault.
6. pneumatic equipment blades method for diagnosing faults according to claim 1, is characterized in that: adopt based on dual-tree complex wavelet image feature extraction fault distinguishing.
7. pneumatic equipment blades method for diagnosing faults according to claim 1, is characterized in that: adopt the image data method of descent based on manifold learning to fault distinguishing.
8. pneumatic equipment blades method for diagnosing faults according to claim 1, is characterized in that: adopt the image data method of descent based on improving manifold learning arithmetic to fault distinguishing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510170405.4A CN104865269A (en) | 2015-04-13 | 2015-04-13 | Wind turbine blade fault diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510170405.4A CN104865269A (en) | 2015-04-13 | 2015-04-13 | Wind turbine blade fault diagnosis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104865269A true CN104865269A (en) | 2015-08-26 |
Family
ID=53911251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510170405.4A Pending CN104865269A (en) | 2015-04-13 | 2015-04-13 | Wind turbine blade fault diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104865269A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105510038A (en) * | 2015-12-31 | 2016-04-20 | 北京金风科创风电设备有限公司 | Wind turbine generator fault monitoring method and device |
| CN105844268A (en) * | 2016-06-13 | 2016-08-10 | 杭州意能电力技术有限公司 | Induced draft fan static blade monitoring method based on videos and induced draft fan static blade monitoring system thereof |
| CN106778723A (en) * | 2016-11-28 | 2017-05-31 | 华中科技大学 | A kind of pneumatic equipment bladess surface image extracting method in complex background environment |
| CN107587983A (en) * | 2017-09-01 | 2018-01-16 | 天津科技大学 | Novel wind motor blade state monitors and fault early warning system |
| JP2018128358A (en) * | 2017-02-09 | 2018-08-16 | 株式会社明和ｅテック | Abnormality monitoring method and abnormality monitoring device |
| CN108459027A (en) * | 2018-03-21 | 2018-08-28 | 华北电力大学 | A kind of blade of wind-driven generator detection method of surface flaw based on image procossing |
| WO2019000818A1 (en) * | 2017-06-26 | 2019-01-03 | 北京金风科创风电设备有限公司 | Method and device for monitoring icing of wind turbine blade |
| CN109404270A (en) * | 2018-12-29 | 2019-03-01 | 湖南主导科技发展有限公司 | A kind of remote water pump control system and method |
| CN110274917A (en) * | 2019-06-17 | 2019-09-24 | 华电电力科学研究院有限公司 | A kind of wind power generation unit blade surface defect access device and camera lens layout method |
| WO2020108016A1 (en) * | 2018-11-30 | 2020-06-04 | 北京金风科创风电设备有限公司 | Tower clearance monitoring system and method therefor |
| CN115791804A (en) * | 2022-12-20 | 2023-03-14 | 中国航发贵州黎阳航空动力有限公司 | Stripe defect detection method for compressor blade |
| CN115861266A (en) * | 2022-12-20 | 2023-03-28 | 中国航发贵州黎阳航空动力有限公司 | Intelligent detection method for compressor blades |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10065314A1 (en) * | 2000-12-30 | 2002-07-18 | Igus Ingenieurgemeinschaft Umw | Method for condition monitoring of wind turbine rotor blades in which sound and vibration sensors are used to generate signals that can be compared with an existing database of signals so that rapid damage assessment can be made |
| CN102944416A (en) * | 2012-12-06 | 2013-02-27 | 南京匹瑞电气科技有限公司 | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades |
| CN103982378A (en) * | 2014-04-25 | 2014-08-13 | 广东电网公司电力科学研究院 | Method for diagnosing surface icing faults of wind power generator blade of power system based on machine visual images |
| CN103984956A (en) * | 2014-04-25 | 2014-08-13 | 广东电网公司电力科学研究院 | Method for diagnosing surface pitting fault of blade of wind turbine generator of electric power system based on machine vision image |
| CN103984952A (en) * | 2014-04-18 | 2014-08-13 | 广东电网公司电力科学研究院 | Method for diagnosing surface crack fault of blade of wind turbine generator of electric power system based on machine vision image |
-
2015
- 2015-04-13 CN CN201510170405.4A patent/CN104865269A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10065314A1 (en) * | 2000-12-30 | 2002-07-18 | Igus Ingenieurgemeinschaft Umw | Method for condition monitoring of wind turbine rotor blades in which sound and vibration sensors are used to generate signals that can be compared with an existing database of signals so that rapid damage assessment can be made |
| CN102944416A (en) * | 2012-12-06 | 2013-02-27 | 南京匹瑞电气科技有限公司 | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades |
| CN103984952A (en) * | 2014-04-18 | 2014-08-13 | 广东电网公司电力科学研究院 | Method for diagnosing surface crack fault of blade of wind turbine generator of electric power system based on machine vision image |
| CN103982378A (en) * | 2014-04-25 | 2014-08-13 | 广东电网公司电力科学研究院 | Method for diagnosing surface icing faults of wind power generator blade of power system based on machine visual images |
| CN103984956A (en) * | 2014-04-25 | 2014-08-13 | 广东电网公司电力科学研究院 | Method for diagnosing surface pitting fault of blade of wind turbine generator of electric power system based on machine vision image |
Non-Patent Citations (1)
| Title |
|---|
| 张磊: "基于计算机视觉的风力机叶片缺陷诊断研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10760551B2 (en) | 2015-12-31 | 2020-09-01 | Beijing Goldwind Science & Creation Windpower Equipment Co., Ltd. | Computer storage medium, computer program product, method for monitoring fault of wind power generator set, and device |
| CN105510038A (en) * | 2015-12-31 | 2016-04-20 | 北京金风科创风电设备有限公司 | Wind turbine generator fault monitoring method and device |
| CN105510038B (en) * | 2015-12-31 | 2018-07-27 | 北京金风科创风电设备有限公司 | Wind turbine generator fault monitoring method and device |
| CN105844268B (en) * | 2016-06-13 | 2019-07-26 | 杭州意能电力技术有限公司 | A kind of air-introduced machine stator blade monitoring method and system based on video |
| CN105844268A (en) * | 2016-06-13 | 2016-08-10 | 杭州意能电力技术有限公司 | Induced draft fan static blade monitoring method based on videos and induced draft fan static blade monitoring system thereof |
| CN106778723A (en) * | 2016-11-28 | 2017-05-31 | 华中科技大学 | A kind of pneumatic equipment bladess surface image extracting method in complex background environment |
| JP2018128358A (en) * | 2017-02-09 | 2018-08-16 | 株式会社明和ｅテック | Abnormality monitoring method and abnormality monitoring device |
| WO2019000818A1 (en) * | 2017-06-26 | 2019-01-03 | 北京金风科创风电设备有限公司 | Method and device for monitoring icing of wind turbine blade |
| US11286913B2 (en) | 2017-06-26 | 2022-03-29 | Beijing Goldwind Science & Creation Windpower Equipment Co., Ltd. | Method and apparatus for monitoring formation of ice on wind turbine blade |
| CN107587983A (en) * | 2017-09-01 | 2018-01-16 | 天津科技大学 | Novel wind motor blade state monitors and fault early warning system |
| CN108459027A (en) * | 2018-03-21 | 2018-08-28 | 华北电力大学 | A kind of blade of wind-driven generator detection method of surface flaw based on image procossing |
| WO2020108016A1 (en) * | 2018-11-30 | 2020-06-04 | 北京金风科创风电设备有限公司 | Tower clearance monitoring system and method therefor |
| US11835029B2 (en) | 2018-11-30 | 2023-12-05 | Beijing Goldwind Science & Creation Windpower Equipment Co., Ltd. | Tower clearance monitoring system and method therefor |
| CN109404270A (en) * | 2018-12-29 | 2019-03-01 | 湖南主导科技发展有限公司 | A kind of remote water pump control system and method |
| CN110274917B (en) * | 2019-06-17 | 2023-12-05 | 华电电力科学研究院有限公司 | Wind turbine generator blade surface defect taking device and lens layout method |
| CN110274917A (en) * | 2019-06-17 | 2019-09-24 | 华电电力科学研究院有限公司 | A kind of wind power generation unit blade surface defect access device and camera lens layout method |
| CN115791804A (en) * | 2022-12-20 | 2023-03-14 | 中国航发贵州黎阳航空动力有限公司 | Stripe defect detection method for compressor blade |
| CN115861266A (en) * | 2022-12-20 | 2023-03-28 | 中国航发贵州黎阳航空动力有限公司 | Intelligent detection method for compressor blades |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104865269A (en) | Wind turbine blade fault diagnosis method | |
| CN109117858B (en) | Method and device for monitoring icing of wind driven generator blade | |
| WO2022077605A1 (en) | Wind turbine blade image-based damage detection and localization method | |
| CN112380952B (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| CN103982378B (en) | Method for diagnosing surface icing faults of wind power generator blade of power system based on machine visual images | |
| CN111696075A (en) | Intelligent fan blade defect detection method based on double-spectrum image | |
| CN103984952B (en) | The method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure | |
| CN111598098B (en) | Water gauge water line detection and effectiveness identification method based on full convolution neural network | |
| CN107833211B (en) | Infrared image-based zero value insulator automatic detection method and device | |
| Xiaoxun et al. | Research on crack detection method of wind turbine blade based on a deep learning method | |
| CN111852792A (en) | Fan blade defect self-diagnosis positioning method based on machine vision | |
| CN113962973A (en) | Power transmission line unmanned aerial vehicle intelligent inspection system and method based on satellite technology | |
| CN112465776B (en) | Crack intelligent detection method based on wind turbine surface blurred image | |
| CN103984956A (en) | Method for diagnosing surface pitting fault of blade of wind turbine generator of electric power system based on machine vision image | |
| CN116539001A (en) | Marine wind power tower verticality detection method and system based on unmanned aerial vehicle | |
| Chen et al. | Attention mechanism-based CNN for surface damage detection of wind turbine blades | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN110781758A (en) | Dynamic video monitoring method and device for abnormal pantograph structure | |
| Lestary et al. | Deep Learning Implementation for Snail Trails Detection in Photovoltaic Module | |
| Wang | Rapid visual detection method of highway pavement sag based on improved Yolov7-tiny | |
| Yuan et al. | Automatic detection of linear mesoscale convective systems | |
| Özer et al. | An approach based on deep learning methods to detect the condition of solar panels in solar power plants | |
| Ren et al. | Research on the Rapid Check and Identification of Insulator Faults in Transmission Lines Based on a Modified Faster RCNN Network | |
| CN117237306A (en) | System and method for expanding defect set and quantifying defects of large wind turbine blade | |
| CN116524347A (en) | Space-time texture image angle identification method based on semi-supervised machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150826 |