CN105651780A - Method, apparatus and system for detecting state of blower blade through unmanned plane - Google Patents
Method, apparatus and system for detecting state of blower blade through unmanned plane Download PDFInfo
- Publication number
- CN105651780A CN105651780A CN201511000214.XA CN201511000214A CN105651780A CN 105651780 A CN105651780 A CN 105651780A CN 201511000214 A CN201511000214 A CN 201511000214A CN 105651780 A CN105651780 A CN 105651780A
- Authority
- CN
- China
- Prior art keywords
- image
- group
- fan blade
- man
- machine
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a method, an apparatus and a system for detecting the state of a blower blade through an unmanned plane. The method comprises the following steps: receiving the first image group of the blower blade, shot in the process of flight along a preset course, from the unmanned plane; analyzing the first image group to obtain the spatial coordinate when the first image group is shot; generating a control signal for starting the unmanned plane to shoot again according to the spatial coordinate, and sending the control signal to the unmanned plane; receiving the second image group of the blower blade from the unmanned plane; and analyzing the second image group to generate the analysis report of the state data of the blower blade. The method, the apparatus and the system for detecting the state of the blower blade through the unmanned plane realize blower blade state detection through using the unmanned plane, improve the detection accuracy and efficiency, and save the operation service cost of the unmanned plane.
Description
Technical field
The present invention relates to technical field of wind power, particularly relate to a kind of method by unmanned machine testing fan blade state, Apparatus and system.
Background technology
The blade of aerogenerator (hereinafter referred to as blower fan) is the key part of mechanical energy by wind energy transformation, in the long-time running process of aerogenerator, the surface of blade can present recessed piece of various state such as blade, blade falls paint, blade cut, blade freeze, blade cracks and blade pollution etc. If these states find not in time and carry out maintenance, the situations such as accelerated deterioration will be there will be, affect the work-ing life of blade.
Current blade state detection method mainly contains following two kinds of modes: one adopts the methods such as spider-man, hanging basket and binoculars to carry out; Another kind adopts without man-machine installation video acquisition device monitor in real time and grasp wind-power blade blade state under various conditions and wind-power blade is carried out examination and maintenance.
But, above-mentioned two kinds of modes have following weak point: first, the danger of first kind of way is higher, and Detection results is poor, it is difficult to meet the demand quick and precisely checking blade; Secondly, in the 2nd kind of mode, without man-machine carry out fan blade check time, without man-machine only in the flight course of default course line to the monitoring of fan blade situation, the fan blade view data precision of collection is not high enough, and causes the waste without man-machine running cost.
Summary of the invention
It is an object of the present invention to provide a kind of method by unmanned machine testing fan blade state, Apparatus and system, carry out fan blade state-detection to realize utilizing accurately and efficiently without man-machine, it is to increase the degree of safety of testing process and reliability.
According to an aspect of the present invention, it is provided that a kind of method by unmanned machine testing fan blade state, comprising: from first group of image without its fan blade taken along the flight of default course line of man-machine reception;Described first group of image is analyzed, obtains volume coordinate during the described first group of image of shooting; Generate for starting without the man-machine control signal again carrying out taking according to described volume coordinate, and described control signal is sent to described without man-machine; From described the 2nd group of image without its fan blade again taken of man-machine reception; Described 2nd group of image is analyzed, generates the analysis report of fan blade state data.
According to a further aspect in the invention, it is provided that a kind of device by unmanned machine testing fan blade state, comprising: the first image receiver module, for from first group of image without its fan blade taken along the flight of default course line of man-machine reception; First image analysis module, for being analyzed by described first group of image, obtains volume coordinate during the described first group of image of shooting; Signal generates and sending module, for generating for starting without the man-machine control signal again carrying out taking according to described volume coordinate, and described control signal is sent to described without man-machine; 2nd image receiver module, for from described the 2nd group of image without its fan blade again taken of man-machine reception; 2nd image analysis module, for being analyzed by described 2nd group of image, generates the analysis report of fan blade state data.
According to a further aspect in the invention, a kind of system by unmanned machine testing fan blade state is provided, comprise without man-machine and as described in above-described embodiment the device by unmanned machine testing fan blade state, described communicate to connect without the man-machine and described device by unmanned machine testing fan blade state.
The method by unmanned machine testing fan blade state that the embodiment of the present invention provides, Apparatus and system, by the analysis to the first group of image presetting course line flight shooting without man-machine edge, obtain the positional information of shooting first group of image, and then generate the control signal of control without man-machine the 2nd group of image again taking high definition, based on the analysis of the 2nd group of image, generate the analysis report of fan blade state data, achieve to utilize and carry out fan blade state-detection without man-machine, improve tolerance range and the efficiency of detection, make the process safety of detection, reliably, and save the cost without the dimension service of man-machine fortune.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the method by unmanned machine testing fan blade state of the embodiment of the present invention one;
Fig. 2 is the illustrative diagram of the application scene of the method by unmanned machine testing fan blade state of the embodiment of the present invention one;
Fig. 3 is the structural representation of the device by unmanned machine testing fan blade state of the embodiment of the present invention two;
Fig. 4 is another structural representation of the device by unmanned machine testing fan blade state of the embodiment of the present invention two.
Embodiment
Below in conjunction with accompanying drawing, the exemplary embodiment of the present invention is described in detail by method, the Apparatus and system of unmanned machine testing fan blade state.
Embodiment one
Fig. 1 is the method flow diagram of the embodiment of the method by unmanned machine testing fan blade state provided by the invention, as shown in Figure 1, is comprised by the method for unmanned machine testing fan blade state:
Step 110: from first group of image without its fan blade taken along the flight of default course line of man-machine reception.
In concrete implementation, when planning is without man-machine default course line, default course line can being resolved into the point in a lot of spaces, the point in each space has respective volume coordinate. Here, volume coordinate can comprise, but is not limited to, longitude, latitude and elevation. Fly in wind-force generating field according to pre-set course line without man-machine, first group of image of the fan blade in shooting wind-force generating field, thus, can real-time reception without the image of the fan blade of the man-machine shooting sent back, these images can the form of photo and/or video flowing store, in order to carrying out follow-up process.
Step 120: analyzed by first group of image, obtains volume coordinate during shooting first group of image.
Specifically, in real time first group of image of fan blade is identified by image recognition technology, when assuming that the blade identified on a certain two field picture finds suspicious state region, so, just can record this image of shooting without man-machine locus, namely without the man-machine residing data comprising the volume coordinates such as longitude, latitude, elevation. In actual applications, the object that the first group of image obtained is analyzed by this step is mainly in order to confirm whether current shooting region exists the target of suspicious state (as falling paint, cut etc.), if any the collection then carrying out the 2nd group of image (more clearly image), for post-processed. As there is no doubtful target, then carry out the shooting of residue region and check.
Step 130: generate for starting without the man-machine control signal again carrying out taking according to volume coordinate, and control signal is sent to without man-machine.
After the process of above-mentioned steps, without man-machine residing locus during owing to obtaining the fan blade image of shooting containing suspicious points, and then can generate without man-machine control signal according to the volume coordinate obtained, that is, send control signal to without man-machine, control its flight and again take to the locus specified.
According to exemplary embodiments of the present invention, step 130 can comprise: according to volume coordinate when photographing first group of image, it is determined that again carries out the volume coordinate taken; Generate the control signal of volume coordinate comprising and again carrying out taking.
In concrete implementation, can calculate according to the volume coordinate photographing blade state, obtain the volume coordinate nearest with suspicious state region, and then generate control unmanned plane during flying to the locus corresponding apart from the volume coordinate that suspicious state region is nearest, the control signal again taken, so that it is as more clear in image picking-up apparatus shooting at close range such as cameras, high-resolution fan blade image, the volume coordinate of the best shooting angle of all right computed range fan blade, generate the locus that the volume coordinate of the extremely best shooting angle of control unmanned plane during flying is corresponding, the control signal again taken. understandably, be conducive to the locus taking high-quality fan blade image to be all applicable to the present invention, it be not limited to above-mentioned two kinds of modes.
Step 140: from the 2nd group of image without its fan blade again taken of man-machine reception.
Step 150: analyzed by the 2nd group of image, generates the analysis report of fan blade state data.
Here, fan blade state can comprise, but is not limited to, following at least one: recessed piece, fall paint, cut, crackle, freeze and pollute. According to exemplary embodiments of the present invention, step 150 can comprise: the 2nd image is carried out pattern recognition, obtains Status Type and the respective level of fan blade; Add up the quantity of each Status Type, and according to the quantity of each Status Type and Status Type and corresponding grade, generate the analysis report of fan blade state data.
Specifically, be different from first group of image received after real-time process, the 2nd group of image after receipt, in order to carry out discriminating and the statistics of the detailed situation of fan blade state. The analysis process of the 2nd group of image is comprised Image semantic classification, blade profile detection, blade injury detection, feature extraction and tagsort. Object is the discriminating being undertaken different states classifying with corresponding grade, generates the analysis report of fan blade state data. It should be noted that, state-detection data can comprise, but is not limited to, and there is the blade quantity of different states, there is the position of the blade of the state such as cut, crackle, the state classification of blade and characterize the grade of the degree of residing state in concrete classification.
Further, above-mentioned 2nd group of image being carried out pattern recognition, the Status Type and the corresponding process that obtain fan blade can comprise: the 2nd group of image is carried out following at least one Image semantic classification: the normalization method of image size, the normalization method of image color and image filtering;Pretreated 2nd group of image is carried out blade profile detection, generates damaged blade image; Damaged blade image is carried out blade injury state-detection, generates scar state region image; Scar state region image is carried out feature extraction, generates the characteristic of scar state region image; The characteristic of scar state region image is inputed to the sorter through training, obtains the faulted condition type of damaged blade and corresponding impairment scale.
For such as cut, crackle etc., cut, crackle are for pollution, belong to the damage with comparatively serious scar, specifically, blade profile detection is split from the background of whole image by the blade-section in photo, to reduce the scope searched for by scar, its main method has brightness step method, color gradient method and texture gradient method. Blade injury detection is similar with contour detecting, and now leaf area is background, is split in scar region from leaf area. It is that relation between the attribute to image pixel and pixel is analyzed that feature is extracted, it is possible to the pixel data of image being converted into a series of numerical characteristics or describes feature, these features can be used for describing image content. Sorter is for classifying scar area image according to different characteristics, and conventional sorter has neural network, SVMs, decision tree, Bayes, K-neighbour etc. Need in advance to utilize a large amount of sampled datas to be trained by sorter based on machine learning techniques, thus, the characteristic of scar area image is inputed to the sorter through training, so that it may obtain the type of impairment of damaged blade and corresponding impairment scale.
Below in conjunction with concrete process example, carry out further the embody rule of the illustratively embodiment of the present invention more intuitively.
Fig. 2 is the illustrative diagram of the application scene of the method by unmanned machine testing fan blade state of the embodiment of the present invention one, with reference to Fig. 2, without man-machine 210 and ground control cabinet 220.
In actual applications, the many rotor wing unmanned aerial vehicles comprising electrical source of power can be adopted without man-machine 210, the Photoelectric Detection equipment such as Signal transmissions radio station, image transmission radio station, visible ray camera such as it carries flight control system, fly control. Offline mode without man-machine 210 mainly contains following two kinds, and one is cruise mode, namely without man-machine 210 along the course line automatic cruising planned in advance. Another kind is hover mode, namely also can keep fixed point hovering under the such as Special Circumstances such as image taking, strong wind atmosphere without man-machine 210.
Ground control cabinet 220 is the control center without man-machine 210, ground control cabinet 220 is kept by Signal transmissions radio station such as flight controlling and without the communication between the flight control system of man-machine 210, by ground control cabinet 220 to sending flight controlling signal without man-machine 210, control the attitude without man-machine 210, lifting, flight etc. all around. The method by unmanned machine testing fan blade state described in the embodiment of the present invention just can realize in ground control cabinet 220.
To detect as cut, crackle etc. represent that the state of damage is described in detail, specifically, fly on default course line without man-machine 210 and take the image of fan blade, and in real time the fan blade of shooting is transferred to ground control cabinet 220, by ground control cabinet 220, the image of this fan blade is processed, if when discovery image exists suspicious fan blade damage field, without the locus residing for man-machine 210 and volume coordinate when recording this image taking.Now, send control signal to without man-machine 210, no longer fly according to the default course line in cruise mode to control it, but flight is to the locus specified, this locus specified can be the former locus that the image of damage field of shooting containing fan blade is corresponding, or the locus that the damage field of the distance fan blade calculated is nearest, then or the locus with best shooting angle that calculates.
After arriving the locus specified, hover mode is changed into by cruise mode, the shooting of high-definition image is carried out in the air without man-machine 210 hoverings, without man-machine 210, the image again taken is back to ground control cabinet 220, the image again taken is analyzed by ground control cabinet 220, and carries out the preservation of degree of impairment statistics and statistics. Mainly will there is the blade quantity of damage, the position of blade that there is damage, the statistics of degree of impairment, and divide impairment scale (as crackle be heavy damage, fall paint for generally damaging, surface contamination be slight damage), generate damage check report according to statistics, and store.
Additionally, it is contemplated that when not moving without the man-machine locus hovering specifying, and carry out shooting by control camera zoom and obtain higher-quality image. It is also conceivable to be integrated into get on without man-machine by above-mentioned image recognition processes, thus the requirement to image transmission radio station speed and performance can be reduced.
The method by unmanned machine testing fan blade state that the embodiment of the present invention provides, by the analysis to the first group of image presetting course line flight shooting without man-machine edge, obtain the positional information of shooting first group of image, and then generate the control signal of control without man-machine the 2nd group of image again taking high definition, based on the analysis of the 2nd group of image, generate the analysis report of fan blade state data, achieve to utilize and carry out fan blade state-detection without man-machine, improve tolerance range and the efficiency of detection, make the process safety of detection, reliably, and save the cost without the dimension service of man-machine fortune. in addition, by being integrated with image recognition technology and UAV Flight Control technology two aspect advantage so that the efficiency without man-machine fan blade state-detection operation is greatly improved.
Embodiment two
Fig. 3 is the structural representation of the device by unmanned machine testing fan blade state of the embodiment of the present invention two, can be used for performing the method steps of embodiment as shown in Figure 1.
With reference to Fig. 3, the first image receiver module 310, first image analysis module 320, signal generation and sending module 330, the 2nd image receiver module 340 and the 2nd image analysis module 350 should be comprised by the device of unmanned machine testing fan blade state.
First image receiver module 310 is for from first group of image without its fan blade taken along the flight of default course line of man-machine reception.
First image analysis module 320, for being analyzed by first group of image, obtains volume coordinate during shooting first group of image.
Signal generation and sending module 330 are for generating for starting without the man-machine control signal again carrying out taking according to volume coordinate, and are sent to control signal without man-machine.
2nd image receiver module 340 is for from the 2nd group of image without its fan blade again taken of man-machine reception.
2nd image analysis module 350, for being analyzed by the 2nd group of image, generates the analysis report of fan blade state data.
The device by unmanned machine testing fan blade state that the embodiment of the present invention provides, by the analysis to the first group of image presetting course line flight shooting without man-machine edge, obtain the positional information of shooting first group of image, and then generate the control signal of control without man-machine the 2nd group of image again taking high definition, based on the analysis of the 2nd group of image, generate the analysis report of fan blade state data, achieve to utilize and carry out fan blade state-detection without man-machine, improve tolerance range and the efficiency of detection, make the process safety of detection, reliably, and save the cost without the dimension service of man-machine fortune.
On the basis of above-described embodiment, Fig. 4 is another structural representation of the device by unmanned machine testing fan blade state of the embodiment of the present invention two.
With reference to Fig. 4, specifically, signal generation and sending module 330 can comprise:
Volume coordinate determining unit 3301 is for according to volume coordinate when photographing first group of image, it is determined that again carry out the volume coordinate taken.
Control signal generates the control signal of volume coordinate that unit 3302 comprises and again carries out taking for generating.
Here, volume coordinate can comprise, but is not limited to, longitude, latitude and elevation.
It should be noted that, fan blade state can comprise, but is not limited to, following at least one: recessed piece, fall paint, cut, crackle, freeze and pollute.
Further, the 2nd image analysis module 350 can comprise:
Image identification unit 3501, for described 2nd image is carried out pattern recognition, obtains Status Type and the respective level of fan blade.
Report generation unit 3502 is for adding up the quantity of each Status Type, and according to the quantity of each Status Type and Status Type and corresponding grade, generates the analysis report of fan blade state data.
Further, image identification unit 3501 can specifically for carrying out following at least one Image semantic classification to the 2nd group of image: the normalization method of image size, the normalization method of image color and image filtering; Pretreated 2nd group of image is carried out blade profile detection, generates leaf image; Leaf image is carried out blade state detection, generates state region image; State region image is carried out feature extraction, generates the characteristic of state region image; The characteristic of state region image is inputed to the sorter through training, obtains the Status Type of blade and corresponding grade.
Compared with prior art, the embodiment of the present invention also has following technique effect:
On the one hand, the present invention carries out real-time status identifying processing by image automatic identification merit by without the man-machine image photographed, and then can generate the analysis report of fan blade state data.
On the other hand, by being integrated with image recognition technology and UAV Flight Control technology two aspect advantage, especially manipulate and carry out arbitrarily approaching of point and observe without man-machine and take pictures, it is to increase accuracy rate, and the efficiency without man-machine fan blade state-detection operation is greatly improved.
Embodiment three
The embodiment of the present invention provides a kind of system by unmanned machine testing fan blade state, comprise without the device by unmanned machine testing fan blade state described in man-machine and previous embodiment two, communicate to connect with by the device of unmanned machine testing fan blade state without man-machine.
The system by unmanned machine testing fan blade state that the embodiment of the present invention provides, by the analysis to the first group of image presetting course line flight shooting without man-machine edge, obtain the positional information of shooting first group of image, and then control is without man-machine the 2nd group of image again taking high definition, achieve to utilize and carry out fan blade state-detection without man-machine, improve tolerance range and the efficiency of detection so that the process safety of detection, reliable, and save the cost without the dimension service of man-machine fortune.
The above; it is only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any it is familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (13)
1. the method by unmanned machine testing fan blade state, it is characterised in that:
From first group of image without its fan blade taken along the flight of default course line of man-machine reception;
Described first group of image is analyzed, obtains volume coordinate during the described first group of image of shooting;
Generate for starting without the man-machine control signal again carrying out taking according to described volume coordinate, and described control signal is sent to described without man-machine;
From described the 2nd group of image without its fan blade again taken of man-machine reception;
Described 2nd group of image is analyzed, generates the analysis report of fan blade state data.
2. method according to claim 1, it is characterised in that: described generation according to described volume coordinate comprises for starting the process without the man-machine control signal again carrying out taking:
According to volume coordinate during described shooting first group of image, it is determined that again carry out the volume coordinate taken;
Generate the control signal of volume coordinate comprising and again carrying out taking.
3. method according to claim 1, it is characterised in that: described fan blade state comprises following at least one: recessed piece, fall paint, cut, crackle, freeze and pollute.
4. method according to claim 3, it is characterised in that: described being analyzed by described 2nd group of image, the process of the analysis report generating fan blade state data comprises:
Described 2nd group of image is carried out pattern recognition, obtains Status Type and the respective level of fan blade;
Add up the quantity of each Status Type, and according to the quantity of described each Status Type and described Status Type and corresponding grade, generate the analysis report of fan blade state data.
5. method according to claim 4, it is characterised in that: described described 2nd group of image being carried out pattern recognition, the process of the Status Type and corresponding grade that obtain fan blade comprises:
Described 2nd group of image is carried out following at least one Image semantic classification: the normalization method of image size, the normalization method of image color and image filtering;
Pretreated 2nd group of image is carried out blade profile detection, generates leaf image;
Described leaf image is carried out blade state detection, generates state region image;
Described state region image is carried out feature extraction, generates the characteristic of state region image;
The characteristic of described state region image is inputed to the sorter through training, obtains the Status Type of blade and corresponding grade.
6. method according to any one of Claims 1 to 5, it is characterised in that: described volume coordinate comprises longitude, latitude and elevation.
7. the device by unmanned machine testing fan blade state, it is characterised in that:
First image receiver module, for from first group of image without its fan blade taken along the flight of default course line of man-machine reception;
First image analysis module, for being analyzed by described first group of image, obtains volume coordinate during the described first group of image of shooting;
Signal generates and sending module, for generating for starting without the man-machine control signal again carrying out taking according to described volume coordinate, and described control signal is sent to described without man-machine;
2nd image receiver module, for from described the 2nd group of image without its fan blade again taken of man-machine reception;
2nd image analysis module, for being analyzed by described 2nd group of image, generates the analysis report of fan blade state data.
8. device according to claim 7, it is characterised in that: described signal generates and sending module comprises:
Volume coordinate determining unit, for according to volume coordinate during described shooting first group of image, it is determined that again carry out the volume coordinate taken;
Control signal generates unit, for generating the control signal of volume coordinate comprising and again carrying out taking.
9. device according to claim 7, it is characterised in that: described fan blade state comprises following at least one: recessed piece, fall paint, cut, crackle, freeze and pollute.
10. device according to claim 9, it is characterised in that: described 2nd group of image analysis module comprises:
Image identification unit, for described 2nd group of image is carried out pattern recognition, obtains Status Type and the respective level of fan blade;
Report generation unit, for adding up the quantity of each Status Type, and according to the quantity of described each Status Type and described Status Type and corresponding grade, generates the analysis report of fan blade state data.
11. devices according to claim 10, it is characterised in that: described image identification unit is used for:
Described 2nd group of image is carried out following at least one Image semantic classification: the normalization method of image size, the normalization method of image color and image filtering;
Pretreated 2nd group of image is carried out blade profile detection, generates leaf image;
Described leaf image is carried out blade state detection, generates state region image;
Described state region image is carried out feature extraction, generates the characteristic of state region image;
The characteristic of described state region image is inputed to the sorter through training, obtains the Status Type of blade and corresponding grade.
12. devices according to any one of claim 7��11, it is characterised in that: described volume coordinate comprises longitude, latitude and elevation.
13. 1 kinds of systems by unmanned machine testing fan blade state, it is characterized in that, comprise without man-machine and according to the arbitrary item of claim 7��12 the device by unmanned machine testing fan blade state, described communicate to connect without the man-machine and described device by unmanned machine testing fan blade state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511000214.XA CN105651780A (en) | 2015-12-28 | 2015-12-28 | Method, apparatus and system for detecting state of blower blade through unmanned plane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511000214.XA CN105651780A (en) | 2015-12-28 | 2015-12-28 | Method, apparatus and system for detecting state of blower blade through unmanned plane |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105651780A true CN105651780A (en) | 2016-06-08 |
Family
ID=56478032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511000214.XA Pending CN105651780A (en) | 2015-12-28 | 2015-12-28 | Method, apparatus and system for detecting state of blower blade through unmanned plane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105651780A (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106370602A (en) * | 2016-08-31 | 2017-02-01 | 纳路易爱姆斯株式会社 | Large-sized structure ultrasonic examination method and system using unmanned aerial vehicles |
| CN106762451A (en) * | 2016-12-05 | 2017-05-31 | 北京金风科创风电设备有限公司 | Fan blade damage detection method, device and system based on unmanned aerial vehicle |
| CN107656537A (en) * | 2016-07-25 | 2018-02-02 | 新疆金风科技股份有限公司 | Unmanned plane route planning method and device, fan blade inspection method and system based on unmanned plane |
| CN108073180A (en) * | 2016-11-08 | 2018-05-25 | 北京金风科创风电设备有限公司 | Control method, the device and system of unmanned plane |
| CN108319290A (en) * | 2017-01-16 | 2018-07-24 | 财团法人金属工业研究发展中心 | Utilize the method on unmanned plane shooting wind turbine blade face, the computer program product and medium capable of reading record of internally stored program |
| CN108733079A (en) * | 2018-06-19 | 2018-11-02 | 上海扩博智能技术有限公司 | Automatic detecting flight path is carried out to wind turbine by unmanned plane and determines method and system |
| CN108869196A (en) * | 2018-06-27 | 2018-11-23 | 上海扩博智能技术有限公司 | By unmanned plane to base region detection method on rear side of blower and system |
| CN108894933A (en) * | 2018-06-27 | 2018-11-27 | 上海扩博智能技术有限公司 | With losing method for catching again and system when by unmanned plane to blower blade tip tracing detection |
| CN108915959A (en) * | 2018-06-27 | 2018-11-30 | 上海扩博智能技术有限公司 | By unmanned plane to blower tip region detour detection method and system |
| CN109131895A (en) * | 2018-07-27 | 2019-01-04 | 上海扩博智能技术有限公司 | Unmanned plane carry device, unmanned plane and the method for detection are automatically tracked for blade |
| CN109470712A (en) * | 2018-12-23 | 2019-03-15 | 北京汉文景科技有限公司 | A kind of wind electricity blade detection system |
| CN109632807A (en) * | 2018-11-28 | 2019-04-16 | 陕西高速公路工程试验检测有限公司 | A kind of portable detection method, apparatus and system |
| CN110145989A (en) * | 2019-06-11 | 2019-08-20 | 广州珠江黄埔大桥建设有限公司 | Distress in concrete detection device and detection method based on unmanned plane |
| CN110471447A (en) * | 2019-08-27 | 2019-11-19 | 无锡风电设计研究院有限公司 | The method for inspecting and system of wind energy conversion system |
| WO2019227438A1 (en) * | 2018-05-31 | 2019-12-05 | 深圳市大疆创新科技有限公司 | Image processing method and device, aircraft, system, and storage medium |
| CN110554704A (en) * | 2019-08-15 | 2019-12-10 | 成都优艾维智能科技有限责任公司 | unmanned aerial vehicle-based fan blade autonomous inspection method |
| CN111289533A (en) * | 2020-02-25 | 2020-06-16 | 国电电力内蒙古新能源开发有限公司 | Fan blade inspection method and device, unmanned aerial vehicle and storage medium |
| CN111461210A (en) * | 2020-03-31 | 2020-07-28 | 天津智惠未来科技有限责任公司 | Unmanned aerial vehicle-based wind power inspection blade defect grade determination method |
| CN111562220A (en) * | 2020-06-02 | 2020-08-21 | 吉林大学 | Rapid and intelligent detection method for bridge diseases |
| CN111595859A (en) * | 2020-05-22 | 2020-08-28 | 三峡大学 | Bridge and culvert damage detection method and damage detection and management system |
| CN111746790A (en) * | 2020-07-21 | 2020-10-09 | 哈尔滨理工大学 | Accurate detection system of fan blade surface damage based on ground shooting image |
| CN111830845A (en) * | 2020-04-30 | 2020-10-27 | 航天图景（北京）科技有限公司 | Automatic inspection simulation system and method for fan blade of unmanned aerial vehicle |
| CN112062062A (en) * | 2020-09-17 | 2020-12-11 | 黄玲玲 | High-altitude operation system of wind driven generator blade and control method thereof |
| CN113406091A (en) * | 2021-06-09 | 2021-09-17 | 东方电气集团科学技术研究院有限公司 | Unmanned aerial vehicle system for detecting fan blade and control method |
| WO2021198967A1 (en) * | 2020-04-02 | 2021-10-07 | Grace And Kowloon Holdings Limited | Tree image data acquisition |
| CN113586360A (en) * | 2021-05-25 | 2021-11-02 | 深圳创动科技有限公司 | Fan detection method, detection device, detection system and readable storage medium |
| CN113758438A (en) * | 2021-07-08 | 2021-12-07 | 重庆市勘测院 | Special building oblique aerial photography and three-dimensional reconstruction method |
| CN114056567A (en) * | 2021-11-22 | 2022-02-18 | 西安热工研究院有限公司 | Wind power blade deicing system and method based on unmanned aerial vehicle cluster |
| CN114439702A (en) * | 2022-01-28 | 2022-05-06 | 华能盐城大丰新能源发电有限责任公司 | Blade state monitoring method and device of wind driven generator |
| CN113406091B (en) * | 2021-06-09 | 2024-07-26 | 东方电气集团科学技术研究院有限公司 | Unmanned aerial vehicle system for fan blade detection and control method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011064565A2 (en) * | 2009-11-25 | 2011-06-03 | Cyberhawk Innovations Limited | Unmanned aerial vehicle |
| CN102297098A (en) * | 2010-06-25 | 2011-12-28 | 通用电气公司 | System and method for wind turbine inspection |
| CN102628425A (en) * | 2011-02-04 | 2012-08-08 | 通用电气公司 | Method and system for wind turbine inspection |
| CN102798635A (en) * | 2011-05-25 | 2012-11-28 | 西门子公司 | Method to inspect components of wind turbine |
| CN103049762A (en) * | 2013-01-24 | 2013-04-17 | 中国神华能源股份有限公司 | Method and device for detecting center plate bolt loss fault |
| CN103154697A (en) * | 2010-09-28 | 2013-06-12 | 阿斯特里姆简易股份公司 | Method and device for non-destructive testing of wind turbine blades |
| CN103267764A (en) * | 2013-05-30 | 2013-08-28 | 东北大学 | Hot-rolled steel plate surface defect image identification method based on neighborhood information estimation |
| CN103870816A (en) * | 2014-03-26 | 2014-06-18 | 中国科学院寒区旱区环境与工程研究所 | Plant identification method and device with high identification rate |
| CN104215640A (en) * | 2014-08-18 | 2014-12-17 | 南京航空航天大学 | Wind-generator blade defect damage inspection method and inspection system based on unmanned helicopter |
| CN104601956A (en) * | 2015-01-15 | 2015-05-06 | 西安工程大学 | Power transmission line online monitoring system and method based on fixed-wing unmanned aerial vehicle |
-
2015
- 2015-12-28 CN CN201511000214.XA patent/CN105651780A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011064565A2 (en) * | 2009-11-25 | 2011-06-03 | Cyberhawk Innovations Limited | Unmanned aerial vehicle |
| CN102297098A (en) * | 2010-06-25 | 2011-12-28 | 通用电气公司 | System and method for wind turbine inspection |
| CN103154697A (en) * | 2010-09-28 | 2013-06-12 | 阿斯特里姆简易股份公司 | Method and device for non-destructive testing of wind turbine blades |
| CN102628425A (en) * | 2011-02-04 | 2012-08-08 | 通用电气公司 | Method and system for wind turbine inspection |
| CN102798635A (en) * | 2011-05-25 | 2012-11-28 | 西门子公司 | Method to inspect components of wind turbine |
| CN103049762A (en) * | 2013-01-24 | 2013-04-17 | 中国神华能源股份有限公司 | Method and device for detecting center plate bolt loss fault |
| CN103267764A (en) * | 2013-05-30 | 2013-08-28 | 东北大学 | Hot-rolled steel plate surface defect image identification method based on neighborhood information estimation |
| CN103870816A (en) * | 2014-03-26 | 2014-06-18 | 中国科学院寒区旱区环境与工程研究所 | Plant identification method and device with high identification rate |
| CN104215640A (en) * | 2014-08-18 | 2014-12-17 | 南京航空航天大学 | Wind-generator blade defect damage inspection method and inspection system based on unmanned helicopter |
| CN104601956A (en) * | 2015-01-15 | 2015-05-06 | 西安工程大学 | Power transmission line online monitoring system and method based on fixed-wing unmanned aerial vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 胡毅 等: "《输电线路遥感巡检与监测技术》", 31 December 2012, 中国电力出版社 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107656537A (en) * | 2016-07-25 | 2018-02-02 | 新疆金风科技股份有限公司 | Unmanned plane route planning method and device, fan blade inspection method and system based on unmanned plane |
| CN106370602A (en) * | 2016-08-31 | 2017-02-01 | 纳路易爱姆斯株式会社 | Large-sized structure ultrasonic examination method and system using unmanned aerial vehicles |
| CN108073180A (en) * | 2016-11-08 | 2018-05-25 | 北京金风科创风电设备有限公司 | Control method, the device and system of unmanned plane |
| CN108073180B (en) * | 2016-11-08 | 2020-07-28 | 北京金风科创风电设备有限公司 | Control method, device and system of unmanned aerial vehicle |
| CN106762451A (en) * | 2016-12-05 | 2017-05-31 | 北京金风科创风电设备有限公司 | Fan blade damage detection method, device and system based on unmanned aerial vehicle |
| CN106762451B (en) * | 2016-12-05 | 2018-10-23 | 北京金风科创风电设备有限公司 | Fan blade damage detection method, device and system based on unmanned aerial vehicle |
| CN108319290A (en) * | 2017-01-16 | 2018-07-24 | 财团法人金属工业研究发展中心 | Utilize the method on unmanned plane shooting wind turbine blade face, the computer program product and medium capable of reading record of internally stored program |
| WO2019227438A1 (en) * | 2018-05-31 | 2019-12-05 | 深圳市大疆创新科技有限公司 | Image processing method and device, aircraft, system, and storage medium |
| CN108733079B (en) * | 2018-06-19 | 2021-08-10 | 上海扩博智能技术有限公司 | Method and system for determining flight path of fan through automatic inspection by unmanned aerial vehicle |
| CN108733079A (en) * | 2018-06-19 | 2018-11-02 | 上海扩博智能技术有限公司 | Automatic detecting flight path is carried out to wind turbine by unmanned plane and determines method and system |
| CN108894933A (en) * | 2018-06-27 | 2018-11-27 | 上海扩博智能技术有限公司 | With losing method for catching again and system when by unmanned plane to blower blade tip tracing detection |
| CN108915959A (en) * | 2018-06-27 | 2018-11-30 | 上海扩博智能技术有限公司 | By unmanned plane to blower tip region detour detection method and system |
| CN108869196A (en) * | 2018-06-27 | 2018-11-23 | 上海扩博智能技术有限公司 | By unmanned plane to base region detection method on rear side of blower and system |
| CN109131895A (en) * | 2018-07-27 | 2019-01-04 | 上海扩博智能技术有限公司 | Unmanned plane carry device, unmanned plane and the method for detection are automatically tracked for blade |
| CN109632807A (en) * | 2018-11-28 | 2019-04-16 | 陕西高速公路工程试验检测有限公司 | A kind of portable detection method, apparatus and system |
| CN109470712A (en) * | 2018-12-23 | 2019-03-15 | 北京汉文景科技有限公司 | A kind of wind electricity blade detection system |
| CN110145989A (en) * | 2019-06-11 | 2019-08-20 | 广州珠江黄埔大桥建设有限公司 | Distress in concrete detection device and detection method based on unmanned plane |
| CN110554704A (en) * | 2019-08-15 | 2019-12-10 | 成都优艾维智能科技有限责任公司 | unmanned aerial vehicle-based fan blade autonomous inspection method |
| CN110554704B (en) * | 2019-08-15 | 2022-04-29 | 成都优艾维智能科技有限责任公司 | Unmanned aerial vehicle-based fan blade autonomous inspection method |
| CN110471447A (en) * | 2019-08-27 | 2019-11-19 | 无锡风电设计研究院有限公司 | The method for inspecting and system of wind energy conversion system |
| CN111289533A (en) * | 2020-02-25 | 2020-06-16 | 国电电力内蒙古新能源开发有限公司 | Fan blade inspection method and device, unmanned aerial vehicle and storage medium |
| CN111289533B (en) * | 2020-02-25 | 2023-06-23 | 国电电力内蒙古新能源开发有限公司 | Inspection method and device for fan blade, unmanned aerial vehicle and storage medium |
| CN111461210A (en) * | 2020-03-31 | 2020-07-28 | 天津智惠未来科技有限责任公司 | Unmanned aerial vehicle-based wind power inspection blade defect grade determination method |
| WO2021198967A1 (en) * | 2020-04-02 | 2021-10-07 | Grace And Kowloon Holdings Limited | Tree image data acquisition |
| CN111830845A (en) * | 2020-04-30 | 2020-10-27 | 航天图景（北京）科技有限公司 | Automatic inspection simulation system and method for fan blade of unmanned aerial vehicle |
| CN111595859A (en) * | 2020-05-22 | 2020-08-28 | 三峡大学 | Bridge and culvert damage detection method and damage detection and management system |
| CN111562220A (en) * | 2020-06-02 | 2020-08-21 | 吉林大学 | Rapid and intelligent detection method for bridge diseases |
| CN111746790A (en) * | 2020-07-21 | 2020-10-09 | 哈尔滨理工大学 | Accurate detection system of fan blade surface damage based on ground shooting image |
| CN112062062A (en) * | 2020-09-17 | 2020-12-11 | 黄玲玲 | High-altitude operation system of wind driven generator blade and control method thereof |
| CN113586360A (en) * | 2021-05-25 | 2021-11-02 | 深圳创动科技有限公司 | Fan detection method, detection device, detection system and readable storage medium |
| CN113406091A (en) * | 2021-06-09 | 2021-09-17 | 东方电气集团科学技术研究院有限公司 | Unmanned aerial vehicle system for detecting fan blade and control method |
| CN113406091B (en) * | 2021-06-09 | 2024-07-26 | 东方电气集团科学技术研究院有限公司 | Unmanned aerial vehicle system for fan blade detection and control method |
| CN113758438A (en) * | 2021-07-08 | 2021-12-07 | 重庆市勘测院 | Special building oblique aerial photography and three-dimensional reconstruction method |
| CN114056567A (en) * | 2021-11-22 | 2022-02-18 | 西安热工研究院有限公司 | Wind power blade deicing system and method based on unmanned aerial vehicle cluster |
| CN114439702A (en) * | 2022-01-28 | 2022-05-06 | 华能盐城大丰新能源发电有限责任公司 | Blade state monitoring method and device of wind driven generator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105651780A (en) | Method, apparatus and system for detecting state of blower blade through unmanned plane | |
| CN107729808B (en) | Intelligent image acquisition system and method for unmanned aerial vehicle inspection of power transmission line | |
| CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
| CN112884931B (en) | Unmanned aerial vehicle inspection method and system for transformer substation | |
| CN104616003B (en) | Foreign matter identification system on power line | |
| CN104865971B (en) | The control method and unmanned plane of a kind of polling transmission line unmanned plane | |
| CN106547814A (en) | A kind of power transmission line unmanned machine patrols and examines the structuring automatic archiving method of image | |
| CN105739512A (en) | Unmanned aerial vehicle automatic tour inspection system and method | |
| CN112270267B (en) | Camera shooting identification system capable of automatically capturing line faults | |
| CN109085573A (en) | Vehicle-mounted unmanned aerial vehicle managing and control system and method | |
| KR101634937B1 (en) | System for automatic vision inspection, method using the same | |
| KR102184693B1 (en) | Automatic landing method of unmanned aerial vehicle into ground-free vehicle, and automatic landing device of unmanned aerial vehicles | |
| CN112162565B (en) | Uninterrupted self-main-pole tower inspection method based on multi-machine collaborative operation | |
| CN110570536A (en) | intelligent line patrol system for extra-high voltage transmission line | |
| CN111244822B (en) | Fixed-wing unmanned aerial vehicle line patrol method, system and device in complex geographic environment | |
| CN111610538A (en) | Unmanned aerial vehicle navigation decoy system | |
| Nasseri et al. | Power line detection and tracking using hough transform and particle filter | |
| CN113326752B (en) | Unmanned aerial vehicle-based photovoltaic power station identification method and system | |
| CN110211159A (en) | A kind of aircraft position detection system and method based on image/video processing technique | |
| CN113486866A (en) | Visual analysis method and system for airport bird identification | |
| CN106094866A (en) | A kind of unmanned plane power circuit polling device and using method thereof | |
| CN114592411B (en) | Carrier parasitic type intelligent inspection method for highway damage | |
| CN109708659A (en) | A kind of distributed intelligence photoelectricity low latitude guard system | |
| CN112493228B (en) | Laser bird repelling method and system based on three-dimensional information estimation | |
| CN114332632A (en) | Safety helmet identification device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20160608 |