CN114428518B - Fan orientation method for automatic inspection of unmanned aerial vehicle fan blade - Google Patents
Fan orientation method for automatic inspection of unmanned aerial vehicle fan blade Download PDFInfo
- Publication number
- CN114428518B CN114428518B CN202111497724.8A CN202111497724A CN114428518B CN 114428518 B CN114428518 B CN 114428518B CN 202111497724 A CN202111497724 A CN 202111497724A CN 114428518 B CN114428518 B CN 114428518B
- Authority
- CN
- China
- Prior art keywords
- fan
- image
- orientation
- aerial vehicle
- unmanned aerial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000007689 inspection Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 37
- 230000009466 transformation Effects 0.000 claims description 16
- 230000000877 morphologic effect Effects 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000001976 improved effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The invention discloses a fan orientation method for automatic inspection of a fan blade of an unmanned aerial vehicle, wherein the real orientation angle of the fan can be estimated rapidly and accurately, the fan orientation method is applied to unmanned aerial vehicle inspection operation of a plurality of wind power stations such as a set source and a fixed edge, the estimation accuracy can be within 1 degree, and the fan orientation method has a high practical application value. The whole fan orientation method has stronger scene adaptability and can be suitable for any fan orientation and blade position. Compared with the existing blower orientation method based on the laser radar, the method has the advantages of being simple and convenient to operate, rapid in processing and the like.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle application, and particularly relates to a fan orientation method for automatic inspection of unmanned aerial vehicle fan blades.
Background
With the rapid development of new energy industry in China, clean energy represented by wind power generation has the characteristics of small pollution, reproducibility and the like, the original energy structure is gradually improved, and positive effects are generated on promoting the sustainable development of regional economy and society. However, with the continuous expansion of the scale of wind farms, the requirement for later-stage safety maintenance of equipment is also growing at a high speed, and the limited inspection manpower and the complex inspection environment greatly influence the operation efficiency and safety of equipment maintenance. Therefore, it is important to find a fan inspection method with high efficiency and safety. The multi-rotor unmanned aerial vehicle has the characteristics of high maneuverability, strong adaptability and the like, works by carrying loads such as a visible light camera, an infrared camera or a laser radar, and can ensure that the unmanned aerial vehicle performs data acquisition autonomously by means of an automatic route planning algorithm, so that the rapidity and the reliability of front-end data acquisition are effectively ensured, and the inspection personnel are helped to efficiently and accurately find and process abnormal conditions such as sand holes, gel coat damage and the like on the fan blades.
For the front-end data acquisition end of the whole unmanned aerial vehicle fan blade inspection, a fan orientation and fan blade positioning technology is a precondition for ensuring the accuracy of route planning, and the fan orientation is the most important, so that whether the unmanned aerial vehicle can accurately fly to the position right in front of a fan plane for fan front view shooting is directly determined. At present, few unmanned aerial vehicle fan blade inspection scheme solutions (such as complex sub-intelligence and expanded intelligence) on the market all use laser radar to carry out blade positioning navigation, and although the accuracy of this mode is higher, because the fan body type is very big, the time consumption of adopting laser radar to carry out earlier stage data acquisition and processing is longer, restricts the high timeliness demand of this business. It is therefore of great importance to find a more compact and rapid method of fan orientation.
Disclosure of Invention
The invention aims to overcome the technical problems in the background art, and aims to provide a fan orientation method for automatic inspection of unmanned aerial vehicle fan blades, which can well utilize the obvious color characteristics of the fan blades in the environment, realize an accurate and reliable fan orientation function through a concise image processing mode, and effectively ensure the efficient implementation of the automatic inspection flow of the whole unmanned aerial vehicle fan blades.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a fan orientation method for automatic inspection of unmanned aerial vehicle fan blades, the method comprising:
performing image processing on the input image to obtain a binarized image with noise removed;
fitting the straight lines in the binarized image with noise removed by using a Hough transformation straight line detection method, and taking the straight line corresponding to the maximum voting number obtained after fitting as a connecting line of a fan blade main body;
obtaining the rotation angle of the fan blade in the image by using the slope of the straight line for the connecting line of the fan blade main body;
performing European transformation on the binarized image with noise removed based on the rotation angle in the image, and cutting out a target area to obtain an integral part image of the fan blade;
dividing the whole part image of the fan blade into an image of the main part of the fan blade and an image of the engine room part, and counting the number of the foreground of the main part of the fan blade and the number of the foreground of the engine room part;
judging the positive and negative directions of the fan according to the number of the foreground of the main body part and the cabin part of the fan blade;
and outputting a final orientation angle value by utilizing the judgment result of the positive and negative directions of the fan, and ending the whole fan orientation process.
The method has the advantages that the obvious color characteristics of the fan blades in the environment can be well utilized, the accurate and reliable fan orientation function is realized through a concise image processing mode, the efficient performance of the automatic inspection flow of the fan blades of the whole unmanned aerial vehicle is effectively ensured, the real orientation angle of the fan can be rapidly and accurately estimated, the method is applied to the unmanned aerial vehicle inspection operation of a plurality of wind power plants such as source and edge fixing, the estimation accuracy can reach within 1 degree, and the method has high practical application value. The whole fan orientation method has stronger scene adaptability and can be suitable for any fan orientation and blade position. Compared with the existing blower orientation method based on the laser radar, the method has the advantages of being simple and convenient to operate, rapid in processing and the like.
Further, the image processing on the input image specifically includes:
s1: extracting a brightness channel of an input image, and counting the mean value and standard deviation of a gray scale image under the brightness channel;
s2: based on the mean value and standard deviation of the gray level images, filtering the input image by utilizing a sliding window to obtain a gray level image with separated front and back;
s3: performing binarization processing on the gray level image separated from the front background by using an Ojin method to obtain a gray level image after the binarization processing;
s4: and carrying out morphological opening and closing operation processing on the gray level image after the binarization processing to obtain a binarized image after noise is removed.
Further, the morphological opening/closing operation processing includes:
and removing a smaller discrete region in the gray level diagram after the binarization processing by using morphological open operation, and further filling gaps of a larger region in the gray level diagram after the binarization processing by using morphological close operation.
Further, the input image is a top view of the unmanned aerial vehicle collected directly above the fan.
Further, before image processing is performed on the input image, the method further includes:
firstly, pitch angle judgment is carried out on a top view collected right above an input fan, if the deviation from the vertical direction is within +/-10 degrees, the top view is judged to be a usable top view, and the subsequent processing is carried out.
Further, the specific process of performing European transformation and clipping the target area comprises the following steps:
taking the image center of the binarized image with noise removed as a rotation center, and taking the rotation angle obtained by the slope of the straight line in the step as the rotation amount to be rotated, so that a corresponding rotation matrix can be calculated;
then, under the action of the rotation matrix, performing European transformation on the binarized image with noise removed, and rotating a fan main body in the image from inclination to horizontal;
and obtaining the outline of the rotated binary image, and cutting and storing all horizontal areas of the rectangle corresponding to the maximum outline.
Further, the judging of the positive and negative directions of the fan specifically includes:
if the number of the foreground of the main body part of the fan blade is larger than that of the cabin part, the blades are arranged at the upper part and the lower part of the cabin, and if the number of the foreground of the main body part of the fan blade is smaller than that of the cabin part, the blades are arranged at the lower part and the upper part of the cabin, so that the judgment of the forward and backward directions of the fan is completed.
Further, the final orientation angle value is output by utilizing the judgment result of the positive and negative directions of the fan; the method specifically comprises the following steps:
after positive and negative judgment of the fan direction, determining whether 180-degree compensation is added according to different directions of the fan direction, so as to obtain an included angle beta between the fan direction and the positive direction of the image, wherein the included angle alpha between the positive direction of the image and the positive direction of the geography can be directly read from a yaw angle of a cradle head in the image attribute, so that the included angle gamma of the positive direction of the hub relative to the positive direction of the geography is the sum of the included angle alpha and the included angle beta, and the final oriented angle belongs to a (-180) interval; and correcting the final orientation angle, wherein the final orientation angle gamma meets the following formula:
compared with the prior art, the invention has the advantages that:
a fan orientation method for automatic inspection of unmanned aerial vehicle fan blades can well utilize obvious color characteristics of the fan blades in the environment, realizes accurate and reliable fan orientation functions in a concise image processing mode, effectively ensures efficient performance of an automatic inspection flow of the whole unmanned aerial vehicle fan blades, can obtain quick and accurate estimation of a real orientation angle of a fan, is applied to unmanned aerial vehicle inspection operation of a plurality of wind power plants such as source and fixed edge, has estimation accuracy within 1 degree, and has strong practical application value. The whole fan orientation method has stronger scene adaptability and can be suitable for any fan orientation and blade position. Compared with the existing blower orientation method based on the laser radar, the method has the advantages of being simple and convenient to operate, rapid in processing and the like.
Drawings
FIG. 1 is a flow chart of the front-end operation of automatic inspection of unmanned aerial vehicle fan blades;
FIG. 2 is a flow chart of a fan orientation method;
FIG. 3 is a top view of a wind turbine collected directly above the wind turbine using a Sinkiang M300 drone;
FIG. 4 is a schematic view of three angles involved in a fan orientation method;
FIG. 5 is a gray scale of a main body of a fan to be selected obtained through front background separation;
FIG. 6 is a graph comparing noise rejection results before and after morphological processing;
fig. 7 is a fan blade body contour diagram obtained by hough transform straight line fitting;
FIG. 8 is a view of a fan body area obtained by clipping;
FIG. 9 is an upper and lower blade body (upper) and nacelle rear (lower) view, as divided in equal parts;
fig. 10 is a diagram of the blower orientation results in an actual blower inspection operation.
Detailed Description
The following describes specific embodiments of the present invention with reference to examples:
it should be noted that the structures, proportions, sizes and the like illustrated in the present specification are used for being understood and read by those skilled in the art in combination with the disclosure of the present invention, and are not intended to limit the applicable limitations of the present invention, and any structural modifications, proportional changes or size adjustments should still fall within the scope of the disclosure of the present invention without affecting the efficacy and achievement of the present invention.
Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.
Embodiment one:
the invention provides a fan orientation method for automatic inspection of unmanned aerial vehicle fan blades, which is mainly applied to a front-end data acquisition end for unmanned aerial vehicle fan blade inspection, and a front-end finishing operation flow is shown in figure 1. As can be seen from the flow chart, the fan orientation method focused by the invention is the basis of subsequent application, the input of the method is the top view acquired by the unmanned aerial vehicle right above the fan, the output is the fan orientation angle estimated by the algorithm, the inside of the algorithm adopts a concise image processing means, the front background separation is carried out by using the remarkable color information of the main body of the fan, then the straight line with the highest number of votes is obtained by using Hough transformation straight line detection fitting, and the positive and negative directions of the orientation are judged, so that the fan orientation angle is finally obtained.
The unmanned plane platform adopted by the invention is Xinjiang M300, and the Buddhist P1 full-frame camera is carried, so that reliable guarantee is provided for safe flight and data acquisition. Specifically, firstly, pitch angle judgment is carried out on a top view collected right above an input fan, if the deviation from the vertical direction is within +/-10 degrees, the top view is judged to be a usable top view, the subsequent processing is carried out, and otherwise, the processing is carried out; then, carrying out color space conversion on the image, converting the image from RGB space to HSV space, extracting a brightness channel in the image, and counting the mean value and standard deviation of a gray level image under the channel; then filtering the gray level map by utilizing a sliding window with equal step length, and reserving partial windows with more than two standard deviations to realize the front background separation of the main body of the image wind turbine and the surrounding environment; then binarizing the filtered gray level image by using an Ojin method, and filtering out noise by using morphological opening and closing operation; then fitting the straight line in the image by using a Hough transformation straight line detection method, taking the straight line corresponding to the maximum voting number as a connecting line of the fan blade main body, and obtaining the rotation angle of the fan plane in the image at the moment; then, european transformation is carried out on the image by utilizing the rotation angle, and a main body part of the fan blade is obtained by cutting; and finally, judging the positive and negative directions of the fan orientation by utilizing the foreground duty ratio of the blade main body, outputting a final orientation angle value, and ending the whole fan orientation process.
Embodiment two:
the invention provides a fan orientation method for automatic inspection of unmanned aerial vehicle fan blades, which is positioned in an extremely important position in the whole fan inspection service, as shown in fig. 1, an automatic route planning algorithm needs to obtain an accurate route according to a fan orientation and fan blade positioning technology, and the fan positioning technology directly determines whether an unmanned aerial vehicle can accurately fly to the position right in front of a fan plane to shoot a fan front view. Therefore, it is a major problem to be solved by the present invention to find a simple and reliable fan orientation method.
As shown in fig. 2, the entire fan orientation process includes seven main parts: extracting brightness channels of an input image, counting the mean value and standard deviation of the brightness channels, utilizing sliding window filtering to realize front background separation, carrying out morphological opening and closing operation on a binarized image, detecting and fitting a straight line corresponding to the maximum voting number through a Hough transformation straight line, carrying out European transformation on the image, cutting a target area, judging the forward and backward directions of a fan, and outputting a final direction angle value. During operation, a full-frame camera of Buddhist P1 mounted on the M300 unmanned aerial vehicle is used for shooting a top view of the fan right above the fan, as shown in fig. 3, the image XMP attribute of the full-frame camera comprises three attitude angles of pan tilt, roll and yaw, and if the deviation of the pitch angle and the vertical direction is within +/-10 degrees, the usable top view is judged, and the subsequent processing is carried out. Then, the yaw angle of the cradle head is recorded, so that the included angle alpha between the positive direction of the image and the positive direction of the geography can be read, but because the included angle beta exists between the fan orientation and the positive direction of the image, the included angle gamma between the fan orientation and the positive direction of the geography, namely the fan orientation result, is needed to be obtained according to the included angle alpha and the included angle beta. Since the angle α is known and the angle β is unknown, the main body of the fan orientation works by estimating the angle β, each of which is shown schematically in fig. 4.
After ensuring the basic information of the input image, the method is implemented as follows:
specifically, as step S1: the luminance channel of the input image is extracted and its mean and standard deviation are counted. The input image is converted from RGB color space to HSV color space (chroma Hue, saturation, brightness Value), and a brightness channel is extracted, wherein the brightness channel describes the brightness change of the image, and the difference between a fan main body and the surrounding environment can be reflected well. And then, counting the mean value and standard deviation of the gray level diagram under the channel to reflect the gray level change condition of the whole image.
Specifically, as step S2: front-background separation is achieved using sliding window filtering. As the standard deviation reflects the discrete degree of the data, for a fan main body with more obvious brightness characteristics, the screening of the fan region in the image can be realized by screening the image blocks with larger local region brightness in a sliding window mode. Specifically, a window with a size of n×n is selected as the sliding window, and the sliding steps in the horizontal and vertical directions are also N, where N is 1/200 of the height of the original image. And counting the pixel mean value of each window region, and setting the window region to be zero if the pixel mean value of the region is smaller than the sum of the gray scale image mean value and the double standard deviation in the step S1. After the whole image is finally circularly traversed, the reserved fan main body is the fan main body to be selected, so that the front background separation of the fan main body and the surrounding environment is preliminarily realized, and the front background separation is shown in fig. 5.
Specifically, as step S3: and carrying out morphological opening and closing operation on the binarized image. Because noise may exist in the filtered gray scale image, the noise needs to be removed to ensure the accuracy of the subsequent calculation result. Specifically, the gray level image is subjected to binarization processing by using an Ojin method, then smaller discrete areas are removed by using morphological open operation in sequence, and gaps of larger areas are further filled by using closed operation. Through this step of processing, noise points can be better rejected, as shown in fig. 6.
Specifically, as step S4: and detecting a straight line corresponding to the fitted maximum voting number by using the Hough transformation straight line. The fan blade main body in the binarized image after noise elimination is most prominent, and for the fan top view, the main body orientation and the blade connecting line are in vertical relation, so that the fan orientation angle can be reversely pushed by determining the deflection angle of the blade connecting line. Because the blades are generally longer and basically distributed in straight lines, the length lines which can be fitted are most theoretically, according to the characteristics, the lines possibly existing in the binary image can be fitted by utilizing Hough transformation, and after the polar coordinate resolution is set, the whole binary image is traversed, so that all the lines meeting the length requirement can be obtained. Then, a straight line with the largest occurrence number (namely the largest number of votes) of the same polar coordinates is selected as a main body connecting line of the fan blade, so that the rotation angle of the fan plane in the image is obtained according to the slope of the straight line, as shown in fig. 7.
Specifically, as step S5: the image is European transformed and the target area is cropped. Although the rotation angle of the blade body in the image can be obtained through the step S4, the positive and negative directions of the direction of the blade body cannot be judged, so that the function of the step is to prepare for the subsequent judgment of the direction of the fan. Specifically, with the image center as the rotation center and the rotation angle obtained by the slope of the straight line in the above steps as the rotation to be measured, the corresponding rotation matrix can be easily calculated; then, under the action of the rotation matrix, the fan main body in the image can be rotated from inclination to horizontal by performing European transformation on the binary image. In order to further avoid the influence of the fan body, the outline of the rotated binary image is obtained, and all horizontal areas of the rectangle corresponding to the maximum outline are cut and stored, so that the cutting of the fan body part can be completed, as shown in fig. 8.
Specifically, as step S6: and judging the positive and negative directions of the fan. Because the positive and negative directions of the fan can bring 180-degree deviation to the final result, the fan main body binary image stored in the step S5 can be equally divided into an upper half part and a lower half part, and at the moment, the rear part of the engine room and the blade main body can be distinguished, as shown in fig. 9; and respectively counting the sum of the foreground numbers in the upper and lower areas, if the upper half area is larger, considering that the blades are arranged under the upper cabin, otherwise, the blades are arranged under the lower cabin, so that the judgment of the forward and backward directions of the fan is completed.
Specifically, as step S7: and outputting the final orientation angle value. After positive and negative judgment of the fan orientation, whether 180-degree compensation is added can be determined according to different orientations, so that an included angle beta between the fan orientation and the positive direction of the image is obtained. Because the included angle alpha between the image positive direction and the geographic positive north direction can be directly read from the yaw angle of the cradle head in the image attribute, the included angle gamma between the hub positive direction and the geographic positive north direction is the sum of the included angle alpha and the included angle beta. Since the final heading angle belongs to the (-180 degree to +180 degree) interval, the result thereof needs to be corrected, and thus the final heading angle γ satisfies the following formula:
in summary, through the seven steps, the true orientation angle of the fan can be rapidly and accurately estimated, and the whole fan orientation method has stronger scene adaptability and can be suitable for any fan orientation and blade position. Compared with the existing blower orientation method based on the laser radar, the method has the advantages of being simple and convenient to operate, rapid in processing and the like.
In particular, as shown in fig. 10, in actual scene verification, the fan orientation method provided by the invention has been applied to unmanned aerial vehicle inspection operation of a plurality of wind power stations such as source and edge setting, and the estimation accuracy can reach within 1 degree, so that the fan orientation method has a relatively strong practical application value.
While the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the above embodiments, and various changes may be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Many other changes and modifications may be made without departing from the spirit and scope of the invention. It is to be understood that the invention is not to be limited to the specific embodiments, but only by the scope of the appended claims.
Claims (6)
1. A fan orientation method for automatic inspection of unmanned aerial vehicle fan blades, the method comprising:
performing image processing on the input image to obtain a binarized image with noise removed;
fitting the straight lines in the binarized image with noise removed by using a Hough transformation straight line detection method, and taking the straight line corresponding to the maximum voting number obtained after fitting as a connecting line of a fan blade main body;
obtaining the rotation angle of the fan blade in the image by using the slope of the straight line for the connecting line of the fan blade main body;
performing European transformation on the binarized image with noise removed based on the rotation angle in the image, and cutting out a target area to obtain an integral part image of the fan blade;
dividing the whole part image of the fan blade into an upper part and a lower part to obtain a main part image and a cabin part image of the fan blade, and counting the number of foreground parts of the main part of the fan blade and the number of foreground parts of the cabin part;
judging the forward and backward directions of the fan according to the foreground numbers of the main body part and the cabin part of the fan, if the foreground number of the main body part of the fan is larger than that of the cabin part, the blades are arranged at the bottom of the cabin, and if the foreground number of the main body part of the fan is smaller than that of the cabin part, the blades are arranged at the bottom of the cabin, so that the forward and backward directions of the fan are judged;
outputting a final orientation angle value by using the positive and negative judgment results of the orientation of the fan, and outputting the final orientation angle value by using the positive and negative judgment results of the orientation of the fan; the method specifically comprises the following steps:
after positive and negative judgment of the fan direction, determining whether 180-degree compensation is added according to different directions of the fan direction, so as to obtain an included angle beta between the fan direction and the positive direction of the image, wherein the included angle alpha between the positive direction of the image and the positive north direction of the geography can be directly read from a yaw angle of a cradle head in the image attribute, so that the included angle gamma of the positive direction of the hub relative to the positive north direction of the geography is the sum of the included angle alpha and the included angle beta, and the final oriented angle belongs to a (-180-degree) interval; and correcting the final orientation angle, wherein the final orientation angle gamma meets the following formula:
and ending the whole fan orientation flow.
2. The fan orientation method for automatic inspection of unmanned aerial vehicle fan blades according to claim 1, wherein the image processing is performed on the input image, specifically comprising:
s1: extracting a brightness channel of an input image, and counting the mean value and standard deviation of a gray scale image under the brightness channel;
s2: based on the mean value and standard deviation of the gray level images, filtering the input image by utilizing a sliding window to obtain a gray level image with separated front and back;
s3: performing binarization processing on the gray level image separated from the front background by using an Ojin method to obtain a gray level image after the binarization processing;
s4: and carrying out morphological opening and closing operation processing on the gray level image after the binarization processing to obtain a binarized image after noise is removed.
3. The fan orientation method for automatic inspection of unmanned aerial vehicle fan blades according to claim 2, wherein the morphological opening and closing operation processing comprises:
and removing a smaller discrete region in the gray level diagram after the binarization processing by using morphological open operation, and further filling gaps of a larger region in the gray level diagram after the binarization processing by using morphological close operation.
4. The method for fan orientation for automated inspection of unmanned aerial vehicle fan blades of claim 1, wherein the input image is a top view of an unmanned aerial vehicle collected directly above the fan.
5. A fan orientation method for automated inspection of unmanned aerial vehicle fan blades of claim 4, wherein prior to image processing the input image, the method further comprises:
firstly, pitch angle judgment is carried out on a top view collected right above an input fan, if the deviation from the vertical direction is within +/-10 degrees, the top view is judged to be a usable top view, and the subsequent processing is carried out.
6. The fan orientation method for automatic inspection of unmanned aerial vehicle fan blades according to claim 1, wherein the specific process of performing the european transformation and cutting the target area comprises the following steps:
taking the image center of the binarized image with noise removed as a rotation center, and taking the rotation angle obtained by the slope of the straight line in the step as the rotation amount to be rotated, so that a corresponding rotation matrix can be calculated;
under the action of the rotation matrix, performing European transformation on the binarized image with noise removed, so that a fan main body in the image can be rotated from inclination to horizontal;
and obtaining the outline of the rotated binary image, and cutting and storing all horizontal areas of the rectangle corresponding to the maximum outline.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111497724.8A CN114428518B (en) | 2021-12-09 | 2021-12-09 | Fan orientation method for automatic inspection of unmanned aerial vehicle fan blade |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111497724.8A CN114428518B (en) | 2021-12-09 | 2021-12-09 | Fan orientation method for automatic inspection of unmanned aerial vehicle fan blade |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114428518A CN114428518A (en) | 2022-05-03 |
| CN114428518B true CN114428518B (en) | 2024-03-22 |
Family
ID=81311240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111497724.8A Active CN114428518B (en) | 2021-12-09 | 2021-12-09 | Fan orientation method for automatic inspection of unmanned aerial vehicle fan blade |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114428518B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115908049B (en) * | 2022-11-18 | 2023-11-21 | 众芯汉创（北京）科技有限公司 | Fan blade hovering position dynamic identification system based on intelligent identification |
| CN116912548A (en) * | 2023-07-19 | 2023-10-20 | 北京图知天下科技有限责任公司 | Blade image processing method based on fan dynamic inspection |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE202017103924U1 (en) * | 2017-06-30 | 2017-07-21 | Ebm-Papst Mulfingen Gmbh & Co. Kg | blower |
| CN107491742A (en) * | 2017-07-28 | 2017-12-19 | 西安因诺航空科技有限公司 | Stable unmanned plane target tracking when a kind of long |
| JP2018021491A (en) * | 2016-08-02 | 2018-02-08 | 株式会社日立製作所 | System and flight route generating method |
| 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 |
| 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 |
| JP2020118141A (en) * | 2019-01-28 | 2020-08-06 | 株式会社日立製作所 | Blade inspection system of wind power generator, wind power generation system, remote integrated monitor system of wind farm |
| CN112882487A (en) * | 2019-11-29 | 2021-06-01 | 北京国电思达科技有限公司 | Unmanned aerial vehicle inspection track generation method, inspection method and system for fan blade |
| CN112904877A (en) * | 2021-01-14 | 2021-06-04 | 星闪世图(台州)科技有限公司 | Automatic fan blade inspection system and method based on unmanned aerial vehicle |
| CN113342041A (en) * | 2021-06-16 | 2021-09-03 | 河北华电沽源风电有限公司 | Method and system for realizing automatic inspection of fan blade power generation equipment by unmanned aerial vehicle |
| CN113723192A (en) * | 2021-07-30 | 2021-11-30 | 鹏城实验室 | Blade image acquisition method in running state of fan |
-
2021
- 2021-12-09 CN CN202111497724.8A patent/CN114428518B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018021491A (en) * | 2016-08-02 | 2018-02-08 | 株式会社日立製作所 | System and flight route generating method |
| DE202017103924U1 (en) * | 2017-06-30 | 2017-07-21 | Ebm-Papst Mulfingen Gmbh & Co. Kg | blower |
| CN107491742A (en) * | 2017-07-28 | 2017-12-19 | 西安因诺航空科技有限公司 | Stable unmanned plane target tracking when a kind of long |
| 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 |
| JP2020118141A (en) * | 2019-01-28 | 2020-08-06 | 株式会社日立製作所 | Blade inspection system of wind power generator, wind power generation system, remote integrated monitor system of wind farm |
| CN112882487A (en) * | 2019-11-29 | 2021-06-01 | 北京国电思达科技有限公司 | Unmanned aerial vehicle inspection track generation method, inspection method and system for fan blade |
| 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 |
| CN112904877A (en) * | 2021-01-14 | 2021-06-04 | 星闪世图(台州)科技有限公司 | Automatic fan blade inspection system and method based on unmanned aerial vehicle |
| CN113342041A (en) * | 2021-06-16 | 2021-09-03 | 河北华电沽源风电有限公司 | Method and system for realizing automatic inspection of fan blade power generation equipment by unmanned aerial vehicle |
| CN113723192A (en) * | 2021-07-30 | 2021-11-30 | 鹏城实验室 | Blade image acquisition method in running state of fan |
Non-Patent Citations (3)
| Title |
|---|
| Simultaneous drone localisation and wind turbine model fitting during autonomous surface inspection;O Moolan-Feroze 等;2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);20191104;论文第2014-2021页 * |
| 基于无人机的风机叶片缺陷自动检测技术;毛希玮;徐莹莹;;复合材料科学与工程;20200915(第09期);论文87-91页 * |
| 基于翼型剖面重心调节的风机叶片优化设计;汪强;张元明;;航空工程进展;20100525(第02期);论文52-56页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114428518A (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114428518B (en) | Fan orientation method for automatic inspection of unmanned aerial vehicle fan blade | |
| CN109936080B (en) | Method for inspecting power transmission line by unmanned aerial vehicle | |
| CN110244766B (en) | Planning method and system for unmanned aerial vehicle routing inspection route of photovoltaic power station | |
| CN111144324B (en) | Unmanned aerial vehicle inspection photovoltaic panel abnormal target analysis management system and method | |
| CN110163177B (en) | Unmanned aerial vehicle automatic sensing and identifying method for wind turbine generator blades | |
| CN110619329B (en) | Carriage number and loading state identification method of railway freight open wagon based on airborne vision | |
| CN109002048B (en) | Multi-rotor unmanned aerial vehicle large-scale centralized photovoltaic power station image data acquisition method | |
| CN107480727A (en) | The unmanned plane image fast matching method that a kind of SIFT and ORB are combined | |
| CN109389056B (en) | Space-based multi-view-angle collaborative track surrounding environment detection method | |
| Mao et al. | Development of power transmission line defects diagnosis system for UAV inspection based on binocular depth imaging technology | |
| CN115115634B (en) | Photovoltaic array hot spot detection method based on infrared image | |
| CN110825110A (en) | Acquisition flight method for power line visible light point cloud resolving photo | |
| CN115240089A (en) | Vehicle detection method of aerial remote sensing image | |
| Xi et al. | A vision-based inspection strategy for large-scale photovoltaic farms using an autonomous UAV | |
| CN114578328B (en) | Automatic calibration method for spatial positions of multiple laser radars and multiple camera sensors | |
| CN114463648B (en) | Method for keeping fan blade positioned in middle of camera vision based on pure vision | |
| CN113256668A (en) | Image segmentation method and device | |
| CN116893685A (en) | Unmanned aerial vehicle route planning method and system | |
| Mayer et al. | AI-based thermal bridge detection of building rooftops on district scale using aerial images | |
| CN115760885B (en) | High-closure-degree wetland forest parameter extraction method based on consumer-level unmanned aerial vehicle image | |
| Sha et al. | Design of patrol monitoring and control system for hot spot of solar photovoltaic module | |
| CN115355952A (en) | Intelligent inspection system for crude oil storage tank | |
| CN111932574B (en) | Building vertical point cloud extraction system and method based on multi-level semantic features | |
| Li et al. | Prediction of wheat gains with imagery from four-rotor UAV | |
| CN111397595B (en) | Method for positioning inspection target of flat single-axis photovoltaic scene unmanned aerial vehicle |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |