CN113205514A - Method, system, equipment and storage medium for acquiring fan blade corrosion information - Google Patents
Method, system, equipment and storage medium for acquiring fan blade corrosion information Download PDFInfo
- Publication number
- CN113205514A CN113205514A CN202110583970.9A CN202110583970A CN113205514A CN 113205514 A CN113205514 A CN 113205514A CN 202110583970 A CN202110583970 A CN 202110583970A CN 113205514 A CN113205514 A CN 113205514A
- Authority
- CN
- China
- Prior art keywords
- information
- image
- corrosion
- image information
- acquiring
- 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
- 230000007797 corrosion Effects 0.000 title claims abstract description 51
- 238000005260 corrosion Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000003628 erosive effect Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 230000007547 defect Effects 0.000 claims description 10
- 239000003365 glass fiber Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000009972 noncorrosive effect Effects 0.000 claims description 3
- 239000003973 paint Substances 0.000 claims description 3
- 239000004576 sand Substances 0.000 claims description 3
- 238000002372 labelling Methods 0.000 abstract description 8
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The present disclosure provides a method, system, device and storage medium for obtaining fan blade corrosion information, wherein the method comprises the steps of: s1: acquiring an image set, wherein the image set comprises a plurality of images containing blades; s2: extracting image information of the image according to a preset step length and a preset direction by using a sliding window until the sliding window traverses the whole image; s3: classifying the extracted image information to obtain image information with corrosion content; s4: and repeating the steps S2-S3 on the unprocessed image until all image information which meets the preset size requirement and has corrosion content is obtained. The method, the system, the equipment and the storage medium for acquiring the fan blade corrosion information can accurately classify the corrosion types, reduce early-stage manual labeling work, have high algorithm running speed and lower performance requirement on a computer, and the calculated amount is far lower than that of a target detection mode in the prior art.
Description
Technical Field
The present disclosure relates to the field of graphical information technology, and in particular, to a method, system, device, and storage medium for obtaining fan blade corrosion information.
Background
At present, the corrosion is directly identified by using a target identification mode, but the method has the following defects: the current stage of target recognition has strict requirements on image size (the image size needs to be small, 200 x 300), while the erosion pattern on the blade is a long strip, and the size of the generated image is very large and far exceeds the image size requirement of target recognition. Although the target identification can also be performed by using a multi-scale division mode, the method is time-consuming, large in calculation amount, very high in requirements on the performance (processing energy of a display card) of the computer, and high in memory occupation of the computer.
The target identification also needs a lot of time to perform previous manual labeling work, and the target needs to be labeled in detail during labeling, which is very high in requirement. And in the classification, the outline of the target does not need to be marked, and only the whole picture needs to be labeled.
In addition, the detection capability of target detection for the corrosion class of the blade is weak, and is not enough to distinguish the corrosion types with subdivision differences.
Disclosure of Invention
The disclosure mainly provides a method, a system, equipment and a storage medium for acquiring fan blade corrosion information, which can accurately classify corrosion types, reduce early manual labeling work, have high algorithm running speed and low performance requirement on a computer, and the calculated amount is far lower than that of a target detection mode in the prior art.
The present disclosure provides a method for obtaining fan blade corrosion information, comprising the steps of:
s1: acquiring an image set, wherein the image set comprises a plurality of images containing blades;
s2: extracting image information of the image according to a preset step length and a preset direction by using a sliding window until the sliding window traverses the whole image to obtain the image information meeting the preset size requirement;
s3: classifying the extracted image information to obtain the image information with corrosion content;
s4: and repeating the steps S2-S3 on the unprocessed image until all the image information which meets the preset size requirement and has corrosion content is obtained.
Preferably, the set of images is obtained by taking a picture of the leaf or is provided by a leaf vendor.
Preferably, the step S4 further includes the following steps:
and classifying the image information meeting the preset size requirement according to the conditions of background, hub, tower column, non-corrosive blade, paint falling, sand hole, slight corrosion of undamaged glass fiber, damaged glass fiber and perforation to obtain classified image information.
Preferably, the method further comprises the following steps: and counting the classified image information into a histogram.
Preferably, the method further comprises the following steps: converting the classified image information to an image corresponding to the blade in a data conversion mode; identifying on the image of the blade whether the blade has a defect and the severity of the defect.
Preferably, the severity of the defect is distinguished by color.
The present disclosure provides a system for acquiring fan blade corrosion information, which is used for implementing the method for acquiring fan blade corrosion information of the present disclosure, and the system includes:
the information acquisition module is used for acquiring the image set;
the sliding window module is used for obtaining the image information meeting the preset size requirement;
and the data processing module is used for classifying the extracted image information and acquiring the image information with corrosion content.
The present disclosure provides an apparatus for obtaining fan blade corrosion information, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method of obtaining wind turbine blade erosion information according to the present disclosure when executing the computer program.
The present disclosure provides a computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of obtaining wind turbine blade corrosion information according to the present disclosure.
This disclosure owing to adopted above technical scheme, makes it have following beneficial effect:
the corrosion type can be accurately classified, early manual labeling work is reduced, the algorithm operation speed is high, the performance requirement on a computer is low, and the calculated amount is far lower than that of a target detection mode in the prior art.
Drawings
FIG. 1 is a flow chart of a method of obtaining fan blade erosion information according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of sliding window image information extraction according to an embodiment of the disclosure;
FIG. 3 is a schematic block diagram of a system for obtaining corrosion information for a wind turbine blade according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of an apparatus for obtaining corrosion information of a fan blade according to an embodiment of the disclosure;
fig. 5 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the disclosure.
Detailed Description
Based on the above, the fan blade corrosion identification has great significance for fan blade maintenance.
At present, the fan blade corrosion identification has strict requirements on the image size (the image size needs to be small, 200 x 300), and the corrosion form on the blade is a strip shape, so that the size of the generated image is very large and far exceeds the image size requirement of target identification. Although the target identification can also be performed by using a multi-scale division mode, the method is time-consuming, large in calculation amount, very high in requirements on the performance (processing energy of a display card) of the computer, and high in memory occupation of the computer. The target identification also needs a lot of time to perform previous manual labeling work, and the target needs to be labeled in detail during labeling, which is very high in requirement.
In order to solve the problems that the existing corrosion identification is time-consuming, the calculation amount is huge, the requirement on the performance (processing energy of a display card) of a computer is very high, and the occupation of the memory of the computer is high, the method, the system, the equipment and the storage medium for acquiring the fan blade corrosion information are provided, the corrosion types can be accurately classified, the early-stage manual labeling work is reduced, the algorithm operation speed is high, the requirement on the performance of the computer is low, and the calculation amount is far lower than that of a target detection mode in the prior art.
The present disclosure is described in detail below with reference to specific examples. The following examples will aid those skilled in the art in further understanding the present disclosure, but are not intended to limit the disclosure in any way. It should be noted that numerous variations and modifications could be made by those skilled in the art without departing from the concepts of the present disclosure. All falling within the scope of the present disclosure.
The following description of the preferred embodiments of the present disclosure will be provided in conjunction with the accompanying drawings, fig. 1-5, and will make the functions and features of the present disclosure better understood.
FIG. 1 is a flow chart of a method for obtaining corrosion information of a fan blade according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a sliding window for extracting image information according to an embodiment of the present disclosure;
FIG. 3 is a schematic block diagram of a system for obtaining corrosion information for a wind turbine blade according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of an apparatus for obtaining corrosion information of a wind turbine blade according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a computer-readable storage medium provided in an embodiment of the present disclosure.
Referring to fig. 1 and fig. 2, a method for acquiring corrosion information of a fan blade according to an embodiment of the present disclosure includes:
s1: acquiring an image set, wherein the image set comprises a plurality of images 1 containing leaves;
the image set is obtained by taking a picture of the leaf or is provided by the leaf vendor.
S2: extracting the image information of the image 1 by using the sliding window 2 according to a preset step length and a preset direction until the sliding window 2 traverses the whole image 1 to obtain the image information meeting the preset size requirement;
in fig. 2, the sliding window 2 only illustrates the process of extracting the image information of a certain position on the image 1 by the sliding window 2, and does not represent the pattern or size or moving direction of the real sliding window 2.
The sliding window 2 is slid continuously to traverse the entire image 1, in the form of dividing the image 1 into a plurality of different small pictures.
S3: classifying the extracted image information to obtain image information with corrosion content;
s4: and repeating the steps S2-S3 on the unprocessed image 1 until all image information which meets the preset size requirement and has corrosion content is obtained.
Step S4 is followed by the further steps of:
and classifying the image information meeting the preset size requirement according to the conditions of background, hub, tower column, non-corrosive blade, paint falling, sand hole, slight corrosion of undamaged glass fiber, damaged glass fiber and perforation to obtain classified image information.
Further comprising the steps of: and counting the classified image information into a histogram.
Further comprising the steps of: converting the classified image information to the image 1 of the corresponding blade in a data conversion mode; the presence and severity of defects in the blade are identified on the image 1 of the blade.
The severity of corrosion is characterized by different colors, and the appearance is more visual and clear.
The severity of the defect is distinguished by color, e.g., red to indicate the region where the defect is severe.
Referring to fig. 3, the present disclosure provides a system for acquiring fan blade corrosion information, for implementing the method for acquiring fan blade corrosion information of the present disclosure, the system includes:
an information acquisition module 301, configured to acquire an image set;
a sliding window module 302, configured to obtain image information meeting a preset size requirement;
and the data processing module 303 is configured to perform classification processing on the extracted image information to obtain image information with erosion content.
Referring to fig. 4, the present disclosure provides an apparatus for obtaining corrosion information of a fan blade, including:
a memory 401 for storing a computer program;
a processor 402 for implementing the steps of the method of obtaining fan blade erosion information according to the present disclosure when executing a computer program.
Referring to fig. 5, the present disclosure provides a computer readable storage medium 500, where the computer readable storage medium 500 stores a computer program, and the computer program is executed by a processor to implement the steps of the method for acquiring the erosion information of the fan blade according to the present disclosure.
The present disclosure has been described in detail with reference to the embodiments shown in the drawings, and various modifications thereof can be made by those skilled in the art. Therefore, certain details of the embodiments should not be construed as limitations of the present disclosure, which are to be interpreted as having a scope defined by the appended claims.
Claims (9)
1. A method for acquiring corrosion information of a fan blade comprises the following steps:
s1: acquiring an image set, wherein the image set comprises a plurality of images containing blades;
s2: extracting image information of the image according to a preset step length and a preset direction by using a sliding window until the sliding window traverses the whole image to obtain the image information meeting the preset size requirement;
s3: classifying the extracted image information to obtain the image information with corrosion content;
s4: and repeating the steps S2-S3 on the unprocessed image until all the image information which meets the preset size requirement and has corrosion content is obtained.
2. The method of obtaining wind turbine blade erosion information according to claim 1, wherein the set of images is obtained by taking a picture of the blade or is provided by a blade manufacturer.
3. The method for acquiring the corrosion information of the fan blade according to claim 1, wherein the step of S4 is further followed by the steps of:
and classifying the image information meeting the preset size requirement according to the conditions of background, hub, tower column, non-corrosive blade, paint falling, sand hole, slight corrosion of undamaged glass fiber, damaged glass fiber and perforation to obtain classified image information.
4. The method of obtaining wind turbine blade erosion information according to claim 3, further comprising the steps of: and counting the classified image information into a histogram.
5. The method of obtaining wind turbine blade erosion information according to claim 3, further comprising the steps of: converting the classified image information to an image corresponding to the blade in a data conversion mode; identifying on the image of the blade whether the blade has a defect and the severity of the defect.
6. The method of obtaining wind turbine blade erosion information according to claim 5, wherein the severity of the defect is distinguished by color.
7. A system for acquiring fan blade corrosion information, for implementing the method for acquiring fan blade corrosion information of any one of claims 1 to 6, the system comprising:
the information acquisition module is used for acquiring the image set;
the sliding window module is used for obtaining the image information meeting the preset size requirement;
and the data processing module is used for classifying the extracted image information and acquiring the image information with corrosion content.
8. An apparatus for obtaining fan blade erosion information, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method of acquiring wind turbine blade erosion information according to any of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of acquiring wind turbine blade corrosion information according to any of the claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110583970.9A CN113205514A (en) | 2021-05-27 | 2021-05-27 | Method, system, equipment and storage medium for acquiring fan blade corrosion information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110583970.9A CN113205514A (en) | 2021-05-27 | 2021-05-27 | Method, system, equipment and storage medium for acquiring fan blade corrosion information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113205514A true CN113205514A (en) | 2021-08-03 |
Family
ID=77023385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110583970.9A Pending CN113205514A (en) | 2021-05-27 | 2021-05-27 | Method, system, equipment and storage medium for acquiring fan blade corrosion information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113205514A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106841214A (en) * | 2017-01-21 | 2017-06-13 | 兰州理工大学 | A kind of non-contact wind power blade dust storm erosion degree detection method |
| CN110009632A (en) * | 2019-04-17 | 2019-07-12 | 国网重庆市电力公司电力科学研究院 | A kind of appraisal procedure, device and the equipment of metal erosion state |
| CN111612786A (en) * | 2020-06-19 | 2020-09-01 | 国网湖南省电力有限公司 | Concrete defect detection method and device based on full convolution neural network and storage medium |
| CN112727704A (en) * | 2020-12-15 | 2021-04-30 | 北京天泽智云科技有限公司 | Method and system for monitoring corrosion of leading edge of blade |
-
2021
- 2021-05-27 CN CN202110583970.9A patent/CN113205514A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106841214A (en) * | 2017-01-21 | 2017-06-13 | 兰州理工大学 | A kind of non-contact wind power blade dust storm erosion degree detection method |
| CN110009632A (en) * | 2019-04-17 | 2019-07-12 | 国网重庆市电力公司电力科学研究院 | A kind of appraisal procedure, device and the equipment of metal erosion state |
| CN111612786A (en) * | 2020-06-19 | 2020-09-01 | 国网湖南省电力有限公司 | Concrete defect detection method and device based on full convolution neural network and storage medium |
| CN112727704A (en) * | 2020-12-15 | 2021-04-30 | 北京天泽智云科技有限公司 | Method and system for monitoring corrosion of leading edge of blade |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109376768B (en) | Aerial image tower signboard fault diagnosis method based on deep learning | |
| CN112837290B (en) | Crack image automatic identification method based on seed filling algorithm | |
| CN103872983A (en) | Device and method for detecting defects on surface of solar cell | |
| CN108509950B (en) | Railway contact net support number plate detection and identification method based on probability feature weighted fusion | |
| CN110751619A (en) | Insulator defect detection method | |
| CN109850518B (en) | Real-time mining adhesive tape early warning tearing detection method based on infrared image | |
| CN112669287B (en) | Electrical equipment temperature monitoring method based on image recognition | |
| CN111597939B (en) | High-speed rail line nest defect detection method based on deep learning | |
| CN112330592A (en) | Fan blade defect detection method and device and storage medium | |
| CN107369162B (en) | Method and system for generating insulator candidate target area | |
| CN113888462A (en) | Crack identification method, system, readable medium and storage medium | |
| CN113435452A (en) | Electrical equipment nameplate text detection method based on improved CTPN algorithm | |
| CN107247967B (en) | Vehicle window annual inspection mark detection method based on R-CNN | |
| CN113688829B (en) | Automatic identification method and system for monitoring picture of transformer substation | |
| CN117994679A (en) | Intelligent image analysis method for defects of wind power equipment | |
| CN114694130A (en) | Method and device for detecting telegraph poles and pole numbers along railway based on deep learning | |
| CN118334373A (en) | SIFT algorithm-based wind turbine generator set cabin feature point matching method and system | |
| CN109508714B (en) | Low-cost multi-channel real-time digital instrument panel visual identification method and system | |
| CN114266895A (en) | Fan blade image segmentation and splicing method and device | |
| CN109389616A (en) | A kind of silk cocoon image background segment method | |
| CN113205514A (en) | Method, system, equipment and storage medium for acquiring fan blade corrosion information | |
| CN114596242A (en) | Defect detection method, defect detection device, electronic equipment and computer readable storage medium | |
| CN111707672A (en) | Method for detecting surface defects of wind power rotary supporting piece | |
| CN110728229A (en) | Image processing method, device, equipment and storage medium | |
| CN112712080B (en) | Character recognition processing method for acquiring image by moving character screen |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210803 |