CN114511511B - Automatic judging method and system for damage degree of blade surface - Google Patents
Automatic judging method and system for damage degree of blade surface Download PDFInfo
- Publication number
- CN114511511B CN114511511B CN202210041530.5A CN202210041530A CN114511511B CN 114511511 B CN114511511 B CN 114511511B CN 202210041530 A CN202210041530 A CN 202210041530A CN 114511511 B CN114511511 B CN 114511511B
- Authority
- CN
- China
- Prior art keywords
- damage
- blade
- image
- blade surface
- texture
- 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
- 230000006378 damage Effects 0.000 title claims abstract description 175
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000012800 visualization Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000003086 colorant Substances 0.000 claims description 4
- 230000009528 severe injury Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 9
- 230000007797 corrosion Effects 0.000 description 7
- 238000005260 corrosion Methods 0.000 description 7
- 208000027418 Wounds and injury Diseases 0.000 description 5
- 239000000306 component Substances 0.000 description 5
- 208000014674 injury Diseases 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012916 structural analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an automatic judging method for the damage degree of the surface of a blade, which comprises the following steps: acquiring a plurality of blade surface damage images to be judged, and preprocessing each blade surface damage image; inputting the preprocessed damage images of the surfaces of the blades into a texture analysis model to judge the damage degree of the surfaces of the blades; and constructing a cloud picture for displaying damage information of different parts according to the judging grade of the damage degree of the blade surface. The invention also discloses an automatic judging system of the damage degree of the blade surface, which comprises an image input unit, an image preprocessing unit, a texture analysis unit and a visualization unit. The method and the system provided by the invention can grasp the surface damage condition of the blade to be detected in detail and vividly.
Description
Technical Field
The invention belongs to the field of industrial detection, and particularly relates to an automatic judging method and system for damage degree of a blade surface.
Background
The blades are key core components of energy power equipment such as a steam turbine, a gas turbine, an aeroengine and the like. The surface of the blade is easy to be damaged due to complex actions such as mechanical load, chemical corrosion and the like in the service process, and the damage comprises the following steps: abrasive wear, erosive wear, cavitation erosion, etc., in the form of pits, grooves, pits, etc., on the blade surface. The damage degree of the surface of the blade is accurately judged to determine maintainability, so that the method is one of important links of blade replacement and remanufacturing, and has important value for guaranteeing the safe service and the running economy of energy power equipment. In the traditional method, subjective damage judgment and recording are mainly carried out on the damage degree of the blade surface through manual visual detection, and the efficiency and accuracy of blade maintenance are seriously affected. In addition, the manual visual detection can only record the whole size and distribution information of the damaged area, the density of the surface damage cannot be described in detail, and the three-dimensional digital information of the blade damage cannot be further constructed.
The digital image is an informationized medium reflecting the surface state of an object, and the surface state of the object can be expressed, described and detected by properly processing and analyzing the informationized medium. Currently, a method for acquiring, processing and analyzing surface information of a target object in a digital image form has been widely used in the fields of remote sensing aerospace, biomedicine, military public security and the like. In the task of judging the damage degree of the blade surface, the method can be used for realizing the automatic analysis of the damage degree of the blade surface. In practice, damage to the blade surface, such as pits, grooves, pits, etc., is typically revealed in the digital image in the form of an approximate texture. Therefore, the problem is suitable for specifically adopting a texture analysis method in digital image processing, and the texture characteristics of a target area in an image are described by defining texture parameters closely related to the graph, so that the texture characteristics can be corresponding to the damage degree of the blade surface. The statistical analysis method, the structural analysis method and the frequency spectrum analysis method are three commonly used digital image texture analysis methods, wherein the statistical analysis method is the most simple to implement, and can be well adapted to the surface damage distribution rules with great difference of the confidentiality, the periodicity and the directionality on the blade. In summary, for the application task of blade surface damage detection, a method for determining the degree of blade surface damage based on texture analysis technology, especially based on statistical analysis method, can be developed and is necessary to provide more surface damage information for artificial visual detection. Further, an automatic judging system for the damage degree of the blade surface is constructed based on the method, so that the daily overhaul efficiency and the maintenance level of important equipment in the related field are improved.
Disclosure of Invention
Aiming at the defects of the existing blade surface damage detection method mainly based on manual visual detection, the invention aims to provide an automatic judging method and system for the damage degree of the blade surface.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an automatic judging method for the damage degree of the surface of a blade comprises the following steps:
s100: acquiring a plurality of blade surface damage images to be judged, and preprocessing each blade surface damage image;
s200: inputting the preprocessed surface damage images of the blades into a texture analysis model to judge the damage degree of the surfaces of the blades;
s300: and constructing a cloud picture for displaying damage information of different parts according to the judging grade of the damage degree of the blade surface.
Preferably, in step S200, the texture analysis model includes a texture feature calculation module and a sliding window assignment module;
the texture feature calculation module is used for judging the damage degree of the damaged area on the surface of the blade by calculating the feature quantity of the gray level co-occurrence matrix;
the sliding window assignment module assigns texture features of areas around each point of the damaged area of the blade surface to the point so as to obtain the damage degree at the point.
Preferably, in step 200, the texture analysis model is built by:
s2001: acquiring a plurality of blade surface damage images with different damage degrees, and preprocessing;
s2002: dividing the preprocessed blade surface damage image into a plurality of damage grades, and calculating the texture characteristic quantity of each image;
s2003: selecting the texture feature quantity most relevant to the damage level according to the relevance;
s2004: fitting out the corresponding relation between the texture feature quantity and the damage level, and determining the value range of the texture feature quantity under each damage level.
Preferably, in step S300, the construction of the cloud image displaying the damage information of different locations is performed by the following manner: and according to the texture feature quantity of each point and surrounding areas of the blade surface damage image, superposing corresponding colors for the point from light to deep, and sequentially representing the damage grade from no damage to severe damage.
Preferably, in step S2001, the preprocessing of the damage image of each blade surface is performed by: and carrying out graying treatment on the damaged images on the surfaces of the blades to obtain gray images.
The invention also provides an automatic judging system for the damage degree of the blade surface, which comprises the following steps:
an image input unit for inputting a blade surface damage image to be determined;
the image preprocessing unit is used for preprocessing the damaged image of the blade surface to be judged;
the texture analysis unit is used for judging the preprocessed blade surface damage image through a texture analysis model so as to obtain damage degree information of the blade surface;
and the visualization unit is used for performing visualization operation on the damage degree information of the blade surface so as to construct a cloud picture for displaying the damage information of different positions.
Preferably, the texture analysis unit comprises a texture feature calculation module and a sliding window assignment module;
the texture feature calculation module is used for judging the damage degree of the damaged area on the surface of the blade by calculating the feature quantity of the gray level co-occurrence matrix;
the sliding window assignment module assigns texture features of areas around each point of the damaged area of the blade surface to the point so as to obtain the damage degree at the point.
Preferably, the texture analysis unit further comprises a texture analysis modeling module for building a texture analysis model.
Preferably, the texture analysis modeling module includes:
the image input and preprocessing sub-module is used for acquiring a plurality of blade surface damage images with different damage degrees and preprocessing the blade surface damage images;
the damage grade dividing sub-module is used for dividing the preprocessed blade surface damage image into a plurality of damage grades and calculating the texture characteristic quantity of each image;
the optimal texture feature selection sub-module is used for selecting texture feature quantity most relevant to the damage level according to the relevance;
and the threshold value determining submodule is used for fitting out the corresponding relation between the texture characteristic quantity and the damage grade so as to determine the value range of the texture characteristic quantity under each damage grade.
The present invention also provides a computer device comprising:
a memory and a processor, wherein,
the memory has stored thereon an executable program executable on the processor,
the processor executes the executable program to implement any of the methods described above.
The present invention also provides a computer readable storage medium storing a computer program which when executed by a processor performs any of the methods described above.
Compared with the prior art, the invention has the beneficial effects that:
first, the invention can assist the manual visual detection of the damage of the blade surface, automatically judge the damage degree of the blade surface, ensure standardization and consistency and improve efficiency.
Secondly, the invention constructs the damage degree cloud picture for displaying the information of different parts, and can provide support for damage detection and rating of various structural components represented by the blades.
Drawings
FIG. 1 is a flow chart of an automatic determination method for damage degree of a blade surface according to an embodiment of the present invention;
FIG. 2 is a schematic view of blade surface damage class provided by another embodiment of the present invention;
FIG. 3 is a fitted relationship of entropy and damage level provided by another embodiment of the present invention;
FIG. 4 is a cloud chart depicting the damage level of different parts of a blade according to another embodiment of the present invention.
Detailed Description
Specific embodiments of the present invention will be described in detail below with reference to fig. 1 to 4 of the accompanying drawings. While specific embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
It should be noted that certain terms are used throughout the description and claims to refer to particular components. Those of skill in the art will understand that a person may refer to the same component by different names. The specification and claims do not identify differences in terms of components, but rather differences in terms of the functionality of the components. As used throughout the specification and claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. The description hereinafter sets forth a preferred embodiment for practicing the invention, but is not intended to limit the scope of the invention, as the description proceeds with reference to the general principles of the description. The scope of the invention is defined by the appended claims.
For the purpose of facilitating an understanding of the embodiments of the present invention, reference will now be made to the drawings, by way of example, and specific examples of which are illustrated in the accompanying drawings.
In one embodiment, as shown in fig. 1, the present invention provides an automatic determination method for a damage degree of a blade surface, including the following steps:
s100: acquiring a plurality of blade surface damage images to be judged, and preprocessing each blade surface damage image;
s200: inputting the preprocessed surface damage images of the blades into a texture analysis model to judge the damage degree of the surfaces of the blades;
s300: and constructing a cloud picture for displaying damage information of different parts according to the judging grade of the damage degree of the blade surface.
In another embodiment, in step S200, the texture analysis model includes a texture feature calculation module and a sliding window assignment module;
the texture feature calculation module is used for judging the damage degree of the damaged area on the surface of the blade by calculating the feature quantity of the gray level co-occurrence matrix;
the sliding window assignment module assigns texture features of areas around each point of the damaged area of the blade surface to the point so as to obtain the damage degree at the point.
In another embodiment, the texture analysis model is built by:
s2001: acquiring a plurality of blade surface damage images with different damage degrees, and preprocessing;
in this step, the preprocessing of the damage image of each blade surface is performed by: and carrying out graying treatment on the damaged images on the surfaces of the blades to obtain gray images.
S2002: dividing the preprocessed blade surface damage image into a plurality of damage grades, and calculating the texture characteristic quantity of each image;
in this step, as shown in fig. 2, the damage of the surface of the blade is exemplified by the damage of the surface of the blade, and the damage image of the surface of the blade is classified into five classes according to the degree of damage, namely, no damage (no corrosion pits), slight damage (1 to 5 corrosion pits), obvious damage (6 to 15 corrosion pits), serious damage (16 to 40 corrosion pits) and serious damage (greater than 40 corrosion pits), according to the degree of the density of the corrosion pits.
Further, a feature quantity of the gray level co-occurrence matrix is calculated according to the following formula, wherein,
the calculation expression of the feature quantity is:
wherein G (i, j) represents the (i, j) th term of the normalized gray level co-occurrence matrix, and k represents the gray level.
The computational expression of entropy is:
wherein G (i, j) represents the (i, j) th term of the normalized gray level co-occurrence matrix, and k represents the gray level.
The computational expression for contrast is:
where G (i, j) represents the (i, j) th term of the normalized gray level co-occurrence matrix, k represents the gray level, and n represents the absolute value of the gray level difference.
The calculation expression of the inverse difference moment is:
wherein G (i, j) represents the (i, j) th term of the normalized gray level co-occurrence matrix, and k represents the gray level.
The computational expression of the autocorrelation is:
wherein G (i, j) represents the (i, j) th term of the normalized gray level co-occurrence matrix, and k represents the gray level. Mu (mu) x Represents the mean, μ of the edge probability matrix summed over the G (i, j) rows y Represents the mean, σ, of the edge probability matrix summing the columns of G (i, j) x Representing the standard deviation, sigma, of the edge probability matrix summed over the G (i, j) rows v Represents the standard deviation of the edge probability matrix summed over the G (i, j) columns.
S2003: selecting the texture feature quantity most relevant to the damage level according to the relevance;
in this step, the correlation coefficient is used to measure the degree of correlation between two variables. Three major correlation coefficients in statistics: pearson correlation coefficient, spearman correlation coefficient, kendel correlation coefficient. The pearson correlation coefficient is selected in this embodiment, and the pearson correlation coefficient between the damage level and the texture feature amount is calculated as follows.
Wherein X represents the damage level, Y represents the texture feature quantity, ρ X，Y Pearson correlation coefficient representing the injury level and texture feature quantity, cov (X, Y) represents covariance of the injury level and texture feature quantity, σ X Standard deviation, sigma, of the lesion scale Y The standard deviation of the texture feature quantity is represented.
Further, as shown in table 1, pearson correlation coefficients of energy, entropy, contrast, autocorrelation, inverse moment, and injury level were calculated.
TABLE 1
| Texture feature quantity | Pearson correlation coefficient |
| (Energy) | -0.59 |
| Entropy of | 0.74 |
| Contrast ratio | 0.64 |
| Auto-correlation | -0.38 |
| Moment of inverse difference | -0.51 |
As can be seen from the pearson correlation coefficients of energy, entropy, contrast, autocorrelation, inverse moment and injury level in table 1, the correlation between entropy and injury level is the strongest.
S2004: fitting out the corresponding relation between the texture feature quantity and the damage level, and determining the value range of the texture feature quantity under each damage level.
In this step, as shown in fig. 3, the relationship between the entropy and the damage level is fitted by a least square method, and as shown in table 2, the range of values of the entropy in each damage level is obtained.
TABLE 2
| Grade | Level 1 | Level 2 | 3 grade | Grade 4 | Grade 5 |
| Entropy of | 0～1.5 | 1.5～1.9 | 1.9～2.5 | 2.5～3.2 | ＞3.2 |
In step S300, the construction of the cloud image displaying the damage information of different parts is performed in the following manner: and according to the texture feature quantity of each point and surrounding areas of the blade surface damage image, superposing corresponding colors from light to deep on the point, and sequentially representing damage grades from no damage to severe damage.
In this step, the entropy of each point is replaced by the entropy of the area around the point, and as shown in table 3, a corresponding color is superimposed on each point according to the damage level corresponding to the entropy.
TABLE 3 Table 3
| Grade | Level 1 | Level 2 | 3 grade | Grade 4 | Grade 5 |
| Gray scale value | 240 | 220 | 190 | 170 | 150 |
Further, fig. 4 shows that the damage image of the blade surface to be determined is determined by the method according to the present invention, and each point is determined by the model, and the result shown in fig. 4 is output, and the result is identical to that observed by naked eyes. According to the texture analysis model, a damage degree cloud picture describing information of different parts is constructed, and the damage grade of each point can be displayed.
In another embodiment, an automatic determination system for the extent of damage to a blade surface includes:
an image input unit for inputting a blade surface damage image to be determined;
the image preprocessing unit is used for preprocessing the damaged image of the blade surface to be judged;
the texture analysis unit is used for judging the preprocessed blade surface damage image through a texture analysis model so as to obtain damage degree information of the blade surface;
and the visualization unit is used for performing visualization operation on the damage degree information of the blade surface so as to construct a cloud picture for displaying the damage information of different positions.
In another embodiment, the texture analysis unit includes a texture feature calculation module and a sliding window assignment module;
the texture feature calculation module is used for judging the damage degree of the damaged area on the surface of the blade by calculating the feature quantity of the gray level co-occurrence matrix;
the sliding window assignment module assigns texture features of areas around each point of the damaged area of the blade surface to the point so as to obtain the damage degree at the point.
In another embodiment, the texture analysis unit further comprises a texture analysis modeling module for building a texture analysis model.
In another embodiment, the texture analysis modeling module includes:
the image input and preprocessing sub-module is used for acquiring a plurality of blade surface damage images with different damage degrees and preprocessing the blade surface damage images;
the damage grade dividing sub-module is used for dividing the preprocessed blade surface damage image into a plurality of damage grades and calculating the texture characteristic quantity of each image;
the optimal texture feature selection sub-module is used for selecting texture feature quantity most relevant to the damage level according to the relevance;
and the threshold value determining submodule is used for fitting out the corresponding relation between the texture characteristic quantity and the damage grade so as to determine the value range of the texture characteristic quantity under each damage grade.
In another embodiment, the present invention also provides a computer apparatus, including:
a memory and a processor, wherein,
the memory has stored thereon an executable program executable on the processor,
the processor executes the executable program to implement the automatic determination method of the degree of damage to the blade surface as in the above-described embodiment.
In another embodiment, a computer readable storage medium stores a computer program, which when executed by a processor, implements a method for automatically determining a degree of damage to a surface of a blade as in the above embodiment.
In this embodiment, it should be understood by those skilled in the art that the method described in the above embodiment may be implemented by a computer program, which when executed, may include all the steps of the above method. Any reference to memory, storage, database, or other medium used in the embodiments provided in this embodiment may include any type of existing nonvolatile memory such as read-only memory ROM, programmable memory PROM, electrically programmable memory EPROM, and any type of volatile memory including static RAM, dynamic RAM, and synchronous DRAM.
The foregoing description of the invention has been presented for the purposes of illustration and description, and is not intended to be limiting. Any partial modification or replacement within the scope of the disclosed technology by any person skilled in the art should be included within the scope of the present invention.
Claims (4)
1. An automatic judging method for the damage degree of the surface of a blade comprises the following steps:
s100: acquiring a plurality of blade surface damage images to be judged, and preprocessing each blade surface damage image;
s200: inputting the preprocessed surface damage images of each blade into a texture analysis model to judge the damage degree of the surface of the blade, wherein the texture analysis model comprises a texture feature calculation module and a sliding window assignment module;
the texture feature calculation module is used for judging the damage degree of the damaged area on the surface of the blade by calculating the feature quantity of the gray level co-occurrence matrix;
the sliding window assignment module assigns texture features of areas around each point of the damaged area of the blade surface to the point so as to obtain the damage degree at the point;
the specific judging mode of the damage degree of the texture analysis model to the surface of the blade is as follows:
dividing the preprocessed blade surface damage image into a plurality of damage grades, and calculating 5 texture feature quantities of energy, entropy, contrast, autocorrelation and inverse difference moment of each image;
selecting texture feature quantity entropy most relevant to the damage level from 5 texture feature quantities according to the relevance;
fitting out the corresponding relation between the entropy and the damage level, and determining the value range of the entropy under each damage level;
s300: according to the judging level of the damage degree of the blade surface, constructing a cloud image for displaying damage information of different parts, wherein the cloud image for displaying the damage information of the different parts comprises the following modes: and according to the entropy of each point and surrounding areas of the blade surface damage image, corresponding colors are superimposed from light to deep to each point, and the damage grades from no damage to severe damage are sequentially represented.
2. The method according to claim 1, wherein in step S100, the preprocessing of each blade surface damage image is performed by: and carrying out graying treatment on the damaged images on the surfaces of the blades to obtain gray images.
3. An automatic determination system for the extent of damage to a blade surface, comprising:
an image input unit for inputting a blade surface damage image to be determined;
the image preprocessing unit is used for preprocessing the damaged image of the blade surface to be judged;
a texture analysis unit for judging the damage degree of the blade surface through a texture analysis model on the preprocessed blade surface damage image, wherein,
the texture analysis model comprises a texture feature calculation module and a sliding window assignment module;
the texture feature calculation module is used for judging the damage degree of the damaged area on the surface of the blade by calculating the feature quantity of the gray level co-occurrence matrix;
the sliding window assignment module assigns texture features of areas around each point of the damaged area of the blade surface to the point so as to obtain the damage degree at the point;
the texture analysis unit includes:
the damage level dividing sub-module is used for dividing the preprocessed blade surface damage image into a plurality of damage levels and calculating 5 texture feature quantities of energy, entropy, contrast, autocorrelation and inverse moment of each image;
the optimal texture feature selection submodule selects texture feature quantity entropy most relevant to the damage level from 5 texture feature quantities according to the relevance;
the threshold value determining submodule is used for fitting out the corresponding relation between the entropy and the damage level and determining the value range of the entropy under each damage level;
and the visualization unit is used for carrying out visualization operation on the damage degree information of the surface of the blade, namely, according to the entropy of each point and surrounding areas of the damage image of the surface of the blade, corresponding colors are overlapped for each point from shallow to deep, and the damage grades from no damage to serious damage are sequentially represented, so as to construct a cloud picture for displaying the damage information of different parts.
4. A computer device, comprising:
a memory and a processor, wherein,
the memory has stored thereon an executable program executable on the processor,
the processor executes the executable program to implement the method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210041530.5A CN114511511B (en) | 2022-01-14 | 2022-01-14 | Automatic judging method and system for damage degree of blade surface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210041530.5A CN114511511B (en) | 2022-01-14 | 2022-01-14 | Automatic judging method and system for damage degree of blade surface |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114511511A CN114511511A (en) | 2022-05-17 |
| CN114511511B true CN114511511B (en) | 2024-02-02 |
Family
ID=81550368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210041530.5A Active CN114511511B (en) | 2022-01-14 | 2022-01-14 | Automatic judging method and system for damage degree of blade surface |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114511511B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2990998A1 (en) * | 2014-08-29 | 2016-03-02 | Institute of Electronics, Chinese Academy of Sciences | Method and device for assessing damage in disaster area |
| CN106910214A (en) * | 2017-02-09 | 2017-06-30 | 中国林业科学研究院资源信息研究所 | A kind of santal trunk insect pest degree of injury level images method of discrimination |
| CN111581409A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Damage image feature database construction method and system and engine |
| KR20200099633A (en) * | 2019-02-14 | 2020-08-25 | 재단법인 아산사회복지재단 | Method and computer program for analyzing texture of an image |
-
2022
- 2022-01-14 CN CN202210041530.5A patent/CN114511511B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2990998A1 (en) * | 2014-08-29 | 2016-03-02 | Institute of Electronics, Chinese Academy of Sciences | Method and device for assessing damage in disaster area |
| CN106910214A (en) * | 2017-02-09 | 2017-06-30 | 中国林业科学研究院资源信息研究所 | A kind of santal trunk insect pest degree of injury level images method of discrimination |
| KR20200099633A (en) * | 2019-02-14 | 2020-08-25 | 재단법인 아산사회복지재단 | Method and computer program for analyzing texture of an image |
| CN111581409A (en) * | 2020-05-13 | 2020-08-25 | 中国民用航空飞行学院 | Damage image feature database construction method and system and engine |
Non-Patent Citations (2)
| Title |
|---|
| 周晓兵,张世芳,邱白晶,赵杰文.近红外图像纹理分析叶片含水率的初步研究.江苏理工大学学报.1999,(第03期),全文. * |
| 朱军伟 ; 张彦娥 ; 王晓敏 ; 李丽 ; .基于图像纹理的玉米叶片叶绿素含量分析研究.微计算机信息.2010,(第10期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114511511A (en) | 2022-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Raadnui | Wear particle analysis—utilization of quantitative computer image analysis: a review | |
| Junk et al. | Predictor-weighting strategies for probabilistic wind power forecasting with an analog ensemble | |
| CN110689531A (en) | Automatic power transmission line machine inspection image defect identification method based on yolo | |
| US8109150B2 (en) | Crack-propagation prediction method and program | |
| CN113838054B (en) | Mechanical part surface damage detection method based on artificial intelligence | |
| CN104680524A (en) | Disease diagnosis method for leaf vegetables | |
| CN110895814B (en) | Aero-engine hole-finding image damage segmentation method based on context coding network | |
| CN109063983A (en) | A kind of natural calamity loss real time evaluating method based on social media data | |
| CN114511511B (en) | Automatic judging method and system for damage degree of blade surface | |
| CN113283768A (en) | Food detection item extraction method, device, equipment and storage medium | |
| CN115600933B (en) | Electric meter power quality detection method and system based on Internet of things | |
| CN116468270A (en) | Cloud model-based substation flood season risk perception assessment method and device | |
| CN116416523A (en) | Machine learning-based rice growth stage identification system and method | |
| WO2023085992A1 (en) | Image analysis of cut flowers | |
| CN115471724A (en) | Fine-grained fish epidemic disease identification fusion algorithm based on self-adaptive normalization | |
| CN113065224A (en) | Deep sea pipeline crack propagation monitoring and reliability evaluation method based on image recognition | |
| CN104915959A (en) | Aerial photography image quality evaluation method and system | |
| Polsterer | Dealing with uncertain multimodal photometric redshift estimations | |
| Marchiningrum | Digital Twin for Predictive Maintenance of Palm Oil Processing Machines | |
| CN114676587B (en) | Fatigue life evaluation method based on load spectrum similarity | |
| CN111445132B (en) | Data processing method, data processing system and computer storage medium | |
| KR100716902B1 (en) | The damage evaluation system of metal and The damage evaluation method of metal using the same | |
| CN114240948A (en) | Intelligent segmentation method and system for structural surface damage image | |
| CN117952482A (en) | Product quality accident grading method and system based on convolutional neural network | |
| de Carvalho Michalski et al. | Applying Principal Component Analysis for Multi-parameter Failure Prognosis and Determination of Remaining Useful Life |
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 |