CN107886511A - A kind of pneumatic equipment bladess surface damage detection method - Google Patents
A kind of pneumatic equipment bladess surface damage detection method Download PDFInfo
- Publication number
- CN107886511A CN107886511A CN201711213704.7A CN201711213704A CN107886511A CN 107886511 A CN107886511 A CN 107886511A CN 201711213704 A CN201711213704 A CN 201711213704A CN 107886511 A CN107886511 A CN 107886511A
- Authority
- CN
- China
- Prior art keywords
- image
- pneumatic equipment
- region
- equipment bladess
- surface damage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of image detecting method of pneumatic equipment bladess surface damage, this method is directed to leaf image, proposes optimization problem corresponding to image segmentation problem.By updating region to be split, and repeatedly solved, finally give the boundary curve of damage, so as to reach the purpose of detection blade injury.The image detecting method of the pneumatic equipment bladess surface damage of the present invention belongs to contactless, test problems is converted into convex optimization problem, and solved using efficient optimization method, method is easy to add necessary segmentation thought, with the advantages of universality height, velocities solved is fast, and precision is high.
Description
Technical field
The present invention relates to equipment damage detection technique field, and in particular to one kind carries out wind energy conversion system based on image Segmentation Technology
The method of blade surface damage check.
Background technology
Pneumatic equipment bladess are as stress members, it may appear that the quality accident of surface damage, it are monitored and detected
It is vital.Sensor array mainly by the way of contact, i.e., is embedded to wind-force by blade surface damage check in advance
The key position of machine blade, the optical signal detected according to fiber-optic output judge position, size and trend of damage etc..This
Class method needs to arrange the sensor of vast number, is huge to wind energy conversion system design, wind energy conversion system stability, wind energy conversion system expense etc.
Challenge.Therefore, the surface damage for pneumatic equipment bladess is, it is necessary to efficient by image procossing this " vision " instrument development
Non-contact detection method.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of pneumatic equipment bladess surface damage based on image Segmentation Technology
Hinder detection method.
The pneumatic equipment bladess surface damage detection method of the present invention, comprises the following steps:
A. the image for obtaining pneumatic equipment bladess is gathered by high resolution camera.
B. gray level image is converted the image into, remembers that the image is, orderIt is image-region, i.e.,Domain.
C. image dividing processing is carried out to pneumatic equipment bladess image according to following steps.
C1. the total degree for setting image to splitk.Given initial region to be split is, initial value, weightWith。
C2. application division Bregman method iteratives
WhereinIt is Lagrange multipliers,It is length item weight,It is level set function,It is regionDCharacteristic function,It is regionIt is flat
Equal gray value.In solution procedure, for regionDOuter point remains that its value is -1, i.e.,,
Solve result is designated as, whereinRepresent current segmentation times.
C3. judge whether segmentation times reach k times, if not up to, giving region to be splitD, initial value, weight
With, and return to step c2.
D. for thekSecondary solving result, its 0- isopleth is sought, is designated as curveC, then curveCIt correspond to blade damage
Hinder the edge in region.
This method is directed to leaf image, by updating cut zone, repeatedly solves corresponding to image segmentation problem and optimizes
Problem, object boundary curve is obtained, so as to reach the purpose of detection blade surface damage.The pneumatic equipment bladess surface of the present invention
The image detecting method of damage belongs to contactless, and test problems are converted into convex optimization problem, is easy to add necessary point
Thought is cut, there is higher universality.Using the convex optimization problem of efficient Optimization Method, velocities solved is fast, and precision is high.
Brief description of the drawings
Fig. 1 is the pneumatic equipment bladess gray level image with damage;
Fig. 2 is the result of segmentation gained for the first time;
Fig. 3 is the result of second of segmentation gained.
Embodiment
With reference to the accompanying drawings and examples further to the detailed description of the invention, following examples be it is descriptive, it is non-limiting
Property, it is impossible to protection scope of the present invention is limited with this.
Embodiment 1
For the pneumatic equipment bladess of certain surface damage, surface damage detection is carried out using the inventive method, comprised the following steps that:
A. the image with damaged blade is gathered.
B. gray level image is converted the image into, remembers that the image is, noteIt is image-region.As shown in figure 1, wherein 2 tables
What is shown is pneumatic equipment bladess, and 1 expression is damage field.
C. image dividing processing is carried out to pneumatic equipment bladess image according to following steps.
C1., segmentation times are set, give prime areaAnd initial value, give weightWith。
C2. first time image segmentation is carried out.Using division Bregman method iteratives
Obtain optimum results。
C3. second of image segmentation is carried out.Update prime area, as shown in Fig. 23, and
Given initial value, give weightWith, asked using division Bregman method iteratives
Topic
And remain in an iterative process, obtain optimum results。
D. optimum results are sought0- isopleth, as shown in Fig. 34, the curve is blade surface damage field
Edge.
Claims (3)
1. a kind of pneumatic equipment bladess surface damage detection method, it is characterised in that comprise the following steps:
A. the image for obtaining pneumatic equipment bladess is gathered by high resolution camera;
B. gray level image is converted the image into, remembers that the image is, orderIt is image-region, i.e.,Domain;
C. image dividing processing is carried out to pneumatic equipment bladess image according to following steps;
C1. the total degree for setting image to splitk;
Given initial region to be split is, initial value, weightWith;
C2. application division Bregman method iteratives
WhereinIt is Lagrange multipliers,It is length item weight,It is level set function,
It is regionDCharacteristic function,It is regionAverage gray value;
In solution procedure, for regionDOuter point remains that its value is -1, i.e.,, solve
Result is obtained to be designated as, whereinRepresent current segmentation times;
C3. judge whether segmentation times reach k times, if not up to, giving region to be splitD, initial value, weightWith, and
Return to step c2;
D. for thekSecondary solving result, its 0- isopleth is sought, is designated as curveC, then curveCIt correspond to blade injury area
The edge in domain.
2. pneumatic equipment bladess surface damage detection method according to claim 1, it is characterised in that:Total time of image segmentation
Number。
3. pneumatic equipment bladess surface damage detection method according to claim 1, it is characterised in that:TheSecondary point
Region to be split in cutting。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711213704.7A CN107886511A (en) | 2017-11-28 | 2017-11-28 | A kind of pneumatic equipment bladess surface damage detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711213704.7A CN107886511A (en) | 2017-11-28 | 2017-11-28 | A kind of pneumatic equipment bladess surface damage detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107886511A true CN107886511A (en) | 2018-04-06 |
Family
ID=61775688
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711213704.7A Pending CN107886511A (en) | 2017-11-28 | 2017-11-28 | A kind of pneumatic equipment bladess surface damage detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107886511A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217430A (en) * | 2014-08-26 | 2014-12-17 | 浙江大学 | Image significance detection method based on L1 regularization |
US20170169310A1 (en) * | 2015-12-14 | 2017-06-15 | Samsung Electronics Co., Ltd. | Method and apparatus for matching stereo images |
CN206369617U (en) * | 2016-12-30 | 2017-08-01 | 中国华能集团清洁能源技术研究院有限公司 | A kind of pneumatic equipment bladess damage active self-checking unit |
CN107153842A (en) * | 2017-04-27 | 2017-09-12 | 西安交通大学 | The fan blade diaphragm damage detecting method split based on edge |
-
2017
- 2017-11-28 CN CN201711213704.7A patent/CN107886511A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217430A (en) * | 2014-08-26 | 2014-12-17 | 浙江大学 | Image significance detection method based on L1 regularization |
US20170169310A1 (en) * | 2015-12-14 | 2017-06-15 | Samsung Electronics Co., Ltd. | Method and apparatus for matching stereo images |
CN206369617U (en) * | 2016-12-30 | 2017-08-01 | 中国华能集团清洁能源技术研究院有限公司 | A kind of pneumatic equipment bladess damage active self-checking unit |
CN107153842A (en) * | 2017-04-27 | 2017-09-12 | 西安交通大学 | The fan blade diaphragm damage detecting method split based on edge |
Non-Patent Citations (2)
Title |
---|
李伟斌 等: "一种图像分割的快速不动点算法", 《电子与信息学报》 * |
李伟斌 等: "基于变分分割模型的结冰冰形测量方法", 《航空学报》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3091657B1 (en) | Photovoltaic string fault identification method, apparatus and system | |
CN103530590B (en) | DPM Quick Response Code recognition system | |
AU2018326401A1 (en) | Method and system for use in performing localisation | |
CN110069993A (en) | A kind of target vehicle detection method based on deep learning | |
CN104199972A (en) | Named entity relation extraction and construction method based on deep learning | |
US20150045923A1 (en) | Material cutting optimization apparatus, system, and method | |
CN102254167B (en) | Method for reducing false reject rate of fingerprint comparison | |
CN102750534B (en) | A kind of method and apparatus of character cutting | |
CN101251896B (en) | Object detecting system and method based on multiple classifiers | |
CN103246641A (en) | Text semantic information analyzing system and method | |
CN103729625A (en) | Face identification method | |
US20150227577A1 (en) | Method and device for guaranteeing consistency of planning data | |
CN104461901A (en) | Method and system for automatically generating test case | |
CN104298746A (en) | Domain literature keyword extracting method based on phrase network diagram sorting | |
WO2007146477B1 (en) | Method and apparatus for adaptive hierarchical processing of print images | |
CN106593781A (en) | Wind driven generator fault detecting system and method based on Android platform | |
CN104915678A (en) | Method and device for detecting target object in power transmission line | |
CN104484533A (en) | Point-cloud-based three-dimensional modeling method for damaged turbine blade of aero-engine | |
MX2021004237A (en) | System and method for using artificial intelligence to process data extracted from utility bills. | |
CN103500323B (en) | Based on the template matching method of self-adaptation gray level image filtering | |
CN103178962B (en) | General-purpose fingerprint authentication method and device | |
CN115761645A (en) | YOLOv 5-based light-weight safety helmet wearing detection method | |
CN103913765A (en) | Nuclide energy spectrum peak searching method | |
CN107886511A (en) | A kind of pneumatic equipment bladess surface damage detection method | |
CN102254353A (en) | Method for describing characteristics of three-dimensional model |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180406 |