CN107607548A - The hidden method for splitting defect of photovoltaic module is detected by 3-D view - Google Patents
The hidden method for splitting defect of photovoltaic module is detected by 3-D view Download PDFInfo
- Publication number
- CN107607548A CN107607548A CN201710902452.2A CN201710902452A CN107607548A CN 107607548 A CN107607548 A CN 107607548A CN 201710902452 A CN201710902452 A CN 201710902452A CN 107607548 A CN107607548 A CN 107607548A
- Authority
- CN
- China
- Prior art keywords
- hidden
- defect
- split
- splitting
- photovoltaic module
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The hidden method for splitting defect disclosed by the invention that photovoltaic module is detected by 3-D view, first establish and hidden split classification standard, the numerical value of reference axis is represented with the length and width of photovoltaic module to be measured and gray value or current density again, establish 3-dimensional image model, then actual grey value corresponding to average gray value and each pixel is obtained from the hidden detection image of splitting of photovoltaic module to be measured, and it is entered into 3-dimensional image model, according to average gray value and the image of actual grey value, filter out it is hidden split defect area, the hidden grade for splitting defect is finally judged according to hidden classification standard of splitting.Compared to manually compare judge it is hidden split grade by way of, the hidden method for splitting defect of the detection avoids error caused by subjective determination, and decision accuracy is high and judges efficiency high, saves human resources.
Description
Technical field
The hidden of photovoltaic module is detected the present invention relates to solar photovoltaic technology field, more particularly to by 3-D view
Split the method for defect.
Background technology
The photovoltaic module of photovoltaic plant easily breaks down, and causes the decrease of power generation of whole photovoltaic plant, in order to subtract
Few photovoltaic module breaks down, and the performance test for photovoltaic module is essential means.Wherein, photovoltaic module is hidden splits event
Barrier is one of major reason for causing photovoltaic module lower power production and security performance reduction.Therefore, it is necessary to photovoltaic module is entered
Row is hidden to split characteristic test.The hidden characteristic of splitting of current photovoltaic module is surveyed using electroluminescent near infrared imaging principle
Examination, and for the whether qualified judgement of photovoltaic module and divide and hidden split grade for reflect the hidden order of severity split and all use
Be artificial subjective determination mode, it is relatively inefficient, and there may be different judgement knots due to different staff
Fruit, easily erroneous judgement is triggered even to make not reaching an agreement between staff, so as to influence testing progress.
The content of the invention
In view of this, it is an object of the invention to provide the hidden side for splitting defect that photovoltaic module is detected by 3-D view
Method, the hidden of photovoltaic module is detected by this method and splits defect and hidden defect of splitting is classified.
In order to realize above-mentioned purpose, present invention employs following technical scheme:
Present invention firstly provides a kind of hidden method for splitting defect that photovoltaic module is detected by 3-D view, including step
Suddenly:S11, collect it is existing it is hidden split defect parameters, establish and hidden split classification standard;S12, photovoltaic group to be measured represented with the numerical value of x-axis
The length of part, the width of photovoltaic module to be measured is represented with the numerical value of y-axis, gray value is represented with the numerical value of z-axis, with the x-axis, y
Axle and z-axis establish 3-dimensional image model as reference axis;S13, detection simultaneously obtain the hidden of photovoltaic module to be measured and split detection image;
S14, calculate the hidden average gray value for splitting detection image obtained;S15, by described hidden split each pixel pair in detection image
The actual grey value answered is input in the 3-dimensional image model in the step S12, and shape is corresponded in the 3-dimensional image model
Into a curved surface, while the hidden average gray value for splitting detection image is input to the 3-D view mould in the step S12
In type, a plane is correspondingly formed in the 3-dimensional image model;S16, the three-dimensional graphical model obtained according to step S15,
Filter out and reach region more than threshold value less than the plane and both difference on the curved surface, judge the region for it is hidden split it is scarce
Fall into region;S17, acquisition hidden the hidden of defect area that split split defect parameters, and hidden according to step S11 foundation splits classification standard,
Judge that each hidden the hidden of defect area that split splits defect rank.
Preferably, the hidden defect parameters of splitting include the hidden length for splitting defect, the hidden width for splitting defect and hidden split defect
Area.
Preferably, it is described it is hidden split detection image carried out for the photovoltaic module to be measured under dark surrounds it is electroluminescent near
Infrared image.
Preferably, the step S11 also splits detection image including collecting hidden the hidden of defect that split of typical case, and the hidden defect of splitting is examined
Survey method also includes step S18:Typical hidden the hidden of defect that split collected according to step S11 splits detection image, and comparison is described hidden to be split
Defect area, determine that hidden the hidden of defect area that split splits defect type.
The hidden method for splitting defect of photovoltaic module, including step are detected by 3-D view present invention also offers another kind
Suddenly:S21, collect it is existing it is hidden split defect parameters, establish and hidden split classification standard;S22, photovoltaic group to be measured represented with the numerical value of x-axis
The length of part, the width of photovoltaic module to be measured is represented with the numerical value of y-axis, current density is represented with the numerical value of z-axis, with the x-axis,
Y-axis and z-axis establish 3-dimensional image model as reference axis;S23, detection simultaneously obtain the hidden of photovoltaic module to be measured and split detection image;
S24, calculate the hidden average current density for splitting detection image obtained;S25, by described hidden split each pixel in detection image
Corresponding actual current density is input in the 3-dimensional image model in the step S12, right in the 3-dimensional image model
A curved surface should be formed, while the hidden average current density for splitting detection image is input to the three-dimensional in the step S12
In iconic model, a plane is correspondingly formed in the 3-dimensional image model;S26, the 3-D graphic obtained according to step S25
Model, filter out and reach region more than threshold value less than the plane and both difference on the curved surface, judge that the region is
It is hidden to split defect area;S27, acquisition hidden the hidden of defect area that split split defect parameters, and hidden according to step S21 foundation splits grade
Standard, judge that each hidden the hidden of defect area that split splits defect rank.
Preferably, the hidden defect parameters of splitting include the hidden length for splitting defect, the hidden width for splitting defect and hidden split defect
Area.
Preferably, it is described it is hidden split detection image carried out for the photovoltaic module to be measured under dark surrounds it is electroluminescent near
Infrared image.
Preferably, the step S21 also splits detection image including collecting hidden the hidden of defect that split of typical case, and the hidden defect of splitting is examined
Survey method also includes step S28:Typical hidden the hidden of defect that split collected according to step S21 splits detection image, and comparison is described hidden to be split
Defect area, determine that hidden the hidden of defect area that split splits defect type.
The hidden method for splitting defect provided in an embodiment of the present invention that photovoltaic module is detected by 3-D view, first establishes hidden split
Classification standard, then the numerical value of reference axis is represented with the length and width of photovoltaic module to be measured and gray value or current density, establish graphics
As model, then actual grey corresponding to average gray value and each pixel is obtained from the hidden detection image of splitting of photovoltaic module to be measured
Value, and is entered into 3-dimensional image model, according to average gray value and the image of actual grey value, filters out and hidden splits defect
Region, the hidden grade for splitting defect is finally judged according to hidden classification standard of splitting.Judge hidden grade of splitting compared to by manually comparing
Mode, the hidden method for splitting defect of detection avoid error caused by subjective determination, and decision accuracy is high and judges efficiency high,
Save human resources.
Brief description of the drawings
Fig. 1 is walked in the hidden method for splitting defect by 3-D view detection photovoltaic module that the embodiment of the present invention 1 provides
The schematic diagram for the 3-dimensional image model that rapid S12 is established;
Fig. 2 is the stream for the hidden method for splitting defect that photovoltaic module is detected by 3-D view that the embodiment of the present invention 1 provides
Cheng Tu;
Fig. 3 is the stream for the hidden method for splitting defect that photovoltaic module is detected by 3-D view that the embodiment of the present invention 2 provides
Cheng Tu.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the accompanying drawings to the specific reality of the present invention
The mode of applying is described in detail.The example of these preferred embodiments is illustrated in the accompanying drawings.Shown in accompanying drawing and according to
What the embodiments of the present invention of accompanying drawing description were merely exemplary, and the present invention is not limited to these embodiments.
Here, it should also be noted that, in order to avoid having obscured the present invention because of unnecessary details, in the accompanying drawings only
Show with according to the solution of the present invention closely related structure and/or processing step, and eliminate relation it is little other are thin
Section.
Embodiment 1
Refering to shown in Fig. 1 and Fig. 2, present embodiments provide it is a kind of by 3-D view detect the hidden of photovoltaic module split defect
Method, including step:S11, collect it is existing it is hidden split defect parameters, establish and hidden split classification standard;S12, the numerical value generation with x-axis
The length of table photovoltaic module to be measured, the width of photovoltaic module to be measured is represented with the numerical value of y-axis, and gray value is represented with the numerical value of z-axis,
Using the x-axis, y-axis and z-axis 3-dimensional image model is established as reference axis;S13, detection simultaneously obtain the hidden of photovoltaic module to be measured and split
Detection image;S14, calculate the hidden average gray value for splitting detection image obtained;S15, hidden split described in detection image
Actual grey value corresponding to each pixel is input in the 3-dimensional image model in the step S12, in the 3-D view mould
A curved surface is correspondingly formed in type, while the hidden average gray value for splitting detection image is input in the step S12
In 3-dimensional image model, a plane is correspondingly formed in the 3-dimensional image model;S16, the three-dimensional obtained according to step S15
Graphical model, filter out and reach region more than threshold value less than the plane and both difference on the curved surface, judge the area
Defect area is split to be hidden in domain;S17, acquisition hidden the hidden of defect area that split split defect parameters, according to hidden the splitting of step S11 foundation
Classification standard, judge that each hidden the hidden of defect area that split splits defect rank.
Specifically, in the step S11, the hidden defect parameters of splitting include the hidden length for splitting defect, the hidden width for splitting defect
Degree and the hidden area for splitting defect.I.e. it is described it is hidden split classification standard be the comprehensive hidden length for splitting defect, the hidden width for splitting defect with
And the hidden area for splitting defect this three parameters, it is different to size hidden to split defect and be classified.
Specifically, in the step S11, first pass through inputted into computer it is existing it is hidden split defect parameters, establish hidden split
Classification standard, according to it is described it is hidden split classification standard write it is hidden split defects detection software, it is described hidden to split the follow-up of defect inspection method
Step is completed in hidden split in defects detection software.Further, in the step S12, by hidden splitting defect to described
The size and number of the cell piece of photovoltaic module to be measured are inputted in inspection software, computer calculates the reality of photovoltaic module to be measured
Area, photovoltaic module to be measured is obtained in the hidden simulative display size split in defects detection software interface and photovoltaic module to be measured
Actual size between scaling, in the hidden length for splitting the image shown in defects detection soft interface, width and the face
Product equidimension, all corresponding actual size size can be calculated with scaling by computer.
It is described hidden to split specific hidden defect parameters scope of splitting corresponding to each classification of classification standard and all answer root in the present embodiment
Set according to test environment and actual mass requirement, similarly, threshold corresponding with the difference of the plane on the curved surface
Value, it should also set according to test environment and actual mass requirement.
Specifically, it is described it is hidden split detection image carried out for the photovoltaic module to be measured under dark surrounds it is electroluminescent near
Infrared image.In the step S12, there is provided CCD (Charge Coupled Device, a charge coupling device) camera, institute
State photovoltaic module carried out under dark surrounds electroluminescent near-infrared image by the computer control CCD camera clapped
Take the photograph acquisition.Specifically, using electroluminescent tester (Electroluminescent Tester, EL tester) to the light
The hidden defect of splitting of volt component is detected, and the electroluminescent tester is connected and led to the photovoltaic module under dark surrounds
Electricity, the photovoltaic module is set to occur electroluminescent, the higher CCD phases of the computer control resolution of the electroluminescent tester
Machine is shot to photovoltaic module, and the CCD camera carries out under dark surrounds the photovoltaic module of acquisition electroluminescent near
Infrared image is sent to computer, is obtained the hidden of photovoltaic module to be measured and is split detection image.
Specifically, in the step S12, the length of photovoltaic module to be measured is represented with x-axis, photovoltaic module to be measured is represented with y-axis
Width, gray value is represented with z-axis, orthogonal coordinate system is first established as reference axis using the x-axis, y-axis and z-axis, by described orthogonal
Coordinate system forms 3-dimensional image model.In the step S15, hidden actual ash corresponding to each pixel is split in detection image by described
Angle value is input in the 3-dimensional image model in the step S12, i.e., fastens to draw in the orthogonal coordinates and described hidden split detection
Point corresponding to the actual grey value of each pixel of image, it is relatively described that projection of this in x-axis and y-axis represents the pixel
The coordinate of orthogonal coordinate system origin, projection of this in z-axis represent the actual grey value of the pixel, and these points are connected
Come, form three-dimensional waveform figure, it is a curved surface to be reflected in the 3-dimensional image model;Simultaneously by the hidden detection image split
When average gray value is input in the 3-dimensional image model in the step S12, it is correspondingly formed in the 3-dimensional image model
One perpendicular to z-axis plane.In the step S16, the curved surface and the difference of the plane, refer to some on the curved surface
The difference of the corresponding gray value in x-axis and y-axis between the equal pixel of projection values in pixel and the plane, i.e., when both
The difference of gray value is more than the threshold value of setting, you can judges that the pixel on curved surface corresponds to the position of photovoltaic module to be measured and belongs to hidden
Defect area is split, the position that several continuous described pixels correspond to photovoltaic module to be measured just constitutes and described hidden splits defect area
Domain.
Specifically, the step S11 also splits detection image including collecting hidden the hidden of defect that split of typical case, and the hidden defect of splitting is examined
Survey method also includes step S18:Typical hidden the hidden of defect that split collected according to step S11 splits detection image, and comparison is described hidden to be split
Defect area, determine that hidden the hidden of defect area that split splits defect type.Because hidden defect of splitting can be divided into according to parameters such as shapes
Different types, such as German ISFH research institutes propose:According to the hidden shape split of cell piece, can fall into 5 types:It is tree-shaped crackle, comprehensive
Mould assembly crackle, shear crack, the crackle parallel to main gate line, perpendicular to grid line and through whole cell piece.The present embodiment can pass through
The hidden detection image of splitting of each cell piece is compared with the hidden hidden detection image of splitting for splitting defect of typical case, so as to further determine that
The hidden type for splitting defect in each cell piece.
The hidden method for splitting defect of the detection can pass through statistics after completing to split hidden on each cell piece and being classified
The hidden quantity for splitting defect at different levels in the photovoltaic module, hidden according to these data judging photovoltaic modulies entirety split the serious of defect
Degree, or the photovoltaic module hidden quantity for splitting defect at different levels are judged whether in the range of qualified photovoltaic module is allowed,
It that is to say and whether qualified evaluation is made in hidden split in standard to the photovoltaic module.
Embodiment 2
As shown in figure 3, present invention also offers it is a kind of by 3-D view detect photovoltaic module the hidden method for splitting defect,
Including step:S21, collect it is existing it is hidden split defect parameters, establish and hidden split classification standard;S22, represented with the numerical value of x-axis it is to be measured
The length of photovoltaic module, the width of photovoltaic module to be measured is represented with the numerical value of y-axis, current density is represented with the numerical value of z-axis, with institute
State x-axis, y-axis and z-axis and establish 3-dimensional image model as reference axis;S23, detection simultaneously obtain the hidden of photovoltaic module to be measured and split detection
Image;S24, calculate the hidden average current density for splitting detection image obtained;S25, by it is described it is hidden split in detection image it is each
Actual current density corresponding to individual pixel is input in the 3-dimensional image model in the step S12, in the 3-D view mould
A curved surface is correspondingly formed in type, while the hidden average current density for splitting detection image is input in the step S12
3-dimensional image model in, a plane is correspondingly formed in the 3-dimensional image model;S26, three obtained according to step S25
Graphical model is tieed up, filters out and reaches region more than threshold value less than the plane and both difference on the curved surface, judging should
Defect area is split to be hidden in region;S27, acquisition hidden the hidden of defect area that split split defect parameters, are established according to step S21 hidden
Classification standard is split, judges that each hidden the hidden of defect area that split splits defect rank.
The hidden method for splitting defect of detection that the present embodiment provides, which is that the detection based on the offer of embodiment 1 is hidden, splits defect method,
The average gray value for detecting key element is replaced by average current density, and actual grey value is replaced by actual current density, its
Remaining content can refer to embodiment 1 and realize.
Reference implementation example 1, similarly, in the present embodiment, the hidden defect parameters of splitting include the hidden length for splitting defect, hidden split
The width of defect and the hidden area for splitting defect.
Similarly, it is described it is hidden split detection image carried out for the photovoltaic module to be measured under dark surrounds it is electroluminescent near
Infrared image.
In the present embodiment, the step S21, which also includes collecting hidden the hidden of defect that split of typical case, splits detection image, it is described it is hidden split it is scarce
Sunken detection method also includes step S28:Typical hidden the hidden of defect that split collected according to step S21 splits detection image, described in comparison
It is hidden to split defect area, determine that hidden the hidden of defect area that split splits defect type.
In summary, the hidden method for splitting defect provided by the invention that photovoltaic module is detected by 3-D view, is first established
It is hidden to split classification standard, then the numerical value of reference axis is represented with the length and width of photovoltaic module to be measured and gray value or current density, establish three
Iconic model is tieed up, then obtains reality corresponding to average gray value and each pixel from the hidden detection image of splitting of photovoltaic module to be measured
Gray value, and be entered into 3-dimensional image model, according to average gray value and the image of actual grey value, filter out hidden split
Defect area, the hidden grade for splitting defect is finally judged according to hidden classification standard of splitting.Judge hidden split compared to by manually comparing
The mode of level, the hidden method for splitting defect of detection avoid error caused by subjective determination, and decision accuracy is high and judges effect
Rate is high, saves human resources.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Other identical element also be present in process, method, article or equipment including the key element.
Described above is only the embodiment of the application, it is noted that for the ordinary skill people of the art
For member, on the premise of the application principle is not departed from, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as the protection domain of the application.
Claims (8)
- A kind of 1. hidden method for splitting defect that photovoltaic module is detected by 3-D view, it is characterised in that including step:S11, collect it is existing it is hidden split defect parameters, establish and hidden split classification standard;S12, the length for representing with the numerical value of x-axis photovoltaic module to be measured, the width of photovoltaic module to be measured is represented with the numerical value of y-axis, Gray value is represented with the numerical value of z-axis, 3-dimensional image model is established as reference axis using the x-axis, y-axis and z-axis;S13, detection simultaneously obtain the hidden of photovoltaic module to be measured and split detection image;S14, calculate the hidden average gray value for splitting detection image obtained;S15, by described hidden split actual grey value corresponding to each pixel in detection image and be input to the three-dimensional in the step S12 In iconic model, a curved surface is correspondingly formed in the 3-dimensional image model, while hidden split being averaged for detection image by described Gray value is input in the 3-dimensional image model in the step S12, and one is correspondingly formed in the 3-dimensional image model and is put down Face;S16, the three-dimensional graphical model obtained according to step S15, filter out on the curved surface less than the plane and both differences Value reaches region more than threshold value, judges that defect area is split in the region to be hidden;S17, acquisition hidden the hidden of defect area that split split defect parameters, and hidden according to step S11 foundation splits classification standard, judges Each hidden the hidden of defect area that split splits defect rank.
- 2. the hidden method for splitting defect according to claim 1 that photovoltaic module is detected by 3-D view, it is characterised in that The hidden defect parameters of splitting include the hidden length for splitting defect, the hidden width for splitting defect and the hidden area for splitting defect.
- 3. the hidden method for splitting defect according to claim 1 that photovoltaic module is detected by 3-D view, it is characterised in that The hidden detection image of splitting carries out electroluminescent near-infrared image for the photovoltaic module to be measured under dark surrounds.
- 4. according to any described hidden methods for splitting defect that photovoltaic module is detected by 3-D view of claim 1-3, it is special Sign is, the step S11 also includes collecting hidden the hidden of defect that split of typical case and splits detection image, described hidden to split defect inspection method also Including step S18:Typical hidden the hidden of defect that split collected according to step S11 splits detection image, comparison it is described it is hidden split defect area, Determine that hidden the hidden of defect area that split splits defect type.
- A kind of 5. hidden method for splitting defect that photovoltaic module is detected by 3-D view, it is characterised in that including step:S21, collect it is existing it is hidden split defect parameters, establish and hidden split classification standard;S22, the length for representing with the numerical value of x-axis photovoltaic module to be measured, the width of photovoltaic module to be measured is represented with the numerical value of y-axis, Current density is represented with the numerical value of z-axis, 3-dimensional image model is established as reference axis using the x-axis, y-axis and z-axis;S23, detection simultaneously obtain the hidden of photovoltaic module to be measured and split detection image;S24, calculate the hidden average current density for splitting detection image obtained;S25, by it is described it is hidden split actual current density corresponding to each pixel in detection image and be input in the step S22 three Tie up in iconic model, be correspondingly formed a curved surface in the 3-dimensional image model, while hidden the flat of detection image is split by described Equal current density is input in the 3-dimensional image model in the step S22, and one is correspondingly formed in the 3-dimensional image model Individual plane;S26, the three-dimensional graphical model obtained according to step S25, filter out on the curved surface less than the plane and both differences Value reaches region more than threshold value, judges that defect area is split in the region to be hidden;S27, acquisition hidden the hidden of defect area that split split defect parameters, and hidden according to step S21 foundation splits classification standard, judges Each hidden the hidden of defect area that split splits defect rank.
- 6. the hidden method for splitting defect according to claim 5 that photovoltaic module is detected by 3-D view, it is characterised in that The hidden defect parameters of splitting include the hidden length for splitting defect, the hidden width for splitting defect and the hidden area for splitting defect.
- 7. the hidden method for splitting defect according to claim 5 that photovoltaic module is detected by 3-D view, it is characterised in that The hidden detection image of splitting carries out electroluminescent near-infrared image for the photovoltaic module to be measured under dark surrounds.
- 8. according to any described hidden methods for splitting defect that photovoltaic module is detected by 3-D view of claim 5-7, it is special Sign is, the step S21 also includes collecting hidden the hidden of defect that split of typical case and splits detection image, described hidden to split defect inspection method also Including step S28:Typical hidden the hidden of defect that split collected according to step S21 splits detection image, comparison it is described it is hidden split defect area, Determine that hidden the hidden of defect area that split splits defect type.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710902452.2A CN107607548A (en) | 2017-09-29 | 2017-09-29 | The hidden method for splitting defect of photovoltaic module is detected by 3-D view |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710902452.2A CN107607548A (en) | 2017-09-29 | 2017-09-29 | The hidden method for splitting defect of photovoltaic module is detected by 3-D view |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107607548A true CN107607548A (en) | 2018-01-19 |
Family
ID=61058062
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710902452.2A Pending CN107607548A (en) | 2017-09-29 | 2017-09-29 | The hidden method for splitting defect of photovoltaic module is detected by 3-D view |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107607548A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109540900A (en) * | 2018-09-25 | 2019-03-29 | 浙江浙能技术研究院有限公司 | A kind of photovoltaic module crack determination method |
CN112419486A (en) * | 2020-12-02 | 2021-02-26 | 广州粤芯半导体技术有限公司 | Three-dimensional reconstruction method for photoresist morphology |
CN112700423A (en) * | 2021-01-06 | 2021-04-23 | 中国民航科学技术研究院 | Method and system for automatically detecting surface damage defects of fuselage based on deep learning |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201440127U (en) * | 2009-03-24 | 2010-04-21 | 陕西众森电能科技有限公司 | Defect detection device for solar cells and modules |
CN102017191A (en) * | 2008-03-31 | 2011-04-13 | Bt成像股份有限公司 | Wafer imaging and processing method and apparatus |
CN103022219A (en) * | 2011-09-20 | 2013-04-03 | 苏州索力旺光伏设备有限公司 | Photovoltaic assembly quality automatic detection method |
JP2015038466A (en) * | 2013-07-16 | 2015-02-26 | 株式会社キーエンス | Three-dimensional image processing apparatus, three-dimensional image processing method, three-dimensional image processing program, computer-readable recording medium, and device for storage |
CN104713887A (en) * | 2015-03-19 | 2015-06-17 | 中信戴卡股份有限公司 | Planar flaw detecting method |
CN105021628A (en) * | 2015-07-19 | 2015-11-04 | 中北大学 | Detection method for surface defects of optical fiber image inverter |
CN106990120A (en) * | 2017-05-02 | 2017-07-28 | 河北大学 | The quality determining method and its detection means of a kind of solar battery sheet |
-
2017
- 2017-09-29 CN CN201710902452.2A patent/CN107607548A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102017191A (en) * | 2008-03-31 | 2011-04-13 | Bt成像股份有限公司 | Wafer imaging and processing method and apparatus |
CN201440127U (en) * | 2009-03-24 | 2010-04-21 | 陕西众森电能科技有限公司 | Defect detection device for solar cells and modules |
CN103022219A (en) * | 2011-09-20 | 2013-04-03 | 苏州索力旺光伏设备有限公司 | Photovoltaic assembly quality automatic detection method |
JP2015038466A (en) * | 2013-07-16 | 2015-02-26 | 株式会社キーエンス | Three-dimensional image processing apparatus, three-dimensional image processing method, three-dimensional image processing program, computer-readable recording medium, and device for storage |
CN104713887A (en) * | 2015-03-19 | 2015-06-17 | 中信戴卡股份有限公司 | Planar flaw detecting method |
CN105021628A (en) * | 2015-07-19 | 2015-11-04 | 中北大学 | Detection method for surface defects of optical fiber image inverter |
CN106990120A (en) * | 2017-05-02 | 2017-07-28 | 河北大学 | The quality determining method and its detection means of a kind of solar battery sheet |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109540900A (en) * | 2018-09-25 | 2019-03-29 | 浙江浙能技术研究院有限公司 | A kind of photovoltaic module crack determination method |
CN112419486A (en) * | 2020-12-02 | 2021-02-26 | 广州粤芯半导体技术有限公司 | Three-dimensional reconstruction method for photoresist morphology |
CN112700423A (en) * | 2021-01-06 | 2021-04-23 | 中国民航科学技术研究院 | Method and system for automatically detecting surface damage defects of fuselage based on deep learning |
CN112700423B (en) * | 2021-01-06 | 2023-05-05 | 中国民航科学技术研究院 | Deep learning-based automatic detection method and system for surface damage defects of airframe |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107764832A (en) | The hidden of photovoltaic module splits defect inspection method | |
CN102508110B (en) | Texture-based insulator fault diagnostic method | |
CN104504388B (en) | A kind of pavement crack identification and feature extraction algorithm and system | |
CN107274393B (en) | Monocrystaline silicon solar cell piece detection method of surface flaw based on grid line detection | |
CN102136061B (en) | Method for automatically detecting, classifying and identifying defects of rectangular quartz wafer | |
CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
CN107607548A (en) | The hidden method for splitting defect of photovoltaic module is detected by 3-D view | |
CN107845090A (en) | A kind of silicon chip detection method and silicon chip detection means | |
CN106990120A (en) | The quality determining method and its detection means of a kind of solar battery sheet | |
CN106238350A (en) | A kind of solar battery sheet method for separating based on machine vision and system | |
CN102621154B (en) | Method and device for automatically detecting cloth defects on line based on improved differential box multi-fractal algorithm | |
CN103778624A (en) | Fabric defect detection method based on optical threshold segmentation | |
Vivekananthan et al. | Concrete bridge crack detection by image processing technique by using the improved OTSU method | |
CN109001224A (en) | Welding seam detection method and detection device | |
CN104964886A (en) | Welded member fatigue stress and strain real-time non-contact type monitoring method | |
CN103630093B (en) | Image analysis method for concrete surface roughness measurement | |
CN110672623A (en) | Geometric appearance defect detection method for solar cell | |
CN110174404A (en) | A kind of online defect detecting device of powder and system | |
CN108509696A (en) | Ancient building health monitoring method and device based on three-dimensional laser scanning technology | |
CN101696877A (en) | On-line detection method of machine vision system to spring verticality | |
CN104315977A (en) | Rubber plug quality detection device and method | |
CN103245666B (en) | Automatic detecting method for appearance defects of storage battery polar plate | |
CN110310275A (en) | A kind of chain conveyor defect inspection method based on image procossing | |
CN101726265A (en) | Online detection method of parallelism of spring by machine vision system |
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 |
Application publication date: 20180119 |
|
RJ01 | Rejection of invention patent application after publication |