CN111242914B - Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm - Google Patents
Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm Download PDFInfo
- Publication number
- CN111242914B CN111242914B CN202010022375.3A CN202010022375A CN111242914B CN 111242914 B CN111242914 B CN 111242914B CN 202010022375 A CN202010022375 A CN 202010022375A CN 111242914 B CN111242914 B CN 111242914B
- Authority
- CN
- China
- Prior art keywords
- photovoltaic module
- hot spot
- pane
- area
- linear regression
- 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
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10048—Infrared 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
- 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
- Y02E10/50—Photovoltaic [PV] energy
Abstract
The invention discloses a photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm, which specifically comprises the following steps: the invention relates to the technical field of inspection of a photovoltaic power generation system, in which S1, converting an RGB image into a gray level map, S2, using a contour recognition algorithm to recognize the contour of a bright spot in the image, calculating the area of the bright spot, comparing a threshold value to determine a hot plate area, S3, recognizing internal grid lines and boundaries of a photovoltaic module to position the hot spot of the photovoltaic module, S4, displaying in a thermodynamic diagram mode, recognizing the internal grid lines of the photovoltaic panel by utilizing pane detection, S5, recognizing the upper edge and the lower edge of the panel by utilizing the inconsistency of data distribution at two sides of the boundary line of the panel, and S6, smoothing the boundaries by adopting linear regression. The method well solves the problems of low manual analysis efficiency and inaccuracy of the existing unmanned aerial vehicle photovoltaic inspection picture, greatly improves the fault detection efficiency and accuracy of the photovoltaic module, and reduces the labor cost.
Description
Technical Field
The invention relates to the technical field of inspection of photovoltaic power generation systems, in particular to a photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm.
Background
With the wide use of unmanned aerial vehicle in photovoltaic inspection, photovoltaic panel's fault detection's efficiency improves greatly, unmanned aerial vehicle carries on the high definition digtal camera and continuously returns tens of thousands of photovoltaic panel's photos in real time, rely on the manual work to accomplish accurately, timely processing, need the computer to detect the defect in real time, when photovoltaic panel breaks down, because the mismatch of electric current and voltage can consume a large amount of electric energy and generate heat in fault region and nearby, luminance is higher than normal position on infrared image, this kind of phenomenon is called "hot spot", develop the discernment of a hot spot and positioning algorithm to photovoltaic panel's fault detection have very important meaning.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm, which solves the problem that a photovoltaic panel infrared image transmitted back by unmanned aerial vehicle photovoltaic inspection cannot be accurately identified in real time by manpower, and the intelligent identification and positioning of the faults of the photovoltaic module are realized by carrying out real-time detection on the photovoltaic module by applying a computer, thereby improving the hot spot detection efficiency and quality of the photovoltaic module.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: the photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm specifically comprises the following steps:
s1, converting an RGB image into a gray scale image, wherein hot spots are embodied in the gray scale image in a bright spot form;
s2, identifying the hot spot area accurately, identifying the outline of the bright spot in the picture by using an outline identification algorithm, calculating the area of the bright spot, and when the area is larger than a set threshold value, reserving the outline of the bright spot, regarding the outline as the hot spot area, and calculating the center point of the hot spot area;
s3, identifying internal grid lines and boundaries of the photovoltaic module, and positioning hot spots of the photovoltaic module;
s4, converting an original image into a gray image by a calculation mode of internal grid lines, then introducing an obtained gray array into excel, and then displaying by a thermodynamic diagram mode, wherein gray values at grid lines belong to smaller values in a row direction, each point on the photovoltaic module is expanded into 4 elements forwards and backwards to form a transverse or longitudinal pane, at the moment, the value at the central point of the pane is the minimum value of the whole grid center, and the longitudinal or transverse grid lines can be correctly identified;
s5, a large number of scattered points exist in the gray level map in the area outside the photovoltaic panel, the upper edge and the lower edge of the panel are identified by utilizing the inconsistency of data distribution at two sides of a boundary line of the panel, one point is selected as the center, 5 points are respectively expanded up and down to form a pane, the sum of the upper 5 values and the sum of the lower 5 values are calculated to respectively represent the panel area and the ground area, the difference between the panel area and the ground area is calculated, the point in the image is traversed by using a complaint algorithm, and the maximum difference is regarded as the boundary line;
s6, recognizing the phenomenon that local points have 'dislocation jumping' aiming at boundary lines of the photovoltaic panel, adopting linear regression to carry out smoothing treatment on the boundary, and fitting all the recognized boundary points into a straight line by using linear regression, wherein the fitted straight line is the lower boundary line.
Preferably, in the step S1, noise points such as reflection of the battery component exist on the gray scale.
Preferably, in the step S2, when the area is greater than the set threshold, the contour of the bright spot is remained and is regarded as a hot spot area, so as to reduce the noise influence in the gray scale map and accurately identify the hot spot area.
Preferably, the pane detection method in step S4 can accurately identify the grid lines inside the photovoltaic module.
Preferably, the pane detection method in step S5 is capable of identifying a photovoltaic panel boundary line.
Preferably, in the step S6, the boundary line recognition local point of the photovoltaic panel has a phenomenon of "dislocation and jump", and the boundary is smoothed by adopting linear regression, so as to improve the accuracy of the boundary recognition of the photovoltaic panel.
(III) beneficial effects
The invention provides a photovoltaic module hot spot defect positioning method based on pane detection and a linear regression algorithm. Compared with the prior art, the method has the following beneficial effects: the photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm specifically comprises the following steps: s2, identifying the outline of the bright spot in the picture by using a contour identification algorithm, calculating the area of the bright spot, reserving the outline of the bright spot when the area is larger than a set threshold, regarding the outline as the hot spot area, calculating the center point of the hot spot area, S3, identifying the internal grid lines and the boundary of the photovoltaic module to position the hot spot of the photovoltaic module, S4, calculating the internal grid lines, converting the original picture into the gray image, then introducing the obtained gray array into excel, displaying by adopting a thermodynamic diagram mode, S5, identifying the upper edge and the lower edge of the panel by utilizing the inconsistency of data distribution at two sides of the boundary line of the panel when the area is larger than the set threshold, S6, identifying the phenomenon of 'off-node jumping' of the local point aiming at the boundary line of the photovoltaic panel, the linear regression is adopted to carry out smoothing treatment on the boundary, all the identified boundary points are fitted into a straight line by using the linear regression, the fitted straight line is the lower boundary line, the problems of low manual analysis efficiency and inaccuracy of the conventional unmanned aerial vehicle photovoltaic inspection picture are well solved, the intelligent recognition and positioning of the hot spot defect of the photovoltaic module are realized by designing the photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm, which can be applied to a computer, the fault detection efficiency and accuracy of the photovoltaic module are greatly improved, the labor cost is reduced, the condition that the infrared image of the photovoltaic panel returned by the unmanned aerial vehicle photovoltaic inspection cannot be accurately recognized in real time is avoided, the real-time detection of the photovoltaic module is carried out by using the computer, the hot spot detection efficiency and quality of the photovoltaic module are improved, and the intelligent recognition and positioning of the faults of the photovoltaic module are realized.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is an effect diagram of converting RGB images into gray scale in the hot spot recognition process of the present invention;
FIG. 3 is a diagram of a hot spot area after the gray value extracted by the thresholding method is greater than a set threshold;
FIG. 4 is a schematic diagram of the hot spot positioning of the present invention;
FIG. 5 is an effect diagram of converting an original image into a gray image, then importing an obtained gray array into excel, and then displaying the gray array in a thermodynamic diagram mode;
FIG. 6 is a schematic depiction of the detection of grid lines within a photovoltaic panel in accordance with the present invention;
FIG. 7 is a graph showing the effect of the picture after identifying the grid lines inside the photovoltaic panel according to the present invention;
FIG. 8 is a schematic depiction of the detection of the upper and lower boundaries of a photovoltaic panel identified by the pane of the present invention;
FIG. 9 is a graph showing the effect of the picture after the upper and lower boundaries of the photovoltaic panel are identified;
fig. 10 is a graph showing the effect of the present invention after smoothing the boundary using linear regression.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-10, the embodiment of the invention provides a technical scheme: the photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm specifically comprises the following steps:
s1, converting an RGB image into a gray scale image, wherein hot spots are embodied in the gray scale image in the form of bright spots, and noise points such as reflection of a battery part exist on the gray scale image;
s2, accurately identifying the hot spot area, identifying the outline of the bright spot in the picture by using an outline identification algorithm, calculating the area of the bright spot, reserving the outline of the bright spot when the area is larger than a set threshold value, regarding the outline as the hot spot area, calculating the center point of the hot spot area, reducing the noise influence in the gray level map, and accurately identifying the hot spot area;
s3, identifying internal grid lines and boundaries of the photovoltaic module, and positioning hot spots of the photovoltaic module;
s4, converting an original image into a gray image by a calculation mode of internal grid lines, then importing an obtained gray array into excel, then displaying by a thermodynamic diagram mode, expanding each point on the photovoltaic module into 4 elements forwards and backwards respectively in the line direction of gray values at the grid lines to form a horizontal or longitudinal pane, wherein the value at the central point of the pane is the minimum value of the whole grid center, and the longitudinal or transverse grid lines can be accurately identified, and the internal grid lines of the photovoltaic module can be accurately identified by applying the pane detection method;
s5, a large number of scattered points exist in the gray level map in the area outside the photovoltaic panel, the upper edge and the lower edge of the panel are identified by utilizing the inconsistency of data distribution at two sides of a boundary line of the panel, one point is selected as the center, 5 points are respectively expanded up and down to form a pane, the sum of the upper 5 values and the sum of the lower 5 values are calculated to respectively represent the panel area and the ground area, the difference between the upper 5 values and the lower 5 values is calculated to respectively represent the panel area and the ground area, the point in the image is traversed by using a complaint algorithm, the maximum difference is regarded as the boundary line, and the boundary line of the photovoltaic panel can be identified by applying the pane detection method;
s6, aiming at the phenomenon that the partial points are separated from each other and jump is recognized by the boundary line of the photovoltaic panel, smoothing is carried out on the boundary by adopting linear regression, all the recognized boundary points are fitted into a straight line by using linear regression, the fitted straight line is the lower boundary line, and the accuracy of recognizing the boundary of the photovoltaic panel is improved.
Fig. 3 is an image of a photovoltaic panel with large-area hot spots and a battery part reflecting light, wherein the gray value extracted by the threshold method is larger than a set threshold value, and the hot spots larger than the threshold value are reserved, namely a hot spot area.
Fig. 4 is a diagram illustrating the principle of hot spot positioning, i.e. which cell the hot spot is on the photovoltaic module.
In conclusion, the invention well solves the problems of low manual analysis efficiency and inaccuracy of the existing unmanned aerial vehicle photovoltaic inspection picture, and by designing the photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm, which can be applied to a computer, the intelligent recognition and positioning of the photovoltaic module hot spot defect are realized, the fault detection efficiency and accuracy of the photovoltaic module are greatly improved, the labor cost is reduced, the condition that the infrared image of the photovoltaic panel returned by the unmanned aerial vehicle photovoltaic inspection cannot be accurately recognized in real time is avoided, the photovoltaic module is detected in real time by using the computer, the hot spot detection efficiency and quality of the photovoltaic module are improved, and the intelligent recognition and positioning of the photovoltaic module fault are realized.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. The photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm is characterized by comprising the following steps of: the method specifically comprises the following steps:
s1, converting an RGB image into a gray scale image, wherein hot spots are embodied in the gray scale image in a bright spot form;
s2, identifying the hot spot area accurately, identifying the outline of the bright spot in the picture by using an outline identification algorithm, calculating the area of the bright spot, and when the area is larger than a set threshold value, reserving the outline of the bright spot, regarding the outline as the hot spot area, and calculating the center point of the hot spot area;
s3, identifying internal grid lines and boundaries of the photovoltaic module, and positioning hot spots of the photovoltaic module;
s4, converting an original image into a gray image by a calculation mode of internal grid lines, then introducing an obtained gray array into excel, and then displaying by a thermodynamic diagram mode, wherein gray values at grid lines belong to smaller values in a row direction, each point on the photovoltaic module is expanded into 4 elements forwards and backwards to form a transverse or longitudinal pane, at the moment, the value at the central point of the pane is the minimum value of the whole grid center, and the longitudinal or transverse grid lines can be correctly identified;
s5, a large number of scattered points exist in the gray level map in the area outside the photovoltaic panel, the upper edge and the lower edge of the panel are identified by utilizing the inconsistency of data distribution at two sides of a boundary line of the panel, one point is selected as the center, 5 points are respectively expanded up and down to form a pane, the sum of the upper 5 values and the sum of the lower 5 values are calculated to respectively represent the panel area and the ground area, the difference between the panel area and the ground area is calculated, the point in the image is traversed by using a complaint algorithm, and the maximum difference is regarded as the boundary line;
s6, recognizing the phenomenon that local points have 'dislocation jumping' aiming at boundary lines of the photovoltaic panel, adopting linear regression to carry out smoothing treatment on the boundary, and fitting all the recognized boundary points into a straight line by using linear regression, wherein the fitted straight line is the lower boundary line.
2. The photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm according to claim 1, wherein the method is characterized by comprising the following steps of: in the step S1, noise points such as reflection of the photovoltaic panel assembly exist on the gray scale image.
3. The photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm according to claim 1, wherein the method is characterized by comprising the following steps of: the pane detection method in the step S4 can accurately identify the grid lines inside the photovoltaic module.
4. The photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm according to claim 1, wherein the method is characterized by comprising the following steps of: the pane detection method is applied in the step S5 to identify the boundary line of the photovoltaic panel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010022375.3A CN111242914B (en) | 2020-01-09 | 2020-01-09 | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010022375.3A CN111242914B (en) | 2020-01-09 | 2020-01-09 | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111242914A CN111242914A (en) | 2020-06-05 |
| CN111242914B true CN111242914B (en) | 2023-09-08 |
Family
ID=70880404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010022375.3A Active CN111242914B (en) | 2020-01-09 | 2020-01-09 | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242914B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113155288B (en) * | 2020-11-30 | 2022-09-06 | 齐鲁工业大学 | Image identification method for hot spots of photovoltaic cell |
| CN113781448B (en) * | 2021-09-14 | 2024-01-23 | 国电四子王旗光伏发电有限公司 | Intelligent defect identification method for photovoltaic power station assembly based on infrared image analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009026661A1 (en) * | 2007-08-30 | 2009-03-05 | Bt Imaging Pty Ltd | Photovoltaic cell manufacturing |
| WO2012019219A1 (en) * | 2010-08-09 | 2012-02-16 | Bt Imaging Pty Ltd | Persistent feature detection |
| CN106815838A (en) * | 2017-01-22 | 2017-06-09 | 晶科电力有限公司 | A kind of method and system of the detection of photovoltaic module hot spot |
| CN107314819A (en) * | 2017-07-03 | 2017-11-03 | 南京绿谷信息科技有限公司 | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image |
| CN108108736A (en) * | 2017-12-22 | 2018-06-01 | 晶科电力科技股份有限公司 | A kind of solar energy photovoltaic panel spot identification method |
| CN108986076A (en) * | 2018-06-15 | 2018-12-11 | 重庆大学 | A kind of photovoltaic array hot spot detection method based on PSO optimization PCNN |
| CN109241923A (en) * | 2018-09-18 | 2019-01-18 | 甘肃启远智能科技有限责任公司 | Photovoltaic module hot spot localization method and device |
| CN109584222A (en) * | 2018-11-19 | 2019-04-05 | 国网江西省电力有限公司电力科学研究院 | A kind of failure modes of the photovoltaic module image based on unmanned plane and discrimination method |
| WO2019214268A1 (en) * | 2018-05-09 | 2019-11-14 | 北京理工大学 | Photovoltaic array fault diagnosis method based on composite information |
-
2020
- 2020-01-09 CN CN202010022375.3A patent/CN111242914B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009026661A1 (en) * | 2007-08-30 | 2009-03-05 | Bt Imaging Pty Ltd | Photovoltaic cell manufacturing |
| WO2012019219A1 (en) * | 2010-08-09 | 2012-02-16 | Bt Imaging Pty Ltd | Persistent feature detection |
| CN106815838A (en) * | 2017-01-22 | 2017-06-09 | 晶科电力有限公司 | A kind of method and system of the detection of photovoltaic module hot spot |
| CN107314819A (en) * | 2017-07-03 | 2017-11-03 | 南京绿谷信息科技有限公司 | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image |
| CN108108736A (en) * | 2017-12-22 | 2018-06-01 | 晶科电力科技股份有限公司 | A kind of solar energy photovoltaic panel spot identification method |
| WO2019214268A1 (en) * | 2018-05-09 | 2019-11-14 | 北京理工大学 | Photovoltaic array fault diagnosis method based on composite information |
| CN108986076A (en) * | 2018-06-15 | 2018-12-11 | 重庆大学 | A kind of photovoltaic array hot spot detection method based on PSO optimization PCNN |
| CN109241923A (en) * | 2018-09-18 | 2019-01-18 | 甘肃启远智能科技有限责任公司 | Photovoltaic module hot spot localization method and device |
| CN109584222A (en) * | 2018-11-19 | 2019-04-05 | 国网江西省电力有限公司电力科学研究院 | A kind of failure modes of the photovoltaic module image based on unmanned plane and discrimination method |
Non-Patent Citations (1)
| Title |
|---|
| 徐庆 ; 张天文 ; 沈道军 ; 李春阳 ; 罗易 ; 周承军 ; .基于光伏电站排布设计数据的无人机热斑巡检系统方案.民营科技.2018,(02),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111242914A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021046951A1 (en) | Image identification method, system, and storage medium | |
| CN111242914B (en) | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm | |
| CN110533086B (en) | Semi-automatic image data labeling method | |
| CN113379703B (en) | Photovoltaic panel dark spot defect detection method based on Yolo-v4 network structure | |
| CN104537367A (en) | VIN code checking method | |
| CN110210060A (en) | The prediction technique of solar energy photovoltaic panel superficial dust degree | |
| CN117132844B (en) | Classifying method for cracks and scratches of photovoltaic panel based on image processing | |
| CN111709931B (en) | Automatic acquisition method and system for strain clamp defect detection and identification report | |
| CN114092454A (en) | Photovoltaic module EL detection method, device and storage medium | |
| CN116228670A (en) | Yolov 5-based photovoltaic defect detection method, device, computer equipment and medium | |
| CN110426395B (en) | Method and device for detecting surface of solar EL battery silicon wafer | |
| CN115690012A (en) | Detection method for wrong connection line of electric energy meter | |
| CN113837994B (en) | Photovoltaic panel defect diagnosis method based on edge detection convolutional neural network | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN105374029A (en) | Segmenting method and system of transformer substation equipment infrared image interest areas | |
| CN113989241A (en) | Photovoltaic module EL defect detection method based on image processing and deep learning fusion | |
| CN115830302B (en) | Multi-scale feature extraction fusion power distribution network equipment positioning identification method | |
| US20230042106A1 (en) | System and method for the statistical analysis of images of photovoltaic panels | |
| CN116030013A (en) | Multi-target multi-category damage defect detection method, system and computer storage medium | |
| CN114529543B (en) | Installation detection method and device for peripheral screw gasket of aero-engine | |
| CN114581407B (en) | Self-adaptive defect detection method for photovoltaic module | |
| CN103065296A (en) | High-resolution remote sensing image residential area extraction method based on edge feature | |
| CN115690505A (en) | Photovoltaic module fault detection method and device, computer equipment and storage medium | |
| Otamendi et al. | A scalable framework for annotating photovoltaic cell defects in electroluminescence images | |
| CN115239002A (en) | New energy distributed photovoltaic power station monitoring and early warning system and method |
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 | ||
| CB02 | Change of applicant information |
Address after: 401-406, Building A, Shuguang Software Park, No. 1, Guanshan 1st Road, Donghu New Technology Development Zone, Wuhan, Hubei 430000 Applicant after: Wuhan Saimo Bosheng Information Technology Co.,Ltd. Address before: 401-406, Building A, Shuguang Software Park, No. 1, Guanshan 1st Road, Donghu New Technology Development Zone, Wuhan, Hubei 430000 Applicant before: WUHAN BOSHENG INFORMATION TECHNOLOGY CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |