CN118096748A - Fault detection method and system for photovoltaic array - Google Patents
Fault detection method and system for photovoltaic array Download PDFInfo
- Publication number
- CN118096748A CN118096748A CN202410501104.4A CN202410501104A CN118096748A CN 118096748 A CN118096748 A CN 118096748A CN 202410501104 A CN202410501104 A CN 202410501104A CN 118096748 A CN118096748 A CN 118096748A
- Authority
- CN
- China
- Prior art keywords
- image
- threshold
- photovoltaic panel
- gray value
- abnormal region
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 58
- 238000000034 method Methods 0.000 claims abstract description 31
- 230000011218 segmentation Effects 0.000 claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000002146 bilateral effect Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention provides a fault detection method and system for a photovoltaic array, and belongs to the technical field of fault detection; the infrared image and the P-V curve data of the photovoltaic array are obtained, the infrared image is processed through a three-threshold method, the whole image of the photovoltaic array assembly can be cut out through one-time segmentation, and the information at the edges and four corners of the image is completely reserved, so that the image area of the photovoltaic panel is reserved; the more accurate abnormal region range can be obtained through secondary segmentation; the area ratio of the abnormal area range on the photovoltaic panel is calculated through the obtained abnormal area range and the corresponding photovoltaic panel image, the power ratio of the current moment and the historical data of the photovoltaic panel is obtained, and the type of the abnormal area range image can be accurately identified through calculating the error rate between the area ratio and the power ratio, so that the misjudgment problem caused by environmental factors such as solar reflection is avoided.
Description
Technical Field
The invention belongs to the technical field of fault detection, and particularly relates to a fault detection method and system for a photovoltaic array.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Photovoltaic devices are increasingly used in the field of new energy, and in the operation process of a photovoltaic array, fault diagnosis and positioning of the photovoltaic array are important to improving photovoltaic power generation efficiency and device maintenance.
At present, common methods for detecting faults of a photovoltaic array are divided into two types, namely electrical characteristic analysis and image analysis; for the image analysis method, in the conventional technical means, the obtained photovoltaic array infrared image is generally used for processing, and hot spots on a fault photovoltaic panel in the image are identified, so that the distribution positions of the fault photovoltaic panel and the photovoltaic panel are determined. When the method is used for fault detection, only factors of the photovoltaic array are considered, and the influence of external environmental factors on the photovoltaic array is not considered; in the detection process, the reflection of sunlight can cause the local temperature rising phenomenon of the photovoltaic array in the infrared image, and in the process of identifying the infrared image of the photovoltaic array, the local temperature rising area can be misjudged as hot spots, and finally misjudgment of fault detection of the photovoltaic array is caused.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a fault detection method and a fault detection system for a photovoltaic array, which are used for dividing an infrared image by a three-threshold dividing method to obtain an abnormal region range image and a photovoltaic panel dividing image, reserving image information of the edge and four corners of the photovoltaic panel and accurately dividing an abnormal region; and the area ratio of the abnormal area range on the corresponding photovoltaic panel is calculated and combined with the power data in the P-V curve data to output a final result, so that the recognition accuracy of the photovoltaic array faults is improved.
To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
A first aspect of the present invention provides a fault detection method for a photovoltaic array, comprising the steps of:
Acquiring an infrared image and P-V curve data of a photovoltaic array, and preprocessing the P-V curve data;
Dividing the infrared image by a three-threshold dividing method to obtain an abnormal region range image and a photovoltaic panel dividing image;
And inputting the abnormal region range image, the corresponding photovoltaic panel segmentation image and the P-V curve data into the BP neural network, calculating the area occupation ratio of the abnormal region range on the corresponding photovoltaic panel, and outputting a final result by combining the P-V curve data.
As an implementation manner, the method for dividing the infrared image by the three-threshold dividing method specifically includes that bilateral filtering processing is firstly carried out on the infrared image, edge points of the image are obtained, a first threshold is obtained based on the obtained edge points, and dividing is carried out through the first threshold, so that a photovoltaic panel divided image is obtained; and performing secondary segmentation based on the photovoltaic panel segmentation image to obtain an abnormal region range image.
In one embodiment, the image is divided into two parts based on the photovoltaic panel, and the abnormal region range image is obtained by taking a first threshold value and an image pixel maximum value as gray value intervals, wherein two gray values with different sizes are contained in the gray value intervals, and the gray value intervals are divided into a first interval, a second interval and a third interval; and determining the values of two gray values with different sizes based on a threshold function, taking the determined small gray value as a second threshold, taking the determined large gray value as a third threshold, and cutting through the third threshold to obtain an abnormal region range image.
As one embodiment, the threshold function is specifically:
Wherein, Is of small gray value,/>Is a large gray value,/>The area ratio occupied by the image for the i-th section portion,For the gray value of the i-th interval part,/>Is the gray value average value.
As an implementation manner, the final result of the combination of the P-V curve data output is specifically that the average power of the power in the P-V curve data of the current photovoltaic panel is calculated and compared with the average power in the normal state of the photovoltaic panel to obtain the power ratio; and comparing the power ratio with the acquired area ratio, and outputting a final result according to the comparison result.
A second aspect of the invention provides a fault detection system for a photovoltaic array, comprising:
The data acquisition module acquires an infrared image and P-V curve data of the photovoltaic array, and preprocesses the P-V curve data;
The image segmentation module is used for segmenting the infrared image by a three-threshold segmentation method to obtain an abnormal region range image and a photovoltaic panel segmented image;
the fault identification module is used for inputting the abnormal region range image, the corresponding photovoltaic panel segmentation image and the P-V curve data into the BP neural network, calculating the area occupation ratio of the abnormal region range on the corresponding photovoltaic panel, and outputting a final result by combining the P-V curve data.
As an implementation manner, the method for dividing the infrared image by the three-threshold dividing method specifically includes that bilateral filtering processing is firstly carried out on the infrared image, edge points of the image are obtained, a first threshold is obtained based on the obtained edge points, dividing is carried out through the first threshold, a photovoltaic panel divided image is obtained, secondary dividing is carried out based on the photovoltaic panel divided image, and an abnormal region range image is obtained.
In one embodiment, the image is divided into two parts based on the photovoltaic panel, and the abnormal region range image is obtained by taking a first threshold value and an image pixel maximum value as gray value intervals, wherein two gray values with different sizes are contained in the gray value intervals, and the gray value intervals are divided into a first interval, a second interval and a third interval; and determining the values of two gray values with different sizes based on a threshold function, taking the determined small gray value as a second threshold, taking the determined large gray value as a third threshold, and cutting through the third threshold to obtain an abnormal region range image.
In a third aspect of the invention, an electronic device is provided, comprising a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement a fault detection method for a photovoltaic array as described above.
In a fourth aspect of the present invention, a computer readable storage medium is provided, storing at least one instruction that when executed by a processor implements a fault detection method for a photovoltaic array as described above.
The one or more of the above technical solutions have the following beneficial effects:
(1) The edge points of the image are obtained by carrying out bilateral filtering processing on the infrared image, the first threshold value is obtained by the edge points, and the photovoltaic panel segmented image is obtained by segmentation through the first threshold value, so that the edge and four corners of the photovoltaic panel in the image are complete, and the integrity of the area of the photovoltaic panel is ensured.
(2) Based on the abnormal region range image obtained by the secondary segmentation, the accurate abnormal region range can be obtained; by calculating the area ratio of the abnormal region range on the corresponding photovoltaic panel and combining the power data in the P-V curve data, the type of the abnormal region can be accurately judged, and the identification precision of the photovoltaic array faults is improved.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a step diagram of a fault detection method for a photovoltaic array according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a photovoltaic panel assembly according to an embodiment of the present invention.
Fig. 3 is a diagram showing meanings of the second threshold and the third threshold in the secondary segmentation according to the embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
Referring to fig. 1, the embodiment discloses a fault detection method for a photovoltaic array, which specifically includes the following steps:
S1, acquiring an infrared image and P-V curve data of a photovoltaic array, and preprocessing the P-V curve data.
In the embodiment, the infrared image of the photovoltaic array is acquired according to a thermal imager suspended by the unmanned aerial vehicle; the obtained P-V curve data comprise the P-V curve data of each photovoltaic panel in the photovoltaic array at the current moment and in the historical normal fault-free running state, and can be obtained through a P-V data detector.
And preprocessing the obtained P-V curve data by removing repeated data, processing missing values, abnormal values and the like.
S2, segmenting the infrared image by a three-threshold segmentation method to obtain an abnormal region range image and a photovoltaic panel segmented image.
And S201, performing bilateral filtering processing on the infrared image to obtain edge points of the image, obtaining a first threshold value based on the obtained edge points, and dividing the image by the first threshold value to obtain a photovoltaic panel divided image.
Before image segmentation, firstly, processing an infrared image through bilateral filtering to remove the blurring problem of the infrared image; considering that the gray values of the pixel points at two sides of the edge point of the target area are larger or smaller than the gray values of the edge point to a certain extent, and the gray values of the target area and the gray values of the non-target area are also greatly different; therefore, the edge point is used as a dividing point for image division, and a better division effect can be obtained.
S2011, acquiring edge points of the filtered image, acquiring positions of the edge points and obtaining corresponding coordinates in a two-dimensional histogram；
S2012, dividing edge points into areas by utilizing diagonals based on diagonal theorySum area/>；
S2013, acquiring an area based on a dotted line distance formulaSum area/>Two edge points m/>, which are furthest from the diagonal、n/>；
S2014, two edge points m、n/>Respectively connecting the two ends of the diagonal line to obtain a region D, wherein the region D is a set of a background region and a target region;
S2015, setting the threshold dividing line T 0 as a perpendicular to the diagonal line, thereby dividing the region D into a target region D 1 and a background region D 2;
At this time, the probability of the threshold parting line T 0 is:
（2-1）
Wherein, Respectively the abscissa value and the ordinate value of the two-dimensional histogram, wherein L-1 is the value range of the abscissa and the ordinate, and is the maximum value of the pixel values in the two-dimensional histogram and the infrared image; 2L-2 is the value range of the threshold dividing line T 0;
S2016, determining the value of a threshold parting line based on a threshold parting line function; when the threshold parting line is T, the threshold parting line function is specifically:
(2-2）
（2 -3）
Wherein, Is the final first threshold.
The image is segmented through the first threshold value, so that information at the edges and four corners of the whole photovoltaic panel assembly can be reserved, the whole area of the photovoltaic panel is ensured, and meanwhile, the photovoltaic panel can be segmented completely; outputting the segmented image and reserving the segmented image as a photovoltaic panel segmented image.
S202, performing secondary segmentation based on the photovoltaic panel segmentation image to obtain an abnormal region range image.
S2021, after the segmentation is performed by the first threshold value, the gray value interval of the infrared image is changed to [ T 1, L-1];
Let the gray level in the image be The number of pixels is/>The total number of pixel points of the image is/>The following formula is given:
（2-4）
（2-5）
Wherein, For gray level/>Probability of occurrence of pixel points in an image/>。
S2022, two gray values C 1 and C 2 with different magnitudes are contained in a gray value interval [ T 1, L-1], and the gray value interval [ T 1, L-1] is divided into a first interval [ T 1,C1 ], a second interval [ C 1+1,C2 ] and a third interval [ C 2 +1, L-1]; at this time, the gray value average of the image is calculated as follows:
（2-6）
S2023, the calculation formula from which the threshold function can be obtained is:
（2-7）
Wherein, Is of small gray value,/>Is a large gray value,/>The area ratio occupied by the image for the i-th section portion,For the gray value of the i-th interval part,/>Is the gray value average value.
When (when)When the maximum value is obtained,/>And/>The value of (1) is the cutting threshold value and passes/>To represent a second threshold,/>To represent a third threshold.
The photovoltaic array is formed by combining all photovoltaic panels, and each photovoltaic panel is formed by combining battery panels; referring to fig. 3, for a cut photovoltaic panel image, where the first threshold T 1 is the pixel value of the entire photovoltaic panel edge, the second threshold T 2 is the pixel value of each panel edge within the photovoltaic panel, and the third threshold T 3 is the pixel value at the edge of the anomaly region range; wherein, a circle frame in the image represents the abnormal region range; the difference of pixel values based on two sides at the edge is large; therefore, the magnitude of the third threshold can be obtained more accurately by the threshold function.
And cutting the image through the acquired third threshold value to acquire a final abnormal region range image. Since the acquired abnormal region range image cannot confirm whether it is a hot spot or an abnormal region due to environmental conditions such as solar reflection, it is necessary to determine the abnormal region image.
S3, inputting the abnormal region range image, the corresponding photovoltaic panel segmentation image and the P-V curve data into the BP neural network, calculating the area occupation ratio of the abnormal region range on the corresponding photovoltaic panel, and outputting a final result by combining the P-V curve data.
Based on the acquisition of the abnormal region range image, acquiring a corresponding photovoltaic panel segmentation image from the stored photovoltaic panel segmentation images, and inputting the abnormal region range image, the corresponding photovoltaic panel segmentation image and the P-V curve data into the BP neural network.
Calculating the area occupation ratio R 1 of the abnormal area range in the photovoltaic panel segmentation image;
Because the obtained P-V curve data are the P-V curve data of each photovoltaic panel in the photovoltaic array at the current moment and in the historical normal fault-free running state, obtaining the power value in the P-V curve data of the photovoltaic panel in the historical normal fault-free running state, and calculating the average power; meanwhile, the power value in the P-V curve data acquired at the current moment is extracted, the power value at the current moment is compared with the average power value, and the power ratio R 2 is obtained.
Calculating an error rate between the area ratio R 1 and the power ratio R 2; the calculation formula is as follows:
(3-1)
Judging the category of the abnormal region range image according to the acquired abnormal region range image and the error rate, and outputting a final result; while the threshold value for the error rate may be chosen to be 5%. When the error rate is less than 5%, the abnormal area range image is a hot spot image, and the photovoltaic panel fault is output; when the error rate is greater than 5%, the abnormal region range image is a normal image, and the output photovoltaic panel is normal.
The principle of the method is that when the abnormal area state obtained from the infrared image of the photovoltaic panel is a hot spot, the panel at the position does not work and is in a fault state; at this time, the error rates of the area ratio R 1 and the power ratio R 2 are not too different and even approach 0; when the abnormal area is caused by sunlight reflection and the like, the operation of the battery plate is not affected, the power ratio R 2 approaches to 1, and the obtained error rate is too large; therefore, whether the abnormal area is caused by hot spots or caused by solar reflection and the like can be automatically identified, secondary identification is not needed through a manual mode after misjudgment, resource waste is avoided, and meanwhile, the identification precision of the hot spots is improved.
The selected P-V curve data has nonlinear characteristics, and the BP neural network can realize nonlinear fitting, so that the method has a better effect on the processing of the P-V curve data; meanwhile, before the BP neural network is used, corresponding data are acquired according to the steps S1-S2 of the application, and the neural network is trained.
Example two
A second aspect of the invention provides a fault detection system for a photovoltaic array, comprising:
The data acquisition module acquires an infrared image and P-V curve data of the photovoltaic array, and preprocesses the P-V curve data;
The image segmentation module is used for segmenting the infrared image by a three-threshold segmentation method to obtain an abnormal region range image and a photovoltaic panel segmented image;
the fault identification module is used for inputting the abnormal region range image, the corresponding photovoltaic panel segmentation image and the P-V curve data into the BP neural network, calculating the area occupation ratio of the abnormal region range on the corresponding photovoltaic panel, and outputting a final result by combining the P-V curve data.
Example III
It is an object of the present embodiment to provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which processor implements the steps of the above method when executing the program.
Example IV
An object of the present embodiment is to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
The steps involved in the devices of the second, third and fourth embodiments correspond to those of the first embodiment of the method, and the detailed description of the embodiments can be found in the related description section of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media including one or more sets of instructions; it should also be understood to include any medium capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any one of the methods of the present invention.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. A fault detection method for a photovoltaic array, comprising the steps of:
Acquiring an infrared image and P-V curve data of a photovoltaic array, and preprocessing the P-V curve data;
Dividing the infrared image by a three-threshold dividing method to obtain an abnormal region range image and a photovoltaic panel dividing image;
And inputting the abnormal region range image, the corresponding photovoltaic panel segmentation image and the P-V curve data into the BP neural network, calculating the area occupation ratio of the abnormal region range on the corresponding photovoltaic panel, and outputting a final result by combining the P-V curve data.
2. The method for detecting faults of a photovoltaic array according to claim 1, wherein the method for dividing the infrared image by a three-threshold dividing method is characterized in that bilateral filtering processing is firstly carried out on the infrared image to obtain edge points of the image, a first threshold is obtained based on the obtained edge points, and the divided image of the photovoltaic panel is obtained by dividing the first threshold; and performing secondary segmentation based on the photovoltaic panel segmentation image to obtain an abnormal region range image.
3. The method for detecting a failure of a photovoltaic array according to claim 2, wherein the performing the secondary segmentation based on the photovoltaic panel segmented image obtains the abnormal region range image by using a first threshold value and an image pixel maximum value as gray value intervals, wherein two gray values with different magnitudes are contained in the gray value intervals, and the gray value intervals are divided into a first interval, a second interval and a third interval; and determining the values of two gray values with different sizes based on a threshold function, taking the determined small gray value as a second threshold, taking the determined large gray value as a third threshold, and cutting through the third threshold to obtain an abnormal region range image.
4. A fault detection method for a photovoltaic array according to claim 3, wherein the threshold function is specifically:
Wherein, Is of small gray value,/>Is a large gray value,/>Area ratio occupied by the image of the i-th section part,/>For the gray value of the i-th interval part,/>Is the gray value average value.
5. The fault detection method for a photovoltaic array according to claim 1, wherein the final result of the combination of the P-V curve data output is specifically that the average power of the power in the P-V curve data of the current photovoltaic panel is calculated, and compared with the average power in the normal state of the photovoltaic panel to obtain the power ratio; and comparing the power ratio with the acquired area ratio, and outputting a final result according to the comparison result.
6. A fault detection system for a photovoltaic array, comprising:
The data acquisition module acquires an infrared image and P-V curve data of the photovoltaic array, and preprocesses the P-V curve data;
The image segmentation module is used for segmenting the infrared image by a three-threshold segmentation method to obtain an abnormal region range image and a photovoltaic panel segmented image;
the fault identification module is used for inputting the abnormal region range image, the corresponding photovoltaic panel segmentation image and the P-V curve data into the BP neural network, calculating the area occupation ratio of the abnormal region range on the corresponding photovoltaic panel, and outputting a final result by combining the P-V curve data.
7. The system for detecting faults of a photovoltaic array according to claim 6, wherein the method for dividing the infrared image by a three-threshold dividing method is characterized in that bilateral filtering processing is firstly carried out on the infrared image, edge points of the image are obtained, a first threshold is obtained based on the obtained edge points, a photovoltaic panel divided image is obtained by dividing the first threshold, secondary division is carried out based on the photovoltaic panel divided image, and an abnormal area range image is obtained.
8. The fault detection system for a photovoltaic array according to claim 7, wherein the performing the secondary segmentation based on the photovoltaic panel segmented image obtains an abnormal region range image, specifically, a first threshold and an image pixel maximum are taken as gray value intervals, two gray values with different magnitudes are contained in the gray value intervals, and the gray value intervals are divided into a first interval, a second interval and a third interval; and determining the values of two gray values with different sizes based on a threshold function, taking the determined small gray value as a second threshold, taking the determined large gray value as a third threshold, and cutting through the third threshold to obtain an abnormal region range image.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of the preceding claims 1-5 when the program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, performs the steps of the method of any of the preceding claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410501104.4A CN118096748B (en) | 2024-04-25 | 2024-04-25 | Fault detection method and system for photovoltaic array |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410501104.4A CN118096748B (en) | 2024-04-25 | 2024-04-25 | Fault detection method and system for photovoltaic array |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118096748A true CN118096748A (en) | 2024-05-28 |
| CN118096748B CN118096748B (en) | 2024-08-30 |
Family
ID=91144295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410501104.4A Active CN118096748B (en) | 2024-04-25 | 2024-04-25 | Fault detection method and system for photovoltaic array |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118096748B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619479A (en) * | 2019-09-23 | 2019-12-27 | 阳光电源股份有限公司 | Fault judgment model modeling method and fault judgment method for photovoltaic module |
| CN111080691A (en) * | 2019-12-17 | 2020-04-28 | 晶科电力科技股份有限公司 | Infrared hot spot detection method and device for photovoltaic module |
| CN112446863A (en) * | 2020-11-24 | 2021-03-05 | 黄静 | Photovoltaic array hot spot detection method and detection system based on image processing |
| CN114663389A (en) * | 2022-03-21 | 2022-06-24 | 上海电气集团股份有限公司 | Photovoltaic module hot spot detection method and device and storage medium |
| CN115115634A (en) * | 2022-08-30 | 2022-09-27 | 江苏华维光电科技有限公司 | Photovoltaic array hot spot detection method based on infrared image |
| CN116843691A (en) * | 2023-09-01 | 2023-10-03 | 尚特杰电力科技有限公司 | Photovoltaic panel hot spot detection method, storage medium and electronic equipment |
| CN117315350A (en) * | 2023-09-26 | 2023-12-29 | 金开智维(宁夏)科技有限公司 | Hot spot detection method and device for photovoltaic solar panel based on unmanned aerial vehicle |
-
2024
- 2024-04-25 CN CN202410501104.4A patent/CN118096748B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619479A (en) * | 2019-09-23 | 2019-12-27 | 阳光电源股份有限公司 | Fault judgment model modeling method and fault judgment method for photovoltaic module |
| CN111080691A (en) * | 2019-12-17 | 2020-04-28 | 晶科电力科技股份有限公司 | Infrared hot spot detection method and device for photovoltaic module |
| CN112446863A (en) * | 2020-11-24 | 2021-03-05 | 黄静 | Photovoltaic array hot spot detection method and detection system based on image processing |
| CN114663389A (en) * | 2022-03-21 | 2022-06-24 | 上海电气集团股份有限公司 | Photovoltaic module hot spot detection method and device and storage medium |
| CN115115634A (en) * | 2022-08-30 | 2022-09-27 | 江苏华维光电科技有限公司 | Photovoltaic array hot spot detection method based on infrared image |
| CN116843691A (en) * | 2023-09-01 | 2023-10-03 | 尚特杰电力科技有限公司 | Photovoltaic panel hot spot detection method, storage medium and electronic equipment |
| CN117315350A (en) * | 2023-09-26 | 2023-12-29 | 金开智维(宁夏)科技有限公司 | Hot spot detection method and device for photovoltaic solar panel based on unmanned aerial vehicle |
Non-Patent Citations (2)
| Title |
|---|
| 张可人等: "基于视觉特性的激光光斑图像分割方法研究", 《激光杂志》, vol. 44, no. 09, 30 September 2023 (2023-09-30), pages 114 - 119 * |
| 申万科等: "改进 U-net 的电气设备紫外图像放电光斑分割", 《红外技术》, 26 January 2024 (2024-01-26), pages 1 - 10 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118096748B (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414507B (en) | License plate recognition method and device, computer equipment and storage medium | |
| CN111428748B (en) | HOG feature and SVM-based infrared image insulator identification detection method | |
| CN108961235A (en) | A kind of disordered insulator recognition methods based on YOLOv3 network and particle filter algorithm | |
| CN115115634B (en) | Photovoltaic array hot spot detection method based on infrared image | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| CN111310746B (en) | Text line detection method, model training method, device, server and medium | |
| CN114581446B (en) | Battery core abnormity detection method and system of laminated battery | |
| CN116612098B (en) | Insulator RTV spraying quality evaluation method and device based on image processing | |
| CN111488945A (en) | Image processing method, image processing device, computer equipment and computer readable storage medium | |
| CN114399484A (en) | Photovoltaic module defect detection method, device, equipment and medium | |
| CN110334775B (en) | Unmanned aerial vehicle line fault identification method and device based on width learning | |
| CN114549393B (en) | Image labeling method, device, equipment and computer storage medium | |
| CN118096748B (en) | Fault detection method and system for photovoltaic array | |
| CN116645413B (en) | Photovoltaic cell panel position identification method and system and photovoltaic robot | |
| CN105205829A (en) | Transformer substation infrared image segmentation method based on improved two-dimensional Otsu algorithm | |
| CN114581407B (en) | Self-adaptive defect detection method for photovoltaic module | |
| CN115758284B (en) | Photovoltaic hot spot fault detection method and system based on fusion kernel entropy and information gain | |
| CN116152195A (en) | Hot spot detection method and device for photovoltaic cell panel and electronic equipment | |
| CN114972871A (en) | Image registration-based few-sample image anomaly detection method and system | |
| CN115310505A (en) | Automatic identification method and system for secondary circuit wiring terminal of mutual inductor | |
| CN114219823A (en) | Method for extracting photovoltaic distribution image of roof and computer equipment | |
| CN115424250A (en) | License plate recognition method and device | |
| CN112150458A (en) | Photovoltaic cell panel welding strip deviation detection method and system based on artificial intelligence | |
| CN104504679A (en) | On-line analysis method of infrared defect on the basis of typical defect map | |
| CN117173385B (en) | Detection method, device, medium and equipment of transformer substation |
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 |