CN107314819A - A kind of detection of photovoltaic plant hot spot and localization method based on infrared image - Google Patents
A kind of detection of photovoltaic plant hot spot and localization method based on infrared image Download PDFInfo
- Publication number
- CN107314819A CN107314819A CN201710533118.4A CN201710533118A CN107314819A CN 107314819 A CN107314819 A CN 107314819A CN 201710533118 A CN201710533118 A CN 201710533118A CN 107314819 A CN107314819 A CN 107314819A
- Authority
- CN
- China
- Prior art keywords
- temperature
- hot spot
- image
- mrow
- array
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 230000004807 localization Effects 0.000 title claims abstract description 43
- 238000012216 screening Methods 0.000 claims description 8
- 238000013461 design Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000010339 dilation Effects 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000003491 array Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000007667 floating Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 16
- 238000011161 development Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 238000003711 image thresholding Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Quality & Reliability (AREA)
- Radiation Pyrometers (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The invention discloses a kind of photovoltaic plant hot spot detection based on infrared image and localization method, including：Based on infrared temperature image, array is divided；Based on array region, hot spot identification；Hot spot is positioned.The present invention is in progress photovoltaic plant hot spot detection, it is proposed that a kind of detection of photovoltaic plant hot spot and localization method based on infrared image, is broadly divided into array division, hot spot identification, three parts of hot spot positioning.Infrared image hot spot detection method is based on compared to existing, the temperature characterisitic of infrared image has been taken into full account, infrared temperature data is directly based upon and carries out array division, computational complexity is low and division effect is good；Based on array region, hot spot is recognized by the way of judging twice, not only detection efficiency is high and precision is higher；The mode matched based on GPS information positions hot spot position, and algorithm complex is low and accuracy is higher.
Description
Technical field
It is more particularly to a kind of to be based on infrared image the present invention relates to hot spot detection, the technical field of infrared image processing
Photovoltaic plant hot spot detection and localization method.
Background technology
In recent years, the photovoltaic solar of China is widely used in large-sized photovoltaic power station, street lamp, house and commercial buildings
Deng.In these places, birds droppings, building, other solar panels etc. are all readily formed to be blocked to photovoltaic array,
And then produce hot spot effect, hence it is evident that and reduction photovoltaic array generating efficiency and service life, even occur fire when serious.In photovoltaic
, it is necessary to periodically be detected to hot spot in the construction in power station and maintenance process.And conventional manual inspection mode must hold high and sweep
Retouch instrument or implement hot spot detection by lift truck, danger coefficient is high, efficiency is low, cost is high.Therefore, research safety, efficient heat
Spot detection method, is of great practical significance for the generating efficiency for improving photovoltaic plant.
Conventional hot spot detection method can substantially be divided into three kinds at present：Bypass diode method in parallel, current and voltage method and
Infrared imagery technique method.Wherein, the main purpose of bypass diode method in parallel is to be reduced by bypass diode by occlusion part
Divide the backward voltage and electric current suffered by cell piece；Current and voltage method is used for the fault diagnosis of photovoltaic array, by analyzing light
Relation between photovoltaic array output current, voltage, builds suitable model, judges whether hot spot phenomenon；Both the above side
Method is all easily destroyed the internal structure of photovoltaic array, and less efficient.Infrared imagery technique method can solve problem above, be based on
The fact that infrared image can reflect temperature characterisitic of the photovoltaic array under different working condition, shot using thermal infrared imager
Infrared image, and detected hot spot by graphical analysis.But the technology for this method is realized relatively fewer at present.
The content of the invention
The purpose of this part is some aspects for summarizing embodiments of the invention and briefly introduces some preferably implementations
Example.It may do a little simplified or be omitted to avoid making our department in this part and the description of the present application summary and denomination of invention
Point, the purpose of specification digest and denomination of invention obscure, and this simplification or omit and cannot be used for limiting the scope of the present invention.
In view of problem present in above-mentioned existing hot spot detection method, it is proposed that the present invention.
Therefore, one of purpose of the invention is to provide the photovoltaic plant hot spot detection based on infrared image and positioning side
Method.
In order to solve the above technical problems, the present invention provides following technical scheme：A kind of photovoltaic plant based on infrared image
Hot spot detection and localization method, including：Based on infrared temperature image, array is divided；Based on array region, hot spot identification；Hot spot
Positioning；Wherein, the division array, including, according to infrared temperature data acquisition gradient image, using algorithm thresholding, and will
The gradient image reversion；The temperature threshold obtained using calculating, removes the shadow region in gradient image after reversion；Using first
Beginning gradient image, obtains local variance image, and obtain binary image；It is converted into temperature histogram；Rectangle is matched, pointwise
, will when template window intermediate value is more than 0.3 for the ratio shared by the sum of 1 point with the point that the temperature histogram intermediate value is 1
The point is set to 1；Otherwise, it is set to 0；Morphological dilations, the image after being matched to rectangle is expanded twice, fills each array side
Edge region；Wherein, the array based on infrared temperature image is divided, and reversion obtains image, is specially：
G (x, y)=I (x, y+1)-I (x, y)；
Wherein, I represents the infrared temperature data of input, is made up of the temperature value of floating point type, size is 640 × 480；g
Represent Initial Gradient image；X, y represent the abscissa and ordinate of each temperature spot respectively.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：The calculating of the temperature threshold, including, a set is defined, each point of the gradient image intermediate value for 1 is right after storage reversion
The temperature value answered, and set is sorted from small to large；The all elements for being located at rear 50% in set are averaged；The average
0.5 times be set to temperature threshold, be specially：
Wherein, g ' represents the gradient image after low temperature screening, and T is a constant, and size is 0.5 times of temperature average.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：The shadow region removed after reversion in gradient image, including, gradient image and initial infrared temperature after the reversion
Data are multiplied, and obtain image a；Each point in image a less than the temperature threshold is set to 0, remaining puts 1, obtains removing reversion
The image b of shadow region in gradient image afterwards, be specially：
Rgra=g'-var
Wherein, RgraThe gradient image after variance removal is represented, var represents local variance image.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：The binary image, including, to the point that Grad in described image b is 1,3 in initial infrared image where asking it ×
Local variance in 3 regions, forms the local variance image；Using algorithm to the local variance image threshold；From institute
The local variance image that thresholding is subtracted in image b is stated, obtains removing the binary image behind non-array region.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：The temperature histogram, including, a temperature set is defined, the temperature set includes the binary image intermediate value
For the temperature value corresponding to 1 each point；Using the temperature set, the temperature histogram of structuring one-dimensional, and it is straight with the temperature
Temperature in square figure corresponding to temperature highest peak value as array mean temperature c；Wherein, the binary image intermediate value is
1 and the corresponding temperature of point be located at effective temperature scope in point, be set to 1, otherwise, be set to 0；Wherein, the effective temperature model
It is [c-4, c+4] to enclose, and the temperature interval of the histogrammic abscissa of temperature is 0.5 °；Specially：
Wherein, RmodeThe array division result after histogram divion is represented, during mode histograms maximum distribution is interval
Digit, represents the mean temperature of array.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：The hot spot identification, including, from the array after division, choose suspicious array；Preliminary screening, determines candidate's hot spot point
Set；Coordinate merges, and is specially：
And, secondary judgement hot spot point.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：The suspicious array, is the maximum temperature value in array and array of the ratio more than 1.5 of the mean temperature c.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：Determination candidate's hot spot point, is higher than the mean temperature c using 5 × 5 window to temperature value in the suspicious array
0.8 times of temperature spot, carry out hot spot judgement, calculate 5 × 5 window in highest temperature Tmax, average temperature Tavg, and by Tmax-c、
Tavg- c is compared with threshold value k1, k2 of setting respectively, and when two differences are all not less than k1, k2 respectively, the point is candidate's hot spot
Point, and be added in candidate's hot spot point set；Wherein, k1, k2 span are [15,18], [2,4] respectively.
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：It is described it is secondary judge, candidate's hot spot point, and if only if Tmax-TavgDifference be not less than temperature threshold k3 when, the point
For real hot spot；Temperature threshold k3 spans are [5,15].
As the photovoltaic plant hot spot detection of the present invention based on infrared image and a kind of preferred scheme of localization method,
Wherein：The hot spot positioning, including, photovoltaic plant construction design drawing is converted into logic chart, by each battle array in logic chart
Corresponding relation is set up between the position coordinates and GPS information of row, and calculates the GPS information of all photovoltaic arrays；Based on described
The result of hot spot identification, utilizes the knot in the GPS information storehouse in the GPS information matching logic figure parsed from infrared image
Really, the specific camera site of width image is determined；According to the result of the division array, hot spot is specifically navigated to positioned at certain width figure
Which array as in；GPS information, the temperature information of hot spot are recorded in the test result text document of generation.
Beneficial effects of the present invention：The present invention is when carrying out the detection of photovoltaic plant hot spot, it is proposed that one kind is based on infrared figure
The photovoltaic plant hot spot detection of picture and localization method, are broadly divided into array division, hot spot identification, three parts of hot spot positioning.Phase
Infrared image hot spot detection method is based on than existing, the temperature characterisitic of infrared image has been taken into full account, has been directly based upon infrared temperature
Degrees of data carries out array division, and computational complexity is low and division effect is good；Based on array region, known by the way of judging twice
Other hot spot, not only detection efficiency is high and precision is higher；The mode matched based on GPS information positions hot spot position, algorithm complex
It is low and accuracy is higher.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, being used required in being described below to embodiment
Accompanying drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this
For the those of ordinary skill of field, without having to pay creative labor, it can also obtain other according to these accompanying drawings
Accompanying drawing.Wherein：
Fig. 1 is the present invention, and the photovoltaic plant hot spot detection based on infrared image is shown with the infrared hybrid optical system in localization method
It is intended to；
Fig. 2 is the present invention, and the photovoltaic plant hot spot detection based on infrared image is shown with the original gradient image in localization method
It is intended to；
Fig. 3 is detected with utilizing algorithm thresholding in localization method for photovoltaic plant hot spot of the present invention based on infrared image
Gradient image schematic diagram；
Fig. 4 is detected with being inverted in localization method after gradient image for photovoltaic plant hot spot of the present invention based on infrared image
Schematic diagram；
Fig. 5 is the present invention, and the photovoltaic plant hot spot detection based on infrared image is screened with gradient image low temperature in localization method
Result schematic diagram afterwards；
Fig. 6 is detected for photovoltaic plant hot spot of the present invention based on infrared image and the image of local variance in localization method shows
It is intended to；
Fig. 7 detects the gradient after being removed with variance in localization method for photovoltaic plant hot spot of the present invention based on infrared image
Image schematic diagram；
Fig. 8 is detected and temperature histogram divion in localization method for photovoltaic plant hot spot of the present invention based on infrared image
Schematic diagram；
Fig. 9 is detected and the histogrammic broken line of temperature in localization method for photovoltaic plant hot spot of the present invention based on infrared image
Figure；
Figure 10 detects the result matched with rectangle in localization method for photovoltaic plant hot spot of the present invention based on infrared image
Schematic diagram；
Figure 11 detects the result with morphological dilation in localization method for photovoltaic plant hot spot of the present invention based on infrared image
Schematic diagram；
Figure 12 is detected and the knot after array identification in localization method for photovoltaic plant hot spot of the present invention based on infrared image
Fruit schematic diagram；
Figure 13 is the present invention, and the photovoltaic plant hot spot detection based on infrared image merges preceding detection with coordinate in localization method
Schematic diagram；
Figure 14 is detected after merging for the photovoltaic plant hot spot detection of the invention based on infrared image with coordinate in localization method
Schematic diagram；
Figure 15 is the present invention, and the photovoltaic plant hot spot detection based on infrared image is judged before hot spot with secondary in localization method
Display result schematic diagram；
Figure 16 is the present invention, and the photovoltaic plant hot spot detection based on infrared image is judged after hot spot with secondary in localization method
Display result schematic diagram.
Embodiment
In order to facilitate the understanding of the purposes, features and advantages of the present invention, with reference to Figure of description pair
The embodiment of the present invention is described in detail.
Many details are elaborated in the following description to facilitate a thorough understanding of the present invention, still the present invention can be with
It is different from other manner described here using other to implement, those skilled in the art can be without prejudice to intension of the present invention
In the case of do similar popularization, therefore the present invention is not limited by following public specific embodiment.
Secondly, the present invention is described in detail with reference to schematic diagram, when the embodiment of the present invention is described in detail, for purposes of illustration only, table
Show that the profile of device architecture can disobey general ratio and make partial enlargement, and the schematic diagram is example, and it should not herein
Limit the scope of protection of the invention.In addition, the three-dimensional space of length, width and depth should be included in actual fabrication.
Thirdly, " one embodiment " or " embodiment " referred to herein refers to may be included at least one realization of the present invention
Special characteristic, structure or characteristic in mode." in one embodiment " that different places occur in this manual is not equal
Refer to same embodiment, nor the single or selective embodiment mutually exclusive with other embodiment.
The detection of the photovoltaic plant hot spot based on infrared image of the present invention and localization method, its specific embodiment are as follows：
1st, the schematic diagram that reference picture 1~11 divides for the array based on infrared temperature image, including following sub-step：
(1) table 1 is obtained according to infrared temperature data, wherein, the data in table 1 are to shoot to obtain ddt by infrared camera
The file of form, switchs to the file of ddt forms the file of csv forms in the sdk development kits carried by infrared camera,
That is, the function carried by camera backstage, has carried out form conversion, in order to read temperature data, table 1 is obtained.Need
Can be by the built-in function in C language it is noted that reading temperature data, can also be by computer manually with Excel's
Pattern is opened, and each data in table 1 correspond to the temperature value of every bit in infrared image.
Table 1
Infrared data in table 1 is converted into infrared temperature image as indicated with 1, and then obtains the gradient image in vertical direction
The original gradient image shown in Fig. 2 is obtained, using Otsu algorithm thresholdings, the gradient image shown in Fig. 3 is obtained, finally by image
" reversion "." reversion " mentioned here is that part white in original image is become into black, by the portion of black in original image
Divide and become white, obtain the image after the reversion shown in Fig. 4；Specially：
G (x, y)=I (x, y+1)-I (x, y) are 1.
Wherein, I represents the infrared temperature data of input, is made up of the temperature value of floating point type, size is 640 × 480；g
Represent Initial Gradient image；X, y represent the abscissa and ordinate of each temperature spot respectively.
(2) the too low point of temperature in gradient image after temperature threshold removal step (1) reversion calculated is utilized；Specifically
For：
Wherein, g ' represents the gradient image after low temperature screening, and T is a constant, and size is 0.5 times of temperature average.
First, it is the temperature value corresponding to 1 each point to define gradient image intermediate value after being inverted in a set, storage (1),
And set is sorted from small to large, then, all elements that rear 50% is located in set are averaged, and by 0.5 times of average
Temperature threshold is set to, finally, gradient image after reversion is multiplied with initial infrared temperature data, image a is obtained；By in image a
Each point less than temperature threshold is set to 0, and remaining puts 1, obtains removing the image b of the shadow region after reversion in gradient image, i.e.,
Fig. 5.That is Fig. 3.
(3) background area is removed using local variance；Specially：
Rgra=g'-var is 3.
Wherein, RgraThe gradient image after variance removal is represented, var represents local variance image.
Gradient image after being screened based on step (2) low temperature is image b (Fig. 5), and it is 1 that gradient image intermediate value is asked for first
Variance of each point in initial infrared image in 3 × 3 regions, constitutes local variance image (as shown in Figure 6)；Then Otsu is utilized
Algorithm is to local variance image thresholding；Local variance image is subtracted in gradient image after the last screening from step (2) low temperature,
Obtain removing the binary image behind non-array region, obtain Fig. 7.
(4) temperature histogram divion；Specially：
Wherein, RmodeThe array division result after histogram divion is represented, during mode histograms maximum distribution is interval
Digit, represents the mean temperature of array.
Based on the binary image in step (3), a temperature set is defined, storage each point of the image intermediate value for 1 is right
The temperature value answered.Element in set is configured to an one-dimensional temperature histogram, i.e., as shown in figure 8, and with histogram
Temperature corresponding to temperature highest peak value as array mean temperature c.It is 1 by step (3) binary image intermediate value, and should
The corresponding temperature of point is located at the point in effective temperature scope, is set to 1；Otherwise, it is set to 0.When constructing temperature histogram, its abscissa
Temperature interval be 0.5 °, temperature effective range refers to [c-4, c+4], obtains temperature histogram (as shown in Figure 9).
(5) rectangle is matched；
Reference picture 10, uses 8 × 10 complete 1 template to go the target image intermediate value that pointwise matching step (4) is obtained for 1
Point, when template window intermediate value is more than 0.3 for the ratio shared by the sum of 1 point, the point is continued to be set to 1；Otherwise, it is set to 0.
(6) morphological dilations；
Reference picture 11, is expanded, to fill out twice using 8 × 1,1 × 6 operator to the binary image in step (5)
Fill the fringe region of each array.
2nd, hot spot, including following sub-step are recognized based on dividing obtained array region in step 1：
(1) from step 1 divides each obtained array, suspicious array is chosen；
Suspicious array is the maximum temperature value and array of the ratio more than 1.5 of the mean temperature c in array, otherwise,
It is considered as the array of normal work, follow-up processing is not done, so as to reduces amount of calculation.
(2) preliminary screening, determines the set of candidate's hot spot point；
Reference picture 12, Figure 12 shows array recognition result, using 5 × 5 window to temperature value in the suspicious array
0.8 times of the temperature spot higher than the mean temperature c, carries out hot spot judgement, calculates the highest temperature T in 5 × 5 windowmax, it is flat
Samming Tavg, and by Tmax-c、TavgThe threshold value k of-c respectively with setting1、k2Compare, when two differences are all not less than k respectively1、k2
When, the point is candidate's hot spot point, and is added in candidate's hot spot point set；k1、k2Span is [15,18], [2,4] respectively.
(3) coordinate merges；Specially：
Wherein, dis (p, q) represents the Euclidean distance between p and 2 points of q, and the position coordinates that 2 points of p, q is (x respectively1,
y1)、(x2,y2).Because the traversal step-length of window is 2, so needing what is be located closer in the set obtained to step (2)
Some candidate's hot spot points carry out coordinate merging, so as to ensure the top left co-ordinate in only record hot spot region.Between any two points
Euclidean distance threshold value is set to 10.For example：As shown in figure 13, it is the schematic diagram before coordinate merges, and after coordinate merges, is obtained
Figure 14.
(4) it is secondary to judge
Reference picture 15, finds by statistics, the threshold of the highest temperature and mean temperature where part strong jamming point in window
Value has also reached the standard of preliminary screening, but in window the difference of the highest temperature and average temperature between the two less than hot spot region
's.Local hot spot in background area middle as shown in Figure 15 is hot spot, therefore, the time obtained based on step (3) by flase drop
Hot spot point is selected, then travels through each candidate's hot spot point successively, and if only if Tmax-TavgDifference be more than or equal to temperature threshold k3When,
It is real hot spot, k just to think the point3Span is [5,15], obtains Figure 16, so as to correctly judge the position of hot spot.
3rd, hot spot is positioned
First, according to photovoltaic plant construction design drawing, the logic chart in whole power station is automatically generated using CAD software, and
Corresponding relation between the position coordinates and GPS information of each array in searching logic chart, calculates the GPS letters of all arrays
Breath, wherein it is desired to explanation, correspondence mappings relation here is that, by execution initial stage, field technician is carried out to power station
Simple to step on duty, selection power station point measures its GPS coordinate as datum mark, then on the logic chart in power station, can will be every
The position coordinates that the gps coordinate of individual point finds each corresponding array is mapped；Secondly, the knot recognized based on step 2 hot spot
Really, the result in the GPS information storehouse in the GPS information matching logic figure parsed from image, determines that the width image is specific
Camera site；Again, the result divided according to array in step 1, specifically navigates to which in certain width image of hot spot
Individual array；Finally, the information such as the GPS information of hot spot, the maximum temperature of hot spot and mean temperature are automatically logged into the survey of generation
In test result document.
It should be understood that this application is not limited to details illustrating in the following description or being illustrated in figure or method.
It will also be appreciated that the wording and term employed in this paper are only in order at description purpose and are not considered as limitation.
In addition, the terse description in order to provide exemplary, can not describe all spies of actual embodiment
Levy (that is, with those incoherent features of optimal mode of the execution present invention currently considered, or it is of the invention incoherent in realizing
Those features).It should be understood that in the development process of any actual embodiment, such as in any engineering or design object,
Substantial amounts of embodiment can be made to determine.Such development effort is probably complicated and time-consuming, but is obtained for those
For the those of ordinary skill of the displosure content, it is not necessary to excessive experiment, the development effort will be a design, manufacture
With the routine work of production.
It should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, although with reference to preferable
The present invention is described in detail embodiment, it will be understood by those within the art that, can be to technology of the invention
Scheme is modified or equivalent substitution, and without departing from the spirit and scope of technical solution of the present invention, it all should cover in this hair
Among bright right.
Claims (10)
1. a kind of detection of photovoltaic plant hot spot and localization method based on infrared image, it is characterised in that including：
Based on infrared temperature image, array is divided；
Based on array region, hot spot identification；And,
Hot spot is positioned；Wherein, the division array, including,
According to infrared temperature data acquisition gradient image, inverted using algorithm thresholding, and by the gradient image；
The temperature threshold obtained using calculating, removes the shadow region in gradient image after reversion；
Using Initial Gradient image, local variance image is obtained, and obtain binary image；
It is converted into temperature histogram；
Rectangle is matched, and pointwise matches the point that the temperature histogram intermediate value is 1, when total institute of the template window intermediate value for 1 point
When the ratio accounted for is more than 0.3, the point is set to 1, otherwise, 0 is set to；And,
Morphological dilations, the image after being matched to rectangle is expanded twice, fills each array edges region；
Wherein, the array based on infrared temperature image is divided, and reversion obtains image, is specially：
G (x, y)=I (x, y+1)-I (x, y)；
Wherein, I represents the infrared temperature data of input, is made up of the temperature value of floating point type, size is 640 × 480；G is represented
Initial Gradient image；X, y represent the abscissa and ordinate of each temperature spot respectively.
2. the detection of photovoltaic plant hot spot and localization method according to claim 1 based on infrared image, it is characterised in that：
The calculating of the temperature threshold, including,
Define one set, storage reversion after gradient image intermediate value for 1 each point corresponding to temperature value, and to gather from it is small to
Big sequence；
The all elements for being located at rear 50% in set are averaged；
Temperature threshold is set to 0.5 times of the average；
Specially：
<mrow>
<msup>
<mi>g</mi>
<mo>,</mo>
</msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mn>1</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>&GreaterEqual;</mo>
<mi>T</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>0</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>e</mi>
<mi>l</mi>
<mi>s</mi>
<mi>e</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>;</mo>
</mrow>
Wherein, g ' represents the gradient image after low temperature screening, and T is a constant, and size is 0.5 times of temperature average.
3. the detection of photovoltaic plant hot spot and localization method according to claim 2 based on infrared image, it is characterised in that：
The shadow region removed after reversion in gradient image, including,
Gradient image is multiplied with initial infrared temperature data after the reversion, obtains image a；
Each point in image a less than the temperature threshold is set to 0, remaining puts 1, obtains removing the moon after reversion in gradient image
The image b in shadow zone domain；
Specially：
Rgra=g '-var
Wherein, RgraThe gradient image after variance removal is represented, var represents local variance image.
4. the detection of photovoltaic plant hot spot and localization method according to claim 3 based on infrared image, it is characterised in that：
The binary image, including,
To the point that Grad in described image b is 1, the local variance in initial infrared image where asking it in 3 × 3 regions, shape
Into the local variance image；
Using algorithm to the local variance image threshold；
The local variance image of thresholding is subtracted from described image b, obtains removing the binary picture behind non-array region
Picture.
5. the detection of photovoltaic plant hot spot and localization method according to claim 4 based on infrared image, it is characterised in that：
The temperature histogram, including,
A temperature set is defined, it is the temperature corresponding to 1 each point that the temperature set, which includes the binary image intermediate value,
Value；
Using the temperature set, the temperature histogram of structuring one-dimensional, and with temperature highest peak value in the temperature histogram
Corresponding temperature as array mean temperature c；
Wherein, the binary image intermediate value is 1 and the corresponding temperature of point is located at point in effective temperature scope, is set to 1, no
Then, it is set to 0；
Wherein, the effective temperature scope is [c-4, c+4], and the temperature interval of the histogrammic abscissa of temperature is 0.5 °；
Specially：
<mrow>
<msub>
<mi>R</mi>
<mrow>
<mi>mod</mi>
<mi>e</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mn>1</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>&Element;</mo>
<mo>&lsqb;</mo>
<mi>mod</mi>
<mi>e</mi>
<mo>-</mo>
<mn>4</mn>
<mo>,</mo>
<mi>mod</mi>
<mi>e</mi>
<mo>+</mo>
<mn>4</mn>
<mo>&rsqb;</mo>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>0</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>e</mi>
<mi>l</mi>
<mi>s</mi>
<mi>e</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>;</mo>
</mrow>
Wherein, RmodeThe array division result after histogram divion is represented, mode is the interval median of histogram maximum distribution,
Represent the mean temperature of array.
6. the detection of photovoltaic plant hot spot and localization method according to claim 5 based on infrared image, it is characterised in that：
The hot spot identification, including,
From the array after division, suspicious array is chosen；
Preliminary screening, determines the set of candidate's hot spot point；
Coordinate merges, and is specially：
<mrow>
<mi>d</mi>
<mi>i</mi>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mi>p</mi>
<mo>,</mo>
<mi>q</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>y</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>;</mo>
</mrow>
And, secondary judgement hot spot point.
7. the detection of photovoltaic plant hot spot and localization method according to claim 6 based on infrared image, it is characterised in that：
The suspicious array, is the maximum temperature value in array and array of the ratio more than 1.5 of the mean temperature c.
8. the detection of photovoltaic plant hot spot and localization method according to claim 7 based on infrared image, it is characterised in that：
Determination candidate's hot spot point, is higher than the 0.8 of the mean temperature c to temperature value in the suspicious array using 5 × 5 window
Temperature spot again, carries out hot spot judgement, calculates the highest temperature T in 5 × 5 windowmax, average temperature Tavg, and by Tmax-c、Tavg-c
Compared respectively with threshold value k1, k2 of setting, when two differences are all not less than k1, k2 respectively, the point is candidate's hot spot point, and is added
It is added in candidate's hot spot point set；
Wherein, k1, k2 span are [15,18], [2,4] respectively.
9. the detection of photovoltaic plant hot spot and localization method according to claim 8 based on infrared image, it is characterised in that：
It is described it is secondary judge, candidate's hot spot point, and if only if Tmax-TavgDifference be not less than temperature threshold k3 when, the point is true
Positive hot spot；
Temperature threshold k3 spans are [5,15].
10. the detection of photovoltaic plant hot spot and localization method according to claim 9 based on infrared image, its feature exist
In：The hot spot positioning, including,
Photovoltaic plant construction design drawing is converted into logic chart, the position coordinates of each array in logic chart and GPS are believed
Corresponding relation is set up between breath, and calculates the GPS information of all photovoltaic arrays；
The result recognized based on the hot spot, utilizes the GPS in the GPS information matching logic figure parsed from infrared image
The result of information bank, determines the specific camera site of width image；
According to the result of the division array, which array of the hot spot in certain width image specifically navigated to；
GPS information, the temperature information of hot spot are recorded in the test result text document of generation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710533118.4A CN107314819B (en) | 2017-07-03 | 2017-07-03 | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710533118.4A CN107314819B (en) | 2017-07-03 | 2017-07-03 | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107314819A true CN107314819A (en) | 2017-11-03 |
| CN107314819B CN107314819B (en) | 2019-04-23 |
Family
ID=60179958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710533118.4A Expired - Fee Related CN107314819B (en) | 2017-07-03 | 2017-07-03 | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107314819B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109215042A (en) * | 2018-09-28 | 2019-01-15 | 吉林电力股份有限公司科技开发分公司 | A kind of photovoltaic battery panel hot spot effect detection system based on computer vision and its calculation method |
| CN109308685A (en) * | 2018-08-09 | 2019-02-05 | 南京邮电大学 | Infrared photovoltaic array dividing method based on Threshold segmentation and K mean cluster |
| CN110736565A (en) * | 2019-09-20 | 2020-01-31 | 陕西榆林能源集团横山煤电有限公司 | Unit wall temperature screening method and device |
| CN110782426A (en) * | 2018-09-11 | 2020-02-11 | 成都极米科技股份有限公司 | Background extraction method and target discrimination method |
| CN111161220A (en) * | 2019-12-11 | 2020-05-15 | 中国计量大学 | Method for detecting and positioning defects of photovoltaic assembly by utilizing infrared image splicing |
| CN111242889A (en) * | 2019-12-03 | 2020-06-05 | 国家电投集团曲阳新能源发电有限公司 | Hot spot identification method and device for photovoltaic module |
| CN111242914A (en) * | 2020-01-09 | 2020-06-05 | 武汉博晟信息科技有限公司 | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm |
| CN111931785A (en) * | 2020-06-19 | 2020-11-13 | 国网山西省电力公司吕梁供电公司 | Edge detection method for infrared image target of power equipment |
| CN111953296A (en) * | 2019-05-17 | 2020-11-17 | 泰州隆基乐叶光伏科技有限公司 | Method and equipment for hot spot film selection of photovoltaic module |
| CN112184711A (en) * | 2020-11-05 | 2021-01-05 | 杭州青枭科技有限公司 | Photovoltaic module defect detection and positioning method and system |
| CN112701186A (en) * | 2020-12-25 | 2021-04-23 | 韩华新能源（启东）有限公司 | Label manufacturing method for thermosensitive camera position detection, label and detection method |
| CN113155288A (en) * | 2020-11-30 | 2021-07-23 | 齐鲁工业大学 | Image identification method for hot spots of photovoltaic cell |
| CN113466253A (en) * | 2020-03-31 | 2021-10-01 | 苏州阿特斯阳光电力科技有限公司 | Method and equipment for detecting hot spot defect of solar cell |
| CN114022482A (en) * | 2022-01-07 | 2022-02-08 | 浙江正泰智维能源服务有限公司 | Photovoltaic panel dotted hot spot detection method, device, equipment and readable storage medium |
| CN116660317A (en) * | 2023-07-25 | 2023-08-29 | 北京智芯微电子科技有限公司 | Hot spot detection method, system, processor and storage medium of photovoltaic array |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012120047A (en) * | 2010-12-02 | 2012-06-21 | Denso Corp | Display device for vehicle |
| US20150086083A1 (en) * | 2013-09-25 | 2015-03-26 | Sikorsky Aircraft Corporation | Structural hot spot and critical location monitoring system and method |
| CN104899936A (en) * | 2015-06-16 | 2015-09-09 | 深圳市联翼风电技术有限公司 | Image recognition based photovoltaic module fault prompting method and system |
| CN106338520A (en) * | 2016-09-18 | 2017-01-18 | 南京林业大学 | Recognition method of surface defects of multilayer solid wood composite floor with surface board being jointed board |
| 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 |
-
2017
- 2017-07-03 CN CN201710533118.4A patent/CN107314819B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012120047A (en) * | 2010-12-02 | 2012-06-21 | Denso Corp | Display device for vehicle |
| US20150086083A1 (en) * | 2013-09-25 | 2015-03-26 | Sikorsky Aircraft Corporation | Structural hot spot and critical location monitoring system and method |
| CN104899936A (en) * | 2015-06-16 | 2015-09-09 | 深圳市联翼风电技术有限公司 | Image recognition based photovoltaic module fault prompting method and system |
| CN106338520A (en) * | 2016-09-18 | 2017-01-18 | 南京林业大学 | Recognition method of surface defects of multilayer solid wood composite floor with surface board being jointed board |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 郭宝柱: "光伏阵列热斑的红外图像处理的研究", 《中国优秀硕士学位论文全文数据库》 * |
| 黄永华等: "光伏阵列故障状态红外图像的分割研究与实现", 《莆田学院学报》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109308685A (en) * | 2018-08-09 | 2019-02-05 | 南京邮电大学 | Infrared photovoltaic array dividing method based on Threshold segmentation and K mean cluster |
| CN110782426B (en) * | 2018-09-11 | 2022-07-12 | 成都极米科技股份有限公司 | Background extraction method and target discrimination method |
| CN110782426A (en) * | 2018-09-11 | 2020-02-11 | 成都极米科技股份有限公司 | Background extraction method and target discrimination method |
| CN109215042A (en) * | 2018-09-28 | 2019-01-15 | 吉林电力股份有限公司科技开发分公司 | A kind of photovoltaic battery panel hot spot effect detection system based on computer vision and its calculation method |
| CN109215042B (en) * | 2018-09-28 | 2021-09-03 | 吉林电力股份有限公司科技开发分公司 | Photovoltaic cell panel hot spot effect detection system based on computer vision and calculation method thereof |
| CN111953296A (en) * | 2019-05-17 | 2020-11-17 | 泰州隆基乐叶光伏科技有限公司 | Method and equipment for hot spot film selection of photovoltaic module |
| CN111953296B (en) * | 2019-05-17 | 2023-08-08 | 泰州隆基乐叶光伏科技有限公司 | Method and equipment for selecting photovoltaic module hot spots |
| CN110736565A (en) * | 2019-09-20 | 2020-01-31 | 陕西榆林能源集团横山煤电有限公司 | Unit wall temperature screening method and device |
| CN111242889A (en) * | 2019-12-03 | 2020-06-05 | 国家电投集团曲阳新能源发电有限公司 | Hot spot identification method and device for photovoltaic module |
| CN111161220A (en) * | 2019-12-11 | 2020-05-15 | 中国计量大学 | Method for detecting and positioning defects of photovoltaic assembly by utilizing infrared image splicing |
| CN111242914A (en) * | 2020-01-09 | 2020-06-05 | 武汉博晟信息科技有限公司 | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm |
| CN111242914B (en) * | 2020-01-09 | 2023-09-08 | 武汉赛摩博晟信息科技有限公司 | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm |
| CN113466253A (en) * | 2020-03-31 | 2021-10-01 | 苏州阿特斯阳光电力科技有限公司 | Method and equipment for detecting hot spot defect of solar cell |
| CN111931785A (en) * | 2020-06-19 | 2020-11-13 | 国网山西省电力公司吕梁供电公司 | Edge detection method for infrared image target of power equipment |
| CN112184711A (en) * | 2020-11-05 | 2021-01-05 | 杭州青枭科技有限公司 | Photovoltaic module defect detection and positioning method and system |
| CN112184711B (en) * | 2020-11-05 | 2024-04-02 | 杭州青枭科技有限公司 | Photovoltaic module defect detection and positioning method and system |
| CN113155288A (en) * | 2020-11-30 | 2021-07-23 | 齐鲁工业大学 | Image identification method for hot spots of photovoltaic cell |
| CN112701186A (en) * | 2020-12-25 | 2021-04-23 | 韩华新能源（启东）有限公司 | Label manufacturing method for thermosensitive camera position detection, label and detection method |
| CN114022482A (en) * | 2022-01-07 | 2022-02-08 | 浙江正泰智维能源服务有限公司 | Photovoltaic panel dotted hot spot detection method, device, equipment and readable storage medium |
| CN116660317A (en) * | 2023-07-25 | 2023-08-29 | 北京智芯微电子科技有限公司 | Hot spot detection method, system, processor and storage medium of photovoltaic array |
| CN116660317B (en) * | 2023-07-25 | 2023-12-22 | 北京智芯微电子科技有限公司 | Hot spot detection method, system, processor and storage medium of photovoltaic array |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107314819B (en) | 2019-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107314819A (en) | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image | |
| CN113378686B (en) | Two-stage remote sensing target detection method based on target center point estimation | |
| CN109919934B (en) | Liquid crystal panel defect detection method based on multi-source domain deep transfer learning | |
| CN107784661A (en) | Substation equipment infrared image classifying identification method based on region-growing method | |
| CN114758252B (en) | Image-based distributed photovoltaic roof resource segmentation and extraction method and system | |
| US11694431B2 (en) | Systems and methods for skyline prediction for cyber-physical photovoltaic array control | |
| CN107742171B (en) | Photovoltaic power station power generation power prediction method based on mobile shadow image recognition | |
| CN103162818B (en) | Based on the laser beam beamwidth evaluation method of invariant moment | |
| CN115205264A (en) | High-resolution remote sensing ship detection method based on improved YOLOv4 | |
| Lü et al. | Comprehensive improvement of camera calibration based on mutation particle swarm optimization | |
| CN113505726A (en) | Photovoltaic group string identification and positioning method in map | |
| CN104866670A (en) | GPS spatial-temporal trajectory-based road network topological change automatic detection method and system | |
| CN104123714B (en) | A kind of generation method of optimal objective detection yardstick in people flow rate statistical | |
| Salamanca et al. | On the detection of solar panels by image processing techniques | |
| CN104537367A (en) | VIN code checking method | |
| CN107481237A (en) | A kind of infrared array image hot spot detection method based on multiframe temperature characterisitic | |
| CN113902792A (en) | Building height detection method and system based on improved RetinaNet network and electronic equipment | |
| CN115457001A (en) | Photovoltaic panel foreign matter detection method, system, device and medium based on VGG network | |
| Schulz et al. | DetEEktor: Mask R-CNN based neural network for energy plant identification on aerial photographs | |
| Yang et al. | Fast simulation modeling and multiple-PS fault diagnosis of the PV array based on I–V curve conversion | |
| CN112702761B (en) | Method and system for detecting coverage hole of wireless sensor network | |
| Mehta et al. | Assessment of solar energy generation potential on roof-tops using image processing | |
| CN112950565A (en) | Method and device for detecting and positioning water leakage of data center and data center | |
| Wu et al. | Ghost-RetinaNet: Fast Shadow DetectionMethod for Photovoltaic Panels Based on Improved RetinaNet. | |
| CN110610474A (en) | Solar panel defect real-time detection method based on infrared image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190423 |