CN112465738A - Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images - Google Patents

Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images Download PDF

Info

Publication number
CN112465738A
CN112465738A CN202011520337.7A CN202011520337A CN112465738A CN 112465738 A CN112465738 A CN 112465738A CN 202011520337 A CN202011520337 A CN 202011520337A CN 112465738 A CN112465738 A CN 112465738A
Authority
CN
China
Prior art keywords
hot spot
data packet
visible light
position information
information data
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
Application number
CN202011520337.7A
Other languages
Chinese (zh)
Other versions
CN112465738B (en
Inventor
李广磊
王玥娇
孙树敏
徐征
袁森
程艳
张兴友
于芃
王士柏
滕玮
魏大钧
王楠
邢家维
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202011520337.7A priority Critical patent/CN112465738B/en
Publication of CN112465738A publication Critical patent/CN112465738A/en
Application granted granted Critical
Publication of CN112465738B publication Critical patent/CN112465738B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—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
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • 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
    • 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention provides an online operation and maintenance method and system of a photovoltaic power station based on infrared and visible light images. The method comprises the steps of obtaining an infrared image and a visible light image of a photovoltaic power station which is currently inspected, light irradiance, temperature and photovoltaic module output voltage and current; splicing and fusing an infrared image and a visible light image of the photovoltaic power station, and extracting hot spot characteristics to obtain the actual position of each hot spot; sequentially judging the shadow type of each hot spot position by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module, and further judging whether to send the hot spot position to the position information data packet to be cleaned; and executing a corresponding operation and maintenance strategy according to whether the inspection is the first inspection.

Description

Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images
Technical Field
The invention belongs to the field of online operation and maintenance of photovoltaic power stations, and particularly relates to an online operation and maintenance method and system of a photovoltaic power station based on infrared and visible light images.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Large photovoltaic power stations are generally built in desert gobi and other places where extensive and rare light sources are sufficient, but the working environment of equipment is also severe. Besides receiving light, the solar panel exposed for a long time also has to face the problems of flying stones, bird droppings, defects of the components and the like. Defective areas in the photovoltaic module (blocked, cracked, bubbled, delaminated, dirty, failed internal connections, etc.) are used as loads to dissipate the energy generated by other areas, resulting in local overheating, a phenomenon known as the "hot spot effect" of the photovoltaic module. The existence of the hot spot can consume a large amount of energy, and not only the power generation efficiency of the photovoltaic power station is seriously influenced, but also the safety of the photovoltaic power station is seriously influenced.
The inventor finds that at present, the traditional operation and maintenance mode of a photovoltaic power station mainly depends on personnel on duty and equipment for inspection, a power station operation and maintenance worker has to hold a thermal imager to regularly carry out hot spot inspection on all photovoltaic arrays of the whole power station, and the operation and maintenance mode has the problems of long troubleshooting time, high missing inspection rate, low hot spot detection accuracy rate, hysteresis of detection results and the like of the power station, so that fault upgrading is easily caused. In addition, with the continuous enlargement of the scale of the photovoltaic power station, the floor area of the photovoltaic power station is increased day by day, the operation failure frequency of a photovoltaic system is also increased continuously, the operation and maintenance workload and the operation difficulty of the photovoltaic power station are increased, and the operation and maintenance cost is also increased.
Disclosure of Invention
In order to solve at least one technical problem in the background art, the invention provides an online operation and maintenance method and system for a photovoltaic power station based on infrared and visible light images, which can timely eliminate external influence factors of hot spots of a photovoltaic module, realize automatic hot spot alarm and positioning investigation, improve operation and maintenance efficiency, reduce operation and maintenance labor cost and further ensure operation safety of the photovoltaic power station.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides an online operation and maintenance method of a photovoltaic power station based on infrared and visible light images.
An online operation and maintenance method for a photovoltaic power station based on infrared and visible light images comprises the following steps:
acquiring an infrared image and a visible light image of a photovoltaic power station which is currently inspected, light irradiance, temperature and output voltage and current of a photovoltaic module;
splicing and fusing an infrared image and a visible light image of the photovoltaic power station, and extracting hot spot characteristics to obtain the actual position of each hot spot;
sequentially judging the shadow type of each hot spot position by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module, and further judging whether to send the hot spot position to the position information data packet to be cleaned;
and executing a corresponding operation and maintenance strategy according to whether the inspection is the first inspection:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
As an implementation mode, the infrared image is preprocessed, the panoramic infrared image and the visible light image of the photovoltaic power station are spliced based on the image feature points, and fusion of the infrared image and the visible light image is achieved.
In one embodiment, hot spot extraction is performed on the fused infrared image and the fused visible light image based on an improved two-dimensional adaptive maximum threshold difference method, so that the actual position of each hot spot is obtained.
In one embodiment, the shadow type of each hot spot position is sequentially judged by adopting an improved fish shoal gray combination prediction method by combining light irradiance, temperature and photovoltaic module output voltage and current.
As an implementation mode, if the hot spot position shadow type is a soft shadow, sending an empty message to the position information data packet to be cleaned; and if the hot spot position shadow type is a hard shadow, storing the hot spot position into the position information data packet to be cleaned.
As an implementation mode, if the hot spot position coincides with the previous time, deleting the hot spot position information in the position information data packet to be cleaned and transferring the hot spot position information to the position information data packet to be manually overhauled; if the hot spot position does not coincide with the previous time, the hot spot position information in the position information data packet to be cleaned at the time is kept unchanged.
According to the position coordinates in the position information data packet to be cleaned, a particle swarm algorithm and a chaotic gravitation comprehensive algorithm are combined to plan the path of the cleaning robot.
As an implementation mode, the path of the cleaning robot is re-planned according to the current updated position information data packet to be cleaned; and generating a report to be overhauled according to the position information data packet to be overhauled manually, and then actively pushing the report to be overhauled to remote operation and maintenance personnel.
The invention provides an online operation and maintenance system of a photovoltaic power station based on infrared and visible light images.
In one or more embodiments, an online operation and maintenance system for a photovoltaic power station based on infrared and visible light images comprises:
the inspection information acquisition module is used for acquiring an infrared image and a visible light image of a currently inspected photovoltaic power station, light irradiance, temperature and photovoltaic module output voltage and current;
the hot spot position detection module is used for splicing and fusing the infrared image and the visible light image of the photovoltaic power station, extracting hot spot characteristics and obtaining the actual position of each hot spot;
the hot spot position shadow type judging module is used for sequentially judging the type of each hot spot position shadow by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module so as to judge whether to send a hot spot position to the current position information data packet to be cleaned;
and the operation and maintenance strategy execution module is used for executing a corresponding operation and maintenance strategy according to whether the current patrol is the first patrol or not:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
In one or more embodiments, an online operation and maintenance system for a photovoltaic power station based on infrared and visible light images comprises:
the information acquisition device is carried on the unmanned aerial vehicle and is used for acquiring an infrared image and a visible light image of a photovoltaic power station, light irradiance, temperature and photovoltaic module output voltage and current which are currently inspected;
the information management center is configured to splice and fuse the infrared image and the visible light image of the photovoltaic power station, extract hot spot characteristics and obtain the actual position of each hot spot;
sequentially judging the shadow type of each hot spot position by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module, and further judging whether to send the hot spot position to the position information data packet to be cleaned;
and executing a corresponding operation and maintenance strategy according to whether the inspection is the first inspection:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the method for online operation and maintenance of a photovoltaic power plant based on infrared and visible light images as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for online operation and maintenance of photovoltaic power plants based on infrared and visible light images as described above.
Compared with the prior art, the invention has the beneficial effects that:
(1) combine rotor unmanned aerial vehicle and remote control's the robot that cleans at photovoltaic power plant fortune dimension in-process, the power station image acquisition is convenient, and detection speed is fast, has reduced fortune dimension personnel's input quantity, and fortune dimension is with low costs, does not receive the topography restriction, and fortune dimension personnel accessible APP long-range knowledge photovoltaic power plant hot spot trouble current situation.
(2) The mode of combining the infrared image and the visible light image is adopted, so that the image contains more comprehensive and accurate information, the hot spot misjudgment rate is reduced, and the accurate positioning of the hot spot position is facilitated.
(3) According to the intelligent operation and maintenance method, the internal cause and the external cause of the hot spot fault of the photovoltaic power station are fully considered, the influence of external factors (soft shadow shielding and dirty surface of the photovoltaic module) of the photovoltaic module on the generation of the hot spot can be actively eliminated, and the accuracy of hot spot detection is improved.
Advantages of 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 incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a flow chart of an online operation and maintenance method of a photovoltaic power station based on infrared and visible light images in an embodiment of the invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. 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 invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
As shown in fig. 1, the online operation and maintenance method for a photovoltaic power station based on infrared and visible light images in this embodiment includes:
s101: and acquiring an infrared image and a visible light image of the currently inspected photovoltaic power station, light irradiance, temperature and photovoltaic module output voltage and current.
In specific implementation, the infrared image can be acquired by adopting an infrared camera, and the visible light image can be acquired by adopting a visible light camera; wherein, infrared camera and visible light camera all carry on unmanned aerial vehicle.
The unmanned aerial vehicle carries a visible light camera to automatically acquire an orthoimage of the photovoltaic power station, an orthoimage full map of the photovoltaic power station is generated, and a flight route of the unmanned aerial vehicle is formulated according to camera performance parameters and the arrangement of the photovoltaic array.
It should be noted here that the drone may be a rotor drone or other type of drone, and those skilled in the art may specifically select the drone according to actual situations.
In some embodiments, the number of polling or the time interval may be set according to actual conditions, such as once per week polling.
The light irradiance, the temperature and the output voltage and current of the photovoltaic module can be acquired by adopting a photovoltaic parameter acquisition unit, wherein the structure of the photovoltaic parameter acquisition unit is an existing structure, such as a photovoltaic illuminance sensor, a temperature sensor, a voltage acquisition circuit, a current acquisition circuit and the like.
S102: and splicing and fusing the infrared image and the visible light image of the photovoltaic power station, and extracting hot spot characteristics to obtain the actual position of each hot spot.
In some embodiments, the infrared image is preprocessed, and the panoramic infrared image and the visible light image of the photovoltaic power station are spliced based on the image feature points, so that the infrared image and the visible light image are fused.
The traditional hot spot detection only adopts infrared image detection, but due to the limitation of the imaging principle, the defects of fuzzy integral pixels, missing scene detail information and the like exist, so that the hot spot detection accuracy is low, missing detection and error detection are easy, the visible light image resolution is high, the infrared target can be highlighted by effectively fusing the infrared image and the visible light image, and the identifiability is increased. In order to realize the fusion of the infrared image and the visible light image of the whole photovoltaic power station, the visible light images and the infrared images are firstly spliced into a panoramic image of the station, and then the panoramic infrared image and the panoramic visible light image are fused. Because the number of the images needing to be spliced is large, the image feature points are extracted in a feature vector searching mode, the searching range of the extreme points is reduced, the matching time of the image edge feature points is reduced to a certain extent, and the purpose of rapidly splicing the images of the unmanned aerial vehicle is achieved.
Specifically, the specific process of fusing the infrared image and the visible light image comprises the following steps:
and searching for the nearest similar characteristic vectors by adopting an optimal node-first BBF (base band filter) search strategy of the K-D tree for respective characteristic vector sets of adjacent images, removing wrong registration by utilizing a PROSAC (process sample consensus) algorithm based on homography matrix constraint, and splicing and fusing a plurality of images into a complete image by adopting an improved optimal stitching point screening criterion so as to realize smooth transition and seamless splicing between the images.
It is understood that in other embodiments, other existing image fusion methods may be used to achieve fusion of the infrared image and the visible light image, and are not described in detail here.
The improved screening process for the optimal suture point screening criteria in this embodiment is as follows:
calculating the intensity value of each pixel point of the adjacent image overlapping area; each column of the first row of the adjacent image overlapping area corresponds to a suture line, and the corresponding pixel point intensity value is an initial value of the suture line criterion. Comparing the criterion values of a set number (for example, 3) of pixel points in the next row adjacent to the current point of each suture line with the criterion values of two adjacent points at the left and right of the current pixel point, selecting the pixel point with the minimum difference with the criterion of the current pixel point to connect and expand the suture line until the pixel point is expanded to the pixel point in the last row of the image, and finally selecting the criterion value and the minimum suture line from the pixel points.
The improved optimal stitching point screening criterion is small in screening calculation amount and short in time consumption, ghost images and double images in the images can be avoided, the stitching lines are natural and smooth, and interference of the stitching lines of the images in hot spot extraction of subsequent images can be effectively reduced.
In specific implementations, according to the formula
Figure BDA0002848717650000081
Calculating the intensity value of each pixel point of the adjacent image overlapping area; wherein F (x, y) represents the intensity value of the image pixel point, Fg(x, y) represents the gray difference of pixel points in the overlapped area of two adjacent original images, L (x +1, y) and L (x-1, y) respectively represent the gradient value of the two adjacent images in the x direction, and L (x, y +1) and L (x, y-1) respectively represent the gradient value of the two adjacent images in the y direction.
The ideal optimal suture line must satisfy the condition that the gray difference and the degree difference of the image pixel points are minimum. In order to find the optimal suture line in the image overlapping region, the strength value F (x, y) of each pixel point in the overlapping region is calculated through a formula, and the smaller the strength value is, the smaller the difference between two overlapping pixel points is proved to be, and the more unobvious the splicing is. The intensity value F (x, y) is calculated to help select the most natural stitching pixel points, and the image stitching quality is improved.
It should be noted that other existing methods may also be used to calculate the intensity value of the pixel point in the overlapping region of each adjacent image, which is not described here again.
In this embodiment, hot spot extraction is realized based on an improved two-dimensional adaptive maximum threshold difference method, and the actual position of each hot spot is obtained.
Specifically, the hot spot extraction process based on the improved two-dimensional adaptive maximum threshold difference method is as follows:
firstly, on the basis of two-dimensional gray level histogram according to formula
Figure BDA0002848717650000091
Obtaining two-dimensional gray level probability density of the pixels; wherein p isijIs the two-dimensional gray scale probability density of a pixel, and pij≥0；fijThe number of pixels with coordinates (i, j) in the two-dimensional histogram is shown; mxn is the grayscale image size;
then using two-dimensional maximum between-class variance Sb＝p0[(u0i-uzi)2+(u0j-uzj)2]+p1[(u1i-uzi)2+(u1j-uzj)2]A threshold value T is obtained for the evaluation function, with which the pixels of the image are divided in gray scale into (I)0，I1) Two classes, respectively, are calculated as belonging to I0，I1Probability vectors p of two classes0、p1Mean vector u0、u1And the global mean vector uz；
Setting (eta )1，η2) And according to the formula
Figure BDA0002848717650000092
(r is 0, 1) calculating (C, C) corresponding to three eta values1，C2) And according to the maximum divergence difference criterion, from (C, C)1，C2) Obtaining corresponding optimal threshold values (T, T)1，T2) Remember | T-T1L is Δ1，|T-T2L is Δ2；
Comparison of Delta1And Δ2Magnitude when Δ1And Δ2When both are greater than 1, if Δ1<Δ2Reset C2←C，C←0.5(C1+C2)，C1Does not change if Δ1>Δ2Reset C1←C，C←0.5(C1+C2)，C2The change is not changed; repeatedly calculating the optimal threshold value (T)，T1，T2) Until a Δ occurs10 or Δ2Taking the value of T at this time as the optimal segmentation threshold value T for image segmentation when the value is equal to 0*(ii) a Setting the pixel gray probability density value less than T in the image*And setting the density value to be 0, setting the density values of the gray probability of the rest pixels to be 1, and ending the algorithm.
Because the actual image is possibly influenced by factors such as noise and the like, the distribution of the actual image on the gray level histogram does not have obvious peak value information, the original self-adaptive maximum threshold difference method is one-dimensional segmentation, the probability of segmentation error and even segmentation failure is high, a two-dimensional threshold segmentation method is added for the method, the space related information of pixel points and the neighborhood of the pixel points is fully considered, the noise resistance is good in the segmentation process, the good segmentation result can be obtained, and hot spots can be quickly and effectively extracted.
It should be noted here that other existing methods can be used to extract the hot spots, such as: neural network model algorithms or deep learning algorithms, etc., which will not be described herein.
S103: and sequentially judging the shadow type of each hot spot position by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module, and further judging whether to send the hot spot position to the position information data packet to be cleaned.
If the hot spot position shadow type is a soft shadow, sending 'null' information to the position information data packet to be cleaned; and if the hot spot position shadow type is a hard shadow, storing the hot spot position into the position information data packet to be cleaned.
In some embodiments, the shadow type of each hot spot position is sequentially determined by using an improved fish school gray combination prediction method by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module.
By adopting the improved fish school gray combined prediction method, the shadow type of each hot spot position can be sequentially judged, trend item data with higher accuracy can be obtained, on the basis, the prediction accuracy of the photovoltaic output power is improved by improving the mixed fish school gray combined prediction model, the error probability of the hot spot shadow type judgment result is reduced, and the system judgment accuracy is guaranteed. Meanwhile, the whole judgment process has low calculation complexity and high information judgment processing speed.
Specifically, in the process of judging the shadow type of a hot spot position by adopting an improved fish school gray combined prediction method, collected light irradiance, temperature and photovoltaic module output voltage and current data are subjected to real-time rolling updating of a historical database, a time sequence of illumination intensity and temperature is decomposed by an improved empirical mode decomposition method based on an optimization idea to obtain smooth trend item data, then the output power of a photovoltaic module is predicted according to an improved mixed fish school gray combined prediction model, finally, error analysis is carried out on the predicted power and the measured power, the soft shadow and hard shadow fault types are judged according to the obtained model precision difference, if the model precision does not reach the second level, the data type is caused by a soft shadow, and otherwise, the data type is caused by a hard shadow.
The original empirical mode decomposition generally adopts a method of presetting a threshold value, has no self-adaptability, and causes the problem that mode aliasing easily occurs to the decomposition result, so the screening iteration criterion which can self-adaptively search the optimal screening iteration times is adopted, the mode aliasing problem is inhibited, and the decomposition precision and efficiency can be improved. The operation process of the improved empirical mode decomposition method based on the optimization idea is as follows:
(1) calculating an original rate to predict, finally carrying out error analysis on predicted power and actually measured power, judging the fault types of soft shadow and hard shadow according to the obtained model precision difference, if the model precision does not reach the second level, indicating that the data type is caused by soft shadow, otherwise, indicating an initial signal extreme value, respectively extending the left end and the right end of the signal by using extreme value extension to form N points, and solving an envelope line through a piecewise thrice Hermite interpolation algorithm;
(2) calculating the average value of the upper envelope and the lower envelope, and calculating the difference value between the original signal and the average value of the envelopes, if the difference value meets two IMF conditions: a. in the whole data sequence, the number of the crossing extreme points and the zero points is equal or different by one at most; b. at any point on the signal, the average of the local maximum and local minimum is zero, which is the first IMF component of the original signal.
(3) If the IMF condition is not met, repeating the steps (1) and (2) by taking the difference as an original signal until two IMF conditions are met;
(4) separating the first IMF component from the original signal, repeating the steps (1) to (3) by taking the smoothed information as the original signal to obtain a second IMF component, determining the iteration times according to a screening iteration criterion by analogy, and if the requirement of the screening iteration criterion is met, taking the smoothed signal for the nth-2 times as the ith IMF component of the original signal, and stopping screening iteration; otherwise, screening iteration is continued until the preset maximum value of the iteration times of each screening process is reached, and the smoothed signal of the maximum screening time is used as the ith IMF component;
(5) and (5) all IMF components in the original signal are printed out to obtain trend item data.
The screening iteration criterion is as follows: by the formula
Figure BDA0002848717650000121
Calculating an objective function; the objective function of the continuous three-time screening iteration process satisfies fin-2<fin-1<fin. Wherein f isinFor the objective function, X is the total number of sampling points of the signal, min[x]The envelope mean signal of the smoothed signal after n iterations is filtered for i IMFs,
Figure BDA0002848717650000122
is min[x]The arithmetic square value of (1).
Specifically, the improved fish school gray combined prediction model is constructed by initializing parameters, setting parameters such as artificial fish school scale, sensing distance, crowding factor, maximum trial frequency allowed by each predation, maximum iteration frequency, upper and lower limits of the visual field range of the artificial fish and further initializing the fish school, wherein the state of the ith artificial fish individual can be expressed as a vector thetai；
Calculating the adaptive value of each artificial fish, and enabling the individual artificial fish to be thetaiAdapted value of f (theta)i) The function is defined as
Figure BDA0002848717650000123
Wherein x(0)(i) Selecting the individual state of the artificial fish with the maximum food concentration and storing the individual state in a bulletin board, wherein the original sequence is n, the number of historical data of a gray model is n, alpha is a background value, and theta is an edge value correction quantity;
and (3) carrying out autonomous preferential movement on the artificial fish individual in basic behaviors of foraging, gathering, rear-end collision and the like, comparing states of the artificial fish individual, preferentially recording, ensuring that an adaptive value recorded by a bulletin board is optimal, repeatedly executing the step until the maximum iteration times is reached to obtain an optimal solution, and substituting the optimal solution into a gray model so as to establish an improved mixed fish school gray combination prediction model.
It is understood herein that in other embodiments, other prediction methods may be used to determine the hotspot location shadow category, such as a deep learning algorithm.
S104: and executing a corresponding operation and maintenance strategy according to whether the inspection is the first inspection:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
If the hot spot position coincides with the previous time, deleting the hot spot position information in the position information data packet to be cleaned and transferring the hot spot position information to the position information data packet to be manually overhauled; if the hot spot position does not coincide with the previous time, the hot spot position information in the position information data packet to be cleaned at the time is kept unchanged.
In some embodiments, the path planning of the cleaning robot is carried out by combining a particle swarm algorithm and a chaotic gravitation comprehensive algorithm according to the position coordinates in the position information data packet to be cleaned, so that the problems that the robot is easy to collide with an obstacle and fall into a local minimum value during global path planning are solved, the convergence speed of the algorithm is high, the global optimal solution can be rapidly calculated, and the accuracy of system path planning is improved.
Specifically, the path planning combining the particle swarm algorithm and the chaotic gravitation comprehensive algorithm comprises the following steps:
(1) randomly initializing particles in a search space, and setting iteration times and parameters in an algorithm;
(2) calculating the fitness function value of each particle, updating the gravity constant, and further calculating the mass and the acceleration of each particle;
(3) according to the formula
Figure BDA0002848717650000141
Updating the velocity of each particle (wherein
Figure BDA0002848717650000142
The moving speed of the particle i in the d dimension; beta is uniformly distributed in the interval [0,1 ]]A random number of (c); c. C1，c2The method is characterized in that the method is an influence coefficient of the particles under the actions of gravitation, memory and social information exchange in the algorithm operation process; gbIs the gravitational constant;
Figure BDA0002848717650000143
acceleration of particle i at time t) in d-dimension, and then according to the formula
Figure BDA0002848717650000144
Updating the position of the particles (
Figure BDA0002848717650000145
Is the position of particle i in d-dimension);
(4) repeatedly executing the steps (2) to (4) by utilizing the advantage of fast particle swarm optimization until the requirement of iteration times is met, and outputting the optimal particle solution after the position is updated
Figure BDA0002848717650000146
(5) To be provided with
Figure BDA0002848717650000147
Is centered according to the formula
Figure BDA0002848717650000148
Performing chaotic local search (where k is iteration number, k is 1,2, …; riCan follow the formula ri(k+1)＝min{rs,max{0,ri(k)+0.35(nk-|Ni(k) |) } } dynamically updated search field radius, rsFor sensing radius, nkFor the number of adjacent search fields, Ni(k) For each particle, a probability of moving to an adjacent search domain; cxd(k) Being a chaotic sequence, cxd(k)＝cxd(k-1)(1-cxd(k-1)))；
(6) If the termination condition is not met, returning to the step (2); otherwise, outputting the optimal solution of the secondary calculation.
The method of the embodiment further comprises the step of replanning the path of the cleaning robot according to the current updated position information data packet to be cleaned; and generating a report to be overhauled according to the position information data packet to be overhauled manually, and then actively pushing the report to be overhauled to remote operation and maintenance personnel.
Example two
The embodiment provides an online operation and maintenance system of photovoltaic power plant based on infrared and visible light image, it includes:
the inspection information acquisition module is used for acquiring an infrared image and a visible light image of a currently inspected photovoltaic power station, light irradiance, temperature and photovoltaic module output voltage and current;
the hot spot position detection module is used for splicing and fusing the infrared image and the visible light image of the photovoltaic power station, extracting hot spot characteristics and obtaining the actual position of each hot spot;
the hot spot position shadow type judging module is used for sequentially judging the type of each hot spot position shadow by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module so as to judge whether to send a hot spot position to the current position information data packet to be cleaned;
and the operation and maintenance strategy execution module is used for executing a corresponding operation and maintenance strategy according to whether the current patrol is the first patrol or not:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
Each module in the online operation and maintenance system of the photovoltaic power station based on the infrared and visible light images in this embodiment corresponds to each step in the online operation and maintenance method of the photovoltaic power station based on the infrared and visible light images in the first embodiment one by one, and the specific implementation process is the same, and will not be described here again.
EXAMPLE III
The embodiment provides an online operation and maintenance system of photovoltaic power plant based on infrared and visible light image, includes:
(1) the information acquisition device is carried on the unmanned aerial vehicle and used for acquiring the infrared image and the visible light image of the current patrolling photovoltaic power station, the light irradiance, the temperature and the photovoltaic module output voltage and current.
For example: carrying out automatic orthoscopic image acquisition on the photovoltaic power station by using an unmanned aerial vehicle to carry a visible light camera, generating an orthoscopic image full map of the photovoltaic power station, and formulating an unmanned aerial vehicle flight line according to camera performance parameters and the arrangement of a photovoltaic array;
the unmanned aerial vehicle carries a visible light camera and an infrared camera to shoot infrared images and visible light images of a plurality of photovoltaic power stations along a photovoltaic panel according to a flight path, the infrared images and the visible light images are transmitted to an information management center through a 4G/5G network, a flying point is returned after the inspection is finished, and the inspection is performed once per week; the photovoltaic parameter acquisition unit acquires light irradiance, temperature and photovoltaic module output voltage and current in real time and transmits the light irradiance, temperature and photovoltaic module output voltage and current to the information management center through a 4G/5G network.
Unmanned aerial vehicle here can adopt rotor unmanned aerial vehicle or the unmanned aerial vehicle of other forms, and the technical personnel in the art can come specific settings according to actual conditions.
(2) The information management center is configured to splice and fuse the infrared image and the visible light image of the photovoltaic power station, extract hot spot characteristics and obtain the actual position of each hot spot;
sequentially judging the shadow type of each hot spot position by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module, and further judging whether to send the hot spot position to the position information data packet to be cleaned;
and executing a corresponding operation and maintenance strategy according to whether the inspection is the first inspection:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
In specific implementation, the information management center transmits the position information data packet to be manually overhauled to the power station operation and maintenance APP through the 4G/5G network, and the report to be overhauled is generated in the power station operation and maintenance APP and then is actively pushed to remote operation and maintenance personnel.
The specific implementation process in the information management center is as described in the first embodiment, and will not be described here again.
Example four
The present embodiment provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the method for online operation and maintenance of a photovoltaic power plant based on infrared and visible light images as described above.
EXAMPLE five
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to implement the steps in the online operation and maintenance method of the photovoltaic power station based on the infrared and visible light images.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An online operation and maintenance method for a photovoltaic power station based on infrared and visible light images is characterized by comprising the following steps:
acquiring an infrared image and a visible light image of a photovoltaic power station which is currently inspected, light irradiance, temperature and output voltage and current of a photovoltaic module;
splicing and fusing an infrared image and a visible light image of the photovoltaic power station, and extracting hot spot characteristics to obtain the actual position of each hot spot;
sequentially judging the shadow type of each hot spot position by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module, and further judging whether to send the hot spot position to the position information data packet to be cleaned;
and executing a corresponding operation and maintenance strategy according to whether the inspection is the first inspection:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
2. The on-line operation and maintenance method for the photovoltaic power station based on the infrared and visible light images as claimed in claim 1, characterized in that the infrared images are preprocessed, and the panoramic infrared image and the visible light image of the photovoltaic power station are spliced out based on the image feature points, so as to realize the fusion of the infrared image and the visible light image;
or
And performing hot spot extraction on the fused infrared image and visible light image based on an improved two-dimensional self-adaptive maximum threshold difference method to obtain the actual position of each hot spot.
3. The on-line operation and maintenance method for photovoltaic power plants based on infrared and visible light images as claimed in claim 1, characterized in that, by combining light irradiance, temperature and photovoltaic module output voltage and current, the shadow category of each hot spot position is sequentially determined by using an improved fish school gray combination prediction method.
4. The online operation and maintenance method of the photovoltaic power station based on the infrared and visible light images as claimed in claim 1 or 3, characterized in that if the hot spot position shadow type is soft shadow, sending "null" information to the current position information data packet to be cleaned; and if the hot spot position shadow type is a hard shadow, storing the hot spot position into the position information data packet to be cleaned.
5. The online operation and maintenance method of the photovoltaic power station based on the infrared and visible light images as claimed in claim 1, characterized in that if the hot spot position of the current time coincides with the hot spot position of the last time, the hot spot position information in the position information data packet to be cleaned of the current time is deleted and transferred to the position information data packet to be manually overhauled; if the hot spot position does not coincide with the previous time, the hot spot position information in the position information data packet to be cleaned at the time is kept unchanged.
6. The online operation and maintenance method of the photovoltaic power station based on the infrared and visible light images as claimed in claim 1, characterized in that the path planning of the cleaning robot is performed by combining a particle swarm algorithm and a chaotic gravitation integration algorithm according to the position coordinates in the position information data packet to be cleaned;
or
Replanning the path of the cleaning robot according to the current updated position information data packet to be cleaned; and generating a report to be overhauled according to the position information data packet to be overhauled manually, and then actively pushing the report to be overhauled to remote operation and maintenance personnel.
7. The utility model provides a photovoltaic power plant online operation and maintenance system based on infrared and visible light image which characterized in that includes:
the inspection information acquisition module is used for acquiring an infrared image and a visible light image of a currently inspected photovoltaic power station, light irradiance, temperature and photovoltaic module output voltage and current;
the hot spot position detection module is used for splicing and fusing the infrared image and the visible light image of the photovoltaic power station, extracting hot spot characteristics and obtaining the actual position of each hot spot;
the hot spot position shadow type judging module is used for sequentially judging the type of each hot spot position shadow by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module so as to judge whether to send a hot spot position to the current position information data packet to be cleaned;
and the operation and maintenance strategy execution module is used for executing a corresponding operation and maintenance strategy according to whether the current patrol is the first patrol or not:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
8. The utility model provides a photovoltaic power plant online operation and maintenance system based on infrared and visible light image which characterized in that includes:
the information acquisition device is carried on the unmanned aerial vehicle and is used for acquiring an infrared image and a visible light image of a photovoltaic power station, light irradiance, temperature and photovoltaic module output voltage and current which are currently inspected;
the information management center is configured to splice and fuse the infrared image and the visible light image of the photovoltaic power station, extract hot spot characteristics and obtain the actual position of each hot spot;
sequentially judging the shadow type of each hot spot position by combining the light irradiance, the temperature and the output voltage and current of the photovoltaic module, and further judging whether to send the hot spot position to the position information data packet to be cleaned;
and executing a corresponding operation and maintenance strategy according to whether the inspection is the first inspection:
if the inspection is performed for the first time, planning a path of the cleaning robot according to the hot spot position coordinates in the position information data packet to be cleaned, issuing a cleaning instruction to the cleaning robot, and continuing the inspection after the cleaning is completed;
if the data packet is not inspected for the first time, all hot spot positions of the position information data packet to be cleaned are correspondingly compared with the hot spot positions of the last time, and the position information data packet to be cleaned and the position information data packet to be manually overhauled are updated according to the comparison result.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method for on-line operation and maintenance of a photovoltaic power plant based on infrared and visible light images of any one of claims 1 to 6.
10. 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, when executing the program, implements the steps of the infrared and visible light image based photovoltaic power plant online operation and maintenance method according to any of claims 1-6.
CN202011520337.7A 2020-12-21 2020-12-21 Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images Active CN112465738B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011520337.7A CN112465738B (en) 2020-12-21 2020-12-21 Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011520337.7A CN112465738B (en) 2020-12-21 2020-12-21 Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images

Publications (2)

Publication Number Publication Date
CN112465738A true CN112465738A (en) 2021-03-09
CN112465738B CN112465738B (en) 2023-05-05

Family

ID=74804648

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011520337.7A Active CN112465738B (en) 2020-12-21 2020-12-21 Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images

Country Status (1)

Country Link
CN (1) CN112465738B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112927222A (en) * 2021-03-29 2021-06-08 福州大学 Method for realizing multi-type photovoltaic array hot spot detection based on hybrid improved Faster R-CNN
CN113139955A (en) * 2021-05-12 2021-07-20 华北电力大学 Photovoltaic module fault identification method and system based on double-light image
CN113284124A (en) * 2021-06-07 2021-08-20 南京航空航天大学 Photovoltaic panel defect detection method based on unmanned aerial vehicle vision
CN113344475A (en) * 2021-08-05 2021-09-03 国网江西省电力有限公司电力科学研究院 Transformer bushing defect identification method and system based on sequence modal decomposition
CN114024504A (en) * 2021-11-11 2022-02-08 国网青海省电力公司清洁能源发展研究院 Photovoltaic array state monitoring method, device and system adopting 5G
CN114951068A (en) * 2022-06-01 2022-08-30 宁波欧达光电有限公司 Photovoltaic module with shadow fault type determination system and cleaning mechanism
CN116667775A (en) * 2023-07-14 2023-08-29 北京国领智能科技有限公司 Unmanned aerial vehicle-based photovoltaic electric field automatic cleaning method and system
CN116862482A (en) * 2023-09-04 2023-10-10 成都昱风能源有限公司 Power station inspection system and method based on artificial intelligence and big data analysis
CN117200971A (en) * 2023-09-11 2023-12-08 重庆千信新能源有限公司 New energy power data transmission method for photovoltaic module based on block chain
CN117237590A (en) * 2023-11-10 2023-12-15 华能新能源股份有限公司山西分公司 Photovoltaic module hot spot identification method and system based on image identification

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108364003A (en) * 2018-04-28 2018-08-03 国网河南省电力公司郑州供电公司 The electric inspection process method and device merged based on unmanned plane visible light and infrared image
CN108961154A (en) * 2018-07-13 2018-12-07 福州大学 Based on the solar cell hot spot detection method for improving non-down sampling contourlet transform
CN109379040A (en) * 2018-11-26 2019-02-22 武汉理工大学 Photovoltaic plant inspection cleaning unmanned plane and its clean method based on machine vision
CN110266268A (en) * 2019-06-26 2019-09-20 武汉理工大学 A kind of photovoltaic module fault detection method based on image co-registration identification
CN110472510A (en) * 2019-07-16 2019-11-19 上海电力学院 Based on infrared and visual picture electrical equipment fault detection method and assessment equipment
CN111738097A (en) * 2020-05-29 2020-10-02 理光软件研究所（北京）有限公司 Target classification method and device, electronic equipment and readable storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108364003A (en) * 2018-04-28 2018-08-03 国网河南省电力公司郑州供电公司 The electric inspection process method and device merged based on unmanned plane visible light and infrared image
CN108961154A (en) * 2018-07-13 2018-12-07 福州大学 Based on the solar cell hot spot detection method for improving non-down sampling contourlet transform
CN109379040A (en) * 2018-11-26 2019-02-22 武汉理工大学 Photovoltaic plant inspection cleaning unmanned plane and its clean method based on machine vision
CN110266268A (en) * 2019-06-26 2019-09-20 武汉理工大学 A kind of photovoltaic module fault detection method based on image co-registration identification
CN110472510A (en) * 2019-07-16 2019-11-19 上海电力学院 Based on infrared and visual picture electrical equipment fault detection method and assessment equipment
CN111738097A (en) * 2020-05-29 2020-10-02 理光软件研究所（北京）有限公司 Target classification method and device, electronic equipment and readable storage medium

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
宋振坤 等: "应用于无人机平台的红外图像拼接技术研究", 《红外技术》 *
李巧昱: "鱼群灰色预测模型在电力负荷预测中的应用", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技II辑（月刊）》 *
沈冬梅: "基于改进引力搜索算法的电力系统机组组合问题的研究", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技II辑（月刊）》 *
郭宝柱: "光伏阵列热斑的红外图像处理的研究", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技II辑（月刊）》 *
陈宝华 等: "基于功率预测的光伏组件阴影故障类型判定", 《电测与仪表》 *

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112927222A (en) * 2021-03-29 2021-06-08 福州大学 Method for realizing multi-type photovoltaic array hot spot detection based on hybrid improved Faster R-CNN
CN112927222B (en) * 2021-03-29 2022-10-04 福州大学 Method for realizing multi-type photovoltaic array hot spot detection based on hybrid improved Faster R-CNN
CN113139955A (en) * 2021-05-12 2021-07-20 华北电力大学 Photovoltaic module fault identification method and system based on double-light image
CN113139955B (en) * 2021-05-12 2024-02-27 华北电力大学 Photovoltaic module fault identification method and system based on double-light image
CN113284124B (en) * 2021-06-07 2022-02-11 南京航空航天大学 Photovoltaic panel defect detection method based on unmanned aerial vehicle vision
CN113284124A (en) * 2021-06-07 2021-08-20 南京航空航天大学 Photovoltaic panel defect detection method based on unmanned aerial vehicle vision
CN113344475B (en) * 2021-08-05 2021-12-31 国网江西省电力有限公司电力科学研究院 Transformer bushing defect identification method and system based on sequence modal decomposition
CN113344475A (en) * 2021-08-05 2021-09-03 国网江西省电力有限公司电力科学研究院 Transformer bushing defect identification method and system based on sequence modal decomposition
CN114024504A (en) * 2021-11-11 2022-02-08 国网青海省电力公司清洁能源发展研究院 Photovoltaic array state monitoring method, device and system adopting 5G
CN114024504B (en) * 2021-11-11 2023-09-22 国网青海省电力公司清洁能源发展研究院 Photovoltaic array state monitoring method, device and system adopting 5G
CN114951068A (en) * 2022-06-01 2022-08-30 宁波欧达光电有限公司 Photovoltaic module with shadow fault type determination system and cleaning mechanism
CN116667775A (en) * 2023-07-14 2023-08-29 北京国领智能科技有限公司 Unmanned aerial vehicle-based photovoltaic electric field automatic cleaning method and system
CN116862482A (en) * 2023-09-04 2023-10-10 成都昱风能源有限公司 Power station inspection system and method based on artificial intelligence and big data analysis
CN116862482B (en) * 2023-09-04 2023-11-07 成都昱风能源有限公司 Power station inspection system and method based on artificial intelligence and big data analysis
CN117200971A (en) * 2023-09-11 2023-12-08 重庆千信新能源有限公司 New energy power data transmission method for photovoltaic module based on block chain
CN117200971B (en) * 2023-09-11 2024-03-26 重庆千信新能源有限公司 New energy power data transmission method for photovoltaic module based on block chain
CN117237590A (en) * 2023-11-10 2023-12-15 华能新能源股份有限公司山西分公司 Photovoltaic module hot spot identification method and system based on image identification
CN117237590B (en) * 2023-11-10 2024-04-02 华能新能源股份有限公司山西分公司 Photovoltaic module hot spot identification method and system based on image identification

Also Published As

Publication number Publication date
CN112465738B (en) 2023-05-05

Similar Documents

Publication Publication Date Title
CN112465738A (en) Photovoltaic power station online operation and maintenance method and system based on infrared and visible light images
CN111220159B (en) Path optimization method for multi-unmanned aerial vehicle cooperative inspection task
CN112633535A (en) Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image
CN108508916B (en) Control method, device and equipment for unmanned aerial vehicle formation and storage medium
CN110200598A (en) A kind of large-scale plant that raises sign exception birds detection system and detection method
CN115861855B (en) Operation and maintenance monitoring method and system for photovoltaic power station
CN109710595B (en) Method for constructing bird damage hotspot diagram of power transmission corridor based on limited information
CN114355907B (en) Cloud-based intelligent garbage identification and cleaning method and system
CN111539355A (en) Photovoltaic panel foreign matter detection system and detection method based on deep neural network
CN109818574A (en) System and method based on the detection of unmanned plane aerial photography technology photovoltaic solar panel hot spot
CN108960134A (en) A kind of patrol UAV image mark and intelligent identification Method
CN116301055A (en) Unmanned aerial vehicle inspection method and system based on building construction
CN116797944A (en) Detection method and system for identifying cleanliness of photovoltaic panel based on unmanned aerial vehicle image
CN116310891A (en) Cloud-edge cooperative transmission line defect intelligent detection system and method
CN111797831A (en) BIM and artificial intelligence based parallel abnormality detection method for poultry feeding
CN116203970A (en) Intelligent obstacle avoidance method and system for inspection robot
CN115297303B (en) Image data acquisition and processing method and device suitable for power grid power transmission and transformation equipment
Bitton et al. Hydra: A framework and algorithms for mixed-initiative UAV-assisted search and rescue
CN116109047A (en) Intelligent scheduling method based on three-dimensional intelligent detection
CN111783726A (en) Herding livestock outlier video acquisition method based on artificial intelligence and BIM
CN115861821B (en) Ecological environment monitoring and protecting method based on multi-objective optimization
CN116909320B (en) Electric power collaborative inspection strategy analysis method based on ant colony algorithm
CN117237814B (en) Large-scale orchard insect condition monitoring method based on attention mechanism optimization
CN109034105B (en) Tuna fishery position prediction method based on unmanned aerial vehicle
WO2024040566A1 (en) Transformer substation intelligent inspection system and method based on image recognition

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