WO2024021548A1 - Procédé et système d'exploitation et de maintenance intelligents de production d'énergie photovoltaïque et support de stockage - Google Patents

Procédé et système d'exploitation et de maintenance intelligents de production d'énergie photovoltaïque et support de stockage Download PDF

Info

Publication number
WO2024021548A1
WO2024021548A1 PCT/CN2023/073799 CN2023073799W WO2024021548A1 WO 2024021548 A1 WO2024021548 A1 WO 2024021548A1 CN 2023073799 W CN2023073799 W CN 2023073799W WO 2024021548 A1 WO2024021548 A1 WO 2024021548A1
Authority
WO
WIPO (PCT)
Prior art keywords
power generation
photovoltaic
photovoltaic power
image information
status
Prior art date
Application number
PCT/CN2023/073799
Other languages
English (en)
Chinese (zh)
Inventor
吴跃波
朱征勇
黄绍宽
陈娅
罗友珍
Original Assignee
重庆跃达新能源有限公司
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 重庆跃达新能源有限公司 filed Critical 重庆跃达新能源有限公司
Publication of WO2024021548A1 publication Critical patent/WO2024021548A1/fr

Links

Classifications

    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • 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
    • G06Q10/20—Administration of product repair or maintenance
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/17—Terrestrial scenes taken from planes or by drones
    • 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

Definitions

  • the present invention relates to the technical field of photovoltaic power generation, and specifically to photovoltaic power generation intelligent operation and maintenance methods, systems and storage media.
  • a photovoltaic power station refers to a photovoltaic power generation system that uses solar energy and uses special materials such as crystalline silicon panels, inverters and other electronic components. It is connected to the power grid and delivers power to the grid. Because solar energy has inexhaustible and With the advantages of being inexhaustible, safe and reliable, and not polluting the environment or destroying the ecological balance, it is regarded as one of the renewable energy sources with the best development prospects. With the continuous increase of photovoltaic power stations, the operation and maintenance work of photovoltaic power stations is becoming more and more important. Be taken seriously. In actual operation, the shielding of dust and other debris will reduce the absorption of solar radiation by the module, affect the surface heat dissipation of the module, and reduce the photoelectric conversion efficiency.
  • the photovoltaic power generation system needs to be operated and maintained (referred to as operation and maintenance).
  • operation and maintenance The current operation and maintenance method of photovoltaic power stations still relies on manual work, relying on staff to use scanners to inspect hot spots and use artificial naked eye observation to detect dust.
  • Most photovoltaic power plants are built in harsh environments such as the wild or deserts. It is usually difficult for workers to reach the operating area, which brings a lot of inconvenience to troubleshooting and processing during the operation and maintenance process. At the same time, it is also time-consuming to rely on manual troubleshooting for large photovoltaic power plants. laborious and less efficient problem.
  • the present invention is intended to provide an intelligent operation and maintenance method for photovoltaic power generation. It identifies photovoltaic components and their status through images, and generates corresponding maintenance plans based on the status of the photovoltaic components. It can save a lot of manpower and effectively improve the troubleshooting and processing of photovoltaic power generation operation and maintenance. s efficiency.
  • the technical solution provided by the invention is: a photovoltaic power generation intelligent operation and maintenance method, which includes the following steps:
  • S1 Collect image information of the photovoltaic power generation area
  • S4 Generate maintenance plans based on the status of photovoltaic components.
  • the working principle and advantage of the present invention are that the method of the present invention mainly uses image recognition to troubleshoot problems and generate solutions.
  • image information of the photovoltaic power generation area is collected. This process replaces the steps of manual inspection and naked eye observation. Then the collected images are analyzed to identify the specific information of the photovoltaic components, including type, model, connection relationship and other information.
  • the method of the present invention analyzes the current operating status of the photovoltaic component through historical image information. Finally, the corresponding maintenance plan is generated based on the current operating status. At this point, the staff can know the current problems of the photovoltaic power station, the operating status, and the corresponding maintenance plan.
  • the above plan eliminates the need for manual inspection by staff and can save money. A large number of manpower can effectively improve the efficiency of troubleshooting and processing during photovoltaic power generation operation and maintenance.
  • the S1 includes:
  • S1-2 Analyze power generation data and identify photovoltaic power generation areas with abnormal power generation
  • S1-3 Collect image information of photovoltaic power generation areas with abnormal power generation.
  • the current photovoltaic power stations occupy an increasingly larger area, and there is also a large workload for image recognition of the entire station.
  • the photovoltaic power generation data analysis is first improved before image recognition to narrow down the troubleshooting. scope. Taking the area as a unit, the recent power generation data is analyzed and compared with the past power generation data. Based on the attenuation ratio of the power generation, it is judged whether the power generation of the photovoltaic power generation area is abnormal, and then the next step of image recognition of the abnormal power generation area is carried out. The above method is helpful to improve the efficiency of troubleshooting.
  • image information of the photovoltaic power generation area is collected through a drone or a surveillance camera, and the image information includes visible light images and infrared images.
  • the image information collected includes visible light images and infrared images. Visible light images can troubleshoot the appearance and color of photovoltaic components. Infrared images can identify photovoltaic illumination on photovoltaic panels and other components, and determine whether there are hot spots through abnormal photovoltaic illumination. phenomenon and discover problems that are difficult to observe with the naked eye.
  • the S2 includes:
  • S2-1 Perform a clearing process on the image information.
  • the clearing process is to analyze the image frame by frame and select the best color difference.
  • Several small images through the image multi-frame fusion algorithm, generate an image with stable ambient light and enhance the contrast and color of the image;
  • S2-2 Analyze the sharpened image information and identify photovoltaic components.
  • the collected image information is processed to clarify it to facilitate the subsequent identification process.
  • the S2-2 includes:
  • S2-2-1 Analyze the sharpened image information and obtain the target outline
  • S2-2-2 Compare the target outline with the component model library to identify specific photovoltaic components.
  • the specific information such as the model of the photovoltaic component is determined through the contour recognition method. After obtaining the specific photovoltaic component, targeted inspection can be carried out, which is conducive to rapid troubleshooting of problems.
  • the S3 includes:
  • S3-1 According to the photovoltaic component, obtain several inspection items of the photovoltaic component;
  • S3-2 Analyze the status of each inspection item of the photovoltaic component based on historical image information.
  • the current status of each inspection item can be determined based on comparative analysis of the before and after images.
  • the above method can quickly identify external problems of photovoltaic components and is suitable for a wide range of inspections of large photovoltaic stations.
  • image recognition a more comprehensive external inspection of photovoltaic components can be carried out, which is subdivided into aspects such as shape integrity, covering, photovoltaic illumination and nearby debris.
  • the algorithm based on the contour recognition and color recognition of visible light images can analyze and identify the percentage of shape integrity of the photovoltaic component, that is, whether there are defects, deformations, rusts, etc.
  • the real-time photovoltaic illumination of photovoltaic components can be identified through infrared images. According to the difference before and after the photovoltaic illumination images, the hot spots and hot spot locations on the photovoltaic components can be identified.
  • the S4 includes:
  • S4-1 Generate several maintenance plans based on the status of photovoltaic components
  • S4-2 Obtain the lighting conditions and select a maintenance plan based on the lighting conditions.
  • each inspection item of photovoltaic components According to the status of each inspection item of photovoltaic components, multiple corresponding maintenance plans are generated, and then specific maintenance plans are selected according to the lighting conditions to avoid affecting the power generation efficiency of the photovoltaic power station during the maintenance process and avoiding additional economic losses.
  • the S3 also includes:
  • S3-3 Calculate the predicted power generation loss of photovoltaic components based on the status of each inspection item
  • S3-4 Compare the predicted power generation loss with the actual power generation loss, and analyze the causes of power generation loss
  • the causes of power generation loss include external causes and internal causes, and the status of the photovoltaic component includes external status and internal status.
  • the specific internal causes need to be analyzed. Based on the internal and external reasons, the external and internal states of the photovoltaic components are analyzed and the internal and external states of the photovoltaic components are counted to facilitate the subsequent steps to generate corresponding maintenance plans for the internal and external states of the photovoltaic components.
  • the present invention also provides a photovoltaic power generation intelligent operation and maintenance system, which adopts the above-mentioned photovoltaic power generation intelligent operation and maintenance method.
  • the present invention also provides a computer-readable storage medium.
  • a computer program is stored on the storage medium.
  • the computer program is executed by a processor, the above-mentioned intelligent operation and maintenance method for photovoltaic power generation is implemented.
  • Figure 1 is a logical block diagram of the intelligent operation and maintenance method of photovoltaic power generation according to an embodiment of the present invention.
  • this embodiment discloses a photovoltaic power generation intelligent operation and maintenance method, which specifically includes the following steps (the numbers of each step in this solution are only used to distinguish the steps and do not limit the specific execution order of each step, and each step also Can be performed simultaneously):
  • S1-1 Obtain photovoltaic power generation data. Obtain the recent power generation data of the photovoltaic power station.
  • S1-2 Analyze the power generation data and identify photovoltaic power generation areas with abnormal power generation. Taking the area as a unit, the recent power generation data is analyzed and compared with the past power generation data, and based on the attenuation ratio of the power generation, it is judged whether the power generation of the photovoltaic power generation area is abnormal.
  • S1-3 Collect image information of photovoltaic power generation areas with abnormal power generation. After determining the photovoltaic power generation area with abnormal power generation, collect images of the photovoltaic power generation area through the dynamic camera of the drone or the fixed surveillance camera of the photovoltaic power generation area.
  • the cameras for image collection include visible light cameras and infrared cameras, which can Visible light images and infrared images are collected separately.
  • the images collected in this embodiment are mainly outdoor photovoltaic panels and other components.
  • S2-1 Perform a clearing process on the image information.
  • the clearing process is to analyze the image frame by frame, select several images with the smallest color difference, and use a multi-frame image fusion algorithm to generate an image with stable ambient light and enhance the image quality. Contrast and color.
  • the initially collected images are usually blurry and lack clarity, which affects the next step of analysis and identification.
  • This embodiment mainly aims at the problem of unclear collected images caused by flickering of ambient light at the photovoltaic power generation site.
  • the collected image information is analyzed, several images with the smallest color difference are selected, and the multi-frame image fusion algorithm is used to correspond to the multi-frame images at different times.
  • the gray values of the pixels are added together to obtain their time-average image.
  • S2-2-1 Analyze the sharpened image information and obtain the target contour.
  • the processed image information is processed layer by layer to obtain the target contour curve in the image.
  • S2-2-2 Compare the target outline with the component model library to identify specific photovoltaic components. Compare the target contour curve with the model component library of the database, and identify the specific model of the photovoltaic equipment there, such as photovoltaic panels, combiner boxes, inverters and other components through image similarity matching and BP neural network algorithms.
  • S3-1 According to the photovoltaic component, obtain several inspection items of the photovoltaic component.
  • the specific photovoltaic component is identified, and the main inspection items of the photovoltaic component are obtained according to the operation and maintenance procedures of the specific model of the photovoltaic component, and organized into a list of inspection items.
  • the main inspection items include the appearance integrity and covering of the photovoltaic component. , photovoltaic illumination and nearby debris. For example, if the identified photovoltaic component is a photovoltaic panel, the shape, coverage, and Further inspections will be conducted on items such as objects and photovoltaic illumination.
  • S3-2 Analyze the status of each inspection item of the photovoltaic component based on historical image information.
  • the above inspection items mainly obtain the historical image information of the photovoltaic component, and judge the current status of each inspection item based on the comparative analysis of the before and after images.
  • the photovoltaic panel is used as the inspection object.
  • the algorithm of contour recognition and color recognition of the visible light image can analyze and identify the shape integrity percentage of the photovoltaic component, that is, whether there are defects, deformations, rusts, etc. in the shape; the coverage of the photovoltaic component
  • the condition of objects that is, the coverage and proportion of foreign objects such as dust, bird droppings, leaves, etc.
  • the real-time photovoltaic illumination of the photovoltaic panel can be identified through infrared images. According to the difference before and after the photovoltaic illumination image, the hot spot condition and hot spot location on the photovoltaic panel can be identified.
  • S4-1 Generate several maintenance plans based on the status of photovoltaic components. According to the status of each inspection item of the photovoltaic components, multiple corresponding maintenance plans are generated. For example, for the problem of covering on the photovoltaic panels, during the maintenance process, you can choose rag cleaning or flushing cleaning, select the water temperature for flushing and cleaning, etc., specific Plan selection also requires subsequent judgment.
  • S4-2 Obtain the lighting conditions and select a maintenance plan based on the lighting conditions.
  • the illumination conditions obtained in this embodiment include illumination angle and photovoltaic temperature. Choosing specific maintenance plans based on light conditions is mainly to avoid affecting the power generation efficiency of the photovoltaic power station during the maintenance process and avoid causing additional economic losses. For example, in the maintenance plan generated above for the problem of covering on photovoltaic panels, there is a rag cleaning or flushing cleaning plan. First, the current illumination angle is obtained, and the coincidence degree of the illumination angle and the orientation angle of the photovoltaic array is compared. If the coincidence degree is high (difference) value angle within 15 degrees), the current illumination angle is direct light.
  • the illumination angle is direct light Choose flush cleaning, that is, flush with water from a distance to avoid the impact of artificial occlusion on the photovoltaic array. If the overlap between the current illumination angle and the orientation angle of the photovoltaic array is low (the difference angle exceeds 15 degrees), then the current illumination angle is scattered light and the light does not directly illuminate the photovoltaic array. You can use a rag with a more detailed cleaning effect to clean.
  • the cleaning process generally uses clean water and a flexible brush or rag for cleaning.
  • the surface temperature of the photovoltaic array module is higher. Direct contact with cold water may cause damage to the glass or components, so it is also necessary to obtain the surface of the photovoltaic module.
  • Temperature select the appropriate cleaning water temperature according to the photovoltaic surface temperature.
  • the temperature difference between the photovoltaic surface temperature and the cleaning water temperature is no more than 8°C, which can avoid irreversible damage to the photovoltaic panels caused by excessive temperature differences.
  • step S3 also includes the following steps:
  • S3-3 Calculate the predicted power generation loss of photovoltaic components based on the status of each inspection item.
  • the external status of the photovoltaic component is identified from the image analysis, such as the shape integrity of the photovoltaic panel, surface coverage, and surrounding debris.
  • S3-4 Compare the predicted power generation loss with the actual power generation loss, and analyze the causes of power generation loss. Compare and analyze the calculated predicted power generation loss with the actual power generation loss. For example, whether the change pattern of the predicted power generation loss due to photovoltaic panel shading is consistent with the actual power generation loss. If the difference between the two is not large, then the current power generation loss is judged. The amount is caused by external causes. If the difference between the two is large, it is judged that in addition to external causes, there are also internal causes of the photovoltaic components that cause the loss of power generation.
  • S3-5 Analyze the status of photovoltaic components based on the causes of power generation loss.
  • the causes of power generation loss include external causes obtained through image recognition and internal causes obtained through data analysis. Based on both internal and external causes, the external and internal states of the photovoltaic components are analyzed. For example, currently one-half of the external area of photovoltaic panels is blocked, and there are large line losses and aging of photovoltaic panels inside. Statistics of the internal and external status of photovoltaic components will facilitate subsequent steps to generate corresponding maintenance plans based on the internal and external status of photovoltaic components.
  • the method of the present invention not only uses images to identify the external status of photovoltaic components, but also uses this technology to analyze and identify whether there are problems inside the photovoltaic components based on actual power generation data, and further determines the internal status of the photovoltaic components based on historical data analysis. Because this solution can more realistically divide the internal and external problems of photovoltaic components, it can more accurately identify the current status of photovoltaic components.
  • This embodiment also provides a photovoltaic power generation intelligent operation and maintenance system, which adopts the above photovoltaic power generation intelligent operation and maintenance method.
  • This embodiment also provides a computer-readable storage medium.
  • a computer program is stored on the storage medium.
  • the computer program is executed by a processor, the above-mentioned intelligent operation and maintenance method for photovoltaic power generation is implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Tourism & Hospitality (AREA)
  • Computing Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Medical Informatics (AREA)
  • Operations Research (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Game Theory and Decision Science (AREA)
  • Remote Sensing (AREA)
  • Development Economics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Photovoltaic Devices (AREA)

Abstract

La présente invention se rapporte au domaine technique de la production d'énergie photovoltaïque. La présente invention divulgue un procédé d'exploitation et de maintenance intelligents de production d'énergie photovoltaïque, qui comprend les étapes suivantes : l'étape S1 consistant à collecter des informations d'image d'une zone de production d'énergie photovoltaïque ; l'étape S2 consistant à analyser les informations d'image et à identifier une partie photovoltaïque ; l'étape S3 consistant, en combinaison avec des informations d'image historiques, à analyser l'état de la partie photovoltaïque ; et l'étape S4 consistant à générer une solution de maintenance en fonction de l'état de la partie photovoltaïque. La présente invention identifie une partie photovoltaïque et son état sur la base d'images et génère une solution de maintenance correspondante en fonction de l'état de la partie photovoltaïque, ce qui permet d'économiser une grande quantité de main-d'œuvre et d'augmenter efficacement l'efficacité de dépannage et de traitement pendant des processus d'exploitation et de maintenance de production d'énergie photovoltaïque.
PCT/CN2023/073799 2022-07-29 2023-01-30 Procédé et système d'exploitation et de maintenance intelligents de production d'énergie photovoltaïque et support de stockage WO2024021548A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210907397.7A CN115169730A (zh) 2022-07-29 2022-07-29 光伏发电智能运维方法、系统及存储介质
CN202210907397.7 2022-07-29

Publications (1)

Publication Number Publication Date
WO2024021548A1 true WO2024021548A1 (fr) 2024-02-01

Family

ID=83478137

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/073799 WO2024021548A1 (fr) 2022-07-29 2023-01-30 Procédé et système d'exploitation et de maintenance intelligents de production d'énergie photovoltaïque et support de stockage

Country Status (2)

Country Link
CN (1) CN115169730A (fr)
WO (1) WO2024021548A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118071033A (zh) * 2024-04-18 2024-05-24 徐州太一世纪能源科技有限公司 一种光伏发电效率分析评价方法
CN118139255A (zh) * 2024-04-30 2024-06-04 无锡照明股份有限公司 一种基于光伏发电的景观灯智能控制方法
CN118367865A (zh) * 2024-06-18 2024-07-19 国网浙江省电力有限公司 基于动态成图的分布式光伏异常监测方法
CN118399888A (zh) * 2024-06-27 2024-07-26 沛煜光电科技(上海)有限公司 离线式光伏组件el综合视觉缺陷检测系统及方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115169730A (zh) * 2022-07-29 2022-10-11 重庆跃达新能源有限公司 光伏发电智能运维方法、系统及存储介质
CN116089790A (zh) * 2022-12-02 2023-05-09 阳光电源（上海）有限公司 一种光伏组件发电量损失的计算方法、装置及电子设备
CN116307915B (zh) * 2023-03-28 2024-04-02 青海德坤电力集团有限公司 一种基于云端技术的远程光伏发电运维管控系统
CN117172962B (zh) * 2023-07-17 2024-04-16 南京工业职业技术大学 基于电力系统的用电节能方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110149002A (zh) * 2019-04-11 2019-08-20 佛山职业技术学院 一种光伏电站无人化运维方法、装置及系统
CN110266268A (zh) * 2019-06-26 2019-09-20 武汉理工大学 一种基于图像融合识别的光伏组件故障检测方法
CN112465812A (zh) * 2020-12-16 2021-03-09 合肥阳光智维科技有限公司 光伏组件的灰尘检测装置及方法
US20210167726A1 (en) * 2017-12-14 2021-06-03 Acciona Energia S.A. Automated photovoltaic plant inspection system and method
CN113554610A (zh) * 2021-07-19 2021-10-26 合肥阳光智维科技有限公司 一种光伏组件运行状态检测方法及其应用装置
CN114596267A (zh) * 2022-02-28 2022-06-07 几何智慧城市科技(广州)有限公司 一种光伏电站的监测运维方法、系统、设备、及存储介质
CN115169730A (zh) * 2022-07-29 2022-10-11 重庆跃达新能源有限公司 光伏发电智能运维方法、系统及存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106040625B (zh) * 2016-07-28 2018-01-12 兰州理工大学 清洁刷能自适应调节的太阳能光伏板清洁设备
CN107679672A (zh) * 2017-10-20 2018-02-09 中冶华天南京电气工程技术有限公司 一种基于积尘发电损失预测的光伏电站清洗时机辅助决策方法
WO2019144317A1 (fr) * 2018-01-24 2019-08-01 Honeywell International Inc. Inspection de panneau solaire par un véhicule aérien sans pilote
CN108809258A (zh) * 2018-08-21 2018-11-13 佛山职业技术学院 一种光伏组件热斑检测系统及热斑检测方法
CN109063855A (zh) * 2018-08-30 2018-12-21 北京酷车易美网络科技有限公司 用于车辆车况鉴定的辅助处理方法及装置
CN111797725A (zh) * 2020-06-18 2020-10-20 浙江大华技术股份有限公司 一种设备状态检测方法、装置及系统
CN114781179B (zh) * 2022-05-12 2023-03-28 广东华矩检测技术有限公司 基于光纤通信信息采集光伏电站发电量损失核定方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210167726A1 (en) * 2017-12-14 2021-06-03 Acciona Energia S.A. Automated photovoltaic plant inspection system and method
CN110149002A (zh) * 2019-04-11 2019-08-20 佛山职业技术学院 一种光伏电站无人化运维方法、装置及系统
CN110266268A (zh) * 2019-06-26 2019-09-20 武汉理工大学 一种基于图像融合识别的光伏组件故障检测方法
CN112465812A (zh) * 2020-12-16 2021-03-09 合肥阳光智维科技有限公司 光伏组件的灰尘检测装置及方法
CN113554610A (zh) * 2021-07-19 2021-10-26 合肥阳光智维科技有限公司 一种光伏组件运行状态检测方法及其应用装置
CN114596267A (zh) * 2022-02-28 2022-06-07 几何智慧城市科技(广州)有限公司 一种光伏电站的监测运维方法、系统、设备、及存储介质
CN115169730A (zh) * 2022-07-29 2022-10-11 重庆跃达新能源有限公司 光伏发电智能运维方法、系统及存储介质

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118071033A (zh) * 2024-04-18 2024-05-24 徐州太一世纪能源科技有限公司 一种光伏发电效率分析评价方法
CN118071033B (zh) * 2024-04-18 2024-07-02 徐州太一世纪能源科技有限公司 一种光伏发电效率分析评价方法
CN118139255A (zh) * 2024-04-30 2024-06-04 无锡照明股份有限公司 一种基于光伏发电的景观灯智能控制方法
CN118367865A (zh) * 2024-06-18 2024-07-19 国网浙江省电力有限公司 基于动态成图的分布式光伏异常监测方法
CN118399888A (zh) * 2024-06-27 2024-07-26 沛煜光电科技(上海)有限公司 离线式光伏组件el综合视觉缺陷检测系统及方法

Also Published As

Publication number Publication date
CN115169730A (zh) 2022-10-11

Similar Documents

Publication Publication Date Title
WO2024021548A1 (fr) Procédé et système d'exploitation et de maintenance intelligents de production d'énergie photovoltaïque et support de stockage
CN113284124B (zh) 一种基于无人机视觉的光伏面板缺陷检测方法
CN107314819A (zh) 一种基于红外图像的光伏电站热斑检测与定位方法
CN105263000A (zh) 基于无人机载双相机的大型光伏电站巡检装置
CN108416294A (zh) 一种基于深度学习的风机叶片故障智能识别方法
CN116452042A (zh) 一种光伏电站智能物联安全监管的方法及系统
CN111667673A (zh) 一种智能检测泄漏的热力管网系统
CN115642877A (zh) 一种基于深度学习的光伏组件异常遮挡检测方法及系统
CN118053118B (zh) 一种光伏性能综合监测评估及维护方法及系统
CN113888559A (zh) 一种光伏组件清洗机器人的智能控制方法
Wang et al. PV abnormal shading detection based on convolutional neural network
CN112653393A (zh) 一种光伏系统iv诊断的控制方法及装置
Li et al. Research and application of photovoltaic power station on-line hot spot detection operation and maintenance system based on unmanned aerial vehicle infrared and visible light detection
CN210693862U (zh) 一种光伏电站组件热斑故障自动检测装置
CN219592377U (zh) 一种光伏组件积灰检测系统
CN116667775A (zh) 一种基于无人机的光伏电场自动清洁方法及系统
CN110610474A (zh) 一种基于红外图像的太阳能板缺陷实时检测方法
Hwang et al. Soiling detection for photovoltaic modules based on an intelligent method with image processing
JP6324564B1 (ja) 太陽電池モジュールのカバーガラス異常検知方法
CN113657621A (zh) 一种隐患监测方法和系统
Oulefki et al. Unveiling the invisible: Enhanced detection and analysis deteriorated areas in solar pv modules using unsupervised sensing algorithms and 3d augmented reality
CN112017071A (zh) 一种bipv屋顶光伏电站智能化运维系统
Calin et al. New approaches in online evaluation of photovoltaic systems efficiency by implementing iot monitoring solutions
CN118282049B (zh) 光伏系统的远程监控方法、装置、设备及存储介质
CN217277944U (zh) 一种光伏组件积灰检测系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23844767

Country of ref document: EP

Kind code of ref document: A1