WO2021073280A1 - 基于红外成像技术的光伏板故障智能诊断系统 - Google Patents

基于红外成像技术的光伏板故障智能诊断系统 Download PDF

Info

Publication number
WO2021073280A1
WO2021073280A1 PCT/CN2020/112375 CN2020112375W WO2021073280A1 WO 2021073280 A1 WO2021073280 A1 WO 2021073280A1 CN 2020112375 W CN2020112375 W CN 2020112375W WO 2021073280 A1 WO2021073280 A1 WO 2021073280A1
Authority
WO
WIPO (PCT)
Prior art keywords
infrared imaging
photovoltaic panel
photovoltaic
image
imaging device
Prior art date
Application number
PCT/CN2020/112375
Other languages
English (en)
French (fr)
Inventor
樊启祥
杜光利
宗清
曾华锋
李学前
卢业平
李献才
冯宗海
Original Assignee
中国华能集团有限公司
华能海南发电股份有限公司
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 中国华能集团有限公司, 华能海南发电股份有限公司 filed Critical 中国华能集团有限公司
Publication of WO2021073280A1 publication Critical patent/WO2021073280A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N25/00—Investigating or analyzing materials by the use of thermal means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • 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
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/757—Matching configurations of points or features
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J2005/0077—Imaging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image
    • 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
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30148—Semiconductor; IC; Wafer

Definitions

  • the invention relates to a solar photovoltaic panel fault diagnosis technology, in particular to a photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology
  • Solar photovoltaic power generation is a new type of power generation technology that uses the photovoltaic effect of the semiconductor interface to directly convert solar radiation energy into electrical energy. It is predicted that solar photovoltaic power generation will occupy an important position in the world's energy consumption in the 21st century. It will not only replace some conventional energy sources, but also become the main body of the world's energy supply. It is estimated that by 2030, renewable energy will account for more than 30% of the total energy structure, and solar photovoltaic power generation will account for more than 10% of the world's total electricity supply; by 2040, renewable energy will account for more than 10% of total energy.
  • solar photovoltaic power generation will account for more than 20% of the total electricity; by the end of the 21st century, renewable energy will account for more than 80% of the energy structure, and solar power generation will account for more than 60%.
  • solar photovoltaic power generation technology The key element of solar photovoltaic power generation technology is solar cells. After the solar cells are connected in series and parallel, they are sealed into solar cell components, that is, solar photovoltaic panels. Together with power controllers and other components, a solar photovoltaic power generation device is formed.
  • Solar photovoltaic power generation device is a power generation device that exposes solar photovoltaic panels to sunlight and converts light energy into direct current.
  • solar photovoltaic power stations are installed with solar photovoltaic panels of a certain scale. If one or several of the solar photovoltaic panels fails, due to the wide area and large number of solar photovoltaic panels installed, it is difficult and time-consuming to rely on personnel inspections to find out. It is laborious; and the temperature of the faulty solar photovoltaic panel is different from that of the normal solar photovoltaic panel. If infrared imaging technology is used, then image recognition technology is used to automatically identify the faulty solar photovoltaic panel and identify the faulty solar energy. The number of the photovoltaic panel, through the alarm to remind the user to repair or replace, can effectively improve the maintenance efficiency of the solar photovoltaic panel and reduce the operation and maintenance cost.
  • the present invention is a photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology designed to solve the above technical problems.
  • a photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology including photovoltaic panels, infrared imaging equipment and image processing equipment; its installation and workflow are: First step: infrared imaging equipment is installed in front of a set of photovoltaic panels and higher than the photovoltaic Board, ensure that 3-10 sets of photovoltaic panels in the vertical direction and 5-20 photovoltaic panels in the horizontal direction can be photographed.
  • the infrared imaging equipment is connected to the image processing equipment through the data line; the second step: debug all the photovoltaic panels in front of the infrared imaging equipment To ensure that each photovoltaic panel is working normally, the image data of all photovoltaic panels in front of it is collected through infrared imaging equipment, and the image data is transmitted to the image processing equipment. The image data is analyzed and processed by the image processing equipment.
  • the panels are numbered, and the image features of each photovoltaic panel are extracted, and then the image features are stored in the image feature library for storage; the third step: the image processing equipment cyclically reads the image data of the photovoltaic panel in front of it collected by the infrared imaging equipment in real time, and Analyze and process the image data and extract features, then compare it with the corresponding image feature data in the image feature library to determine whether the photovoltaic panel with the corresponding number is faulty; if there is a fault, the number and fault level of the faulty photovoltaic panel are displayed , And alarm, and then continue to read the image data of the next infrared imaging device; if there is no failure, continue to read the image data of the next infrared imaging device.
  • the infrared imaging device of the photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology is an infrared imaging device with a network interface.
  • the infrared imaging device is an infrared thermal imager.
  • the infrared imaging device is an infrared imager.
  • the infrared imaging device is an infrared camera.
  • the photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology has n infrared imaging devices, 1 ⁇ n ⁇ 100, all infrared imaging devices are connected to the switch through the standard PoE-IEEE802.3 interface, and then processed with the image through the switch The equipment is connected, and at the same time, the infrared imaging equipment is powered by the Ethernet network.
  • the photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology
  • its image processing equipment applies convolutional neural network (CNN) to the collected images, performs gray-scale filtering to extract image features, and flattens them into vectors; Calculate the distance between the photovoltaic panel image vector and the corresponding image vector in the feature library to obtain the image similarity between the faulty photovoltaic panel and the normal operating photovoltaic panel; determine the fault level of the photovoltaic panel according to the calculated similarity, and determine the alarm according to the fault level replace.
  • CNN convolutional neural network
  • the infrared imaging equipment is installed 5 meters in front of a set of photovoltaic panels and 3 meters higher than the photovoltaic panel, ensuring that it can photograph 5 sets of photovoltaic panels in the vertical direction and 10 panels in the horizontal direction. Photovoltaic panels.
  • the beneficial effect of the present invention is to diagnose photovoltaic panel faults through the photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology, the fault diagnosis is timely and accurate, the operation and maintenance efficiency of the system is improved, and the photovoltaic power station is always running in the best state.
  • Figure 1 is a schematic diagram of the location of the infrared imaging equipment and photovoltaic panels of the present invention.
  • Figure 2 is a diagram of the connection relationship between n infrared imaging devices and image processing devices of the present invention.
  • FIG. 3 is a working flow chart of the present invention.
  • an intelligent diagnosis system for photovoltaic panel faults based on infrared imaging technology of the present invention includes photovoltaic panels 1, infrared imaging equipment 2 and image processing equipment; its installation and work flow are: First step: infrared
  • the imaging device 2 is installed in front of a set of photovoltaic panels 1 and higher than the photovoltaic panels to ensure that 3-10 sets of photovoltaic panels 1 in the vertical direction and 5-20 photovoltaic panels 1 in the horizontal direction can be photographed in front of it.
  • the infrared imaging device 2 is connected to it through a data cable.
  • Step 2 Debug all the photovoltaic panels 1 in front of the infrared imaging device 2 to ensure that each photovoltaic panel 1 is working normally, and then collect the image data of all photovoltaic panels 1 in front of it through the infrared imaging device 2
  • the image data is transmitted to the image processing equipment, the image data is analyzed and processed by the image processing equipment, each photovoltaic panel is numbered, and the image features of each photovoltaic panel are extracted, and then the image features are stored in the image feature library for storage;
  • the infrared imaging device 2 of the photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology is an infrared imaging device 2 with a network interface.
  • the infrared imaging device 2 is an infrared thermal imager.
  • the infrared imaging device 2 of the photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology is an infrared imager.
  • the infrared imaging device 2 is an infrared camera.
  • infrared imaging devices 2 there are n infrared imaging devices 2, 1 ⁇ n ⁇ 100, and all infrared imaging devices 2 are connected to the switch through the standard PoE-IEEE802.3 interface, and then connected to the switch through the switch The image processing equipment is connected, and at the same time, the infrared imaging equipment 2 is powered by the Ethernet network.
  • the photovoltaic panel fault intelligent diagnosis system based on infrared imaging technology
  • its image processing equipment applies a convolutional neural network (CNN) to the collected images, performs gray-scale filtering to extract image features, and flattens them into vectors; Calculate the distance between the photovoltaic panel image vector and the corresponding image vector in the feature library to obtain the image similarity between the faulty photovoltaic panel and the normal operating photovoltaic panel; determine the fault level of the photovoltaic panel according to the calculated similarity, and determine the alarm according to the fault level replace.
  • CNN convolutional neural network
  • the infrared imaging device 2 is installed 5 meters in front of a group of photovoltaic panels 1 and 3 meters higher than the photovoltaic panel, ensuring that 5 groups of photovoltaic panels can be photographed vertically in front of it. 10 photovoltaic panels horizontally.
  • the present invention is not limited to the above-mentioned best embodiments, and any other products identical or similar to the present invention derived by anyone under the enlightenment of the present invention fall within the protection scope of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Chemical & Material Sciences (AREA)
  • Pathology (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Quality & Reliability (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Photovoltaic Devices (AREA)
  • Testing Of Individual Semiconductor Devices (AREA)

Abstract

一种基于红外成像技术的光伏板（1）故障智能诊断系统，红外成像设备（2）安装在一组光伏板（1）前并高出光伏板（1），调试好光伏板（1）后，首先，通过红外成像设备（2）采集其前方的所有光伏板（1）的图像数据，图像处理设备对图像数据进行分析处理，并提取每一块光伏板（1）的图像特征并入库保存；然后图像处理设备循环读取红外成像设备（2）实时采集图像数据，并对数据进行分析处理和特征提取，然后与图像特征库中对应的图像特征数据进行比较，判断其对应编号的光伏板（1）是否有故障，并显示和报警。通过基于红外成像技术的光伏板（1）故障智能诊断系统诊断光伏板（1）故障，故障诊断及时、准确，提高了系统的运维效率，保障光伏发电站时刻运行在最佳状态。

Description

基于红外成像技术的光伏板故障智能诊断系统 技术领域
本发明涉及太阳能光伏板故障诊断技术，具体地说，涉及一种基于红外成像技术的光伏板故障智能诊断系统
背景技术
在能源日益紧缺的今天，太阳能的利用越来越受到人们的重视。太阳能光伏发电是利用半导体界面的光生伏特效应而将太阳光辐射能直接转换为电能的一种新型发电技术。据预测，太阳能光伏发电在21世纪会占据世界能源消费的重要席位，不但要替代部分常规能源，而且将成为世界能源供应的主体。预计到2030年，可再生能源在总能源结构中占到30％以上，而太阳能光伏发电在世界总电力供应中的占比也将达到10％以上；到2040年，可再生能源将占总能耗的50％以上，太阳能光伏发电将占总电力的20％以上；到21世纪末，可再生能源在能源结构中将占到80％以上，太阳能发电将占到60％以上。这些数字足以显示出太阳能光伏产业的发展前景及其在能源领域重要的战略地位。
太阳能光伏发电技术的关键元件是太阳能电池片，太阳能电池片经过串、并联后封闭成太阳能电池组件亦即太阳能光伏板，再配合功率控制器等部件就形成了太阳能光伏发电装置。太阳能光伏发电装置是将太阳能光伏板暴露在阳光下，将光能转换为直流电的发电装置。
一般太阳能光伏发电站都安装了一定规模的太阳能光伏板，如果其中某一块或几块太阳能光伏板出现故障，由于安装太阳能光伏板的场地广，数量多，依靠人员巡查发现难度比较大，而且费时又费力；而出现故障的太阳能光伏板与正常的太阳能光伏板在温度上有差别，如果通过红外成像技术，再通过图像 识别技术对出现故障的太阳能光伏板进行自动识别，标识出有故障的太阳能光伏板的编号，通过报警提示用户进行维修或更换，可以有效的提高太阳能光伏板的维护效率并降低运维成本。
发明内容
本发明正是为了解决上述技术问题而设计的一种基于红外成像技术的光伏板故障智能诊断系统。
本发明解决其技术问题所采用的技术方案是：
一种基于红外成像技术的光伏板故障智能诊断系统，包括光伏板、红外成像设备和图像处理设备；其安装和工作流程是：第一步：红外成像设备安装在一组光伏板前并高出光伏板，保证可以拍摄到其前方纵向3-10组光伏板，横向5-20块光伏板，红外成像设备通过数据线连接到图像处理设备；第二步：调试好该红外成像设备前的所有光伏板，确保每一块光伏板工作正常，再通过红外成像设备采集其前方的所有光伏板的图像数据，将图像数据传输给图像处理设备，经图像处理设备对图像数据进行分析处理，对每一块光伏板进行编号，并提取每一块光伏板的图像特征，然后将图像特征存入图像特征库保存；第三步：图像处理设备循环读取红外成像设备实时采集的其前方光伏板的图像数据，并对图像数据进行分析处理和特征提取，然后与图像特征库中对应的图像特征数据进行比较，判断其对应编号的光伏板是否有故障；如果有故障，则显示有故障的光伏板编号和故障等级，并报警，然后继续读取下一个红外成像设备的图像数据；如果没有故障，则继续读取下一个红外成像设备的图像数据。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备为具有网络接口的红外成像设备。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备为红 外热成像仪。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备为红外成像仪。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备为红外摄像头。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备有n个，1≤n≤100，所有红外成像设备通过标准PoE-IEEE802.3接口与交换机连接，再通过交换机与图像处理设备相连，同时实现对红外成像设备以太网络供电。
所述基于红外成像技术的光伏板故障智能诊断系统，其图像处理设备对采集的图像，应用卷积神经网络(CNN)，进行灰度过滤提取图像特征，并扁平化成向量；将获取待判断的光伏板图像向量与特征库中与之对应的图像向量进行距离计算，获取故障光伏板与正常运行光伏板图像相似度；根据计算所得的相似度，确定光伏板的故障等级，根据故障等级确定报警更换。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备安装在一组光伏板前5米，并高出光伏板3米，保证可以拍摄到其前方纵向5组光伏板，横向10块光伏板。
本发明的有益效果是通过基于红外成像技术的光伏板故障智能诊断系统诊断光伏板故障，故障诊断及时、准确，提高了系统的运维效率，保障光伏发电站时刻运行在最佳状态。
附图说明
图1为本发明红外成像设备与光伏板布设位置示意图。
图2为本发明n个红外成像设备与图像处理设备连接关系图。
图3为本发明工作流程图。
具体实施方式
下面结合附图和实施例对本发明进一步说明。
如图1-3所示，本发明一种基于红外成像技术的光伏板故障智能诊断系统，包括光伏板1、红外成像设备2和图像处理设备；其安装和工作流程是：第一步：红外成像设备2安装在一组光伏板1前并高出光伏板，保证可以拍摄到其前方纵向3-10组光伏板1，横向5-20块光伏板1，红外成像设备2通过数据线连接到图像处理设备；第二步：调试好该红外成像设备2前的所有光伏板1，确保每一块光伏板1工作正常，再通过红外成像设备2采集其前方的所有光伏板1的图像数据，将图像数据传输给图像处理设备，经图像处理设备对图像数据进行分析处理，对每一块光伏板进行编号，并提取每一块光伏板的图像特征，然后将图像特征存入图像特征库保存；第三步：图像处理设备循环读取红外成像设备2实时采集的其前方光伏板1的图像数据，并对图像数据进行分析处理和特征提取，然后与图像特征库中对应的图像特征数据进行比较，判断其对应编号的光伏板1是否有故障；如果有故障，则显示有故障的光伏板1编号和故障等级，并报警，然后继续读取下一个红外成像设备2的图像数据；如果没有故障，则继续读取下一个红外成像设备2的图像数据。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备2为具有网络接口的红外成像设备2。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备2为红外热成像仪。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备2为红外成像仪。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备2为红外 摄像头。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备2有n个，1≤n≤100，所有红外成像设备2通过标准PoE-IEEE802.3接口与交换机连接，再通过交换机与图像处理设备相连，同时实现对红外成像设备2以太网络供电。
所述基于红外成像技术的光伏板故障智能诊断系统，其图像处理设备对采集的图像，应用卷积神经网络(CNN)，进行灰度过滤提取图像特征，并扁平化成向量；将获取待判断的光伏板图像向量与特征库中与之对应的图像向量进行距离计算，获取故障光伏板与正常运行光伏板图像相似度；根据计算所得的相似度，确定光伏板的故障等级，根据故障等级确定报警更换。
所述基于红外成像技术的光伏板故障智能诊断系统，其红外成像设备2安装在一组光伏板1前5米，并高出光伏板3米，保证可以拍摄到其前方纵向5组光伏板，横向10块光伏板。
本发明不局限于上述最佳实施方式，任何人在本发明的启示下得出的其他任何与本发明相同或相近似的产品，均落在本发明的保护范围之内。

Claims (8)

  1. 一种基于红外成像技术的光伏板故障智能诊断系统，包括光伏板(1)、红外成像设备(2)和图像处理设备；其特征在于：第一步：红外成像设备(2)安装在一组光伏板(1)前并高出光伏板，保证可以拍摄到其前方纵向3-10组光伏板(1)，横向5-20块光伏板(1)，红外成像设备(2)通过数据线连接到图像处理设备；第二步：调试好该红外成像设备(2)前的所有光伏板(1)，确保每一块光伏板(1)工作正常，再通过红外成像设备(2)采集其前方的所有光伏板(1)的图像数据，将图像数据传输给图像处理设备，经图像处理设备对图像数据进行分析处理，对每一块光伏板进行编号，并提取每一块光伏板的图像特征，然后将图像特征存入图像特征库保存；第三步：图像处理设备循环读取红外成像设备(2)实时采集的其前方光伏板(1)的图像数据，并对图像数据进行分析处理和特征提取，然后与图像特征库中对应的图像特征数据进行比较，判断其对应编号的光伏板(1)是否有故障；如果有故障，则显示有故障的光伏板(1)编号和故障等级，并报警，然后继续读取下一个红外成像设备(2)的图像数据；如果没有故障，则继续读取下一个红外成像设备(2)的图像数据。
  2. 根据权利要求1所述的基于红外成像技术的光伏板故障智能诊断系统，其特征在于：红外成像设备(2)为具有网络接口的红外成像设备。
  3. 根据权利要求1或2所述的基于红外成像技术的光伏板故障智能诊断系统，其特征在于：红外成像设备(2)为红外热成像仪。
  4. 根据权利要求1或2所述的基于红外成像技术的光伏板故障智能诊断系统，其特征在于：红外成像设备(2)为红外成像仪。
  5. 根据权利要求4所述的基于红外成像技术的光伏板故障智能诊断系统，其特征在于：红外成像设备(2)为红外摄像头。
  6. 根据权利要求2所述的基于红外成像技术的光伏板故障智能诊断系统， 其特征在于：红外成像设备(2)有n个，1≤n≤100，所有红外成像设备(2)通过标准PoE-IEEE802.3接口与交换机连接，再通过交换机与图像处理设备相连，同时实现对红外成像设备(2)以太网络供电。
  7. 根据权利要求1所述的基于红外成像技术的光伏板故障智能诊断系统，其特征在于：图像处理设备对采集的图像，应用卷积神经网络，进行灰度过滤提取图像特征，并扁平化成向量；将获取待判断的光伏板图像向量与特征库中与之对应的图像向量进行距离计算，获取故障光伏板与正常运行光伏板图像相似度；根据计算所得的相似度，确定光伏板的故障等级，根据故障等级确定报警更换。
  8. 根据权利要求1所述的基于红外成像技术的光伏板故障智能诊断系统，其特征在于：红外成像设备(2)安装在一组光伏板(1)前5米，并高出光伏板3米，保证可以拍摄到其前方纵向5组光伏板(1)，横向10块光伏板(1)。
PCT/CN2020/112375 2019-10-17 2020-08-31 基于红外成像技术的光伏板故障智能诊断系统 WO2021073280A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910989089.1 2019-10-17
CN201910989089.1A CN110736547A (zh) 2019-10-17 2019-10-17 基于红外成像技术的光伏板故障智能诊断系统

Publications (1)

Publication Number Publication Date
WO2021073280A1 true WO2021073280A1 (zh) 2021-04-22

Family

ID=69269207

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/112375 WO2021073280A1 (zh) 2019-10-17 2020-08-31 基于红外成像技术的光伏板故障智能诊断系统

Country Status (2)

Country Link
CN (1) CN110736547A (zh)
WO (1) WO2021073280A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113242018A (zh) * 2021-06-17 2021-08-10 合肥阳光智维科技有限公司 一种光伏设备故障诊断方法及其应用装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110736547A (zh) * 2019-10-17 2020-01-31 华能海南发电股份有限公司 基于红外成像技术的光伏板故障智能诊断系统
CN112539838A (zh) * 2020-10-15 2021-03-23 广西电网有限责任公司南宁供电局 一种基于数据库人工智能型红外成像测温系统
CN113473078A (zh) * 2021-06-09 2021-10-01 国网上海市电力公司 一种基于增强现实技术的红外运维巡检方法和装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103808727A (zh) * 2012-11-13 2014-05-21 上海太阳能工程技术研究中心有限公司 太阳能光伏板故障诊断方法
CN107483014A (zh) * 2017-06-16 2017-12-15 理光软件研究所（北京）有限公司 一种光伏板故障自动检测方法
JP2018082602A (ja) * 2016-11-18 2018-05-24 北陸電話工事株式会社 太陽電池モジュール劣化診断システム
CN207439960U (zh) * 2017-11-22 2018-06-01 北京汉能光伏投资有限公司 太阳能组件故障检测系统
CN207798722U (zh) * 2018-01-31 2018-08-31 上海挪亚检测认证集团有限公司 一种利用红外扫描诊断太阳能光伏板故障的诊断装置
CN109813716A (zh) * 2017-11-22 2019-05-28 北京汉能光伏投资有限公司 太阳能组件故障检测系统和方法
CN110736547A (zh) * 2019-10-17 2020-01-31 华能海南发电股份有限公司 基于红外成像技术的光伏板故障智能诊断系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002329879A (ja) * 2001-05-02 2002-11-15 Sumitomo Kinzoku Kozan Siporex Kk 太陽電池アレイの欠陥検出方法
CN107123114A (zh) * 2017-04-21 2017-09-01 佛山市南海区广工大数控装备协同创新研究院 一种基于机器学习的布匹缺陷检测方法及装置
CN107607207B (zh) * 2017-08-22 2019-06-28 中国科学院深圳先进技术研究院 一种电力设备热故障诊断方法、系统及电子设备
CN107831173A (zh) * 2017-10-17 2018-03-23 哈尔滨工业大学（威海） 光伏组件缺陷检测方法及系统
CN108647716B (zh) * 2018-05-09 2021-08-06 北京理工大学 一种基于复合信息的光伏阵列故障诊断方法
CN108921100B (zh) * 2018-07-04 2020-12-01 武汉高德智感科技有限公司 一种基于可见光图像与红外图像融合的人脸识别方法及系统
CN109187558A (zh) * 2018-10-10 2019-01-11 中南大学 一种基于无人机的光伏电站自动巡检系统
CN109447157B (zh) * 2018-10-30 2020-10-23 国网四川省电力公司广元供电公司 一款移动型电网作业巡检系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103808727A (zh) * 2012-11-13 2014-05-21 上海太阳能工程技术研究中心有限公司 太阳能光伏板故障诊断方法
JP2018082602A (ja) * 2016-11-18 2018-05-24 北陸電話工事株式会社 太陽電池モジュール劣化診断システム
CN107483014A (zh) * 2017-06-16 2017-12-15 理光软件研究所（北京）有限公司 一种光伏板故障自动检测方法
CN207439960U (zh) * 2017-11-22 2018-06-01 北京汉能光伏投资有限公司 太阳能组件故障检测系统
CN109813716A (zh) * 2017-11-22 2019-05-28 北京汉能光伏投资有限公司 太阳能组件故障检测系统和方法
CN207798722U (zh) * 2018-01-31 2018-08-31 上海挪亚检测认证集团有限公司 一种利用红外扫描诊断太阳能光伏板故障的诊断装置
CN110736547A (zh) * 2019-10-17 2020-01-31 华能海南发电股份有限公司 基于红外成像技术的光伏板故障智能诊断系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113242018A (zh) * 2021-06-17 2021-08-10 合肥阳光智维科技有限公司 一种光伏设备故障诊断方法及其应用装置
CN113242018B (zh) * 2021-06-17 2023-08-04 阳光智维科技股份有限公司 一种光伏设备故障诊断方法及其应用装置

Also Published As

Publication number Publication date
CN110736547A (zh) 2020-01-31

Similar Documents

Publication Publication Date Title
WO2021073280A1 (zh) 基于红外成像技术的光伏板故障智能诊断系统
CN104601108B (zh) 一种小型光伏电站的故障诊断方法
KR101390405B1 (ko) 태양광 발전 설비 관리를 위한 모니터링 및 제어 시스템
CN106230378B (zh) 一种光伏电站组串故障的诊断方法
CN107831387A (zh) 一种电力站设备运行状况智能监测方法
Wang et al. Probability modeling for PV array output interval and its application in fault diagnosis
CN110277962A (zh) 一种应用无人机及逆变器返灌技术对光伏电池组件进行el实时在线图谱收集分析诊断方法
KR101297078B1 (ko) 태양광 전지모듈별 고장 진단 가능한 태양광 발전 모니터링 장치 및 이를 이용한 태양광 발전 시스템의 고장진단 방법
CN111460644A (zh) 一种具有故障诊断和功率预测功能的光伏阵列监测系统
CN206099897U (zh) 一种带有故障识别功能的光伏电站
CN113485432A (zh) 一种基于无人机的光伏电站电致发光智能诊断系统及方法
CN113037214A (zh) 一种基于s-v曲线的光伏组件阴影遮挡故障诊断方法
Yun et al. Research on fault diagnosis of photovoltaic array based on random forest algorithm
Pan et al. Research on output distribution modeling of photovoltaic modules based on kernel density estimation method and its application in anomaly identification
CN110022130A (zh) 一种光伏阵列故障检测设备和方法
WO2014142388A1 (ko) 태양광 발전 시스템의 발전분석 장치 및 방법
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
CN109672220A (zh) 一种村级的光伏电站管理系统及其控制方法
CN108551330A (zh) 一种光伏组件阵列监测系统及监测方法
Tan et al. Denoising convolutional neural networks based dust accumulation status evaluation of photovoltaic panel
Li et al. Insulator infrared image segmentation algorithm based on dynamic mask and box annotation
CN210693862U (zh) 一种光伏电站组件热斑故障自动检测装置
Guerriero et al. Real time monitoring of solar fields with cost/revenue analysis of fault fixing
CN209298905U (zh) 一种村级的光伏电站管理系统
CN106953596A (zh) 一种光伏电站故障检测系统

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: 20875890

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20875890

Country of ref document: EP

Kind code of ref document: A1