WO2023246062A1 - Intelligent video-based electric power analysis and monitoring structure, system and method, and storage medium thereof - Google Patents
Intelligent video-based electric power analysis and monitoring structure, system and method, and storage medium thereof Download PDFInfo
- Publication number
- WO2023246062A1 WO2023246062A1 PCT/CN2022/142785 CN2022142785W WO2023246062A1 WO 2023246062 A1 WO2023246062 A1 WO 2023246062A1 CN 2022142785 W CN2022142785 W CN 2022142785W WO 2023246062 A1 WO2023246062 A1 WO 2023246062A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- video
- image
- comparison
- wind turbine
- data
- Prior art date
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 59
- 238000004458 analytical method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 230000000052 comparative effect Effects 0.000 abstract 2
- 238000012423 maintenance Methods 0.000 description 7
- 239000003550 marker Substances 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
-
- 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
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Definitions
- This application relates to the field of video analysis and monitoring technology, specifically to the power intelligent video analysis and monitoring structure, system, method and storage medium.
- Wind power is a kind of new energy. Wind power has been widely used in recent years. Wind power is generally set up in relatively environmentally friendly environments. In harsh places, routine maintenance is difficult, so monitoring devices need to be installed to monitor the operation of wind turbines at all times.
- the purpose of this application is to provide an electric power intelligent video analysis monitoring structure, system, method and storage medium, which is simple to operate and highly repeatable, improves the efficiency of wind turbine monitoring and the accuracy of wind turbine monitoring, and not only reduces the It reduces the monitoring cost of wind turbines, facilitates timely maintenance of wind turbines, and reduces potential safety hazards in production. Therefore, the above technical problems can be solved.
- This application provides an electric power intelligent video analysis and monitoring structure, including: a comparison video image collector and a reference video collector.
- the comparison video image collector and the reference video collector are electrically connected to a data processor respectively.
- the data The processor is electrically connected to the fault early warning device.
- the electric power intelligent video analysis and monitoring structure, system, method and storage medium provided by this application are simple to operate and highly repeatable, which improves the efficiency and accuracy of wind turbine monitoring and not only reduces the cost of wind power generation It reduces the monitoring cost of the unit, facilitates timely maintenance of the wind turbine unit, and reduces potential safety hazards in production.
- This application also provides an electric power intelligent video analysis and monitoring system, including:
- the reference video collection module is used to collect the video information of the wind wheel of the standard wind turbine generator under normal working conditions as the reference video data;
- the comparison video collection module is used to collect the video information of the wind turbine operation under the current working state of the wind turbine as comparison video data
- the data processing module is used to compare the comparison video data with the reference video data by taking the rotation period of the wind turbine of a wind turbine as the duration, and use the comparison video and the reference video to determine the wind turbine rotation image of the wind turbine. Compare the data to determine whether the current working status of the wind turbine is normal, and transmit the data of whether the current working status of the wind turbine is normal to the fault warning module;
- the fault warning module is used to determine whether to issue a fault warning prompt based on the received data on whether the current working status of the wind turbine generator set is normal.
- a module for adjusting the duration of the comparison video includes: a module for adjusting the duration of the comparison video.
- the module for adjusting the duration of the comparison video is used to adjust the starting point of the comparison video data through image frame comparison of the comparison video data and the reference video data, so that the comparison video
- the relative position of the wind wheel and the environment on the starting point image is set correspondingly to the position of the wind wheel and the environment on the starting point image of the reference video; the content of the comparison video data is fast-forwarded or zoomed according to the time length, so that the duration of the comparison video is consistent with the reference
- the videos are the same length.
- a reference video preprocessing module which is used to split the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame;
- the reference video image and the comparison video image of the same frame are used as one data group to obtain multiple data groups; the angle of the reference video image in each data group is adjusted to complete the preprocessing of the reference video.
- an image angle adjustment module which is used to mark points on each blade and hub of the wind wheel in the reference video image and the comparison video image respectively; connect the reference video images respectively Two marker images are formed with the marker points on the comparison video image; the two marker images are compared, and the angle of the comparison video image is adjusted based on the marker image on the reference video image.
- the data processing module includes: an image edge determination module, which is used to mark each coordinate point with the coordinate of each pixel point on the image in the wind turbine rotation image data;
- the pixel is a device, and the pixels in the adjacent 16 ⁇ 16 positions are recorded as a group of pixels; the average gray value of each group of pixels is recorded as the gray level of the group of pixels; through the comparison of the gray levels of each group of pixels , obtain the position and boundary shape image of the wind turbine rotor.
- This application also provides an electric power intelligent video analysis and monitoring method, which includes the following steps:
- Collect the rotation video of the current wind turbine set use a point on the rotor in the rotation video as the mark point, and use the time it takes for the mark point to rotate once as the rotation period of the wind wheel; use the starting point and end point time of each rotation cycle as the boundary , intercept the current rotation video of the wind turbine as a comparison video;
- preprocessing the reference video includes the following steps: adjusting the duration of the comparison video; splitting the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame; The reference video image and comparison video image of the same frame are used as one data group to obtain multiple data groups; the angle of the reference video image in each data group is adjusted to complete the preprocessing of the reference video;
- Obtaining the position and boundary shape of the wind wheel in each frame of the reference video image and the comparison video image includes the following steps: mark each coordinate point with the coordinate of each pixel point on the image; use each pixel point as a device, record its adjacent 16
- the pixels in the ⁇ 16 position are a group of pixels; the average gray value of each group of pixels is recorded as the gray level of the group of pixels; through the comparison of the gray levels of each group of pixels, the position and boundary shape image of the wind wheel is obtained.
- the present application also provides a computer-readable storage medium on which a computer program is stored.
- the program is executed by a processor, the power intelligent video analysis and monitoring method described in any one of the above is implemented.
- the power intelligent video analysis and monitoring structure, system, method and storage medium provided by this application can obtain the comparison video of each frame and the wind turbine rotation image of the wind turbine set in the reference video, and compare the wind turbine rotor of the wind turbine set through frame comparison. Compare the wind wheel rotation image of the comparison video with the wind wheel rotation image of the benchmark video, determine whether the position and boundary shape image of the wind wheel on each frame of the benchmark video and the comparison video are the same, determine whether the wind wheel is faulty, and determine the current situation accordingly. Whether the wind turbine is in normal working condition, its operation is simple and repeatable, which improves the efficiency of wind turbine monitoring and the accuracy of wind turbine monitoring. It not only reduces the monitoring cost of wind turbines, but also facilitates the monitoring of wind turbines. Carry out timely maintenance and reduce safety risks in production.
- Figure 1 is a circuit diagram of an electric power intelligent video analysis and monitoring structure provided by an embodiment of the present application.
- Figure 2 is a flow chart of an electric power intelligent video analysis and monitoring system provided by an embodiment of the present application.
- Figure 3 is a flow chart of an electric power intelligent video analysis and monitoring method provided by an embodiment of the present application.
- an electric power intelligent video analysis and monitoring structure provided by one embodiment of this application includes: a comparison video image collector and a reference video collection.
- the comparison video image collector and the reference video collector are electrically connected to a data processor respectively, and the data processor is electrically connected to the fault early warning device;
- the reference video collector is used to collect standard wind turbine generator sets The video in the normal working state of the wind turbine is used as a reference video signal, and the reference video signal is sent to the data processor.
- the comparison video image collector is used to collect the video in the current working state of the wind turbine as a comparison video signal, and compares the data
- the processor sends a comparison video signal, and the data processor detects the signal, processes the signal, takes one rotation cycle as the duration, compares the comparison video data with the reference video data, and makes a judgment by comparing the rotation image of the wind wheel in the video and the reference video.
- the data of whether the current working status of the wind turbine is normal is transmitted to the fault early warning device; the fault early warning device receives the data of whether the current working status of the wind turbine is normal, determines whether the current working status of the wind turbine is abnormal, and issues a fault warning prompt; obtains each frame comparison video Compare the rotor rotation image of the wind turbine generator set in the reference video and compare the rotor rotation image of the wind turbine generator set wind rotor comparison video with the wind rotor rotation image of the reference video to determine each frame of the reference video Compare the position and boundary shape image of the wind wheel on the video to determine whether the wind wheel is faulty and determine whether the current working status of the wind turbine is normal.
- the operation is simple and repeatable, which improves the efficiency of wind turbine monitoring.
- the work efficiency and accuracy of wind turbine monitoring not only reduce the monitoring cost of wind turbines, but also facilitate timely maintenance of wind turbines and reduce safety hazards in production.
- the rotation image of the wind wheel can be selected from the position image and boundary shape image of the wind wheel.
- one embodiment of the present application also provides an electric power intelligent video analysis and monitoring system, including:
- the reference video collection module is used to collect the video information of the wind wheel of the standard wind turbine generator under normal working conditions as the reference video data;
- the comparison video collection module is used to collect the video information of the wind turbine operation under the current working state of the wind turbine as comparison video data
- the data processing module is used to compare the comparison video data with the reference video data by taking the rotation period of the wind turbine of a wind turbine as the duration, and use the comparison video and the reference video to determine the wind turbine rotation image of the wind turbine. Compare the data to determine whether the current working status of the wind turbine is normal, and transmit the data of whether the current working status of the wind turbine is normal to the fault warning module;
- Adjust the duration module of the comparison video is used to adjust the starting point of the comparison video data through the image frame comparison of the comparison video data and the reference video data, so that the contrast between the wind wheel and the environment on the starting point image of the comparison video is
- the relative position is set correspondingly to the position of the wind wheel and the environment on the starting point image of the reference video; the content of the comparison video data is fast-forwarded or zoomed according to the time length, so that the duration of the comparison video is consistent with the duration of the reference video;
- a reference video preprocessing module which is used to split the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame; combine the reference video image of the same frame and Compare the video images as a data group to obtain multiple data groups; adjust the angle of the reference video image in each data group to complete the preprocessing of the reference video;
- Image angle adjustment module the image angle adjustment module is used to mark each blade and hub of the wind wheel in the reference video image and the comparison video image with points respectively; connect the marking points on the reference video image and the comparison video image respectively Form two marked images; compare the two marked images, and use the marked image on the reference video image as a benchmark to adjust the angle of the compared video image;
- the image edge determination module is used to mark each coordinate point with the coordinates of each pixel point on the image in the wind turbine rotation image data; using each pixel point as a device, record the pixels in its adjacent 16 ⁇ 16 positions as one A group of pixels; record the average grayscale value of each group of pixels as the grayscale of the group of pixels; obtain the position and boundary shape image of the wind turbine rotor by comparing the grayscale of each group of pixels;
- the fault warning module is used to determine whether to issue a fault warning prompt based on the received data on whether the current working status of the wind turbine is normal; its operation is simple and highly repeatable, which improves the work efficiency of power intelligent video analysis and monitoring and the power intelligent video analysis
- the accuracy of monitoring not only reduces the monitoring cost of wind turbines, but also facilitates timely maintenance of wind turbines and reduces safety hazards in production; its simple operation and strong repeatability improve the efficiency of wind turbine monitoring.
- the accuracy of wind turbine monitoring not only reduces the monitoring cost of wind turbines, but also facilitates timely maintenance of wind turbines and reduces safety hazards in production.
- one embodiment of the present application also provides an electric power intelligent video analysis and monitoring method, which includes the following steps:
- the above method specifically includes the following steps:
- Collect the rotation video of the current wind turbine set use a point on the rotor in the rotation video as the mark point, and use the time it takes for the mark point to rotate once as the rotation period of the wind wheel; use the starting point and end point time of each rotation cycle as the boundary , intercept the current rotation video of the wind turbine as a comparison video;
- Preprocessing the reference video includes the following steps: adjusting the duration of the comparison video; splitting the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame; The reference video image and the comparison video image of the same frame are used as one data group to obtain multiple data groups; the angle of the reference video image in each data group is adjusted to complete the preprocessing of the reference video; and the reference video image at the same time point is processed. Perform image edge determination on each frame of the reference video and comparison video, and determine the position and boundary shape of the wind wheel on each frame of the reference video and comparison video respectively.
- Obtaining the position and boundary shape of the wind wheel on each frame of the reference video image and comparison video image includes the following steps: Mark each coordinate point with the coordinates of each pixel point on the image; use each pixel point as a device, record the pixels in its adjacent 16 ⁇ 16 positions as a group of pixel points; calculate the average gray level of each group of pixel points The value is recorded as the grayscale of the group of pixels; through the comparison of the grayscale of each group of pixels, the position and boundary shape image of the wind wheel are obtained; it is judged whether the position and boundary shape image of the wind wheel on each frame of the reference video and the comparison video are the same, and based on This determines whether the current working status of the wind turbine is normal;
- One embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored.
- the program is executed by a processor, the power intelligent video analysis and monitoring method described in any one of the above is implemented.
- the electric power intelligent video analysis and monitoring structure, system, method and storage medium obtained each frame comparison video and compare the wind turbine rotation image of the wind turbine generator set in the reference video, and compare the wind turbine generator set through frame comparison. Compare the wind wheel rotation image of the comparison video with the wind wheel rotation image of the benchmark video, determine whether the position and boundary shape image of the wind wheel on each frame of the benchmark video and the comparison video are the same, determine whether the wind wheel is faulty, and based on this Determining whether the current working status of the wind turbine is normal, its operation is simple and repeatable, which improves the efficiency of wind turbine monitoring and the accuracy of wind turbine monitoring. It not only reduces the monitoring cost of wind turbines, but also facilitates wind turbine monitoring. Generator units are maintained in a timely manner, reducing safety hazards in production.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Wind Motors (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
Abstract
The present application provides an intelligent video-based electric power analysis and monitoring structure, system, and method, and a storage medium thereof. The structure comprises a comparative video image acquisition device and a reference video acquisition device; the comparative video image acquisition device and the reference video acquisition device are electrically connected to a data processor, separately; and the data processor is electrically connected to a fault early warning device. The present application features simple operations and high repeatability, and improves the working efficiency of wind turbine monitoring and the precision of wind turbine monitoring, such that not only wind turbine monitoring cost is reduced, but also a wind turbine can be conveniently maintained in time, thereby reducing potential safety hazards during production.
Description
相关申请的交叉引用Cross-references to related applications
本申请要求在2022年06月21日提交中国专利局、申请号为202210703054.9、发明名称为“电力智能视频分析监控结构、系统、方法及其存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application requires the priority of the Chinese patent application submitted to the China Patent Office on June 21, 2022, with the application number 202210703054.9 and the invention name "Power Intelligent Video Analysis and Monitoring Structure, System, Method and Storage Medium", and its entire content incorporated herein by reference.
本申请涉及视频分析监控技术领域，具体涉及电力智能视频分析监控结构、系统、方法及其存储介质。This application relates to the field of video analysis and monitoring technology, specifically to the power intelligent video analysis and monitoring structure, system, method and storage medium.
随着社会发展，资源变得越来越短缺，因此人们越来越致力于新能源的开发，风力发电属于新能源的一种，风力发电近年来使用的较为广泛，风力发电一般设置在环境比较恶劣的地方，日常维护较为困难，因此需要设置监控装置来时刻监测风力发电机组的运行情况。With the development of society, resources are becoming more and more scarce, so people are becoming more and more committed to the development of new energy. Wind power is a kind of new energy. Wind power has been widely used in recent years. Wind power is generally set up in relatively environmentally friendly environments. In harsh places, routine maintenance is difficult, so monitoring devices need to be installed to monitor the operation of wind turbines at all times.
现在的风力发电机组通常只能对风力发电机组进行拍摄照片进行运行状态监控，由专业人员通过拍摄照片判断风力发电机组是否产生故障，这样的监控方式需要消耗大量的人力，对工作人员的专业性要求较高，工作人员的工作量过于繁重，影响监控的效率，而且人为主观因素不可避免地会导致监控精度较差，风力发电机组无法得到及时的维护。Today's wind turbines can usually only take photos of the wind turbine to monitor the operating status. Professionals can judge whether the wind turbine is faulty by taking photos. This kind of monitoring method requires a lot of manpower and has a negative impact on the professionalism of the staff. The requirements are high and the workload of the staff is too heavy, which affects the efficiency of monitoring. Moreover, human subjective factors will inevitably lead to poor monitoring accuracy and the wind turbines cannot be maintained in time.
而且研究人员发现风力发电机组的风轮中心位置如果发生变化，是由于受损、老化等引起机械位置发生了变化，则导致风轮与风轮配合工作的其他部件位置关系发生变化了，这种情况必然导致发电机组不能正常工作了；如果风轮外形发生变化了，则可能是由于叶片受损残缺不全导致的，虽然发电机组能工作，但会导致发电机组整体性能降低，这种情况也会导致发电机组不能正常工作；同一时刻每帧图片中风轮外形如果不一致，则说明风轮快慢发生了变化，这种情况也会导致发电机组不能正常工作；造成风力发电机组不能正常工作的因素较复查，因此，对风力发电机组的视频分析监控提出了更大的挑战。Moreover, researchers have found that if the center position of the wind turbine of the wind turbine changes, it is due to changes in the mechanical position due to damage, aging, etc., which will lead to changes in the positional relationship between the wind wheel and other components that work together. This kind of The situation will inevitably lead to the generator set not working properly; if the shape of the wind wheel changes, it may be due to damaged and incomplete blades. Although the generator set can work, the overall performance of the generator set will be reduced. This situation will also As a result, the generator set cannot work normally; if the shape of the wind turbine in each frame of the picture at the same time is inconsistent, it means that the speed of the wind turbine has changed. This situation will also cause the generator set to not work normally; the factors that cause the wind turbine set to not work properly are more complex than review , Therefore, the video analysis and monitoring of wind turbines poses a greater challenge.
发明内容Contents of the invention
本申请的目的在于提供电力智能视频分析监控结构、系统、方法及其存储介质，其操作简单，可重复性强，提高了风力发电机组监控的工作效率和风力 发电机组监控的精度，不仅降低了风力发电机组的监控成本，而且便于对风力发电机组进行及时维护，降低了生产中的安全隐患，因此，可解决上述技术问题。The purpose of this application is to provide an electric power intelligent video analysis monitoring structure, system, method and storage medium, which is simple to operate and highly repeatable, improves the efficiency of wind turbine monitoring and the accuracy of wind turbine monitoring, and not only reduces the It reduces the monitoring cost of wind turbines, facilitates timely maintenance of wind turbines, and reduces potential safety hazards in production. Therefore, the above technical problems can be solved.
为了达到上述目的，本申请的技术方案如下：In order to achieve the above objectives, the technical solutions of this application are as follows:
本申请提供一种电力智能视频分析监控结构，包括：对比视频图像采集器和基准视频采集器，所述对比视频图像采集器和所述基准视频采集器分别与数据处理器电连接，所述数据处理器与所述故障预警器电连接。This application provides an electric power intelligent video analysis and monitoring structure, including: a comparison video image collector and a reference video collector. The comparison video image collector and the reference video collector are electrically connected to a data processor respectively. The data The processor is electrically connected to the fault early warning device.
本申请提供的电力智能视频分析监控结构、系统、方法及其存储介质，其操作简单，可重复性强，提高了风力发电机组监控的工作效率和风力发电机组监控的精度，不仅降低了风力发电机组的监控成本，而且便于对风力发电机组进行及时维护，降低了生产中的安全隐患。The electric power intelligent video analysis and monitoring structure, system, method and storage medium provided by this application are simple to operate and highly repeatable, which improves the efficiency and accuracy of wind turbine monitoring and not only reduces the cost of wind power generation It reduces the monitoring cost of the unit, facilitates timely maintenance of the wind turbine unit, and reduces potential safety hazards in production.
本申请还提供了一种电力智能视频分析监控系统，包括：This application also provides an electric power intelligent video analysis and monitoring system, including:
基准视频采集模块，用于采集标准风力发电机组的风轮在正常工作状态下的视频信息作为基准视频数据；The reference video collection module is used to collect the video information of the wind wheel of the standard wind turbine generator under normal working conditions as the reference video data;
对比视频采集模块，用于采集当前风力发电机组工作状态下风轮工作的视频信息作为对比视频数据；The comparison video collection module is used to collect the video information of the wind turbine operation under the current working state of the wind turbine as comparison video data;
数据处理模块，用于以一个风力发电机组的风轮转动周期为时长，将对比视频数据与基准视频数据进行比对，通过所述对比视频与所述基准视频内风力发电机组的风轮转动图像数据比对判断当前风力发电机组工作状态是否正常，并传输当前风力发电机组工作状态是否正常数据至故障预警模块；The data processing module is used to compare the comparison video data with the reference video data by taking the rotation period of the wind turbine of a wind turbine as the duration, and use the comparison video and the reference video to determine the wind turbine rotation image of the wind turbine. Compare the data to determine whether the current working status of the wind turbine is normal, and transmit the data of whether the current working status of the wind turbine is normal to the fault warning module;
故障预警模块，用于根据接收到的当前风力发电机组工作状态是否正常数据判定是否发出故障预警提示。The fault warning module is used to determine whether to issue a fault warning prompt based on the received data on whether the current working status of the wind turbine generator set is normal.
作为可选技术方案，包括：调节对比视频的时长模块，所述调节对比视频的时长模块用于通过对比视频数据和基准视频数据的图像帧比对，调节对比视频数据的起始点，使对比视频起始点图像上风轮与环境的相对位置与基准视频起始点图像上风轮与环境的位置呈相对应设置；按照时间长度对对比视频数据的内容进行快进或缩放处理，使对比视频的时长与基准视频的时长一致。As an optional technical solution, it includes: a module for adjusting the duration of the comparison video. The module for adjusting the duration of the comparison video is used to adjust the starting point of the comparison video data through image frame comparison of the comparison video data and the reference video data, so that the comparison video The relative position of the wind wheel and the environment on the starting point image is set correspondingly to the position of the wind wheel and the environment on the starting point image of the reference video; the content of the comparison video data is fast-forwarded or zoomed according to the time length, so that the duration of the comparison video is consistent with the reference The videos are the same length.
作为可选技术方案，包括：基准视频预处理模块，所述基准视频预处理模块用于将基准视频和时长调节后的对比视频按每一帧分别拆分多个基准视频图像和对比视频图像；将同一帧的基准视频图像和对比视频图像作为一个数据组，获得多个数据组；对每个数据组内的基准视频图像进行角度调节，完成对基准视频的预处理。As an optional technical solution, it includes: a reference video preprocessing module, which is used to split the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame; The reference video image and the comparison video image of the same frame are used as one data group to obtain multiple data groups; the angle of the reference video image in each data group is adjusted to complete the preprocessing of the reference video.
作为可选技术方案，包括：图像角度调节模块，所述图像角度调节模块用于分别对基准视频图像和对比视频图像中的风轮的每个叶片和轮毂处以点进行 标记；分别连接基准视频图像和对比视频图像上的标记点形成两个标记图；对比两个标记图，并以基准视频图像上的标记图为基准，调节对比视频图像的角度。As an optional technical solution, it includes: an image angle adjustment module, which is used to mark points on each blade and hub of the wind wheel in the reference video image and the comparison video image respectively; connect the reference video images respectively Two marker images are formed with the marker points on the comparison video image; the two marker images are compared, and the angle of the comparison video image is adjusted based on the marker image on the reference video image.
作为可选技术方案，所述数据处理模块包括：图像边缘判定模块，所述图像边缘判定模块用于以风轮转动图像数据中图像上每个像素点的坐标标记每个坐标点；以每个像素点为器，记其相邻的16×16位置内的像素为一组像素点；将每组像素点的平均灰度值记为该组像素的灰度；通过每组像素灰度的对比，获取风力发电机组的风轮的位置和边界形状图像。As an optional technical solution, the data processing module includes: an image edge determination module, which is used to mark each coordinate point with the coordinate of each pixel point on the image in the wind turbine rotation image data; The pixel is a device, and the pixels in the adjacent 16×16 positions are recorded as a group of pixels; the average gray value of each group of pixels is recorded as the gray level of the group of pixels; through the comparison of the gray levels of each group of pixels , obtain the position and boundary shape image of the wind turbine rotor.
本申请还提供一种电力智能视频分析监控方法，包括以下步骤：This application also provides an electric power intelligent video analysis and monitoring method, which includes the following steps:
采集标准风力发电机组在风轮正常工作状态下的视频作为基准视频；Collect videos of standard wind turbines under normal working conditions of the wind turbine as a benchmark video;
采集当前风力发电机组工作状态下的视频作为对比视频；Collect videos of the current working status of wind turbines as comparison videos;
以一个转动周期为时长，将对比视频与基准视频进行比对，通过对比视频与基准视频的风轮转动图像判断当前风力发电机组工作状态是否正常；Using one rotation cycle as the duration, compare the comparison video with the benchmark video, and determine whether the current working status of the wind turbine is normal by comparing the wind wheel rotation images of the video and the benchmark video;
判定当前风力发电机组工作状态不正常时，发出故障预警提示。When it is determined that the current working status of the wind turbine is abnormal, a fault warning will be issued.
作为可选技术方案具体包括以下步骤：As an optional technical solution, it specifically includes the following steps:
当标准风力发电机组在风轮转速稳定后，采集标准风力发电机组风轮的转动视频；以一个转动周期为时长，截取标准风力发电机组转动的视频，作为基准视频；When the standard wind turbine set has stabilized the rotor speed, collect the rotation video of the standard wind turbine set's wind rotor; use one rotation cycle as the duration, intercept the video of the standard wind turbine set's rotation as the benchmark video;
采集当前风力发电机组的转动视频；以转动视频中风轮上的一个点作为标记点，以标记点转动一周的时间作为风轮的转动周期；以每个转动周期的起始点和终止点时间为界，截取当前风力发电机组的转动视频作为对比视频；Collect the rotation video of the current wind turbine set; use a point on the rotor in the rotation video as the mark point, and use the time it takes for the mark point to rotate once as the rotation period of the wind wheel; use the starting point and end point time of each rotation cycle as the boundary , intercept the current rotation video of the wind turbine as a comparison video;
对基准视频进行预处理，并对同一时间点的每帧基准视频和对比视频进行图像边缘判定，分别确定每帧基准视频和对比视频上风轮的位置和边界形状；判断每帧基准视频和对比视频上风轮的位置和边界形状图像是否相同，并据此确定当前风力发电机组工作状态是否正常；Preprocess the reference video, and perform image edge determination on each frame of the reference video and comparison video at the same time point, respectively determine the position and boundary shape of the wind wheel on each frame of the reference video and comparison video; determine each frame of the reference video and comparison video Whether the position and boundary shape image of the upper wind rotor are the same, and based on this, it is determined whether the current working status of the wind turbine is normal;
判定当前风力发电机组工作状态不正常时，发出故障预警提示。When it is determined that the current working status of the wind turbine is abnormal, a fault warning will be issued.
作为可选技术方案，对基准视频进行预处理包括以下步骤：调节对比视频的时长；将基准视频和时长调节后的对比视频按每一帧分别拆分多个基准视频图像和对比视频图像；将同一帧的基准视频图像和对比视频图像作为一个数据组，获得多个数据组；对每个数据组内的基准视频图像进行角度调节，完成对基准视频的预处理；As an optional technical solution, preprocessing the reference video includes the following steps: adjusting the duration of the comparison video; splitting the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame; The reference video image and comparison video image of the same frame are used as one data group to obtain multiple data groups; the angle of the reference video image in each data group is adjusted to complete the preprocessing of the reference video;
获取每帧基准视频图像和对比视频图像中风轮的位置和边界形状包括以下步骤：以图像上每个像素点的坐标标记每个坐标点；以每个像素点为器，记其 相邻的16×16位置内的像素为一组像素点；将每组像素点的平均灰度值记为该组像素的灰度；通过每组像素灰度的对比，获取风轮的位置和边界形状图像。Obtaining the position and boundary shape of the wind wheel in each frame of the reference video image and the comparison video image includes the following steps: mark each coordinate point with the coordinate of each pixel point on the image; use each pixel point as a device, record its adjacent 16 The pixels in the ×16 position are a group of pixels; the average gray value of each group of pixels is recorded as the gray level of the group of pixels; through the comparison of the gray levels of each group of pixels, the position and boundary shape image of the wind wheel is obtained.
本申请还提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述中任一项所述的电力智能视频分析监控方法。The present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the power intelligent video analysis and monitoring method described in any one of the above is implemented.
本申请提供的电力智能视频分析监控结构、系统、方法及其存储介质，获取每帧对比视频与基准视频内风力发电机组的风轮转动图像比对并通过帧对比的方式将风力发电机组风轮的对比视频的风轮转动图像和基准视频的风轮转动图像进行对比，判断每帧基准视频和对比视频上风轮的位置和边界形状图像是否相同，确定风轮是否发生故障，并据此确定当前风力发电机组工作状态是否正常，其操作简单，可重复性强，提高了风力发电机组监控的工作效率和风力发电机组监控的精度，不仅降低了风力发电机组的监控成本，而且便于对风力发电机组进行及时维护，降低了生产中的安全隐患。The power intelligent video analysis and monitoring structure, system, method and storage medium provided by this application can obtain the comparison video of each frame and the wind turbine rotation image of the wind turbine set in the reference video, and compare the wind turbine rotor of the wind turbine set through frame comparison. Compare the wind wheel rotation image of the comparison video with the wind wheel rotation image of the benchmark video, determine whether the position and boundary shape image of the wind wheel on each frame of the benchmark video and the comparison video are the same, determine whether the wind wheel is faulty, and determine the current situation accordingly. Whether the wind turbine is in normal working condition, its operation is simple and repeatable, which improves the efficiency of wind turbine monitoring and the accuracy of wind turbine monitoring. It not only reduces the monitoring cost of wind turbines, but also facilitates the monitoring of wind turbines. Carry out timely maintenance and reduce safety risks in production.
图1为本申请一个实施例提供的一种电力智能视频分析监控结构的电路图。Figure 1 is a circuit diagram of an electric power intelligent video analysis and monitoring structure provided by an embodiment of the present application.
图2为本申请一个实施例提供的一种电力智能视频分析监控系统的流程图。Figure 2 is a flow chart of an electric power intelligent video analysis and monitoring system provided by an embodiment of the present application.
图3为本申请一个实施例提供的一种电力智能视频分析监控方法的流程图。Figure 3 is a flow chart of an electric power intelligent video analysis and monitoring method provided by an embodiment of the present application.
下面结合附图详细说明本申请的可选实施方式。Optional implementations of the present application are described in detail below with reference to the accompanying drawings.
可以理解，本申请是通过一些实施例为了达到本申请的目的，如图1所示，本申请一个实施例提供的一种电力智能视频分析监控结构，包括：对比视频图像采集器和基准视频采集器，所述对比视频图像采集器和所述基准视频采集器分别与数据处理器电连接，所述数据处理器与所述故障预警器电连接；所述基准视频采集器用于采集标准风力发电机组在风轮正常工作状态下的视频作为基准视频信号，并对数据处理器发送基准视频信号，所述对比视频图像采集器用于采集当前风力发电机组工作状态下的视频作为对比视频信号，并对数据处理器发送对比视频信号，所述数据处理器检测到信号，处理信号，以一个转动周期为时长，将对比视频数据与基准视频数据进行对比，通过对比视频与基准视频内风轮的转动图像判断当前风力发电机组工作状态是否正常数据传输至故障预警器；故障预警器接收当前风力发电机组工作状态是否正常数据，判定当前风力发电机组工作状态不正常时，发出故障预警提示；获取每帧对比视频 与基准视频内风力发电机组的风轮转动图像比对并通过帧对比的方式将风力发电机组风轮的对比视频的风轮转动图像和基准视频的风轮转动图像进行对比，判断每帧基准视频和对比视频上风轮的位置和边界形状图像是否相同，确定风轮是否发生故障，并据此确定当前风力发电机组工作状态是否正常，其操作简单，可重复性强，提高了风力发电机组监控的工作效率和风力发电机组监控的精度，不仅降低了风力发电机组的监控成本，而且便于对风力发电机组进行及时维护，降低了生产中的安全隐患。It can be understood that this application achieves the purpose of this application through some embodiments. As shown in Figure 1, an electric power intelligent video analysis and monitoring structure provided by one embodiment of this application includes: a comparison video image collector and a reference video collection. The comparison video image collector and the reference video collector are electrically connected to a data processor respectively, and the data processor is electrically connected to the fault early warning device; the reference video collector is used to collect standard wind turbine generator sets The video in the normal working state of the wind turbine is used as a reference video signal, and the reference video signal is sent to the data processor. The comparison video image collector is used to collect the video in the current working state of the wind turbine as a comparison video signal, and compares the data The processor sends a comparison video signal, and the data processor detects the signal, processes the signal, takes one rotation cycle as the duration, compares the comparison video data with the reference video data, and makes a judgment by comparing the rotation image of the wind wheel in the video and the reference video. The data of whether the current working status of the wind turbine is normal is transmitted to the fault early warning device; the fault early warning device receives the data of whether the current working status of the wind turbine is normal, determines whether the current working status of the wind turbine is abnormal, and issues a fault warning prompt; obtains each frame comparison video Compare the rotor rotation image of the wind turbine generator set in the reference video and compare the rotor rotation image of the wind turbine generator set wind rotor comparison video with the wind rotor rotation image of the reference video to determine each frame of the reference video Compare the position and boundary shape image of the wind wheel on the video to determine whether the wind wheel is faulty and determine whether the current working status of the wind turbine is normal. The operation is simple and repeatable, which improves the efficiency of wind turbine monitoring. The work efficiency and accuracy of wind turbine monitoring not only reduce the monitoring cost of wind turbines, but also facilitate timely maintenance of wind turbines and reduce safety hazards in production.
风轮转动图像可选风轮的位置图像和边界形状图像。The rotation image of the wind wheel can be selected from the position image and boundary shape image of the wind wheel.
如图2所示，本申请一个实施例还提供了一种电力智能视频分析监控系统，包括：As shown in Figure 2, one embodiment of the present application also provides an electric power intelligent video analysis and monitoring system, including:
基准视频采集模块，用于采集标准风力发电机组的风轮在正常工作状态下的视频信息作为基准视频数据；The reference video collection module is used to collect the video information of the wind wheel of the standard wind turbine generator under normal working conditions as the reference video data;
对比视频采集模块，用于采集当前风力发电机组工作状态下风轮工作的视频信息作为对比视频数据；The comparison video collection module is used to collect the video information of the wind turbine operation under the current working state of the wind turbine as comparison video data;
数据处理模块，用于以一个风力发电机组的风轮转动周期为时长，将对比视频数据与基准视频数据进行比对，通过所述对比视频与所述基准视频内风力发电机组的风轮转动图像数据比对判断当前风力发电机组工作状态是否正常，并传输当前风力发电机组工作状态是否正常数据至故障预警模块；The data processing module is used to compare the comparison video data with the reference video data by taking the rotation period of the wind turbine of a wind turbine as the duration, and use the comparison video and the reference video to determine the wind turbine rotation image of the wind turbine. Compare the data to determine whether the current working status of the wind turbine is normal, and transmit the data of whether the current working status of the wind turbine is normal to the fault warning module;
调节对比视频的时长模块，所述调节对比视频的时长模块用于通过对比视频数据和基准视频数据的图像帧比对，调节对比视频数据的起始点，使对比视频起始点图像上风轮与环境的相对位置与基准视频起始点图像上风轮与环境的位置呈相对应设置；按照时间长度对对比视频数据的内容进行快进或缩放处理，使对比视频的时长与基准视频的时长一致；Adjust the duration module of the comparison video. The module for adjusting the duration of the comparison video is used to adjust the starting point of the comparison video data through the image frame comparison of the comparison video data and the reference video data, so that the contrast between the wind wheel and the environment on the starting point image of the comparison video is The relative position is set correspondingly to the position of the wind wheel and the environment on the starting point image of the reference video; the content of the comparison video data is fast-forwarded or zoomed according to the time length, so that the duration of the comparison video is consistent with the duration of the reference video;
基准视频预处理模块，所述基准视频预处理模块用于将基准视频和时长调节后的对比视频按每一帧分别拆分多个基准视频图像和对比视频图像；将同一帧的基准视频图像和对比视频图像作为一个数据组，获得多个数据组；对每个数据组内的基准视频图像进行角度调节，完成对基准视频的预处理；A reference video preprocessing module, which is used to split the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame; combine the reference video image of the same frame and Compare the video images as a data group to obtain multiple data groups; adjust the angle of the reference video image in each data group to complete the preprocessing of the reference video;
图像角度调节模块，所述图像角度调节模块用于分别对基准视频图像和对比视频图像中的风轮的每个叶片和轮毂处以点进行标记；分别连接基准视频图像和对比视频图像上的标记点形成两个标记图；对比两个标记图，并以基准视频图像上的标记图为基准，调节对比视频图像的角度；Image angle adjustment module, the image angle adjustment module is used to mark each blade and hub of the wind wheel in the reference video image and the comparison video image with points respectively; connect the marking points on the reference video image and the comparison video image respectively Form two marked images; compare the two marked images, and use the marked image on the reference video image as a benchmark to adjust the angle of the compared video image;
图像边缘判定模块，用于以风轮转动图像数据中图像上每个像素点的坐标标记每个坐标点；以每个像素点为器，记其相邻的16×16位置内的像素为一组 像素点；将每组像素点的平均灰度值记为该组像素的灰度；通过每组像素灰度的对比，获取风力发电机组的风轮的位置和边界形状图像；The image edge determination module is used to mark each coordinate point with the coordinates of each pixel point on the image in the wind turbine rotation image data; using each pixel point as a device, record the pixels in its adjacent 16×16 positions as one A group of pixels; record the average grayscale value of each group of pixels as the grayscale of the group of pixels; obtain the position and boundary shape image of the wind turbine rotor by comparing the grayscale of each group of pixels;
故障预警模块，用于根据接收到的当前风力发电机组工作状态是否正常数据判定是否发出故障预警提示；其操作简单，可重复性强，提高了电力智能视频分析监控的工作效率和电力智能视频分析监控的精度，不仅降低了风力发电机组的监控成本，而且便于对风力发电机组进行及时维护，降低了生产中的安全隐患；其操作简单，可重复性强，提高了风力发电机组监控的工作效率和风力发电机组监控的精度，不仅降低了风力发电机组的监控成本，而且便于对风力发电机组进行及时维护，降低了生产中的安全隐患。The fault warning module is used to determine whether to issue a fault warning prompt based on the received data on whether the current working status of the wind turbine is normal; its operation is simple and highly repeatable, which improves the work efficiency of power intelligent video analysis and monitoring and the power intelligent video analysis The accuracy of monitoring not only reduces the monitoring cost of wind turbines, but also facilitates timely maintenance of wind turbines and reduces safety hazards in production; its simple operation and strong repeatability improve the efficiency of wind turbine monitoring. And the accuracy of wind turbine monitoring not only reduces the monitoring cost of wind turbines, but also facilitates timely maintenance of wind turbines and reduces safety hazards in production.
如图3所示，本申请一个实施例还提供了一种电力智能视频分析监控方法，包括以下步骤：As shown in Figure 3, one embodiment of the present application also provides an electric power intelligent video analysis and monitoring method, which includes the following steps:
采集标准风力发电机组在风轮正常工作状态下的视频作为基准视频；Collect videos of standard wind turbines under normal working conditions of the wind turbine as a benchmark video;
采集当前风力发电机组工作状态下的视频作为对比视频；Collect videos of the current working status of wind turbines as comparison videos;
以一个转动周期为时长，将对比视频与基准视频进行比对，通过对比视频与基准视频的风轮转动图像判断当前风力发电机组工作状态是否正常；Using one rotation cycle as the duration, compare the comparison video with the benchmark video, and determine whether the current working status of the wind turbine is normal by comparing the wind wheel rotation images of the video and the benchmark video;
判定当前风力发电机组工作状态不正常时，发出故障预警提示；When it is determined that the current working status of the wind turbine is abnormal, a fault warning will be issued;
上述方法具体包括以下步骤：The above method specifically includes the following steps:
当标准风力发电机组在风轮转速稳定后，采集标准风力发电机组风轮的转动视频；以一个转动周期为时长，截取标准风力发电机组转动的视频，作为基准视频；When the standard wind turbine set has stabilized the rotor speed, collect the rotation video of the standard wind turbine set's wind rotor; use one rotation cycle as the duration, intercept the video of the standard wind turbine set's rotation as the benchmark video;
采集当前风力发电机组的转动视频；以转动视频中风轮上的一个点作为标记点，以标记点转动一周的时间作为风轮的转动周期；以每个转动周期的起始点和终止点时间为界，截取当前风力发电机组的转动视频作为对比视频；Collect the rotation video of the current wind turbine set; use a point on the rotor in the rotation video as the mark point, and use the time it takes for the mark point to rotate once as the rotation period of the wind wheel; use the starting point and end point time of each rotation cycle as the boundary , intercept the current rotation video of the wind turbine as a comparison video;
对基准视频进行预处理，对基准视频进行预处理包括以下步骤：调节对比视频的时长；将基准视频和时长调节后的对比视频按每一帧分别拆分多个基准视频图像和对比视频图像；将同一帧的基准视频图像和对比视频图像作为一个数据组，获得多个数据组；对每个数据组内的基准视频图像进行角度调节，完成对基准视频的预处理；并对同一时间点的每帧基准视频和对比视频进行图像边缘判定，分别确定每帧基准视频和对比视频上风轮的位置和边界形状；获取每帧基准视频图像和对比视频图像中风轮的位置和边界形状包括以下步骤：以图像上每个像素点的坐标标记每个坐标点；以每个像素点为器，记其相邻的16×16位置内的像素为一组像素点；将每组像素点的平均灰度值记为该组像素的灰度；通过每组像素灰度的对比，获取风轮的位置和边界形状图像；判断每帧 基准视频和对比视频上风轮的位置和边界形状图像是否相同，并据此确定当前风力发电机组工作状态是否正常；Preprocess the reference video. Preprocessing the reference video includes the following steps: adjusting the duration of the comparison video; splitting the reference video and the comparison video after the duration adjustment into multiple reference video images and comparison video images according to each frame; The reference video image and the comparison video image of the same frame are used as one data group to obtain multiple data groups; the angle of the reference video image in each data group is adjusted to complete the preprocessing of the reference video; and the reference video image at the same time point is processed. Perform image edge determination on each frame of the reference video and comparison video, and determine the position and boundary shape of the wind wheel on each frame of the reference video and comparison video respectively. Obtaining the position and boundary shape of the wind wheel on each frame of the reference video image and comparison video image includes the following steps: Mark each coordinate point with the coordinates of each pixel point on the image; use each pixel point as a device, record the pixels in its adjacent 16×16 positions as a group of pixel points; calculate the average gray level of each group of pixel points The value is recorded as the grayscale of the group of pixels; through the comparison of the grayscale of each group of pixels, the position and boundary shape image of the wind wheel are obtained; it is judged whether the position and boundary shape image of the wind wheel on each frame of the reference video and the comparison video are the same, and based on This determines whether the current working status of the wind turbine is normal;
如果同一时间点每帧基准视频和对比视频中风轮的位置和边界形状图像相同，则说明风轮相对其他部件的位置没有变化，风轮没有发生变化，发电机组工作状态正常，不发出故障预警提示；If the position and boundary shape image of the wind wheel in each frame of the reference video and the comparison video at the same time point are the same, it means that the position of the wind wheel relative to other components has not changed, the wind wheel has not changed, the generator set is working normally, and no fault warning is issued. ;
如果同一时间点每帧基准视频和对比视频中风轮的位置和边界形状图像不相同，则说明风轮相对其他部件的位置发生变化，风轮发生变化，发电机组工作状态不正常，发出故障预警提示。If the position and boundary shape image of the wind wheel in each frame of the reference video and comparison video at the same time point are different, it means that the position of the wind wheel relative to other components has changed, the wind wheel has changed, the working status of the generator set is abnormal, and a fault warning prompt is issued. .
本申请一个实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述中任一项所述的电力智能视频分析监控方法。One embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the power intelligent video analysis and monitoring method described in any one of the above is implemented.
本申请实施例提供的电力智能视频分析监控结构、系统、方法及其存储介质，获取每帧对比视频与基准视频内风力发电机组的风轮转动图像比对并通过帧对比的方式将风力发电机组风轮的对比视频的风轮转动图像和基准视频的风轮转动图像进行对比，判断每帧基准视频和对比视频上风轮的位置和边界形状图像是否相同，确定风轮是否发生故障，并据此确定当前风力发电机组工作状态是否正常，其操作简单，可重复性强，提高了风力发电机组监控的工作效率和风力发电机组监控的精度，不仅降低了风力发电机组的监控成本，而且便于对风力发电机组进行及时维护，降低了生产中的安全隐患。The electric power intelligent video analysis and monitoring structure, system, method and storage medium provided by the embodiments of the present application obtain each frame comparison video and compare the wind turbine rotation image of the wind turbine generator set in the reference video, and compare the wind turbine generator set through frame comparison. Compare the wind wheel rotation image of the comparison video with the wind wheel rotation image of the benchmark video, determine whether the position and boundary shape image of the wind wheel on each frame of the benchmark video and the comparison video are the same, determine whether the wind wheel is faulty, and based on this Determining whether the current working status of the wind turbine is normal, its operation is simple and repeatable, which improves the efficiency of wind turbine monitoring and the accuracy of wind turbine monitoring. It not only reduces the monitoring cost of wind turbines, but also facilitates wind turbine monitoring. Generator units are maintained in a timely manner, reducing safety hazards in production.
可以理解，本申请是通过一些实施例进行描述的，本领域技术人员知悉的，在不脱离本申请的精神和范围的情况下，可以对这些特征和实施例进行各种改变或等效替换。另外，在本申请的教导下，可以对这些特征和实施例进行修改以适应具体的情况及材料而不会脱离本申请的精神和范围。因此，本申请不受此处所公开的具体实施例的限制，所有落入本申请的权利要求范围各种改变或等效替换。另外，在本申请的教导下，可以对这些特征和实施例进行修改以适应具体的情况及材料而不会脱离本申请的精神和范围。因此，本申请不受此处所公开的具体实施例的限制，所有落入本申请的权利要求范围内的实施例都属于本申请所保护的范围内。It can be understood that the present application has been described through some embodiments. Those skilled in the art know that various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of the present application. In addition, the features and embodiments may be modified to adapt a particular situation and material to the teachings of this application without departing from the spirit and scope of this application. Therefore, the present application is not limited to the specific embodiments disclosed here, and all changes or equivalent substitutions falling within the scope of the claims of the present application are intended. In addition, the features and embodiments may be modified to adapt a particular situation and material to the teachings of this application without departing from the spirit and scope of this application. Therefore, this application is not limited by the specific embodiments disclosed here, and all embodiments falling within the scope of the claims of this application belong to the scope of protection of this application.
Claims (10)
- 一种电力智能视频分析监控结构，其特征在于，包括：对比视频图像采集器和基准视频采集器，所述对比视频图像采集器和所述基准视频采集器分别与数据处理器电连接，所述数据处理器与故障预警器电连接。An intelligent video analysis and monitoring structure for electric power, which is characterized in that it includes: a comparison video image collector and a reference video collector, the comparison video image collector and the reference video collector are electrically connected to a data processor respectively, and the The data processor is electrically connected to the fault early warning device.
- 一种电力智能视频分析监控系统，其特征在于，包括：An electric power intelligent video analysis and monitoring system, which is characterized by including:基准视频采集模块，用于采集标准风力发电机组的风轮在正常工作状态下的视频信息作为基准视频数据；The reference video collection module is used to collect the video information of the wind wheel of the standard wind turbine generator under normal working conditions as the reference video data;对比视频采集模块，用于采集当前风力发电机组工作状态下风轮工作的视频信息作为对比视频数据；The comparison video collection module is used to collect the video information of the wind turbine operation under the current working state of the wind turbine as comparison video data;数据处理模块，用于以一个风力发电机组的风轮转动周期为时长，将对比视频数据与基准视频数据进行比对，通过所述对比视频与所述基准视频内风力发电机组的风轮转动图像数据比对判断当前风力发电机组工作状态是否正常，并传输当前风力发电机组工作状态是否正常数据至故障预警模块；The data processing module is used to compare the comparison video data with the reference video data by taking the rotation period of the wind turbine of a wind turbine as the duration, and use the comparison video and the reference video to determine the wind turbine rotation image of the wind turbine. Compare the data to determine whether the current working status of the wind turbine is normal, and transmit the data of whether the current working status of the wind turbine is normal to the fault warning module;故障预警模块，用于根据接收到的当前风力发电机组工作状态是否正常数据判定是否发出故障预警提示。The fault warning module is used to determine whether to issue a fault warning prompt based on the received data on whether the current working status of the wind turbine generator set is normal.
- 根据权利要求2所述的电力智能视频分析监控系统，其特征在于，包括：调节对比视频的时长模块，所述调节对比视频的时长模块用于通过对比视频数据和基准视频数据的图像帧比对，调节对比视频数据的起始点，使对比视频起始点图像上风轮与环境的相对位置与基准视频起始点图像上风轮与环境的位置呈相对应设置；按照时间长度对对比视频数据的内容进行快进或缩放处理，使对比视频的时长与基准视频的时长一致。The electric power intelligent video analysis and monitoring system according to claim 2, characterized in that it includes: a module for adjusting the duration of the comparison video, the module for adjusting the duration of the comparison video is used to compare the image frames of the comparison video data and the reference video data. , adjust the starting point of the comparison video data so that the relative position of the wind wheel and the environment on the comparison video starting point image and the position of the wind wheel and the environment on the reference video starting point image are set correspondingly; the content of the comparison video data is fastened according to the time length. Advanced or scaling processing to make the duration of the comparison video consistent with the duration of the reference video.
- 根据权利要求3所述的电力智能视频分析监控系统，其特征在于，包括：基准视频预处理模块，所述基准视频预处理模块用于将基准视频和时长调节后的对比视频按每一帧分别拆分多个基准视频图像和对比视频图像；将同一帧的基准视频图像和对比视频图像作为一个数据组，获得多个数据组；对每个数据组内的基准视频图像进行角度调节，完成对基准视频的预处理。The power intelligent video analysis and monitoring system according to claim 3, characterized by comprising: a reference video pre-processing module, the reference video pre-processing module is used to separate the reference video and the duration-adjusted comparison video according to each frame. Split multiple reference video images and comparison video images; use the reference video image and comparison video image of the same frame as one data group to obtain multiple data groups; adjust the angle of the reference video image in each data group to complete the comparison Preprocessing of benchmark videos.
- 根据权利要求4所述的电力智能视频分析监控系统，其特征在于，包括：图像角度调节模块，所述图像角度调节模块用于分别对基准视频图像和对比视频图像中的风轮的每个叶片和轮毂处以点进行标记；分别连接基准视频图像和对比视频图像上的标记点形成两个标记图；对比两个标记图，并以基准视频图像上的标记图为基准，调节对比视频图像的角度。The power intelligent video analysis and monitoring system according to claim 4, characterized in that it includes: an image angle adjustment module, the image angle adjustment module is used to adjust each blade of the wind wheel in the reference video image and the comparison video image respectively. and the wheel hub are marked with points; connect the marking points on the reference video image and the comparison video image to form two marking images; compare the two marking images, and use the marking image on the reference video image as a benchmark to adjust the angle of the comparison video image .
- 根据权利要求2所述的电力智能视频分析监控系统，其特征在于，所述数据处理模块包括：图像边缘判定模块，所述图像边缘判定模块用于以风轮转 动图像数据中图像上每个像素点的坐标标记每个坐标点；以每个像素点为器，记其相邻的16×16位置内的像素为一组像素点；将每组像素点的平均灰度值记为该组像素的灰度；通过每组像素灰度的对比，获取风力发电机组的风轮的位置和边界形状图像。The power intelligent video analysis and monitoring system according to claim 2, characterized in that the data processing module includes: an image edge determination module, the image edge determination module is used to rotate each pixel on the image in the image data with a wind wheel Mark each coordinate point with the coordinates of the point; take each pixel as a device, record the pixels within its adjacent 16×16 positions as a group of pixels; record the average gray value of each group of pixels as this group of pixels The grayscale of each group of pixels is compared to obtain the position and boundary shape image of the wind turbine rotor.
- 一种电力智能视频分析监控方法，其特征在于，包括以下步骤：An electric power intelligent video analysis and monitoring method, which is characterized by including the following steps:采集标准风力发电机组在风轮正常工作状态下的视频作为基准视频；Collect videos of standard wind turbines under normal working conditions of the wind turbine as a benchmark video;采集当前风力发电机组工作状态下的视频作为对比视频；Collect videos of the current working status of wind turbines as comparison videos;以一个转动周期为时长，将对比视频与基准视频进行比对，通过对比视频与基准视频的风轮转动图像判断当前风力发电机组工作状态是否正常；Using one rotation cycle as the duration, compare the comparison video with the benchmark video, and determine whether the current working status of the wind turbine is normal by comparing the wind wheel rotation images of the video and the benchmark video;判定当前风力发电机组工作状态不正常时，发出故障预警提示。When it is determined that the current working status of the wind turbine is abnormal, a fault warning will be issued.
- 根据权利要求7所述的电力智能视频分析监控方法，其特征在于，具体包括以下步骤：The electric power intelligent video analysis and monitoring method according to claim 7, characterized in that it specifically includes the following steps:当标准风力发电机组在风轮转速稳定后，采集标准风力发电机组风轮的转动视频；以一个转动周期为时长，截取标准风力发电机组转动的视频，作为基准视频；When the standard wind turbine set has stabilized the rotor speed, collect the rotation video of the standard wind turbine set's wind rotor; use one rotation cycle as the duration, intercept the video of the standard wind turbine set's rotation as the benchmark video;采集当前风力发电机组的转动视频；以转动视频中风轮上的一个点作为标记点，以标记点转动一周的时间作为风轮的转动周期；以每个转动周期的起始点和终止点时间为界，截取当前风力发电机组的转动视频作为对比视频；Collect the rotation video of the current wind turbine set; use a point on the rotor in the rotation video as the mark point, and use the time it takes for the mark point to rotate once as the rotation period of the wind wheel; use the starting point and end point time of each rotation cycle as the boundary , intercept the current rotation video of the wind turbine as a comparison video;对基准视频进行预处理，并对同一时间点的每帧基准视频和对比视频进行图像边缘判定，分别确定每帧基准视频和对比视频上风轮的位置和边界形状；判断每帧基准视频和对比视频上风轮的位置和边界形状图像是否相同，并据此确定当前风力发电机组工作状态是否正常；Preprocess the reference video, and perform image edge determination on each frame of the reference video and comparison video at the same time point, respectively determine the position and boundary shape of the wind wheel on each frame of the reference video and comparison video; determine each frame of the reference video and comparison video Whether the position and boundary shape image of the upper wind rotor are the same, and based on this, it is determined whether the current working status of the wind turbine is normal;判定当前风力发电机组工作状态不正常时，发出故障预警提示。When it is determined that the current working status of the wind turbine is abnormal, a fault warning will be issued.
- 根据权利要求7所述的电力智能视频分析监控方法，其特征在于，对基准视频进行预处理包括以下步骤：调节对比视频的时长；将基准视频和时长调节后的对比视频按每一帧分别拆分多个基准视频图像和对比视频图像；将同一帧的基准视频图像和对比视频图像作为一个数据组，获得多个数据组；对每个数据组内的基准视频图像进行角度调节，完成对基准视频的预处理；The power intelligent video analysis and monitoring method according to claim 7, characterized in that preprocessing the reference video includes the following steps: adjusting the duration of the comparison video; splitting the reference video and the comparison video after the duration adjustment according to each frame. Divide into multiple reference video images and comparison video images; use the reference video image and comparison video image of the same frame as one data group to obtain multiple data groups; adjust the angle of the reference video image in each data group to complete the benchmark Video preprocessing;获取每帧基准视频图像和对比视频图像中风轮的位置和边界形状包括以下步骤：以图像上每个像素点的坐标标记每个坐标点；以每个像素点为器，记其相邻的16×16位置内的像素为一组像素点；将每组像素点的平均灰度值记为该组像素的灰度；通过每组像素灰度的对比，获取风轮的位置和边界形状图像。Obtaining the position and boundary shape of the wind wheel in each frame of the reference video image and the comparison video image includes the following steps: mark each coordinate point with the coordinate of each pixel point on the image; use each pixel point as a device, record its adjacent 16 The pixels in the ×16 position are a group of pixels; the average gray value of each group of pixels is recorded as the gray level of the group of pixels; through the comparison of the gray levels of each group of pixels, the position and boundary shape image of the wind wheel is obtained.
- 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求7-9中任一项所述的电力智能视频分析监控方法。A computer-readable storage medium with a computer program stored thereon, characterized in that when the program is executed by a processor, the power intelligent video analysis and monitoring method as described in any one of claims 7-9 is implemented.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210703054.9 | 2022-06-21 | ||
| CN202210703054.9A CN115174856A (en) | 2022-06-21 | 2022-06-21 | Electric power intelligent video analysis monitoring structure, system, method and storage medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023246062A1 true WO2023246062A1 (en) | 2023-12-28 |
Family
ID=83487660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/142785 WO2023246062A1 (en) | 2022-06-21 | 2022-12-28 | Intelligent video-based electric power analysis and monitoring structure, system and method, and storage medium thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115174856A (en) |
| WO (1) | WO2023246062A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115174856A (en) * | 2022-06-21 | 2022-10-11 | 西安热工研究院有限公司 | Electric power intelligent video analysis monitoring structure, system, method and storage medium thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130307961A1 (en) * | 2011-02-01 | 2013-11-21 | Jordi Puigcorbé Punzano | Device and method for visual analysis of a wind turbine blade |
| CN204166347U (en) * | 2014-05-26 | 2015-02-18 | 温州电力设计有限公司 | Wind power generating set supervisory system |
| CN111160272A (en) * | 2019-12-31 | 2020-05-15 | 西安古鲸电子技术有限公司 | Intelligent image fault judgment and early warning system |
| CN115174856A (en) * | 2022-06-21 | 2022-10-11 | 西安热工研究院有限公司 | Electric power intelligent video analysis monitoring structure, system, method and storage medium thereof |
-
2022
- 2022-06-21 CN CN202210703054.9A patent/CN115174856A/en active Pending
- 2022-12-28 WO PCT/CN2022/142785 patent/WO2023246062A1/en unknown
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130307961A1 (en) * | 2011-02-01 | 2013-11-21 | Jordi Puigcorbé Punzano | Device and method for visual analysis of a wind turbine blade |
| CN204166347U (en) * | 2014-05-26 | 2015-02-18 | 温州电力设计有限公司 | Wind power generating set supervisory system |
| CN111160272A (en) * | 2019-12-31 | 2020-05-15 | 西安古鲸电子技术有限公司 | Intelligent image fault judgment and early warning system |
| CN115174856A (en) * | 2022-06-21 | 2022-10-11 | 西安热工研究院有限公司 | Electric power intelligent video analysis monitoring structure, system, method and storage medium thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115174856A (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416294B (en) | Fan blade fault intelligent identification method based on deep learning | |
| WO2023246062A1 (en) | Intelligent video-based electric power analysis and monitoring structure, system and method, and storage medium thereof | |
| EP3741994B1 (en) | Tower clearance monitoring system and method therefor | |
| US11466666B2 (en) | Method and device for stitching wind turbine blade images, and storage medium | |
| US20240052805A1 (en) | Controlling wind turbine | |
| CN107764198B (en) | Engine stator blade axial gap light projection measuring device and method | |
| WO2024027009A1 (en) | Infrared thermal imaging defect inspection method and apparatus for substation insulator | |
| CN104730081A (en) | Failure detection system for wind power blade | |
| CN204536215U (en) | A kind of fault detection system for wind-power blade | |
| Guo et al. | Detecting and positioning of wind turbine blade tips for uav-based automatic inspection | |
| CN205135913U (en) | String of a musical instrument locating template and setting angle of blade measurement system of wind turbine generator system blade | |
| CN115218801B (en) | Wind driven generator clearance distance measuring method and device based on machine vision | |
| CN113176268A (en) | Wind power blade surface damage detection method based on cloud deck shooting image | |
| CN111237135A (en) | Health state monitoring device and method for blades of wind turbine | |
| US11421660B2 (en) | Video monitoring method and system for wind turbine blade | |
| CN102435394A (en) | Blade pneumatic imbalance detection method and device of wind generating set | |
| CN104865472A (en) | Aerogenerator slip ring detection system and detection method thereof | |
| CN111914743A (en) | Method and device for detecting safety helmet of transformer substation worker | |
| EP4180658A1 (en) | Optimal position for wind turbine blade sound signal collection and selection method therefor | |
| CN114442658A (en) | Automatic inspection system for unmanned aerial vehicle of power transmission and distribution line and operation method thereof | |
| CN113464379B (en) | Floating type offshore wind turbine running state monitoring method | |
| CN115726934A (en) | Method and device for measuring clearance value of wind driven generator | |
| CN211819806U (en) | Health state monitoring device for blades of wind turbine | |
| CN111028289B (en) | Method for positioning foreign matters in equipment in transformer substation based on template matching | |
| CN206972438U (en) | A kind of wind power generating set is classified yaw control device |
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: 22947797 Country of ref document: EP Kind code of ref document: A1 |