WO2023029445A1 - 一种风力发电机净空值的测量方法及装置 - Google Patents
一种风力发电机净空值的测量方法及装置 Download PDFInfo
- Publication number
- WO2023029445A1 WO2023029445A1 PCT/CN2022/082150 CN2022082150W WO2023029445A1 WO 2023029445 A1 WO2023029445 A1 WO 2023029445A1 CN 2022082150 W CN2022082150 W CN 2022082150W WO 2023029445 A1 WO2023029445 A1 WO 2023029445A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- edge
- tower
- blade
- distance
- pixel
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims description 46
- 238000004590 computer program Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 238000000691 measurement method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- the present application relates to the technical field of wind power generation, in particular to a method and device for measuring the clearance value of a wind power generator.
- the clearance value of the wind turbine refers to the straight-line distance from the blade tip to the tower wall when the blade of the wind turbine is vertical to the horizontal plane. If the headroom of the wind turbine is too small, the blades of the wind turbine may come into contact with the tower, causing an accident. However, due to the high installation position of the blades of the wind power generator, it is difficult to directly measure the clearance value of the wind power generator.
- the embodiments of the present application provide a method and device for measuring the clearance value of a wind turbine, aiming at providing a technical solution capable of accurately measuring the clearance value of a wind turbine.
- the embodiment of the present application provides a method for measuring the headroom value of a wind turbine, the method comprising:
- the target image is obtained by taking a picture of the wind generator by an image acquisition device, the target image includes blades and towers of the wind generator, and the image acquisition device is deployed on the side of the wind generator;
- edge of the tower includes a first edge and a second edge
- an actual clearance value of the wind power generator is determined, and the actual clearance value is an actual distance from the blade tip point to the edge of the target.
- the determining the tower pixel width from the first edge to the second edge on the plane where the tip point is located includes:
- the first pixel distance is the pixel distance from the midpoint of the first edge to the second edge
- the second pixel distance is the second edge The pixel distance from the midpoint of to the first edge
- the pixel width of the tower is determined according to the first pixel distance and the second pixel distance.
- the detecting the edge of the tower and the tip point of the blade in the target image includes:
- Image recognition is performed on the target image, and a plurality of tower edge points and blade borders are determined, the tower edge points are the boundary points between the tower and the external environment, and the blade borders include the tip of the blade image;
- the determining the blade tip point according to the blade frame includes:
- a point with the smallest distance from the ground is selected from the plurality of blade edge points as the blade tip point.
- said acquiring the target image includes:
- a video frame including the blade and the tower is determined as the target image.
- the determining the actual clearance value of the wind power generator according to the pixel width of the tower and the clearance pixel distance includes:
- the reference distance being the width of the tower
- the scaling ratio reflecting the ratio between the length of the reference distance on the target image and the actual length of the reference distance
- the actual clearance value of the wind power generator is determined according to the scaling ratio and the clearance pixel distance.
- the determining the actual clearance value of the wind power generator according to the pixel width of the tower and the clearance pixel distance includes:
- the first headroom value is determined as the actual headroom value in response to the first headroom value being less than the second headroom value.
- the embodiment of the present application provides a device for measuring the headroom value of a wind turbine, the device comprising:
- the image acquisition module is used to acquire a target image, the target image is captured by the image acquisition device on the wind power generator, the target image includes the blades and the tower of the wind power generator, and the image acquisition device is deployed on the the side of the wind turbine;
- An image recognition module configured to detect the edge of the tower and the tip point of the blade in the target image, wherein the edge of the tower includes a first edge and a second edge;
- a first determination module configured to determine the tower pixel width from the first edge to the second edge on the plane where the blade tip point is located;
- the second determination module is used to determine the clearance pixel distance from the blade tip point to the target edge on the plane where the blade tip point is located, and the target edge is the distance between the first edge and the second edge that is close to the edge of the blade;
- the third determining module is configured to determine the actual clearance value of the wind turbine according to the pixel width of the tower and the pixel distance of the clearance, and the actual clearance value is the actual distance from the blade tip point to the target edge distance.
- the first determining module is configured to calculate the first pixel distance and the second pixel distance, the first pixel distance being the pixel distance from the midpoint of the first edge to the second edge , the second pixel distance is the pixel distance from the midpoint of the second edge to the first edge; the tower pixel width is determined according to the first pixel distance and the second pixel distance.
- the image recognition module is configured to perform image recognition on the target image, and determine a plurality of tower edge points and blade borders, the tower edge points being the boundary points between the tower and the external environment,
- the blade frame includes an image of the tip portion of the blade; the blade tip point is determined according to the blade frame; straight line fitting is performed on the plurality of tower edge points, and the first edge and the second edge are determined. Two edges.
- the image recognition module is configured to perform edge point recognition on the blade border, determine a plurality of blade edge points; select a point with the smallest distance from the ground from the plurality of blade edge points as the blade tip point.
- the obtaining module is configured to obtain a target video; identify a video frame containing the blade and the tower from the target video; determine the video frame containing the blade and the tower as The target image.
- the third determining unit is configured to obtain a reference distance, the reference distance being the width of the tower; determining a scaling ratio according to the tower pixel width and the reference distance, and the scaling ratio reflects The ratio between the length of the reference distance on the target image and the actual length of the reference distance; determine the actual clearance value of the wind power generator according to the scaling ratio and the clearance pixel distance.
- the third determining unit is configured to calculate a first headroom value according to the tower tube pixel width and the headroom pixel distance; obtain a second headroom value, and the second headroom value is a headroom obtained in advance value; determining the first headroom value as the actual headroom value in response to the first headroom value being less than the second headroom value.
- the embodiment of the present application provides a measurement system for the clearance value of a wind turbine, and the system includes an image acquisition device and a data processing device;
- the image acquisition device is deployed on the side of the wind power generator, and is used for image acquisition of the wind power generator to obtain a target image, the target image including the blades and the tower of the wind power generator, and the image acquisition device ;
- the data processing device is configured to execute the method for measuring the clearance value of the wind power generator as described in the aforementioned first aspect.
- the embodiment of the present application provides a computer-readable storage medium, which stores a computer program.
- the processor executes the calculation of the clearance value of the wind turbine as described in the first aspect. Measurement methods.
- the embodiment of the present application provides a computer device, including a processor and a memory storing a computer program.
- the processor executes the wind turbine clearance as described in the first aspect. The method of measuring the value.
- This application provides a method and device for measuring the headroom value of a wind-driven generator.
- the target image captured by the image acquisition device for the wind-driven generator can be obtained first, and then the target image can be obtained from the target image.
- the blades and the tower of the wind power generator are detected, and the first edge and the second edge of the tower, as well as the tip point of the blade are obtained.
- the tower pixel width from the first edge to the second edge on the plane where the blade tip point is located may be determined, and the clearance pixel distance from the blade tip point to the target edge on the plane where the blade tip point is located may be determined.
- the target edge is the tower edge closer to the blade among the first edge and the second edge.
- the actual clearance value of the wind turbine can be determined according to the pixel width of the tower and the pixel distance of the clearance. In this way, by processing the image of the wind power generator through image processing, the edge of the tower tube of the wind power generator and the tip points of the blades can be accurately found from the image. Then, through the width of the tower on the target image and the actual width of the tower, the actual distance of the wind generator can be accurately calculated.
- FIG. 1 is a schematic diagram of an application scenario of a method for measuring the headroom value of a wind turbine provided by an embodiment of the present application;
- Fig. 2 is a schematic flow chart of the measurement method of the headroom value of the wind power generator provided by the embodiment of the present application;
- Fig. 3 is a schematic structural diagram of a measuring device for the clearance value of a wind power generator provided in an embodiment of the present application.
- Fan blades are important equipment for converting wind energy into electrical energy, but during operation, the blades will undergo certain deformation and displacement due to the wind force bearing different loads.
- the tower is the main load-bearing mechanism of the wind turbine. For large wind turbines, the height usually reaches more than 100 meters. At present, it is not uncommon for wind turbine blades to collide with the tower during rotation and cause damage to the wind turbine.
- the clearance distance refers to the minimum geometric distance between the blade tip and the tower when the blade tip sweeps the surface of the tower. In order to avoid blade tip sweeping Tower phenomenon, if the clearance distance is less than the safe value, an early warning can be generated and the power turned off, so as to avoid the contact between the blades of the fan and the tower, thereby ensuring the safe operation of the fan.
- the deformation of the blades of the wind power generator can be monitored by means of strain gauges and the like, so as to determine the headroom value of the wind power generator.
- the traditional method of monitoring blade deformation requires one or more strain gauges to be arranged on the blades of the wind turbine, and the deformation value of the blade at the position of the strain gauges can be determined through the strain gauges.
- the contact sensor will adversely affect the structure and strength of the blade.
- the contact sensor is expensive and difficult to repair once it fails.
- an embodiment of the present application provides a method and device for measuring the headroom value of a wind-driven generator.
- a detailed introduction will be made below in conjunction with the accompanying drawings of the description. Firstly, the application scenario of the method for measuring the headroom value of the wind turbine provided by the embodiment of the present application is introduced.
- this figure is a schematic diagram of an application scenario of a method for measuring the clearance value of a wind turbine provided by an embodiment of the present application, including a wind turbine 110 , an image acquisition device 120 and a data processing device 130 .
- the wind power generator 110 includes blades 111 and a tower 112 .
- the image acquisition device 120 is deployed at a position where the blade 111 and the tower 112 can be photographed, and the image acquisition device 120 is connected to the data processing device 130 .
- the image collection device 120 can be used to collect images and send them to the data processing device 130, and the data processing device 130 can execute the method for measuring the clearance value of the wind turbine provided by any embodiment of the present application.
- the image acquisition device 120 may be deployed on the side of the wind turbine 110 .
- the image acquisition device 120 may be deployed on a plane perpendicular to the central axis of the wind power generator 110 .
- the image acquisition device 120 is located 200 meters away from the wind turbine.
- the data processing device 130 may be a computer or a server, or may be a software platform running on a server cluster.
- the data processing device 130 may be a device running a wind power generator main control program. That is to say, the main control program of the wind turbine and the program for measuring the clearance value can run on the same computer device, or the method for measuring the clearance value of the wind turbine provided in the embodiment of the present application can be integrated in the main control program of the wind turbine. program.
- Fig. 2 is the method flow chart of the method for measuring the headroom value of the wind power generator provided by the embodiment of the present application, including:
- the data processing device may first acquire the target image.
- the target image is obtained by image acquisition of the wind turbine, including images of blades and towers of the wind turbine.
- the target image may include an image of a tip point of a blade of a wind generator.
- the target image may be an image frame extracted from a video.
- the image acquisition device can continuously acquire images of the wind turbine to obtain a target video composed of multiple frames of images.
- the data processing device may split the target video into multiple frames of images, and process each frame of images separately. That is to say, the target image can be a frame image in the target video.
- the target image may be an image acquired by the image acquisition device 120 on the wind power generator 130 .
- S202 Detect an edge of the tower and a tip point of the blade in the target image.
- the data processing device can perform image recognition on the target image, detect the tower and blade tip points of the wind generator from the target image, and obtain the first edge, the second edge and the tip point.
- the first edge and the second edge are the dividing line between the tower of the wind generator and the external environment
- the tip point is the position on the blade of the wind generator farthest from the rotation axis of the blade.
- the blade tip point of the blade may be identified first from the target image, and then the first edge and the second edge of the tower are determined according to the position of the blade tip point.
- the data processing device may first intercept the blade frame image from the target image, for example, through image segmentation or manual interception by a technician. Then, the leaf border image can be transformed into a grayscale image, and Gaussian filtering is performed on the grayscale image. After Gaussian filtering, at least one leaf edge point can be identified from the leaf frame image by Canny edge detection technology and Contours edge point recognition technology. Wherein, the leaf edge point is the boundary point between the region where the leaf is located and the non-leaf region on the target image.
- the data processing device can determine whether the number of leaf edge points is greater than a first threshold, if the number of leaf edge points is less than the first threshold, indicating that the number of leaf edge points in the leaf frame image is small, and As for not being able to filter out leaf tip points from leaf edge points. Then, the image processing device can determine that the target image cannot be used to identify the tip point, and can calculate the headroom value of the wind turbine through other images. If the number of leaf edge points is greater than or equal to the first threshold, the image processing device can perform a transverse gradient arrangement, and select from a plurality of leaf edge points in the leaf border image by means of image threshold calculation, image binarization, Contours edge point recognition, etc. Filter out leaf tip points. Specifically, in the process of determining the tip point, the edge point of the blade closest to the ground can be determined as the tip point of the blade,
- the image processing device can further identify the first edge and the second edge of the tower. Specifically, the image processing device can first intercept the frame image of the tower tube, then convert the image of the frame frame of the tower tube into a grayscale image, and obtain a lateral gradient image, and then perform image threshold calculation, image binarization, Canny edge detection and Contours edge Techniques such as point recognition determine multiple tower edge points of the tower. After the multiple tower edge points are obtained, straight line fitting can be performed on the multiple tower edge points, thereby determining the first edge and the second edge of the tower.
- S203 Determine a tower pixel width from the first edge to the second edge on the plane where the blade tip point is located.
- the data processing device may determine the tower pixel width.
- the pixel width of the tower is the width of the image corresponding to the tower on the target image, that is, the pixel width between the first edge and the second edge on the target image, for example, it may be the pixel between the first edge and the second edge number.
- the distance from the point on the first edge to the second edge and the distance from the point on the second edge to the first edge can be calculated separately, and then the average value The way to get the pixel width of the tower.
- the data processing device may first calculate the first pixel distance and the second pixel distance, the first pixel distance is the pixel distance from the midpoint of the first edge to the second edge, and the second pixel distance is the pixel distance from the midpoint of the second edge to The pixel distance of the first edge.
- the first pixel distance and the second pixel distance may be averaged, and the average value may be used as the tower tube pixel width.
- the data processing device may also determine the clearance pixel distance according to the blade tip point.
- the headroom pixel distance is the pixel distance from the tip point to the edge of the target on the plane where the tip point is located, for example, it may be the number of pixels from the tip point to the edge of the target.
- the target edge is an edge closer to the blade among the first edge and the second edge.
- the pixel distance from the first edge to the tip point and the pixel distance from the second edge to the tip point can be calculated respectively, and the pixel distance from the first edge to the tip point Distance and the pixel distance from the second edge to the tip point, the shorter distance is taken as the headroom pixel distance.
- S205 Determine the actual clearance value of the wind power generator according to the pixel width of the tower and the clearance pixel distance.
- the pixel width of the tower tube and the pixel distance of the headroom can be obtained through image processing.
- the distance obtained here is the distance between the tower and the tip point on the target image, not the actual width and clearance of the tower.
- the actual clearance value of the wind turbine can be determined according to the pixel width of the tower and the pixel distance of the clearance.
- the data processing device can obtain a reference distance, and the reference distance is the width of the tower of the wind power generator, that is, the actual width of the tower of the wind power generator. Then, the scaling can be determined based on the tower pixel width and the reference distance.
- the scaling ratio can reflect the pixel width corresponding to the unit length on the target image, that is, the pixel width corresponding to the line segment on the target image after the line segment with a fixed length on the plane where the tip point is located is captured by the image acquisition device as the target image. After the scaling ratio is determined, the actual clearance value of the wind turbine can be determined according to the scaling ratio and the clearance pixel distance.
- C real represents the actual clearance value of the wind turbine
- c represents the clearance pixel distance
- D real represents the reference distance
- d represents the pixel width of the tower.
- the towers of wind turbines may be tapered, and towers of different heights have different widths.
- the theoretical length of the blade and the height of the tower can be obtained first, and the theoretical height corresponding to the tip point can be calculated, and the tower can be determined according to the theoretical height corresponding to the tip point and the shape of the tower.
- the width of the theoretical height which is used as a reference distance to calculate the actual clearance value of the wind turbine.
- the blades of the wind-driven generator are in a rotating state, and correspondingly, the position of the lowest point of the blades of the wind-driven generator may also be in a state of changing at any time.
- the image acquisition device can continuously acquire images of the wind turbine to obtain multiple images.
- the data processing device may process each of the multiple images, determine multiple clearance values, and determine the smallest clearance value among the multiple clearance values as the actual clearance value.
- the data processing device may first process the first target image to obtain the first headroom value. Next, the data processing device may process the second target image to obtain a second headroom value. The data processing device can compare the size of the first headroom value and the second headroom value, and determine the smaller headroom value as the actual headroom value. Assuming that the first headroom value is smaller than the second headroom value, the data processing device may determine the first headroom value as the actual headroom value, and the data processing device may obtain a third headroom value according to the third target image, and compare the third headroom value with the actual headroom value The size of the value. If the third headroom value is greater than or equal to the actual headroom value, the data processing device may discard the third headroom value. If the third headroom value is smaller than the actual headroom value, the data processing device may determine the third headroom value as the actual headroom value.
- This application provides a method for measuring the clearance value of a wind turbine.
- the target image captured by the image acquisition device for the wind turbine can be obtained first, and then the target image can be detected from the target image.
- the blades and the tower of the wind power generator obtain the first edge and the second edge of the tower, and the tip points of the blades.
- the tower pixel width from the first edge to the second edge on the plane where the blade tip point is located may be determined, and the clearance pixel distance from the blade tip point to the target edge on the plane where the blade tip point is located may be determined.
- the target edge is the tower edge closer to the blade among the first edge and the second edge.
- the actual clearance value of the wind turbine can be determined according to the pixel width of the tower and the pixel distance of the clearance. In this way, by processing the image of the wind power generator through image processing, the edge of the tower tube of the wind power generator and the tip points of the blades can be accurately found from the image. Then, through the width of the tower on the target image and the actual width of the tower, the actual distance of the wind generator can be accurately calculated.
- the present application also provides a corresponding device.
- the following will introduce the device provided by the embodiment of the present application from the perspective of functional modularization.
- the device 300 can be applied to the data processing device 130 in the embodiment shown in FIG. 1, including:
- the image acquisition module 310 is used to acquire a target image, the target image is captured by the image acquisition device on the wind power generator, the target image includes the blades and the tower of the wind power generator, and the image acquisition device is deployed in the the side of the wind turbine;
- An image recognition module 320 configured to detect the edge of the tower and the tip point of the blade in the target image, wherein the edge of the tower includes a first edge and a second edge;
- the first determination module 330 is configured to determine the tower pixel width from the first edge to the second edge on the plane where the blade tip point is located;
- the second determination module 340 is configured to determine the clearance pixel distance from the blade tip point to the target edge on the plane where the blade tip point is located, and the target edge is the closest one of the first edge and the second edge the edge of the blade;
- the third determination module 350 is configured to determine the actual clearance value of the wind turbine according to the pixel width of the tower and the pixel distance of the clearance, and the actual clearance value is the distance from the blade tip point to the target edge actual distance.
- This application provides a measuring device for the headroom value of a wind turbine.
- the target image captured by the image acquisition device for the wind turbine can be obtained first, and then the target image can be detected from the target image.
- the blades and the tower of the wind power generator obtain the first edge and the second edge of the tower, and the tip points of the blades.
- the tower pixel width from the first edge to the second edge on the plane where the blade tip point is located may be determined, and the clearance pixel distance from the blade tip point to the target edge on the plane where the blade tip point is located may be determined.
- the target edge is the tower edge closer to the blade among the first edge and the second edge.
- the actual clearance value of the wind turbine can be determined according to the pixel width of the tower and the pixel distance of the clearance. In this way, by processing the image of the wind power generator through image processing, the edge of the tower tube of the wind power generator and the tip points of the blades can be accurately found from the image. Then, through the width of the tower on the target image and the actual width of the tower, the actual distance of the wind generator can be accurately calculated.
- the first determining module 330 is configured to calculate the first pixel distance and the second pixel distance, the first pixel distance being the midpoint of the first edge to The pixel distance of the second edge, the second pixel distance is the pixel distance from the midpoint of the second edge to the first edge; determine the pixel distance according to the first pixel distance and the second pixel distance The pixel width of the tower tube.
- the image recognition module 320 is configured to perform image recognition on the target image to determine a plurality of tower edge points and blade borders, the tower edge points being the The boundary point between the cylinder and the external environment, the blade frame includes the image of the tip part of the blade; the blade tip point is determined according to the blade frame; straight line fitting is performed on the plurality of tower edge points to determine the the first edge and the second edge.
- the image recognition module 320 is configured to perform edge point recognition on the blade border, determine a plurality of blade edge points; select a distance from the ground from the plurality of blade edge points The smallest point serves as the tip point.
- the acquiring module 310 is configured to acquire a target video; identify a video frame containing the blade and the tower from the target video; The video frame of the tower is determined as the target image.
- the third determining unit 350 is configured to acquire a reference distance, the reference distance being the width of the tower; determine according to the pixel width of the tower and the reference distance Scaling ratio, the scaling ratio embodies the ratio between the length of the reference distance on the target image and the actual length of the reference distance; determine the actual distance of the wind turbine according to the scaling ratio and the clear pixel distance Headroom.
- the third determining unit 350 is configured to calculate a first headroom value according to the tower tube pixel width and the headroom pixel distance; obtain a second headroom value, and the second The headroom value is a pre-calculated headroom value; in response to the first headroom value being smaller than the second headroom value, the first headroom value is determined as the actual headroom value.
- the embodiment of the present application also provides a measurement system for the clearance value of the wind power generator, and the system includes an image acquisition device and a data processing device.
- the image acquisition device may be the image acquisition device 120 in the embodiment shown in FIG. 1
- the data processing device may be the data processing device 130 in the embodiment shown in FIG. 1 .
- the data processing device can be used to execute the method for measuring the clearance value of the wind power generator described in any embodiment of the present application.
- An embodiment of the present application provides a computer-readable storage medium, which stores a computer program.
- the processor executes the method for measuring the headroom value of a wind turbine as described in any embodiment of the present application. .
- An embodiment of the present application provides a computer device, including a processor and a memory storing a computer program.
- the processor executes the calculation of the clearance value of the wind power generator as described in any embodiment of the present application. Measurement methods.
- each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the difference from other embodiments.
- the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiment. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without creative effort.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
一种风力发电机（110）净空值的测量方法及装置，可以先获取图像采集设备（120）对风力发电机（110）拍摄得到的目标图像，接着从目标图像中检测出风力发电机的叶片（111）和塔筒（112），得到塔筒（112）的第一边缘和第二边缘以及叶片（111）的叶尖点。接着，可以确定叶尖点所在的平面上第一边缘到第二边缘的塔筒像素宽度，并确定叶尖点所在的平面上从叶尖点到目标边缘的净空像素距离。目标边缘为第一边缘和第二边缘中距离叶片更近的塔筒边缘。在确定塔筒像素宽度和净空像素距离之后，可以根据塔筒像素宽度和净空像素距离，确定风力发电机的实际净空值。如此，可以准确地计算出风力发电机的实际距离。
Description
本申请要求于2021年08月31日提交中国专利局、申请号为202111015687.2、申请名称为“一种风力发电机净空值的测量方法及装置”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。
本申请涉及风力发电技术领域，尤其涉及一种风力发电机净空值的测量方法及装置。
随着环境污染的加重，清洁能源得到了越来越广泛的应用。其中，风能作为一种无污染、可再生的绿色能源，它对于解决全球性的能源危机和环境危机有着重要的意义。随着科学技术的发展，风电技术已经相当成熟，更大型、性能更好的风力发电机组已经开发并投入生产试运行。
但是，由于风力发电机大多都安装在环境较恶劣的地区，容易发生故障，若没有及时预警故障，不仅会影响设备的寿命和工作效率，甚至会导致风力发电机损毁等重大事故，带来无法挽回的损失。为了防止风力发电机出现故障，需要对风力发电机的工作条件进行监控。其中，对风力发电机净空值的测量是确保风力发电机的重要手段。
风力发电机的净空值是指风力发电机的叶片垂直水平面时叶尖到塔筒壁的直线距离。如果风力发电机的净空值过小，风力发电机的叶片可能与塔筒接触，发生事故。但是，由于风力发电机组的叶片的安装位置较高，难以直接对风力发电机的净空值进行测量。
发明内容
有鉴于此，本申请实施例提供了一种风力发电机净空值的测量方法及装置，旨在提供一种能够准确测量风力发电机净空值的技术方案。
第一方面，本申请实施例提供了一种风力发电机净空值的测量方法，所述方法包括：
获取目标图像，所述目标图像由图像采集设备对风力发电机拍摄得到，所述目标图像包括所述风力发电机的叶片和塔筒，所述图像采集设备部署于所述风力发电机的侧面；
在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点，其中，所述塔筒的边缘包括第一边缘和第二边缘；
确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度；
确定所述叶尖点所处的平面上所述叶尖点到目标边缘的净空像素距离，所述目标边缘为所述第一边缘和所述第二边缘中靠近所述叶片的边缘；
根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值，所述实际净空值为所述叶尖点到所述目标边缘的实际距离。
可选地，所述确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度包括：
计算所述第一像素距离和第二像素距离，所述第一像素距离为所述第一边缘的中点到所述第二边缘的像素距离，所述第二像素距离为所述第二边缘的中点到所述第一边缘的像素距离；
根据所述第一像素距离和所述第二像素距离确定所述塔筒像素宽度。
可选地，所述在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点包括：
对所述目标图像进行图像识别，确定多个塔筒边缘点和叶片边框，所述塔筒边缘点为所述塔筒与外界环境的分界点，所述叶片边框包括所述叶片的尖端部分的图像；
根据所述叶片边框确定所述叶尖点；
对所述多个塔筒边缘点进行直线拟合，确定所述第一边缘和所述第二边缘。
可选地，所述根据所述叶片边框确定所述叶尖点包括：
对所述叶片边框进行边缘点识别，确定多个叶片边缘点；
从所述多个叶片边缘点中选择与地面距离最小的点作为所述叶尖点。
可选地，所述获取目标图像包括：
获取目标视频；
从所述目标视频中识别包含所述叶片和所述塔筒的视频帧；
将包含所述叶片和所述塔筒的视频帧确定为所述目标图像。
可选地，所述根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值包括：
获取参考距离，所述参考距离为所述塔筒的宽度；
根据所述塔筒像素宽度和所述参考距离确定缩放比例，所述缩放比例体现所述参考距离在目标图像上的长度与所述参考距离的实际长度之间的比值；
根据所述缩放比例和所述净空像素距离确定所述风力发电机的实际净空值。
可选地，所述根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值包括：
根据所述塔筒像素宽度和所述净空像素距离计算第一净空值；
获取第二净空值，所述第二净空值是预先计算得到的净空值；
响应于所述第一净空值小于所述第二净空值，将所述第一净空值确定为所述实际净空值。
第二方面，本申请实施例提供了一种风力发电机净空值的测量装置，所述装置包括：
图像获取模块，用于获取目标图像，所述目标图像由图像采集设备对风力发电机拍摄得到，所述目标图像包括所述风力发电机的叶片和塔筒，所述图像采集设备部署于所述风力发电机的侧面；
图像识别模块，用于在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点，其中，所述塔筒的边缘包括第一边缘和第二边缘；
第一确定模块，用于确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度；
第二确定模块，用于确定所述叶尖点所处的平面上所述叶尖点到目标边缘的净空像素距离，所述目标边缘为所述第一边缘和所述第二边缘中靠近所述叶片的边缘；
第三确定模块，用于根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值，所述实际净空值为所述叶尖点到所述目标边缘的实际距离。
可选地，所述第一确定模块，用于计算所述第一像素距离和第二像素距离，所述第一像素距离为所述第一边缘的中点到所述第二边缘的像素距离，所述第二像素距离为所述第二边缘的中点到所述第一边缘的像素距离；根据所述第一像素距离和所述第二像素距离确定所述塔筒像素宽度。
可选地，所述图像识别模块，用于对所述目标图像进行图像识别，确定多个塔筒边缘点和叶片边框，所述塔筒边缘点为所述塔筒与外界环境的分界点，所述叶片边框包括所述叶片的尖端部分的图像；根据所述叶片边框确定所述叶尖点；对所述多个塔筒边缘点进行直线拟合，确定所述第一边缘和所述第二边缘。
可选地，所述图像识别模块，用于对所述叶片边框进行边缘点识别，确定多个叶片边缘点；从所述多个叶片边缘点中选择与地面距离最小的点作为所述叶尖点。
可选地，所述获取模块，用于获取目标视频；从所述目标视频中识别包含所述叶片和所述塔筒的视频帧；将包含所述叶片和所述塔筒的视频帧确定为所述目标图像。
可选地，所述第三确定单元，用于获取参考距离，所述参考距离为所述塔筒的宽度；根据所述塔筒像素宽度和所述参考距离确定缩放比例，所述缩放比例体现所述参考距离在目标图像上的长度与所述参考距离的实际长度之间的比值；根据所述缩放比例和所述净空像素距离确定所述风力发电机的实际净空值。
可选地，所述第三确定单元，用于根据所述塔筒像素宽度和所述净空像素距离计算第一净空值；获取第二净空值，所述第二净空值是预先计算得到的净 空值；响应于所述第一净空值小于所述第二净空值，将所述第一净空值确定为所述实际净空值。
第三方面，本申请实施例提供了一种风力发电机净空值的测量系统，所述系统包括图像采集设备和数据处理设备；
所述图像采集设备部署于风力发电机的侧面，用于对所述风力发电机进行图像采集，得到目标图像，所述目标图像包括所述风力发电机的叶片和塔筒，所述图像采集设备；
所述数据处理设备，用于执行如前述第一方面所述的风力发电机净空值的测量方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器运行时，处理器执行如前述第一方面所述的风力发电机净空值的测量方法。
第五方面，本申请实施例提供了一种计算机设备，包括处理器和存储计算机程序的存储器，所述计算机程序被处理器运行时，处理器执行如前述第一方面所述的风力发电机净空值的测量方法。
本申请提供了一种风力发电机净空值的测量方法及装置，在测量风力发电机的净空值的过程中，可以先获取图像采集设备对风力发电机拍摄得到的目标图像，接着从目标图像中检测出风力发电机的叶片和塔筒，得到塔筒的第一边缘和第二边缘，以及叶片的叶尖点。接着，可以确定叶尖点所在的平面上第一边缘到第二边缘的塔筒像素宽度，并确定叶尖点所在的平面上从叶尖点到目标边缘的净空像素距离。其中，目标边缘为第一边缘和第二边缘中距离叶片更近的塔筒边缘。在确定塔筒像素宽度和净空像素距离之后，可以根据塔筒像素宽度和净空像素距离，确定风力发电机的实际净空值。这样，通过图像处理对风力发电机的图像进行处理，可以准确地从图像中找到风力发电机的塔筒边缘以及叶片的叶尖点。接着，通过塔筒在目标图像上的宽度和塔筒的实际宽度，可以准确地计算出风力发电机的实际距离。
为更清楚地说明本实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的风力发电机净空值的测量方法的应用场景示意图；
图2为本申请实施例提供的风力发电机净空值的测量方法的流程示意图；
图3为本申请实施例提供的风力发电机净空值的测量装置的一种结构示意图。
风机叶片是将风能转化为电能的重要设备，但在运行过程中叶片会因承受不同载荷的风力而产生一定的形变和位移。塔架是风机的主要承重机构，对于大型风机而言，通常高度都会达到百米以上。目前，风机叶片在旋转过程中和塔架发生碰撞而导致风机损毁已是屡见不鲜，净空距离是指叶片尖端扫过塔架表面时叶尖部位距离塔架的最小几何距离，为了避免出现叶尖扫塔的现象，如果净空距离小于安全值，可以生成预警并关闭电源，从而避免风机的叶片与塔筒接触，从而保证风机的运行安全。
在传统技术中，可以通过应变片等方式对风力发电机的叶片的形变情况进行监控，从而确定风力发电机的净空值。但是，传统的监测叶片形变的方法，需要在风力发电机的叶片上布置一个或多个应变片，通过应变片即可确定叶片在应变片所在的位置的形变值。但是，一方面接触式传感器会对叶片结构和强度造成不利影响，另一方面接触式传感器价格昂贵，一旦发生故障难以维修。
为了给出能够快捷准确地确定风力发电机的净空值的技术方案，本申请实施例提供了一种风力发电机净空值的测量方法及装置。以下结合说明书附图进行详细介绍。首先对本申请实施例提供的风力发电机净空值的测量方法的应用场景进行介绍。
参见图1，该图为本申请实施例提供的风力发电机净空值的测量方法的一种应用场景示意图，包括风力发电机110、图像采集设备120和数据处理设备 130。其中，风力发电机110包括叶片111和塔筒112。图像采集设备120部署在能够拍摄到叶片111和塔筒112的位置，且图像采集设备120与数据处理设备130连接。图像采集设备120可以用于采集图像，并向数据处理设备130发送，数据处理设备130可以执行本申请任一实施例提供的风力发电机净空值的测量方法。
可选地，图像采集设备120可以部署于风力发电机110的侧面。例如，可以在垂直于风力发电机110的中心轴线的平面上部署图像采集设备120。在一些可能的实现方式中，图像采集设备120位于风机侧方200米的位置。
以下结合说明书附图，从图1中数据处理设备130的角度对本申请实施例提供的风力发电机净空值的测量方法进行说明。需要说明的是，所述数据处理设备130可以是计算机或服务器，也可以是运行于服务器集群的软件平台。在一些可能的实现方式中，所述数据处理设备130可以是运行风力发电机主控程序的设备。也就是说，风力发电机的主控程序和测量净空值的程序可以运行于同一台计算机设备，或者，本申请实施例提供的风力发电机净空值的测量方法可以集成在风力发电机的主控程序中。
显然，所描述的实施例仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
参见图2，图2为本申请实施例提供的风力发电机净空值的测量方法的方法流程图，包括：
S201：获取目标图像。
为了确定风力发电机的实际净空值，数据处理设备可以先获取目标图像。目标图像为对风力发电机进行图像采集得到的，其中包括风力发电机的叶片和塔筒的图像。可选地，目标图像中可以包括风力发电机的叶片的叶尖点的图像。
在本申请实施例中，目标图像可以是从视频中提取出的图像帧。具体地，图像采集设备可以持续对风力发电机进行图像采集，得到由多帧图像组成的目标视频。在接收到目标视频之后，数据处理设备可以将目标视频拆分为多帧图像，并分别对每一帧图像进行处理。也就是说，目标图像可以是目标视频中的 一帧图像。
当数据处理设备为图1所示实施例中数据处理设备130时，目标图像可以是图像采集设备120对风力发电机130进行图像采集得到的图像。
S202：在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点。
在获取到目标图像之后，数据处理设备可以对目标图像进行图像识别，从目标图像中检测风力发电机的塔筒和叶片的叶尖点，得到第一边缘、第二边缘和叶尖点。其中，第一边缘和第二边缘为风力发电机的塔筒与外界环境之间的分界线，叶尖点为风力发电机的叶片上距离叶片转动轴最远的位置。
在本申请实施例中，可以先从目标图像中识别出叶片的叶尖点，再根据叶尖点的位置确定塔筒的第一边缘和第二边缘。
具体地，数据处理设备可以先从目标图像中截取出叶片边框图像，例如通过图像分割或由技术人员手动截取。接着，可以将叶片边框图像装换为灰度图，并对灰度图进行高斯滤波。在进行高斯滤波之后，可以通过Canny边缘检测技术和Contours边缘点识别技术，从叶片边框图像中识别出至少一个叶片边缘点。其中，叶片边缘点为目标图像上叶片所在区域与非叶片区域的分界点。
在得到至少一个叶片边缘点之后，数据处理设备可以判断叶片边缘点的数量是否大于第一阈值，如果叶片边缘点的数量小于第一阈值，说明叶片边框图像中叶片边缘点的数量较少，以至于无法从叶片边缘点中筛选出叶尖点。那么，图像处理设备可以确定目标图像无法用于叶尖点的识别，可以通过其他图像计算风力发电机的净空值。如果叶片边缘点的数量大于或等于第一阈值，图像处理设备可以进行横向梯度排列，并通过图像阈值计算、图像二值化、Contours边缘点识别等方式从叶片边框图像的多个叶片边缘点中筛选出叶尖点。具体地，在确定叶尖点的过程中，可以将距离地面最近的叶片边缘点确定为叶片的叶尖点，
在得到叶尖点之后，图像处理设备可以进一步识别塔筒的第一边缘和第二边缘。具体地，图像处理设备可以先截取塔筒边框图像，再将塔筒边框图像转换为灰度图，并得到横向梯度图，接着再通过图像阈值计算、图像二值化、Canny边缘检测和Contours边缘点识别等技术确定塔筒的多个塔筒边缘点。在得到多个塔筒边缘点之后，可以对多个塔筒边缘点进行直线拟合，从而确定塔 筒的第一边缘和所述第二边缘。
S203：确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度。
在确定叶尖点、第一边缘和第二边缘之后，数据处理设备可以确定塔筒像素宽度。其中，塔筒像素宽度为目标图像上塔筒对应的图像的宽度，即目标图像上第一边缘到第二边缘之间的像素宽度，例如可以是从第一边缘到第二边缘之间的像素个数。
可选地，为了提高塔筒像素宽度的准确性，可以分别计算第一边缘上的点到第二边缘的距离，和第二边缘上的点到第一边缘的距离，再通过取平均值的方式得到塔筒像素宽度。具体地，数据处理设备可以先计算第一像素距离和第二像素距离，第一像素距离为第一边缘的中点到第二边缘的像素距离，第二像素距离为第二边缘的中点到第一边缘的像素距离。接着，可以将第一像素距离和第二像素距离取平均值，并将平均值作为塔筒像素宽度。
S204：确定所述叶尖点所处的平面上所述叶尖点到目标边缘的净空像素距离。
在本申请实施例中，数据处理设备还可以根据叶尖点确定净空像素距离。净空像素距离为叶尖点所在的平面上叶尖点到目标边缘的像素距离，例如可以是从叶尖点到目标边缘的像素个数。其中，目标边缘为第一边缘和第二边缘中距离叶片较近的边缘。
可选地，在计算净空像素距离的过程中，可以分别计算第一边缘到叶尖点的像素距离，和第二边缘到叶尖点的像素距离，并将第一边缘到叶尖点的像素距离和第二边缘到叶尖点的像素距离中较短的距离作为净空像素距离。
S205：根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值。
在上述步骤中，通过图像处理可以得到塔筒像素宽度和净空像素距离。但是，这里得到的距离是塔筒和叶尖点在目标图像上的距离，并不是塔筒的实际宽度和实际净空值。那么，为了得到风力发电机的实际净空值，可以根据塔筒像素宽度和净空像素距离，确定风力发电机的实际净空值。
具体地，数据处理设备可以获取参考距离，参考距离为风力发电机的塔筒 宽度，即风力发电机的塔筒的实际宽度。接着，可以根据塔筒像素宽度和参考距离确定缩放比例。缩放比例能够体现单位长度在目标图像上对应的像素宽度，即，叶尖点所在的平面上具有固定长度的线段被图像采集设备采集为目标图像之后，该线段在目标图像上对应的像素宽度。在确定缩放比例之后，可以根据缩放比例和净空像素距离确定风力发电机的实际净空值。
可选地，上述计算过程可以通过如下公式表示：
其中，C
real表示风力发电机的实际净空值，c表示净空像素距离，D
real表示参考距离，d表示塔筒像素宽度。
在实际的应用场景中，风力发电机的塔筒可能成锥形，不同高度的塔筒宽度不同。为了准确地确定风力发电机的净空值，可以先获取叶片理论长度和塔筒高度，计算出叶尖点对应的理论高度，并根据叶尖点对应的理论高度和塔筒的形状确定塔筒在理论高度的宽度，将该宽度作为参考距离计算风力发电机的实际净空值。
在风力发电机工作的过程中，风力发电机的叶片处于转动的状态，相应地，风力发电机的叶片的最低点的位置也可能随时处于改变的状态。那么，为了提高风力发电机的实际净空值的准确性，图像采集设备可以持续对风力发电机进行图像采集，得到多张图像。数据处理设备可以对多张图像中每张图像进行处理，确定多个净空值，并将多个净空值中最小的净空值确定为实际净空值。
举例说明。假设图像采集设备采集到了第一目标图像、第二目标图像和第三目标图像共三张目标图像，那么数据处理设备可以先对第一目标图像进行处理，得到第一净空值。接着，数据处理设备可以对第二目标图像进行处理，得到第二净空值。数据处理设备可以比较第一净空值和第二净空值的大小，并将其中较小的净空值确定为实际净空值。假设第一净空值小于第二净空值，数据处理设备可以将第一净空值确定为实际净空值，数据处理设备可以根据第三目标图像得到第三净空值，并比较第三净空值和实际净空值的大小。如果第三净空值大于或等于实际净空值，数据处理设备可以丢弃第三净空值。如果第三净空值小于实际净空值，数据处理设备可以将第三净空值确定为实际净空值。
本申请提供了一种风力发电机净空值的测量方法，在测量风力发电机的净空值的过程中，可以先获取图像采集设备对风力发电机拍摄得到的目标图像，接着从目标图像中检测出风力发电机的叶片和塔筒，得到塔筒的第一边缘和第二边缘，以及叶片的叶尖点。接着，可以确定叶尖点所在的平面上第一边缘到第二边缘的塔筒像素宽度，并确定叶尖点所在的平面上从叶尖点到目标边缘的净空像素距离。其中，目标边缘为第一边缘和第二边缘中距离叶片更近的塔筒边缘。在确定塔筒像素宽度和净空像素距离之后，可以根据塔筒像素宽度和净空像素距离，确定风力发电机的实际净空值。这样，通过图像处理对风力发电机的图像进行处理，可以准确地从图像中找到风力发电机的塔筒边缘以及叶片的叶尖点。接着，通过塔筒在目标图像上的宽度和塔筒的实际宽度，可以准确地计算出风力发电机的实际距离。
以上为本申请实施例提供风力发电机净空值的方法的一些具体实现方式，基于此，本申请还提供了对应的装置。下面将从功能模块化的角度对本申请实施例提供的装置进行介绍。
参见图3所示的风力发电机净空值装置的结构示意图，所述装置300可以应用于图1所示实施例中的数据处理设备130，包括：
图像获取模块310，用于获取目标图像，所述目标图像由图像采集设备对风力发电机拍摄得到，所述目标图像包括所述风力发电机的叶片和塔筒，所述图像采集设备部署于所述风力发电机的侧面；
图像识别模块320，用于在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点，其中，所述塔筒的边缘包括第一边缘和第二边缘；
第一确定模块330，用于确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度；
第二确定模块340，用于确定所述叶尖点所处的平面上所述叶尖点到目标边缘的净空像素距离，所述目标边缘为所述第一边缘和所述第二边缘中靠近所述叶片的边缘；
第三确定模块350，用于根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值，所述实际净空值为所述叶尖点到所述目标边 缘的实际距离。
本申请提供了一种风力发电机净空值的测量装置，在测量风力发电机的净空值的过程中，可以先获取图像采集设备对风力发电机拍摄得到的目标图像，接着从目标图像中检测出风力发电机的叶片和塔筒，得到塔筒的第一边缘和第二边缘，以及叶片的叶尖点。接着，可以确定叶尖点所在的平面上第一边缘到第二边缘的塔筒像素宽度，并确定叶尖点所在的平面上从叶尖点到目标边缘的净空像素距离。其中，目标边缘为第一边缘和第二边缘中距离叶片更近的塔筒边缘。在确定塔筒像素宽度和净空像素距离之后，可以根据塔筒像素宽度和净空像素距离，确定风力发电机的实际净空值。这样，通过图像处理对风力发电机的图像进行处理，可以准确地从图像中找到风力发电机的塔筒边缘以及叶片的叶尖点。接着，通过塔筒在目标图像上的宽度和塔筒的实际宽度，可以准确地计算出风力发电机的实际距离。
可选地，在一些可能的实现中，所述第一确定模块330，用于计算所述第一像素距离和第二像素距离，所述第一像素距离为所述第一边缘的中点到所述第二边缘的像素距离，所述第二像素距离为所述第二边缘的中点到所述第一边缘的像素距离；根据所述第一像素距离和所述第二像素距离确定所述塔筒像素宽度。
可选地，在一些可能的实现中，所述图像识别模块320，用于对所述目标图像进行图像识别，确定多个塔筒边缘点和叶片边框，所述塔筒边缘点为所述塔筒与外界环境的分界点，所述叶片边框包括所述叶片的尖端部分的图像；根据所述叶片边框确定所述叶尖点；对所述多个塔筒边缘点进行直线拟合，确定所述第一边缘和所述第二边缘。
可选地，在一些可能的实现中，所述图像识别模块320，用于对所述叶片边框进行边缘点识别，确定多个叶片边缘点；从所述多个叶片边缘点中选择与地面距离最小的点作为所述叶尖点。
可选地，在一些可能的实现中，所述获取模块310，用于获取目标视频；从所述目标视频中识别包含所述叶片和所述塔筒的视频帧；将包含所述叶片和所述塔筒的视频帧确定为所述目标图像。
可选地，在一些可能的实现中，所述第三确定单元350，用于获取参考距 离，所述参考距离为所述塔筒的宽度；根据所述塔筒像素宽度和所述参考距离确定缩放比例，所述缩放比例体现所述参考距离在目标图像上的长度与所述参考距离的实际长度之间的比值；根据所述缩放比例和所述净空像素距离确定所述风力发电机的实际净空值。
可选地，在一些可能的实现中，所述第三确定单元350，用于根据所述塔筒像素宽度和所述净空像素距离计算第一净空值；获取第二净空值，所述第二净空值是预先计算得到的净空值；响应于所述第一净空值小于所述第二净空值，将所述第一净空值确定为所述实际净空值。
此外，本申请实施例还提供了一种风力发电机净空值的测量系统，所述系统包括图像采集设备和数据处理设备。可选地，所述图像采集设备可以是图1所示实施例中图像采集设备120，所述数据处理设备可以是图1所示实施例中数据处理设备130。所述数据处理设备，可以用于执行本申请任一实施例所述的风力发电机净空值的测量方法。
本申请实施例提供了一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器运行时，处理器执行如本申请任一实施例所述的风力发电机净空值的测量方法。
本申请实施例提供了一种计算机设备，包括处理器和存储计算机程序的存储器，所述计算机程序被处理器运行时，处理器执行如本申请任一实施例所述的风力发电机净空值的测量方法。
本申请实施例中提到的“第一”、“第二”(若存在)等名称中的“第一”、“第二”只是用来做名字标识，并不代表顺序上的第一、第二。
通过以上的实施方式的描述可知，本领域的技术人员可以清楚地了解到上述实施例方法中的全部或部分步骤可借助软件加通用硬件平台的方式来实现。基于这样的理解，本申请的技术方案可以以软件产品的形式体现出来，该计算机软件产品可以存储在存储介质中，如只读存储器(英文：read-only memory，ROM)/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者诸如路由器等网络通信设备)执行本申请各个实施例或者实施例的某些部分所述的方法。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相 似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于装置实施例而言，由于其基本相似于方法实施例，所以描述得比较简单，相关之处参见方法实施例的部分说明即可。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
以上所述仅是本申请示例性的实施方式，并非用于限定本申请的保护范围。
Claims (17)
- 一种风力发电机净空值的测量方法，其特征在于，所述方法包括：获取目标图像，所述目标图像由图像采集设备对风力发电机拍摄得到，所述目标图像包括所述风力发电机的叶片和塔筒，所述图像采集设备部署于所述风力发电机的侧面；在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点，其中，所述塔筒的边缘包括第一边缘和第二边缘；确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度；确定所述叶尖点所处的平面上所述叶尖点到目标边缘的净空像素距离，所述目标边缘为所述第一边缘和所述第二边缘中靠近所述叶片的边缘；根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值，所述实际净空值为所述叶尖点到所述目标边缘的实际距离。
- 根据权利要求1所述的方法，其特征在于，所述确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度包括：计算所述第一像素距离和第二像素距离，所述第一像素距离为所述第一边缘的中点到所述第二边缘的像素距离，所述第二像素距离为所述第二边缘的中点到所述第一边缘的像素距离；根据所述第一像素距离和所述第二像素距离确定所述塔筒像素宽度。
- 根据权利要求1所述的方法，其特征在于，所述在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点包括：对所述目标图像进行图像识别，确定多个塔筒边缘点和叶片边框，所述塔筒边缘点为所述塔筒与外界环境的分界点，所述叶片边框包括所述叶片的尖端部分的图像；根据所述叶片边框确定所述叶尖点；对所述多个塔筒边缘点进行直线拟合，确定所述第一边缘和所述第二边缘。
- 根据权利要求3所述的方法，其特征在于，所述根据所述叶片边框确定所述叶尖点包括：对所述叶片边框进行边缘点识别，确定多个叶片边缘点；从所述多个叶片边缘点中选择与地面距离最小的点作为所述叶尖点。
- 根据权利要求1至4任一项所述的方法，其特征在于，所述获取目标图像包括：获取目标视频；从所述目标视频中识别包含所述叶片和所述塔筒的视频帧；将包含所述叶片和所述塔筒的视频帧确定为所述目标图像。
- 根据权利要求1至4任一项所述的方法，其特征在于，所述根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值包括：获取参考距离，所述参考距离为所述塔筒的宽度；根据所述塔筒像素宽度和所述参考距离确定缩放比例，所述缩放比例体现所述参考距离在目标图像上的长度与所述参考距离的实际长度之间的比值；根据所述缩放比例和所述净空像素距离确定所述风力发电机的实际净空值。
- 根据权利要求1所述的方法，其特征在于，所述根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值包括：根据所述塔筒像素宽度和所述净空像素距离计算第一净空值；获取第二净空值，所述第二净空值是预先计算得到的净空值；响应于所述第一净空值小于所述第二净空值，将所述第一净空值确定为所述实际净空值。
- 一种风力发电机净空值的测量装置，其特征在于，所述装置包括：图像获取模块，用于获取目标图像，所述目标图像由图像采集设备对风力发电机拍摄得到，所述目标图像包括所述风力发电机的叶片和塔筒，所述图像采集设备部署于所述风力发电机的侧面；图像识别模块，用于在所述目标图像中检测所述塔筒的边缘，以及所述叶片的叶尖点，其中，所述塔筒的边缘包括第一边缘和第二边缘；第一确定模块，用于确定所述叶尖点所处的平面上所述第一边缘到所述第二边缘的塔筒像素宽度；第二确定模块，用于确定所述叶尖点所处的平面上所述叶尖点到目标边缘 的净空像素距离，所述目标边缘为所述第一边缘和所述第二边缘中靠近所述叶片的边缘；第三确定模块，用于根据所述塔筒像素宽度和所述净空像素距离，确定所述风力发电机的实际净空值，所述实际净空值为所述叶尖点到所述目标边缘的实际距离。
- 根据权利要求8所述的装置，其特征在于，所述第一确定模块，用于计算所述第一像素距离和第二像素距离，所述第一像素距离为所述第一边缘的中点到所述第二边缘的像素距离，所述第二像素距离为所述第二边缘的中点到所述第一边缘的像素距离；根据所述第一像素距离和所述第二像素距离确定所述塔筒像素宽度。
- 根据权利要求9所述的装置，其特征在于，所述图像识别模块，用于对所述目标图像进行图像识别，确定多个塔筒边缘点和叶片边框，所述塔筒边缘点为所述塔筒与外界环境的分界点，所述叶片边框包括所述叶片的尖端部分的图像；根据所述叶片边框确定所述叶尖点；对所述多个塔筒边缘点进行直线拟合，确定所述第一边缘和所述第二边缘。
- 根据权利要求10所述的装置，其特征在于，所述图像识别模块，用于对所述叶片边框进行边缘点识别，确定多个叶片边缘点；从所述多个叶片边缘点中选择与地面距离最小的点作为所述叶尖点。
- 根据权利要求8至11任一项所述的装置，其特征在于，所述获取模块，用于获取目标视频；从所述目标视频中识别包含所述叶片和所述塔筒的视频帧；将包含所述叶片和所述塔筒的视频帧确定为所述目标图像。
- 根据权利要求8至11任一项所述的装置，其特征在于，所述第三确定单元，用于获取参考距离，所述参考距离为所述塔筒的宽度；根据所述塔筒像素宽度和所述参考距离确定缩放比例，所述缩放比例体现所述参考距离在目标图像上的长度与所述参考距离的实际长度之间的比值；根据所述缩放比例和所述净空像素距离确定所述风力发电机的实际净空值。
- 根据权利要求8所述的装置，其特征在于，所述第三确定单元，用于根据所述塔筒像素宽度和所述净空像素距离计算 第一净空值；获取第二净空值，所述第二净空值是预先计算得到的净空值；响应于所述第一净空值小于所述第二净空值，将所述第一净空值确定为所述实际净空值。
- 一种风力发电机净空值的测量系统，其特征在于，所述系统包括图像采集设备和数据处理设备；所述图像采集设备部署于风力发电机的侧面，用于对所述风力发电机进行图像采集，得到目标图像，所述目标图像包括所述风力发电机的叶片和塔筒，所述图像采集设备；所述数据处理设备，用于执行如权利要求1-7任一项所述的风力发电机净空值的测量方法。
- 一种计算机可读存储介质，存储有计算机程序，其特征在于，所述计算机程序被处理器运行时，处理器执行权利要求1-7中任一项所述的风力发电机净空值的测量方法。
- 一种计算机设备，包括处理器和存储计算机程序的存储器，其特征在于，所述计算机程序被处理器运行时，处理器执行如权利要求1-7中任一项所述的风力发电机净空值的测量方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015687.2A CN115726934A (zh) | 2021-08-31 | 2021-08-31 | 一种风力发电机净空值的测量方法及装置 |
| CN202111015687.2 | 2021-08-31 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023029445A1 true WO2023029445A1 (zh) | 2023-03-09 |
Family
ID=85291620
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/082150 WO2023029445A1 (zh) | 2021-08-31 | 2022-03-22 | 一种风力发电机净空值的测量方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115726934A (zh) |
| WO (1) | WO2023029445A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118224050A (zh) * | 2024-03-29 | 2024-06-21 | 武汉市迪特影像科技有限公司 | 一种新型无人值守式风电机组外部监测机器人系统 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2511523A1 (de) * | 2011-04-11 | 2012-10-17 | Baumer Innotec AG | Windkraftanlage mit Einrichtung zur Messung des Abstands zwischen Rotorblatt und Turm sowie Verfahren zur Abstandsmessung |
| CA2883772A1 (en) * | 2014-03-04 | 2015-09-04 | Steffen Bunge | Method for replacing the blades of a wind turbine to maintain safe operation |
| CN106091941A (zh) * | 2016-06-21 | 2016-11-09 | 远景能源（江苏）有限公司 | 风力发电机叶尖塔筒净空的测量方法 |
| CN109559354A (zh) * | 2018-11-30 | 2019-04-02 | 北京金风科创风电设备有限公司 | 测量塔架净空的方法、双目系统的标定方法以及装置 |
| WO2020108016A1 (zh) * | 2018-11-30 | 2020-06-04 | 北京金风科创风电设备有限公司 | 塔架净空监测系统及其方法 |
| CN111255636A (zh) * | 2018-11-30 | 2020-06-09 | 北京金风科创风电设备有限公司 | 确定风力发电机组的塔架净空的方法和装置 |
| CN112539143A (zh) * | 2020-11-30 | 2021-03-23 | 明阳智慧能源集团股份公司 | 一种通过叶尖发射信号的风力发电机组净空监测方法 |
| CN112761897A (zh) * | 2021-01-13 | 2021-05-07 | 国电联合动力技术有限公司 | 风电机组叶片监控方法、装置及风力发电机 |
| CN113309674A (zh) * | 2021-03-31 | 2021-08-27 | 新疆金风科技股份有限公司 | 风力发电机组的净空距离确定方法及装置 |
-
2021
- 2021-08-31 CN CN202111015687.2A patent/CN115726934A/zh active Pending
-
2022
- 2022-03-22 WO PCT/CN2022/082150 patent/WO2023029445A1/zh active Application Filing
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2511523A1 (de) * | 2011-04-11 | 2012-10-17 | Baumer Innotec AG | Windkraftanlage mit Einrichtung zur Messung des Abstands zwischen Rotorblatt und Turm sowie Verfahren zur Abstandsmessung |
| CA2883772A1 (en) * | 2014-03-04 | 2015-09-04 | Steffen Bunge | Method for replacing the blades of a wind turbine to maintain safe operation |
| CN106091941A (zh) * | 2016-06-21 | 2016-11-09 | 远景能源（江苏）有限公司 | 风力发电机叶尖塔筒净空的测量方法 |
| CN109559354A (zh) * | 2018-11-30 | 2019-04-02 | 北京金风科创风电设备有限公司 | 测量塔架净空的方法、双目系统的标定方法以及装置 |
| WO2020108016A1 (zh) * | 2018-11-30 | 2020-06-04 | 北京金风科创风电设备有限公司 | 塔架净空监测系统及其方法 |
| CN111255636A (zh) * | 2018-11-30 | 2020-06-09 | 北京金风科创风电设备有限公司 | 确定风力发电机组的塔架净空的方法和装置 |
| US20210088030A1 (en) * | 2018-11-30 | 2021-03-25 | Beijing Goldwind Science & Creation Windpower Equipment Co,, Ltd. | Tower clearance monitoring system and method therefor |
| CN112539143A (zh) * | 2020-11-30 | 2021-03-23 | 明阳智慧能源集团股份公司 | 一种通过叶尖发射信号的风力发电机组净空监测方法 |
| CN112761897A (zh) * | 2021-01-13 | 2021-05-07 | 国电联合动力技术有限公司 | 风电机组叶片监控方法、装置及风力发电机 |
| CN113309674A (zh) * | 2021-03-31 | 2021-08-27 | 新疆金风科技股份有限公司 | 风力发电机组的净空距离确定方法及装置 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118224050A (zh) * | 2024-03-29 | 2024-06-21 | 武汉市迪特影像科技有限公司 | 一种新型无人值守式风电机组外部监测机器人系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115726934A (zh) | 2023-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037133B (zh) | 一种基于无人机巡检图像的电力设备缺陷智能识别方法及其系统 | |
| US11421659B2 (en) | Method and device for determining tower clearance for wind turbine | |
| CN108416294B (zh) | 一种基于深度学习的风机叶片故障智能识别方法 | |
| EP2369176A1 (en) | Wind turbine and method for measuring the pitch angle of a wind turbine rotor blade | |
| CN102508110A (zh) | 基于纹理的绝缘子缺陷诊断方法 | |
| CN104865269A (zh) | 风力机叶片故障诊断方法 | |
| WO2023029445A1 (zh) | 一种风力发电机净空值的测量方法及装置 | |
| CN115830024B (zh) | 基于图像分割的桥梁拉索微小运动振动检测方法 | |
| CN205135913U (zh) | 一种风电机组叶片的弦线定位模板及叶片安装角测量系统 | |
| CN115993096A (zh) | 一种高层建筑变形测量方法 | |
| CN114581446B (zh) | 一种叠片电池的电芯异常检测方法及系统 | |
| WO2024109027A1 (zh) | 风电机组、风电叶片及风电叶片截面翼型的失速监测方法 | |
| CN116939532B (zh) | 一种基于5g的通信塔远程监测系统 | |
| CN115078382A (zh) | 基于视频图像的桥梁裂缝监测系统 | |
| CN110136059A (zh) | 直线特征的风电叶片图像拼接方法 | |
| CN115218801A (zh) | 基于机器视觉的风力发电机净空距离测量方法及装置 | |
| CN115239646A (zh) | 输电线路的缺陷检测方法、装置、电子设备及存储介质 | |
| CN110782411A (zh) | 一种基于图像处理的防震锤滑移识别方法 | |
| CN114639025A (zh) | 一种无人机辅助下风力机叶片检修方法及装置 | |
| CN116958841B (zh) | 基于图像识别的配电线路无人机巡检系统 | |
| CN115342033A (zh) | 基于叶片净空和风轮转速的尾流检测方法及系统 | |
| KR20190062834A (ko) | 풍력 발전기의 블레이드 검사장치 및 그 방법 | |
| Di et al. | Research on Real-Time Power Line Damage Detection Method Based on YOLO Algorithm | |
| CN113250914A (zh) | 一种机舱塔顶2d位移测量方法、系统、设备及存储介质 | |
| CN114299403A (zh) | 一种电塔插销检测方法 |
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: 22862592 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: 22862592 Country of ref document: EP Kind code of ref document: A1 |