WO2021218137A1 - 基于红外图像的弓网检测方法、装置、系统、介质及设备 - Google Patents

基于红外图像的弓网检测方法、装置、系统、介质及设备 Download PDF

Info

Publication number
WO2021218137A1
WO2021218137A1 PCT/CN2020/131615 CN2020131615W WO2021218137A1 WO 2021218137 A1 WO2021218137 A1 WO 2021218137A1 CN 2020131615 W CN2020131615 W CN 2020131615W WO 2021218137 A1 WO2021218137 A1 WO 2021218137A1
Authority
WO
WIPO (PCT)
Prior art keywords
pantograph
infrared image
infrared
image
bow
Prior art date
Application number
PCT/CN2020/131615
Other languages
English (en)
French (fr)
Inventor
黄鹏辉
刘智聪
王俊平
陈胜蓝
毛慧华
沈云波
旷世
Original Assignee
株洲中车时代电气股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株洲中车时代电气股份有限公司 filed Critical 株洲中车时代电气股份有限公司
Publication of WO2021218137A1 publication Critical patent/WO2021218137A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J2005/0077—Imaging

Definitions

  • the present invention mainly relates to the technical field of rail transit, and specifically refers to an infrared image-based method, device, system, medium and equipment for the detection of a pantograph and net.
  • the catenary conduction high value and the pull-out value are not only the core parameters of the catenary suspension, but also the contact parameters of the pantograph working surface. Once the value exceeds the standard, it may cause the pantograph of the electric locomotive to disconnect and cause the bow scraping and drilling failure. In severe cases, the pantograph and catenary suspension will be directly damaged, causing the power supply circuit to fail to work normally.
  • Manual inspection is mainly based on manual operations, requiring inspectors to climb on the roof of the vehicle to detect the pantograph and the pole to detect the catenary.
  • the advantage of manual detection is that it is more flexible and can identify different faults manually.
  • the disadvantages are low efficiency, poor safety, interfere with driving during operation, and cannot realize real-time detection, and cannot give early warning of large-scale arcing during operation. .
  • the contact detection method effectively improves the detection accuracy.
  • the disadvantage is that the use of the contact line detection vehicle for detection needs to occupy the train running line, which will interfere with the normal driving, and some detection devices and solutions need to modify the pantograph structure, which will affect the power receiving The various properties of the bow may eventually lead to inaccurate detection results.
  • the non-contact ranging detection method is mainly manifested in two aspects of research. On the one hand, it is the application of laser ranging, on the other hand, it is the application of ultrasonic ranging.
  • the non-contact ranging pantograph detection has the characteristics of high detection efficiency and low traffic interference. However, the two also have certain shortcomings.
  • the laser detection function is relatively single, while the ultrasonic detection accuracy is poor, and more applications are temporarily in the theoretical stage.
  • the technical problem to be solved by the present invention is that: in view of the technical problems existing in the prior art, the present invention provides an infrared image-based bow-net detection method, device, system, Medium and equipment.
  • a method for detecting bow and net based on infrared images including the steps:
  • step 2) when any one or more of the detected temperature, conduction height, and pull-out value of the pantograph and catenary exceeds the corresponding preset threshold value, a fault alarm is issued.
  • step 1) the full-field infrared image of the pantograph and the catenary is obtained in real time through an infrared camera.
  • the temperature data stream is read in the infrared camera, and every time a frame of temperature data is read, the grayscale image is converted into an RGB image to form an infrared image.
  • the invention also discloses a bow net detection device based on infrared images, which includes
  • Infrared detection unit for real-time acquisition of infrared images of the pantograph and catenary in the full field of view
  • the analysis module is used to analyze the infrared image of the full field of view, match the pantograph, and detect the current state of the ascending bow and the position of the pantograph in the infrared image;
  • the infrared detection unit includes an infrared camera.
  • the present invention further discloses an infrared image-based bow-net detection system, which includes
  • the first program module is used to obtain the full-field infrared image of the pantograph and catenary in real time;
  • the second program module is used to analyze the infrared image of the full field of view, match the pantograph, and detect the current ascending state and the position of the pantograph in the infrared image;
  • the present invention also discloses a computer-readable storage medium on which a computer program is stored, and when the computer program is run by a processor, the steps of the above-mentioned infrared image-based method for detection of bow nets are executed.
  • the present invention further discloses a computer device, including a memory and a processor, and a computer program is stored on the memory, and the computer program executes the steps of the infrared image-based method for detecting bow nets when run by the processor. .
  • the infrared image-based pantograph detection method of the present invention is used for pantograph detection. It has the safety and efficiency of non-contact detection, and can be detected in real time around the clock; in addition, compared with other non-contact detection equipment, the application
  • the advanced image recognition algorithm is used to detect the temperature, lead height, and pull-out of the bow-net, and its stability and accuracy are higher.
  • the infrared image-based bow-net detection method of the present invention obtains infrared images in real time and performs analysis and detection of various functional parameters.
  • the detection value exceeds the alarm threshold
  • the infrared image and video data at the time of failure are automatically recorded and the failure is notified to the ground server in real time.
  • its fault response is more real-time.
  • Fig. 1 is a flowchart of an embodiment of the method of the present invention.
  • Figure 2 is a flow chart of the method of the present invention in a specific application.
  • Fig. 3 is a schematic diagram of an infrared image in an embodiment of the present invention.
  • Figure 4 is a schematic diagram of the infrared image detection process of the present invention.
  • the infrared image-based method for detecting bow-net in this embodiment includes the following steps:
  • the infrared image-based pantograph detection method of this embodiment uses infrared thermal imaging technology to realize all-weather, full-field infrared thermal imaging detection of the operating relationship of the catenary, pantograph, and pantograph, forming a full-field temperature monitoring; Infrared image, use image recognition algorithm to match the pantograph to detect the current ascending state; use image recognition algorithm to match the pantograph and identify the contact line by detecting the contact point between the pantograph and the contact line Position, combined with the calibration information of the lead height and the pull-out value to calculate the lead height and the pull-out value; at the same time, the detection range is wide and the operation is simple.
  • the infrared image-based pantograph detection method of the present invention is used for pantograph detection. It has the safety and efficiency of non-contact detection, and can be detected in real time around the clock; in addition, compared with other non-contact detection equipment, the application
  • the advanced image recognition algorithm is used to detect the temperature, lead height, and pull-out of the bow-net, and its stability and accuracy are higher.
  • the infrared image-based bow-net detection method of the present invention obtains infrared images in real time and performs analysis and detection of various functional parameters.
  • the detection value exceeds the alarm threshold
  • the infrared image and video data at the time of failure are automatically recorded and the failure is notified to the ground server in real time.
  • its fault response is more real-time.
  • step 2) when any one or more of the detected temperature, conduction height, and pull-out value of the pantograph and catenary exceeds the corresponding preset threshold, a fault alarm is issued, and at the same time Information such as images and videos before and after the fault point is sent to the ground server so that the maintenance personnel can perform repairs in time, so as to realize the fault real-time alarm and upload function.
  • step 1) the infrared camera is used to obtain the full-field infrared image of the pantograph and the catenary in real time; the temperature data stream is read in the infrared camera, and each frame of temperature data is read, the grayscale image Convert it to RGB image to form infrared image; save the converted RGB image as video to record the temperature of the whole field of view of the pantograph network when the train is running, which is convenient for maintenance personnel to perform offline analysis of the train line.
  • the software of the present invention is mainly composed of an infrared camera full-field temperature detection thread, a temperature conversion RGB pseudo-color thread, a bow raising end and a guide height pull algorithm detection thread, a video real-time saving thread, and a fault real-time alarm upload thread, as shown in Figure 2. Show.
  • the program After the infrared camera software starts to run, the program first runs the initialization function, that is, reads the configuration files saved on the hard disk, such as the camera IP, fault alarm temperature, lead height, pull-out threshold, infrared algorithm template file path, etc. If the read IP matches the infrared camera connected to the current main box, the login is successful;
  • the infrared camera starts to read the temperature data stream at a frequency of 50 Hz. Every time a frame of temperature data is read, the 16-bit grayscale image is converted into a 32-bit RGB image through a pseudo-color algorithm. The RGB image is encoded and saved as MP4 in real time. Video to record the temperature of the full field of view of the bow net when the train is running;
  • each frame of infrared RGB image converted in real time will pass the detection of the rising state, the detection of geometric parameters, and the detection of the temperature of the full field of view of the bow net.
  • the infrared image into a grayscale image according to the channel selection (select R channel or G channel).
  • the pantograph is identified and detected by matching each image template. Whether the pantograph is in the ascending state, and the specific position of the pantograph in the image; the line detection is used to identify and track the contact line, and finally the contact point, namely the lead height and pull-out value image data, are converted into The actual lead height and pull value data.
  • the full field of view temperature detection is to calculate the actual temperature value of each point according to the value of each pixel of the entire 16-bit grayscale image, and then the specific coordinate position of the pantograph obtained by the detection of the rising state of the bow is in the area The temperature value of each coordinate point is matched, and finally the pantograph temperature detection is completed.
  • the program will determine whether the detected bow net temperature, lead height, and pull-out exceed the threshold in real time. If the threshold is exceeded, the program will record the time of the failure and trigger the failure to notify the ground server in real time, and the time before and after the failure Upload the infrared picture and video data of the camera to the ground server for analysts to analyze the details of the fault.
  • the invention also discloses a bow net detection device based on infrared images, which includes
  • Infrared detection unit for real-time acquisition of infrared images of the pantograph and catenary in the full field of view
  • Analysis module (such as a single-chip microcomputer module), used to analyze the full-field infrared image, match the pantograph, and detect the current state of the ascending bow and the position of the pantograph in the infrared image;
  • the infrared detection unit includes an infrared camera and is installed on the roof of the locomotive. After calibrating and measuring the area where the pantograph and catenary are located, the analysis module uses advanced image recognition algorithms to monitor the full-field temperature, lead height, and pull-out value of the pantograph in real time. If an arc occurs at a short-term fault point during train travel, instantaneous high temperature will be generated. The analysis module can detect and determine that the temperature value exceeds the normal threshold in real time.
  • the device of the present invention also has the advantages described in the above method, and has a simple structure and easy operation.
  • the invention also discloses an infrared image-based bow net detection system, which includes
  • the first program module is used to obtain the full-field infrared image of the pantograph and catenary in real time;
  • the second program module is used to analyze the infrared image of the full field of view, match the pantograph, and detect the current ascending state and the position of the pantograph in the infrared image;
  • the present invention further discloses a computer-readable storage medium, on which a computer program is stored, and the computer program executes the above-mentioned infrared image-based detection method for bow-net detection when the computer program is run by a processor.
  • the present invention also discloses a computer device including a memory and a processor, and a computer program is stored on the memory, and the computer program executes the above-mentioned infrared image-based method for detecting the bow net when being run by the processor.
  • the present invention implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium.
  • the computer program is executed by a processor, The steps of the foregoing method embodiments can be implemented.
  • the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms.
  • the computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access Memory (RAM, Random Access Memory), electric carrier signal, telecommunications signal, software distribution medium, etc.
  • the memory may be used to store computer programs and/or modules, and the processor implements various functions by running or executing the computer programs and/or modules stored in the memory and calling data stored in the memory.
  • the memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, flash memory Flash Card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device, etc.
  • non-volatile memory such as hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, flash memory Flash Card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Current-Collector Devices For Electrically Propelled Vehicles (AREA)

Abstract

基于红外图像的弓网检测方法、装置、系统、介质及设备，属于轨道交通技术领域，用于解决目前弓网检测人工检测效率低、安全性高以及其它接触式检测精度低、稳定性差的问题。基于红外图像的弓网检测方法具体包括：1）实时获取受电弓和接触网的全视场红外图像；2）分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。基于红外图像的弓网检测方法具有准确度高、稳定性好、响应实时性高等优点。

Description

基于红外图像的弓网检测方法、装置、系统、介质及设备
本申请要求于2020年04月28日提交中国专利局、申请号为2020103474062、发明名称为“一种基于红外图像的弓网检测方法、装置及系统”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。
技术领域
本发明主要涉及轨道交通技术领域，特指一种基于红外图像的弓网检测方法、装置、系统、介质及设备。
背景技术
电力机车运行过程中，由电流、滑动摩擦和电弧引起的温升如果超过弓网的容许温度，就会在很大程度上增加弓网系统的磨损，减少接触线和滑板的使用寿命，严重情况下可能会造成断线等事故。接触网导高值、拉出值既是接触网悬挂核心参数，也是受电弓工作面接触参数，该值一旦超标，就有可能导致电力机车受电弓脱线而造成刮弓、钻弓故障，严重情况下将直接损坏受电弓、接触网悬挂，导致供电回路无法正常工作。保证弓网系统运行安全最基本的工作是实现对弓网系统进行实时、准确、高效地监控和检测，了解弓网系统的运行工况，对产生的故障作出快速判断和决策，并及时完成后期的维护。
为实现弓网系统的安全，出现了一系列的检测与维护手段，如人工检测、接触式的弓网检测、非接触式测距弓网检测等。人工检测主要以人工作业为主，需要检测人员登车顶检测受电弓和登杆检测接触网。人工检测优势在于灵活性较强，可人工鉴别不同故障，缺点是效率很低，安全性较差，作业时干扰行车，并且无法实现实时检测，对运行当中的大规模拉弧现象无法做出预警。接触式检测方法有效地提高了检测精度，缺点是利用接触线检测车进行检测需要占用列车运行线路，会干扰到正常行车，而部分检测装置与方案需要改造受电弓结构，如此会影响受电弓的各项性能，最终可能导致检测结果不准确。非接触式测距检测方式主要表现为两方面 的研究，一方面为激光测距应用，另一方面为超声波测距应用，非接触式测距弓网检测具有检测效率高，行车干扰小的特点，但是二者也存在一定的缺点，激光检测功能相对较为单一，而超声波检测精度较差，更多应用暂处于理论阶段。
综上所述，随着时代与科技的进步，人们致力于寻找一种更为稳定、精准的方式去实现弓网运行状态的检测。
发明内容
本发明要解决的技术问题就在于：针对现有技术存在的技术问题，本发明提供一种准确度高、稳定性好、响应实时性高的基于红外图像的弓网检测方法、装置、系统、介质及设备。
为解决上述技术问题，本发明提出的技术方案为：
一种基于红外图像的弓网检测方法，包括步骤：
1)实时获取受电弓和接触网的全视场红外图像；
2)分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
作为上述技术方案的进一步改进：
在步骤2)中，当检测的受电弓和接触网的温度、导高、拉出值中的任意一个或多个超过对应预设阈值时，进行故障报警。
在步骤1)中，通过红外相机实时获取受电弓和接触网的全视场红外图像。
在红外相机读取温度数据流，每读取一帧温度数据，将灰度图转换为RGB图，形成红外图像。
将转换的RGB图像保存为视频，以记录列车运行时弓网全视场温度。
本发明还公开了一种基于红外图像的弓网检测装置，包括
红外检测单元，用于实时获取受电弓和接触网的全视场红外图像；
分析模块，用于分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
作为上述技术方案的进一步改进：
所述红外检测单元包括红外相机。
本发明进一步公开了一种基于红外图像的弓网检测系统，包括
第一程序模块，用于实时获取受电弓和接触网的全视场红外图像；
第二程序模块，用于分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
本发明还公开了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序在被处理器运行时执行如上所述的基于红外图像的弓网检测方法的步骤。
本发明进一步公开了一种计算机设备，包括存储器和处理器，所述存储器上存储有计算机程序，所述计算机程序在被处理器运行时执行如上所述的基于红外图像的弓网检测方法的步骤。
与现有技术相比，本发明的优点在于：
本发明的基于红外图像的弓网检测方法，用于弓网检测，其具备非接触式检测的安全性与高效性，可全天候实时检测；另外相比较于其他非接触式检测设备而言，运用先进的图像识别算法进行弓网温度、导高、拉出检测，其稳定性与准确性更高。
本发明的基于红外图像的弓网检测方法，实时获取红外图像并进行各项功能参数的分析检测，当检测值超过报警阈值时，自动记录故障时刻红外图像视频数据并实时触发故障通告给地面服务器，相比较其他检测方案而言，其故障响应实时性更高。
附图说明
图1为本发明的方法在实施例的流程图。
图2为本发明的方法在具体应用时的流程图。
图3为本发明的红外图像在实施例的示意图。
图4为本发明的红外图像检测过程示意图。
具体实施方式
以下结合说明书附图和具体实施例对本发明作进一步描述。
如图1至图3所示，本实施例的基于红外图像的弓网检测方法，包括步骤：
1)实时获取受电弓和接触网的全视场红外图像；
2)分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
本实施例的基于红外图像的弓网检测方法，通过红外热成像技术实现对接触网、受电弓以及弓网运行关系的全天候、全视场红外热成像检测，形成全视场温度监控；对红外图像，采用图像识别算法对受电弓进行匹配，来检测当前升弓状态；采用图像识别算法对受电弓进行匹配，以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息来计算导高、拉出值；同时检测范围广，操作简便。
本发明的基于红外图像的弓网检测方法，用于弓网检测，其具备非接触式检测的安全性与高效性，可全天候实时检测；另外相比较于其他非接触式检测设备而言，运用先进的图像识别算法进行弓网温度、导高、拉出检测，其稳定性与准确性更高。
本发明的基于红外图像的弓网检测方法，实时获取红外图像并进行各项功能参数的分析检测，当检测值超过报警阈值时，自动记录故障时刻红外图像视频数据并实时触发故障通告给地面服务器，相比较其他检测方案 而言，其故障响应实时性更高。
本实施例中，在步骤2)中，当检测的受电弓和接触网的温度、导高、拉出值中的任意一个或多个超过对应预设阈值时，进行故障报警，并同时将故障点时刻前后的图像视频等信息发送至地面服务器，以便检修人员及时进行维修，从而实现故障实时报警、上传功能。
本实施例中，在步骤1)中，通过红外相机实时获取受电弓和接触网的全视场红外图像；在红外相机读取温度数据流，每读取一帧温度数据，将灰度图转换为RGB图，形成红外图像；将转换的RGB图像保存为视频，以记录列车运行时弓网全视场温度，便于检修维护人员对列车线路进行离线分析。
下面结合一具体完整的实施例对本发明的方法做进一步说明：
本发明的软件主要由红外相机全视场温度检测线程、温度转换RGB伪彩线程、升弓端以及导高拉出算法检测线程、视频实时保存线程、故障实时报警上传线程组成，如图2所示。
红外相机软件开始运行后，程序首先运行初始化函数，即读取硬盘上保存的配置文件，如相机IP、故障报警温度、导高、拉出的阈值、红外算法模板文件路径等。若读取的IP与当前主机箱连接的红外相机匹配则登陆成功；
红外相机开始以50赫兹频率读取温度数据流，每读取一帧温度数据，随即将16位的灰度图通过伪彩算法转换为32位的RGB图像，RGB图像经过编码实时地保存为MP4视频，以记录列车运行时弓网全视场温度；
实时转换的每一帧红外RGB图像会通过升弓状态检测、几何参数检测、弓网全视场温度检测。如图4所示，首先需根据通道选择情况(选择R通道或G通道)将红外图片转化为灰度图片，其次，在灰度图像中通过各个图像模板的匹配进行受电弓的识别，检测受电弓是否处于升弓状态，以及受电弓在图像的具体位置；通过线检测进行接触线的识别和跟踪，最后得到接触点即导高和拉出值图像数据，再通过标定关系转化为实际的导高和拉出值数据。
全视场温度检测即根据整幅16位灰度图的每个像素点值，计算出每个点的实际温度值，再根据升弓状态检测得出的受电弓具体坐标位置将该区 域内的温度值进行每个坐标点匹配，最后完成弓网温度检测。
在故障实时报警上传线程中，程序会实时判断检测的弓网温度、导高、拉出是否超过阈值，若超过阈值，程序会记录故障时刻并实时触发故障通告给地面服务器，并将故障时刻前后的红外图片视频数据上传至地面服务器，供分析人员分析故障详情。
本发明还公开了一种基于红外图像的弓网检测装置，包括
红外检测单元，用于实时获取受电弓和接触网的全视场红外图像；
分析模块(如单片机等模块)，用于分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
红外检测单元包括红外相机，安装于机车车顶。在对受电弓和接触网所在区域进行标定测量后，分析模块运用先进的图像识别算法，实时监测弓网的全视场温度、导高、拉出值。如果在列车行进中出现短时间的故障点拉弧，将产生瞬间高温，分析模块可实时检测并判断该温度值超过正常阈值，当列车运行时出现几何参数故障，红外检测图像识别算法能实时检测并判断导高或者拉出值超过正常阈值，并记录故障点时刻前后图片视频并发送故障报警给地面服务器，以便检修人员及时进行维修。
本发明的装置，同样具有如上方法所述的优点，而且结构简单、操作简便。
本发明还公开了一种基于红外图像的弓网检测系统，包括
第一程序模块，用于实时获取受电弓和接触网的全视场红外图像；
第二程序模块，用于分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
本发明进一步公开了一种计算机可读存储介质，其上存储有计算机程序，计算机程序在被处理器运行时执行如上所述的基于红外图像的弓网检 测方法。
本发明还公开了一种计算机设备，包括存储器和处理器，存储器上存储有计算机程序，计算机程序在被处理器运行时执行如上所述的基于红外图像的弓网检测方法。
本发明实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，计算机程序可存储于一个计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，计算机程序包括计算机程序代码，计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。计算机可读介质可以包括：能够携带计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。存储器可用于存储计算机程序和/或模块，处理器通过运行或执行存储在存储器内的计算机程序和/或模块，以及调用存储在存储器内的数据，实现各种功能。存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其它易失性固态存储器件等。
以上仅是本发明的优选实施方式，本发明的保护范围并不仅局限于上述实施例，凡属于本发明思路下的技术方案均属于本发明的保护范围。应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理前提下的若干改进和润饰，应视为本发明的保护范围。

Claims (10)

  1. 一种基于红外图像的弓网检测方法，其特征在于，包括步骤：
    1)实时获取受电弓和接触网的全视场红外图像；
    2)分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
    基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
    以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
  2. 根据权利要求1所述的基于红外图像的弓网检测方法，其特征在于，在步骤2)中，当检测的受电弓和接触网的温度、导高、拉出值中的任意一个或多个超过对应预设阈值时，进行故障报警。
  3. 根据权利要求1所述的基于红外图像的弓网检测方法，其特征在于，在步骤1)中，通过红外相机实时获取受电弓和接触网的全视场红外图像。
  4. 根据权利要求1或2或3所述的基于红外图像的弓网检测方法，其特征在于，红外相机读取温度数据流，每读取一帧温度数据，将灰度图转换为RGB图，形成红外图像。
  5. 根据权利要求4所述的基于红外图像的弓网检测方法，其特征在于，将转换的RGB图像保存为视频，以记录列车运行时弓网全视场温度。
  6. 一种基于红外图像的弓网检测装置，其特征在于，包括
    红外检测单元，用于实时获取受电弓和接触网的全视场红外图像；
    分析模块，用于分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
    基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
    以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
  7. 根据权利要求6所述的基于红外图像的弓网检测装置，其特征在于，所述红外检测单元包括红外相机。
  8. 一种基于红外图像的弓网检测系统，其特征在于，包括
    第一程序模块，用于实时获取受电弓和接触网的全视场红外图像；
    第二程序模块，用于分析全视场红外图像，对受电弓进行匹配，检测当前升弓状态以及受电弓在红外图像中的位置；
    基于受电弓在红外图像中的位置，检测受电弓所在区域的全视场温度；
    以及对接触线进行识别，通过检测受电弓与接触线的接触点位置，结合导高、拉出值的标定信息计算得到导高、拉出值。
  9. 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，所述计算机程序在被处理器运行时执行如权利要求1～5中任意一项所述的基于红外图像的弓网检测方法。
  10. 一种计算机设备，包括存储器和处理器，所述存储器上存储有计算机程序，其特征在于，所述计算机程序在被处理器运行时执行如权利要求1～5中任意一项所述的基于红外图像的弓网检测方法。
PCT/CN2020/131615 2020-04-28 2020-11-26 基于红外图像的弓网检测方法、装置、系统、介质及设备 WO2021218137A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010347406.2 2020-04-28
CN202010347406.2A CN111521271A (zh) 2020-04-28 2020-04-28 一种基于红外图像的弓网检测方法、装置及系统

Publications (1)

Publication Number Publication Date
WO2021218137A1 true WO2021218137A1 (zh) 2021-11-04

Family

ID=71903998

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/131615 WO2021218137A1 (zh) 2020-04-28 2020-11-26 基于红外图像的弓网检测方法、装置、系统、介质及设备

Country Status (2)

Country Link
CN (1) CN111521271A (zh)
WO (1) WO2021218137A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114383735A (zh) * 2021-12-17 2022-04-22 暨南大学 基于机器视觉的火电机组空冷阵列温度场监测方法及装置
CN114577325A (zh) * 2022-03-01 2022-06-03 西南交通大学 一种强风地区接触悬挂运行状态在线监测预警系统及方法
CN114812903A (zh) * 2022-05-20 2022-07-29 无锡铁安轨道交通科技有限公司 一种用于动车的弓网压力360°动态检测系统
CN114909990A (zh) * 2022-03-02 2022-08-16 上海天链轨道交通检测技术有限公司 一种车载非接触式的接触线磨耗测量方法、装置与系统
CN116109987A (zh) * 2023-04-07 2023-05-12 中铁电气化局集团有限公司 基于深度学习的接触网悬挂部件故障检测方法和装置
CN116128810A (zh) * 2022-12-15 2023-05-16 众芯汉创（北京）科技有限公司 一种基于前端识别的红外缺陷检测方法和系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111521271A (zh) * 2020-04-28 2020-08-11 株洲中车时代电气股份有限公司 一种基于红外图像的弓网检测方法、装置及系统
CN112762877B (zh) * 2020-12-28 2023-03-21 成都国铁电气设备有限公司 一种地铁接触网刚性接触线磨耗预警方法及装置
CN117726830B (zh) * 2024-02-07 2024-04-23 南京地铁运营咨询科技发展有限公司 基于单目图像的弓网在线检测方法、系统及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08265904A (ja) * 1995-03-17 1996-10-11 West Japan Railway Co 電車線路の集電機能異常検知装置
CN103759658A (zh) * 2014-01-27 2014-04-30 成都国铁电气设备有限公司 一种基于红外图像处理实现对接触网几何参数检测的方法
CN109961429A (zh) * 2019-03-22 2019-07-02 武汉工程大学 一种基于单目红外图像的受电弓检测定位方法及系统
KR20190105760A (ko) * 2018-03-06 2019-09-18 한국철도기술연구원 영상 처리에 기반한 전기철도 팬터그래프 모니터링 장치 및 방법
CN209802413U (zh) * 2019-05-28 2019-12-17 中车株洲电力机车有限公司 一种受电弓的状态监测系统及轨道交通车辆
CN210123312U (zh) * 2019-06-03 2020-03-03 上海汽车集团股份有限公司 受电弓极板温度监测系统
CN111521271A (zh) * 2020-04-28 2020-08-11 株洲中车时代电气股份有限公司 一种基于红外图像的弓网检测方法、装置及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004042837A (ja) * 2002-07-15 2004-02-12 Toshiba Corp 架線検測装置
CN109141255A (zh) * 2018-10-18 2019-01-04 北京华开领航科技有限责任公司 一种弓网监测方法
CN109785377B (zh) * 2019-01-09 2023-05-26 中国科学院上海微系统与信息技术研究所 弓网状态的检测方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08265904A (ja) * 1995-03-17 1996-10-11 West Japan Railway Co 電車線路の集電機能異常検知装置
CN103759658A (zh) * 2014-01-27 2014-04-30 成都国铁电气设备有限公司 一种基于红外图像处理实现对接触网几何参数检测的方法
KR20190105760A (ko) * 2018-03-06 2019-09-18 한국철도기술연구원 영상 처리에 기반한 전기철도 팬터그래프 모니터링 장치 및 방법
CN109961429A (zh) * 2019-03-22 2019-07-02 武汉工程大学 一种基于单目红外图像的受电弓检测定位方法及系统
CN209802413U (zh) * 2019-05-28 2019-12-17 中车株洲电力机车有限公司 一种受电弓的状态监测系统及轨道交通车辆
CN210123312U (zh) * 2019-06-03 2020-03-03 上海汽车集团股份有限公司 受电弓极板温度监测系统
CN111521271A (zh) * 2020-04-28 2020-08-11 株洲中车时代电气股份有限公司 一种基于红外图像的弓网检测方法、装置及系统

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114383735A (zh) * 2021-12-17 2022-04-22 暨南大学 基于机器视觉的火电机组空冷阵列温度场监测方法及装置
CN114383735B (zh) * 2021-12-17 2024-03-26 暨南大学 基于机器视觉的火电机组空冷阵列温度场监测方法及装置
CN114577325A (zh) * 2022-03-01 2022-06-03 西南交通大学 一种强风地区接触悬挂运行状态在线监测预警系统及方法
CN114577325B (zh) * 2022-03-01 2022-12-23 西南交通大学 一种强风地区接触悬挂运行状态在线监测预警系统及方法
CN114909990A (zh) * 2022-03-02 2022-08-16 上海天链轨道交通检测技术有限公司 一种车载非接触式的接触线磨耗测量方法、装置与系统
CN114909990B (zh) * 2022-03-02 2024-04-05 上海天链轨道交通检测技术有限公司 一种车载非接触式的接触线磨耗测量方法、装置与系统
CN114812903A (zh) * 2022-05-20 2022-07-29 无锡铁安轨道交通科技有限公司 一种用于动车的弓网压力360°动态检测系统
CN116128810A (zh) * 2022-12-15 2023-05-16 众芯汉创（北京）科技有限公司 一种基于前端识别的红外缺陷检测方法和系统
CN116128810B (zh) * 2022-12-15 2024-01-23 众芯汉创（北京）科技有限公司 一种基于前端识别的红外缺陷检测方法和系统
CN116109987A (zh) * 2023-04-07 2023-05-12 中铁电气化局集团有限公司 基于深度学习的接触网悬挂部件故障检测方法和装置

Also Published As

Publication number Publication date
CN111521271A (zh) 2020-08-11

Similar Documents

Publication Publication Date Title
WO2021218137A1 (zh) 基于红外图像的弓网检测方法、装置、系统、介质及设备
EP2174117B1 (en) Pantograph damage and wear monitoring system
CN103115647B (zh) 轨道交通弓网工况监测系统
CN109239077B (zh) 弓网接触硬点检测装置及方法
CN202793389U (zh) 一种高铁接触网在线巡检装置
Landi et al. Hough transform and thermo-vision for monitoring pantograph-catenary system
Aydin et al. A robust anomaly detection in pantograph-catenary system based on mean-shift tracking and foreground detection
Aydin et al. A new contactless fault diagnosis approach for pantograph-catenary system
WO2024027009A1 (zh) 一种变电站绝缘子的红外热成像缺陷检测方法及装置
CN107633266B (zh) 一种电力机车接触网受电弓电弧检测方法
CN113295145A (zh) 一种弓网运行状态的检测系统及检测方法
Ishino et al. Detection system of damaged cables using video obtained from an aerial inspection of transmission lines
CN108681733A (zh) 一种基于图像处理的受电弓状态异常检测系统及检测方法
CN111561967A (zh) 弓网运行状态实时在线检测方法及系统
KR20200056879A (ko) 전차 선로의 조류 둥지 자동 검출 장치 및 방법
CN113916293A (zh) 一种电动列车接触网悬挂状态及弓网关系检测系统
CN111076750B (zh) 一种用于检测接触网吊弦线夹松脱的装置及方法
CN111812457A (zh) 输电线路及杆塔设备动、静态特征全覆盖故障评估模型
CN112285111A (zh) 一种受电弓前碳滑板缺陷检测方法、装置、系统和介质
CN115049623A (zh) 一种视觉分割分析受电弓轮廓的装置
CN113556474B (zh) 刚性接触网悬挂装置的触发拍摄方法及装置
JP2005287184A (ja) 監視装置
Lin et al. A fault detection method of high speed train pantograph based on deep learning
CN114742746A (zh) 一种非接触式检测弓姿态、羊角缺失的方法、装置及系统
CN108322699B (zh) 一种基于视频图像检测电弧闪光的方法

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: 20933660

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: 20933660

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20933660

Country of ref document: EP

Kind code of ref document: A1