[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2021082593A1 - 污秽的分类方法、装置、设备、介质及数据获取系统 - Google Patents

污秽的分类方法、装置、设备、介质及数据获取系统 Download PDF

Info

Publication number
WO2021082593A1
WO2021082593A1 PCT/CN2020/107541 CN2020107541W WO2021082593A1 WO 2021082593 A1 WO2021082593 A1 WO 2021082593A1 CN 2020107541 W CN2020107541 W CN 2020107541W WO 2021082593 A1 WO2021082593 A1 WO 2021082593A1
Authority
WO
WIPO (PCT)
Prior art keywords
pollution
spectrum data
score map
insulator
score
Prior art date
Application number
PCT/CN2020/107541
Other languages
English (en)
French (fr)
Inventor
张福增
王婷婷
徐永生
陈少杰
廖一帆
肖微
曾向君
卢威
Original Assignee
南方电网科学研究院有限责任公司
中国南方电网有限责任公司
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 南方电网科学研究院有限责任公司, 中国南方电网有限责任公司 filed Critical 南方电网科学研究院有限责任公司
Publication of WO2021082593A1 publication Critical patent/WO2021082593A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2323—Non-hierarchical techniques based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB

Definitions

  • the present invention relates to the technical field of insulator contamination classification, in particular to a contamination classification method, device, equipment, medium and data acquisition system.
  • insulators play a dual role of mechanical connection and electrical insulation between the wire and the tower.
  • insulators are used for insulation or mechanical fixing between conductors and grounding bodies.
  • the insulator is affected by emissions from factories, transportation, agriculture, mines and life, as well as natural dust falling, etc., so some contaminants will accumulate on the surface of the insulator during the working process.
  • a pollution flashover discharge may occur, leading to a pollution flashover accident.
  • the current method of identifying the contamination on the surface of the insulator is to use the image detection method.
  • the image of the insulator is taken first, and then a series of processing is performed on the image of the insulator to analyze the distribution of algae contamination.
  • the image analysis results have great errors, and it is impossible to accurately distinguish the type of contamination on the surface of the insulator.
  • the embodiments of the present invention provide a pollution classification method, device, equipment, medium, and data acquisition system, which can effectively solve the problem that the prior art cannot accurately distinguish the pollution type of the insulator surface.
  • An embodiment of the present invention provides a pollution classification method, including:
  • the pollution score map includes: a first pollution score map and a second pollution score map;
  • the pollution type includes: algae pollution and ordinary pollution.
  • the judging the pollution type of the to-be-tested pollution on the surface of the insulator according to the pollution score map specifically includes:
  • the pollution type of the pollution to be tested is algae pollution
  • the pollution type of the pollution to be tested is ordinary pollution.
  • the method further includes:
  • the wavelength range of the spectrum data is from 195.825 nm to 641.167 nm.
  • Another embodiment of the present invention correspondingly provides a spectral data acquisition system, which is used to acquire the number of spectra of the pollution to be measured in the pollution classification method;
  • the spectral data acquisition system includes: a sample box, a laser, a reflector for reflecting the laser signal of the laser, and a reflector for receiving the signal reflected by the reflector, refracting the signal and emitting it to the sample
  • the controller is respectively connected to the control end of the laser and the control end of the spectrometer, the input end of the spectrometer is connected to the collimator, and the output end of the spectrometer is connected to the calculator;
  • the laser is facing the center of the reflector, the reflector is inclined at a preset angle, a sample box is arranged along the main optical axis of the convex lens, and the collimator is arranged 45 degrees above the sample box.
  • the signal reflected by the reflector is incident from the optical center of the convex lens.
  • Another embodiment of the present invention correspondingly provides a pollution classification device, including:
  • the acquisition module is used to acquire the spectrum data of the contamination to be measured on the surface of the insulator;
  • the analysis module is used to perform cluster analysis on the full-spectrum data according to a preset principal component analysis model to obtain a pollution score map; wherein, the pollution score map includes: a first pollution score map and a second pollution score map ;
  • the classification module is used for judging the pollution type of the pollution to be tested on the surface of the insulator according to the pollution score map; wherein, the pollution type includes: algae pollution and ordinary pollution.
  • the device further includes:
  • the preprocessing module is used to remove the interference of the background spectrum in the spectrum data.
  • Another embodiment of the present invention provides a filthy classification terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor executes the computer program When realizing the pollution classification method described in the above-mentioned embodiments of the invention.
  • Another embodiment of the present invention provides a storage medium, the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device on which the computer-readable storage medium is located is controlled to execute the above-mentioned embodiments of the invention.
  • the classification method of the filth is a storage medium, the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device on which the computer-readable storage medium is located is controlled to execute the above-mentioned embodiments of the invention.
  • the pollution classification method, device, equipment and medium disclosed in the embodiments of the present invention obtain full spectrum data by obtaining the spectrum data of the contamination to be measured on the surface of the insulator, and then normalizing the spectrum data. Perform cluster analysis on the full-spectrum data according to the preset principal component analysis model to obtain the pollution score map, and then judge the pollution type of the insulator surface to be tested according to the pollution score map, so as to accurately distinguish the pollution of the insulator surface.
  • the pollution type problem avoids the pollution flashover discharge caused by the damp and pollution of the transmission line insulator, and improves the reliability and safety of the transmission line.
  • FIG. 1 is a schematic flowchart of a method for classifying pollution according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a waveform of normalization processing provided by an embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of a system for acquiring spectral data according to an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of a pollution classification device provided by an embodiment of the present invention.
  • Fig. 5 is a schematic structural diagram of a dirty classification device provided by an embodiment of the present invention.
  • Fig. 1 is a schematic flowchart of a pollution classification method according to an embodiment of the present invention.
  • the spectral data is acquired by the spectral data acquisition system. There are 12312 data points obtained, and the spectrum data of the wavelength range from 195.825nm to 641.167nm
  • S20 Perform normalization processing on the spectrum data to obtain full spectrum data.
  • the normalized full-spectrum data is used as the input matrix of the preset principal component analysis model.
  • S30 Perform cluster analysis on the full-spectrum data according to a preset principal component analysis model to obtain a pollution score map; wherein the pollution score map includes: a first pollution score map and a second pollution score map.
  • the principal component analysis method is a numerical dimensionality reduction method. Variables are mapped to a low-dimensional coordinate system through space to reduce the linear correlation between the variables, so that the input objects can be clustered through the principal component analysis model.
  • the preset principal component analysis model can be obtained by inputting the full-spectrum data into the component analysis formula.
  • the pollution type of the pollution to be tested is algae pollution
  • the pollution type of the pollution to be tested is ordinary pollution.
  • the method further includes:
  • the background spectrum is obtained before the experiment, and the mat ab software is used to remove the interference of the background spectrum.
  • FIG. 3 is a schematic structural diagram of a system for acquiring spectral data according to an embodiment of the present invention.
  • An embodiment of the present invention correspondingly provides a spectral data acquisition system for acquiring the number of spectra of the pollution to be measured in the pollution classification method;
  • the spectral data acquisition system includes: a sample box, a laser, a reflector for reflecting the laser signal of the laser, and a reflector for receiving the signal reflected by the reflector, refracting the signal and emitting it to the sample
  • the controller is connected to the control end of the laser and the control end of the spectrometer respectively, the input end of the spectrometer is connected to the collimator, and the output end of the spectrometer is connected to the calculator.
  • the input end of the spectrometer is connected to the collimator through an optical fiber.
  • the laser is facing the center of the reflector, the reflector is inclined at a preset angle, a sample box is arranged along the main optical axis of the convex lens, and the collimator is arranged 45 degrees above the sample box.
  • the signal reflected by the reflector is incident from the optical center of the convex lens.
  • the reflector is inclined at a preset angle of 45 degrees.
  • FIG. 4 is a schematic structural diagram of a pollution classification device provided by an embodiment of the present invention.
  • An embodiment of the present invention correspondingly provides a pollution classification device, including:
  • the obtaining module 10 is used to obtain the spectrum data of the contamination to be measured on the surface of the insulator.
  • the processing module 20 is used for normalizing the spectrum data to obtain full spectrum data.
  • the analysis module 30 is configured to perform cluster analysis on the full-spectrum data according to a preset principal component analysis model to obtain a pollution score map; wherein, the pollution score map includes: a first pollution score map and a second pollution score map Figure.
  • the classification module 40 is used for judging the pollution type of the pollution to be tested on the surface of the insulator according to the pollution score map; wherein, the pollution type includes: algae pollution and ordinary pollution.
  • the device further includes:
  • the preprocessing module is used to remove the interference of the background spectrum in the spectrum data.
  • the embodiment of the present invention provides a pollution classification device, which obtains the spectrum data of the pollution to be measured on the surface of the insulator, normalizes the spectrum data to obtain the full spectrum data, and then compares the full spectrum data according to a preset principal component analysis model.
  • the data is clustered and analyzed to obtain a pollution score map, and then determine the type of pollution to be tested on the surface of the insulator based on the pollution score map, so as to accurately distinguish the type of pollution to be tested on the surface of the insulator, and avoid the transmission line insulator from being damp Pollution flashover caused by pollution improves the reliability and safety of transmission lines.
  • Fig. 5 is a schematic diagram of a dirty classification device provided by an embodiment of the present invention.
  • the dirty classification device of this embodiment includes a processor, a memory, and a computer program stored in the memory and running on the processor.
  • the processor executes the computer program, the steps in the above-mentioned various pollution classification method embodiments are implemented.
  • the processor executes the computer program, the function of each module/unit in the foregoing device embodiments is realized.
  • the computer program may be divided into one or more modules/units, and the one or more modules/units are stored in the memory and executed by the processor to complete the present invention.
  • the one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the dirty classification device.
  • the dirty classification device may be computing devices such as desktop computers, notebooks, palmtop computers, and cloud servers.
  • the dirty classification equipment may include, but is not limited to, a processor and a memory.
  • the schematic diagram is only an example of dirty classification equipment, and does not constitute a limitation on the ** device/terminal device. It may include more or less components than shown in the figure, or a combination of certain components , Or different components, for example, the dirty classification device may also include input and output devices, network access devices, buses, and so on.
  • the so-called processor can be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
  • the processor is the control center of the dirty classification equipment, and various interfaces and lines are used to connect the entire dirty classification equipment. Various parts.
  • the memory may be used to store the computer program and/or module, and the processor can realize the pollution by running or executing the computer program and/or module stored in the memory and calling data stored in the memory.
  • the memory may mainly include a storage program area and a storage data area.
  • the storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; the storage data area may store Data created based on the use of mobile phones (such as audio data, phone book, etc.), etc.
  • the memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disks, memory, plug-in hard disks, smart media cards (SMC), and secure digital (SD) cards.
  • non-volatile memory such as hard disks, memory, plug-in hard disks, smart media cards (SMC), and secure digital (SD) cards.
  • Flash Card at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
  • the integrated module/unit of the dirty classification device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • 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. When the program is executed by the processor, it can implement the steps of the foregoing method embodiments.
  • 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 the 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), electrical carrier signal, telecommunications signal, and software distribution media, etc.
  • the device embodiments described above are only illustrative, and the units described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physically separate. Units can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the connection relationship between the modules indicates that they have a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative work.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Discrete Mathematics (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

一种污秽的分类方法，包括：获取绝缘子表面的待测污秽的光谱数据；对光谱数据进行归一化处理得到全光谱数据；根据预设的主成分分析法模型对全光谱数据进行聚类分析，得到污秽得分图；根据污秽得分图判断缘子表面的待测污秽的污秽类型；其中，污秽类型包括：藻类污秽以及普通污秽。还提供了一种污秽的分类装置、设备、介质及数据获取系统，采用多个实施例解决了现有技术无法准确地分辨绝缘子表面污秽的污秽类型的问题。

Description

污秽的分类方法、装置、设备、介质及数据获取系统 技术领域
本发明涉及绝缘子污秽分类技术领域，尤其涉及一种污秽的分类方法、装置、设备、介质及数据获取系统。
背景技术
在输电线路中，绝缘子在导线和铁塔之间起着机械连接和电气绝缘的双重作用，主要有悬式绝缘子、耐张绝缘子、横担绝缘子等。在变电站或换流站中，绝缘子用于导线和接地体之间的绝缘或机械固定。绝缘子在运行中由于受到工厂、交通、农业、矿山和生活等的排放物，以及自然灰尘飘落等的影响，所以绝缘子在工作过程中表面会积累了一些污秽物质。在潮湿环境中，若绝缘子表面附着的是藻类污秽，则可能发生污闪放电，导致发生污闪事故。
目前识别绝缘子表面污秽的方法是利用图像检测法进行检测，测量过程中首先拍摄绝缘子图像，再对绝缘子图像进行一系列处理，可以分析藻类污秽的分布情况。而由于藻类的生长状况、藻类的分布情况、藻类污秽堆积的厚度等差异都会对藻类颜色造成影响，因此图像分析结果存在极大的误差，无法准确的分辨绝缘子表面污秽的污秽类型。
发明内容
本发明实施例提供一种污秽的分类方法、装置、设备、介质及数据获取系统，能有效解决现有技术无法准确的分辨绝缘子表面污秽的污秽类型的问题。
本发明一实施例提供一种污秽的分类方法，包括：
获取绝缘子表面的待测污秽的光谱数据；
对所述光谱数据进行归一化处理得到全光谱数据；
根据预设的主成分分析法模型对所述全光谱数据进行聚类分析，得到污秽得分图；其中，所述污秽得分图包括：第一污秽得分图以及第二污秽得分图；
根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽类型；其中，所述污秽类型包括：藻类污秽以及普通污秽。
作为上述方案的改进，所述根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽类型，具体包括:
所述第一污秽得分图得分小于5000且所述第二污秽得分图得分大于0，则所述待测污秽的污秽类型为藻类污秽；
所述第一污秽得分图得分小于5000且所述第二污秽得分图得分小于0，则所述待测污秽的污秽类型为普通污秽。
作为上述方案的改进，在所述获取绝缘子表面的待测污秽的光谱数据之后，对所述光谱数据进行归一化处理得到全光谱数据之前，还包括：
去除所述光谱数据中背景光谱的干扰。
作为上述方案的改进，所述光谱数据的波长范围为195.825纳米～641.167纳米。
本发明另一实施例对应提供了一种光谱数据的获取系统，用于获取所述的污秽的分类方法中的所述待测污秽的光谱数；
所述光谱数据的获取系统包括：样品箱、激光器、用于反射所述激光器的激光信号的反光体、用于接收所述反光体反射后的信号并将所述信号折射后发射至所述样品箱的凸透镜、用于接收所述样品箱中待测污秽的光谱信号的直准镜、光谱仪、用于接收所述光谱仪的光谱信号的计算器以及用于控制所述激光器与所述光谱仪的控制器；
所述控制器分别连接所述激光器的控制端及所述光谱仪的控制端连接，所述光谱仪的输入端与所述直准镜连接，所述光谱仪的输出端与所述计算器连接；
所述激光器正对于所述反光体的中心，所述反光体倾斜预设的角度，沿所述凸透镜主光轴设置有样品箱，所述样品箱的斜上方45度设置有所述直准镜；其中，所述反光体反射后的信号从所述凸透镜光心射入。
本发明另一实施例对应提供了一种污秽的分类装置，包括：
获取模块，用于获取绝缘子表面的待测污秽的光谱数据；
处理模块，用于对所述光谱数据进行归一化处理得到全光谱数据；
分析模块，用于根据预设的主成分分析法模型对所述全光谱数据进行聚类分析，得到污秽得分图；其中，所述污秽得分图包括：第一污秽得分图以及第二污秽得分图；
分类模块，用于根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽类型；其中，所述污秽类型包括：藻类污秽以及普通污秽。
作为上述方案的改进，所述装置还包括：
预处理模块，用于去除所述光谱数据中背景光谱的干扰。
本发明另一实施例提供了一污秽的分类终端设备，包括处理器、存储器以及存储在所述存储器中且被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时实现上述发明实施例所述的污秽的分类方法。
本发明另一实施例提供了一种存储介质，所述计算机可读存储介质包括存储的计算机程序，其中，在所述计算机程序运行时控制所述计算机可读存储介质所在设备执行上述发明实施例所述的污秽的分类方法。
与现有技术相比，本发明实施例公开的污秽的分类方法、装置、设备及介质，通过获取绝缘子表面的待测污秽的光谱数据，对光谱数据进行归一化处理得到全 光谱数据，再根据预设的主成分分析法模型对全光谱数据进行聚类分析，从而得到污秽得分图，进而根据污秽得分图判断绝缘子表面的待测污秽的污秽类型，达到准确分辨绝缘子表面的待测污秽的污秽类型的问题，避免了输电线路绝缘子由受潮污秽引发的污闪放电，提高了输电线路的可靠性和安全性。
附图说明
图1是本发明一实施例提供的一种污秽的分类方法的流程示意图；
图2是本发明一实施例提供的归一化处理的波形示意图；
图3是本发明一实施例提供的一种光谱数据的获取系统的结构示意图；
图4是本发明一实施例提供的一种污秽的分类装置的结构示意图；
图5是本发明一实施例提供的一种污秽的分类设备的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
参见图1，是本发明一实施例提供的一种污秽的分类方法的流程示意图。
本发明实施例提供的一种污秽的分类方法，包括：
S10,获取绝缘子表面的待测污秽的光谱数据。
在本实施例中，通过光谱数据的获取系统获取光谱数据。得到有12312个数据点，波长范围从195.825nm～641.167nm的光谱数据
S20,对所述光谱数据进行归一化处理得到全光谱数据。
具体地，参见图2，将归一化处理后的全光谱数据作为预设的主成分分析法 模型的输入矩阵。
S30,根据预设的主成分分析法模型对所述全光谱数据进行聚类分析，得到污秽得分图；其中，所述污秽得分图包括：第一污秽得分图以及第二污秽得分图。
其中，主成分分析法是数值降维方法，变量通过空间映射到低维坐标系中，减少变量间的线性相关性，从而可以通过主成分分析法模型对输入对象进行聚类分析。
具体地，讲所述全光谱数据输入至至成份分析公式即可得出预设的主成分分析模型。
S40,根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽类型；其中，所述污秽类型包括：藻类污秽以及普通污秽。
具体地，所述第一污秽得分图得分小于5000且所述第二污秽得分图得分大于0，则所述待测污秽的污秽类型为藻类污秽；
所述第一污秽得分图得分小于5000且所述第二污秽得分图得分小于0，则所述待测污秽的污秽类型为普通污秽。
综上所述，通过获取绝缘子表面的待测污秽的光谱数据，对光谱数据进行归一化处理得到全光谱数据，再根据预设的主成分分析法模型对全光谱数据进行聚类分析，从而得到污秽得分图，进而根据污秽得分图判断绝缘子表面的待测污秽的污秽类型，达到准确分辨绝缘子表面的待测污秽的污秽类型的问题，避免了输电线路绝缘子由受潮污秽引发的污闪放电，提高了输电线路的可靠性和安全性。
作为上述方案的改进，在所述获取绝缘子表面的待测污秽的光谱数据之后，对所述光谱数据进行归一化处理得到全光谱数据之前，还包括：
去除所述光谱数据中背景光谱的干扰。
在本实施例中，在实验前获得背景光谱，利用mat l ab软件去除背景光谱的 干扰。
参见图3，是本发明一实施例提供的一种光谱数据的获取系统的结构示意图。
本发明一实施例对应提供了一种光谱数据的获取系统，用于获取所述的污秽的分类方法中的所述待测污秽的光谱数；
所述光谱数据的获取系统包括：样品箱、激光器、用于反射所述激光器的激光信号的反光体、用于接收所述反光体反射后的信号并将所述信号折射后发射至所述样品箱的凸透镜、用于接收所述样品箱中待测污秽的光谱信号的直准镜、光谱仪、用于接收所述光谱仪的光谱信号的计算器以及用于控制所述激光器与所述光谱仪的控制器；
所述控制器分别连接所述激光器的控制端及所述光谱仪的控制端连接，所述光谱仪的输入端与所述直准镜连接，所述光谱仪的输出端与所述计算器连接。在本实施例中，光谱仪的输入端通过光纤与直准镜连接。
所述激光器正对于所述反光体的中心，所述反光体倾斜预设的角度，沿所述凸透镜主光轴设置有样品箱，所述样品箱的斜上方45度设置有所述直准镜；其中，所述反光体反射后的信号从所述凸透镜光心射入。其中，所述反光体倾斜预设的角度，为45度。
具体地，利用激光诱导击穿光谱技术，通过产生功率密度极高的激光脉冲，在附着污秽的绝缘子表面诱导产生等离子体经给直准镜利用光纤收集等离子体，得到光谱信息，光谱仪将得到的光谱信息发送至计算器。
参见图4，是本发明一实施例提供的一种污秽的分类装置的结构示意图。
本发明一实施例对应提供了一种污秽的分类装置，包括：
获取模块10，用于获取绝缘子表面的待测污秽的光谱数据。
处理模块20，用于对所述光谱数据进行归一化处理得到全光谱数据。
分析模块30，用于根据预设的主成分分析法模型对所述全光谱数据进行聚类分析，得到污秽得分图；其中，所述污秽得分图包括：第一污秽得分图以及第二污秽得分图。
分类模块40，用于根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽类型；其中，所述污秽类型包括：藻类污秽以及普通污秽。
作为上述方案的改进，所述装置还包括：
预处理模块，用于去除所述光谱数据中背景光谱的干扰。
本发明实施例提供一种污秽的分类装置，通过获取绝缘子表面的待测污秽的光谱数据，对光谱数据进行归一化处理得到全光谱数据，再根据预设的主成分分析法模型对全光谱数据进行聚类分析，从而得到污秽得分图，进而根据污秽得分图判断绝缘子表面的待测污秽的污秽类型，达到准确分辨绝缘子表面的待测污秽的污秽类型的问题，避免了输电线路绝缘子由受潮污秽引发的污闪放电，提高了输电线路的可靠性和安全性。
参见图5，是本发明一实施例提供的污秽的分类设备的示意图。该实施例的污秽的分类设备包括：处理器、存储器以及存储在所述存储器中并可在所述处理器上运行的计算机程序。所述处理器执行所述计算机程序时实现上述各个污秽的分类方法实施例中的步骤。或者，所述处理器执行所述计算机程序时实现上述各装置实施例中各模块/单元的功能。
示例性的，所述计算机程序可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器中，并由所述处理器执行，以完成本发明。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序在所述污秽的分类设备中的执行过程。
所述污秽的分类设备可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。所述污秽的分类设备可包括，但不仅限于，处理器、存储器。本领 域技术人员可以理解，所述示意图仅仅是污秽的分类设备的示例，并不构成对**装置/终端设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述污秽的分类设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等，所述处理器是所述污秽的分类设备的控制中心，利用各种接口和线路连接整个污秽的分类设备的各个部分。
所述存储器可用于存储所述计算机程序和/或模块，所述处理器通过运行或执行存储在所述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，实现所述污秽的分类设备的各种功能。所述存储器可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据手机的使用所创建的数据(比如音频数据、电话本等)等。此外，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、或其他易失性固态存储器件。
其中，所述污秽的分类设备集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，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，所述的计算机程序可存储于一计算机可读 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，所述计算机程序包括计算机程序代码，所述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。所述计算机可读介质可以包括：能够携带所述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。
需说明的是，以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。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。另外，本发明提供的装置实施例附图中，模块之间的连接关系表示它们之间具有通信连接，具体可以实现为一条或多条通信总线或信号线。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。
以上所述是本发明的优选实施方式，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的前提下，还可以做出若干改进和润饰，这些改进和润饰也视为本发明的保护范围。

Claims (9)

  1. 一种污秽的分类方法，其特征在于，包括：
    获取绝缘子表面的待测污秽的光谱数据；
    对所述光谱数据进行归一化处理得到全光谱数据；
    根据预设的主成分分析法模型对所述全光谱数据进行聚类分析，得到污秽得分图；其中，所述污秽得分图包括：第一污秽得分图以及第二污秽得分图；
    根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽类型；其中，所述污秽类型包括：藻类污秽以及普通污秽。
  2. 如权利要求1所述的污秽的分类方法，其特征在于，所述根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽类型，具体包括:
    所述第一污秽得分图得分小于5000且所述第二污秽得分图得分大于0，则所述待测污秽的污秽类型为藻类污秽；
    所述第一污秽得分图得分小于5000且所述第二污秽得分图得分小于0，则所述待测污秽的污秽类型为普通污秽。
  3. 如权利要求1所述的污秽的分类方法，其特征在于，在所述获取绝缘子表面的待测污秽的光谱数据之后，对所述光谱数据进行归一化处理得到全光谱数据之前，还包括：
    去除所述光谱数据中背景光谱的干扰。
  4. 如权利要求1所述的污秽的分类方法，其特征在于，所述光谱数据的波长范围为195.825纳米～641.167纳米。
  5. 一种光谱数据的获取系统，用于获取如权利要求1-4所述的污秽的分类方法中的所述待测污秽的光谱数据；
    所述光谱数据的获取系统包括：样品箱、激光器、用于反射所述激光器的激光信号的反光体、用于接收所述反光体反射后的信号并将所述信号折射后发射至所述样品箱的凸透镜、用于接收所述样品箱中待测污秽的光谱信号的直准镜、光谱仪、用于接收所述光谱仪的光谱信号的计算器以及用于控制所述激光器与所述光谱仪的控制器；
    所述控制器分别连接所述激光器的控制端及所述光谱仪的控制端连接，所述光谱仪的输入端与所述直准镜连接，所述光谱仪的输出端与所述计算器连接；
    所述激光器正对于所述反光体的中心，所述反光体倾斜预设的角度，沿所述凸透镜主光轴设置有样品箱，所述样品箱的斜上方45度设置有所述直准镜；其中，所述反光体反射后的信号从所述凸透镜光心射入。
  6. 一种污秽的分类装置，其特征在于，包括：
    获取模块，用于获取绝缘子表面的待测污秽的光谱数据；
    处理模块，用于对所述光谱数据进行归一化处理得到全光谱数据；
    分析模块，用于根据预设的主成分分析法模型对所述全光谱数据进行聚类分析，得到污秽得分图；其中，所述污秽得分图包括：第一污秽得分图以及第二污秽得分图；
    分类模块，用于根据所述污秽得分图判断所述绝缘子表面的待测污秽的污秽 类型；其中，所述污秽类型包括：藻类污秽以及普通污秽。
  7. 如权利要求6所述的污秽的分类装置，其特征在于，所述装置还包括：
    预处理模块，用于去除所述光谱数据中背景光谱的干扰。
  8. 一种污秽的分类终端设备，其特征在于，包括处理器、存储器以及存储在所述存储器中且被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时实现如权利要求1至4中任意一项所述的污秽的分类方法。
  9. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质包括存储的计算机程序，其中，在所述计算机程序运行时控制所述计算机可读存储介质所在设备执行如权利要求1至4中任意一项所述的污秽的分类方法。
PCT/CN2020/107541 2019-10-31 2020-08-06 污秽的分类方法、装置、设备、介质及数据获取系统 WO2021082593A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911053928.5 2019-10-31
CN201911053928.5A CN110826615A (zh) 2019-10-31 2019-10-31 污秽的分类方法、装置、设备、介质及数据获取系统

Publications (1)

Publication Number Publication Date
WO2021082593A1 true WO2021082593A1 (zh) 2021-05-06

Family

ID=69551848

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/107541 WO2021082593A1 (zh) 2019-10-31 2020-08-06 污秽的分类方法、装置、设备、介质及数据获取系统

Country Status (2)

Country Link
CN (1) CN110826615A (zh)
WO (1) WO2021082593A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114494867A (zh) * 2022-01-19 2022-05-13 湖北工业大学 一种改进AlexNet网络的绝缘子快速分类识别方法
CN114577807A (zh) * 2022-01-11 2022-06-03 国网青海省电力公司检修公司 基于高光谱特征量归一化编码表的绝缘子状态检测方法
CN115656202A (zh) * 2022-10-25 2023-01-31 西安交通大学 用于绝缘子表面状态的多波段光学检测装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110826615A (zh) * 2019-10-31 2020-02-21 南方电网科学研究院有限责任公司 污秽的分类方法、装置、设备、介质及数据获取系统
CN113624713A (zh) * 2021-08-16 2021-11-09 云南电网有限责任公司电力科学研究院 一种用于支柱绝缘子表面污秽成分的检测方法及装置
CN115165908B (zh) * 2022-06-10 2024-09-06 西南交通大学 基于高光谱的室外绝缘子污秽程度检测方法及其系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102004088A (zh) * 2010-11-09 2011-04-06 清华大学 一种基于神经网络的煤质特性在线测量方法
CN109060700A (zh) * 2018-09-04 2018-12-21 安徽科技学院 一种对铜离子不同吸附容量的螺旋藻快速鉴别方法
CN110826615A (zh) * 2019-10-31 2020-02-21 南方电网科学研究院有限责任公司 污秽的分类方法、装置、设备、介质及数据获取系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102087212B (zh) * 2010-11-25 2012-07-04 西南大学 基于主成份分析的葛粉掺假鉴别方法
CN106501697A (zh) * 2016-10-20 2017-03-15 清华大学深圳研究生院 一种用于在带电绝缘子表面着生藻类的环境模拟装置及方法
CN107543821B (zh) * 2017-09-07 2020-05-05 国网四川省电力公司电力科学研究院 一种绝缘子藻类生长程度评估方法
CN108051341A (zh) * 2017-12-05 2018-05-18 清华大学深圳研究生院 一种覆藻硅橡胶表面憎水性测量结果的修正方法
CN108593582A (zh) * 2018-04-12 2018-09-28 山东建筑大学 一种红外光谱快速判定沥青油源的方法
CN108844941B (zh) * 2018-05-30 2021-10-12 武汉工程大学 一种基于拉曼光谱和pca-hca的不同品位磷矿的鉴别和分类方法
CN109799244A (zh) * 2019-03-29 2019-05-24 云南电网有限责任公司电力科学研究院 一种直流系统绝缘子表面污秽状态检测方法及检测系统
CN110132938B (zh) * 2019-05-29 2021-08-31 南京财经大学 一种拉曼光谱法鉴别大米种类的特征数据提取方法
CN110261405B (zh) * 2019-07-31 2021-06-22 西南交通大学 基于显微高光谱技术的绝缘子污秽成分识别方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102004088A (zh) * 2010-11-09 2011-04-06 清华大学 一种基于神经网络的煤质特性在线测量方法
CN109060700A (zh) * 2018-09-04 2018-12-21 安徽科技学院 一种对铜离子不同吸附容量的螺旋藻快速鉴别方法
CN110826615A (zh) * 2019-10-31 2020-02-21 南方电网科学研究院有限责任公司 污秽的分类方法、装置、设备、介质及数据获取系统

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114577807A (zh) * 2022-01-11 2022-06-03 国网青海省电力公司检修公司 基于高光谱特征量归一化编码表的绝缘子状态检测方法
CN114494867A (zh) * 2022-01-19 2022-05-13 湖北工业大学 一种改进AlexNet网络的绝缘子快速分类识别方法
CN115656202A (zh) * 2022-10-25 2023-01-31 西安交通大学 用于绝缘子表面状态的多波段光学检测装置
CN115656202B (zh) * 2022-10-25 2024-06-04 西安交通大学 用于绝缘子表面状态的多波段光学检测装置

Also Published As

Publication number Publication date
CN110826615A (zh) 2020-02-21

Similar Documents

Publication Publication Date Title
WO2021082593A1 (zh) 污秽的分类方法、装置、设备、介质及数据获取系统
CN104520806B (zh) 用于云监控的异常检测
CN110221145B (zh) 电力设备故障诊断方法、装置及终端设备
US20130162241A1 (en) Detecting malicious hardware by measuring radio frequency emissions
WO2021045846A1 (en) Cybersecurity vulnerability classification and remediation based on installation base
CN110247933B (zh) 实现防火墙策略的方法和装置
CN109660533B (zh) 实时识别异常流量的方法、装置、计算机设备和存储介质
US9716704B2 (en) Code analysis for providing data privacy in ETL systems
CN114943673A (zh) 瑕疵图像生成方法、装置、电子设备及存储介质
WO2021082594A1 (zh) 一种绝缘材料表面的藻类检测方法、装置和设备
CN105721406A (zh) 一种获取ip黑名单的方法和装置
Zhang et al. Knitting needle fault detection system for hosiery machine based on laser detection and machine vision
Yu et al. Principal component analysis and analysis of variance on the effects of entellan new on the Raman spectra of fibers
US20210357251A1 (en) Electronic device and non-transitory storage medium implementing test path coordination method
US10346716B2 (en) Fast joint template machining
US20210182458A1 (en) Method, device and computer program product for data simulation
CN111459932A (zh) 基于区块链的数据存证方法、装置及存储介质
CN111581499A (zh) 一种数据归一化方法、装置、设备及可读存储介质
Elachgar et al. Information security, 4TH wave
CN114006838B (zh) 流控设备的测试方法及系统
CN110083807B (zh) 合同的修改影响自动预测方法、装置、介质及电子设备
CN110134435A (zh) 一种代码修复案例获取方法、装置、设备及存储介质
CN109472766B (zh) 桥梁螺栓区域定位方法及终端设备
US11188748B2 (en) Scalable structure learning via context-free recursive document decomposition
CN111222739B (zh) 核电站的任务分配方法及核电站的任务分配系统

Legal Events

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

Ref document number: 20883144

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 11/10/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20883144

Country of ref document: EP

Kind code of ref document: A1