Hyperspectral visualization and three-dimensional reconstruction detection device and technology for insulation state of power equipment

Abstract

The application discloses a kind of power equipment insulation state hyperspectral visualization stereoscopic reconstruction detection device and technology, the device includes bidirectional reflection characteristic test system, bidirectional reflection spectrum library, hyperspectral image acquisition system, laser radar LiDAR system, display unit, data processing unit;Wherein, bidirectional reflection characteristic test system test obtains bidirectional reflection spectrum library as basis;Hyperspectral image acquisition system acquires image data and synchronously obtains reflection spectrum-image gray three-dimensional data;Laser radar LiDAR system acquires and obtains the three-dimensional coordinate information of target to be measured;Data processing unit analyzes reflection spectrum-image gray three-dimensional data and LiDAR image data, and carries out the visualization diagnosis of power equipment outer insulation state by display unit.The application fuses three-dimensional imaging technology to realize the stereoscopic three-dimensional reconstruction of insulating piece multispectral photometry, to realize the visualization detection of the insulation state of outer insulating piece under complex measurement environment.

Description

Technical Field

[0001] This invention belongs to the field of online technical technology of external insulation status of insulating components, and in particular, it is a hyperspectral visualization three-dimensional reconstruction detection device and technology for the insulation status of power equipment. Background Technology

[0002] Among power system accidents, pollution flashover and lightning flashover pose the greatest threat to the external insulation of the power system, with pollution flashover causing far greater losses than lightning damage. Under complex meteorological conditions (fog, dew, drizzle, and acidic wet deposition, etc.), the electrical strength of insulators will decrease significantly. Flashover of contaminated insulator strings can lead to large-scale and prolonged power outages, seriously threatening the safe and stable operation of the power system. On the other hand, the main component of widely used silicone rubber composite insulators is siloxane, a high-molecular organic polymer bonded by covalent bonds. Due to the complex terrain and variable environment of the areas traversed by transmission lines, insulators face various harsh external conditions in actual operation, such as high-altitude strong ultraviolet radiation, heavy pollution, and acid rain (fog). This causes the chemical bonds in the material to break and the material to change, leading to aging and deterioration. Aging is mainly manifested as a decrease or loss of surface hydrophobicity, pulverization, cracking, and a deterioration in anti-pollution flashover performance. The insulation performance of the insulator decreases, and the flashover voltage also decreases, easily causing power grid faults and resulting in huge economic losses.

[0003] Traditional methods for assessing the condition of external insulation components are mostly offline inspections. However, transmission lines traverse vast areas with complex terrain and variable environments, often requiring personnel to climb poles for operation, which is inconvenient and unsafe. Furthermore, the sheer number of insulators involved necessitates significant resource investment using traditional methods, resulting in wasted manpower and materials, and failing to meet the required accuracy and timeliness for practical engineering applications. Therefore, finding a more convenient, direct, non-contact, rapid, and non-destructive method for inspecting the surface contamination and aging of silicone rubber materials in power equipment is crucial for maintaining the safe and stable operation of power systems.

[0004] Based on airborne multispectral imaging technology and integrating functions such as intelligent sensing and fault prediction, an intelligent inspection technology for the external insulation status of transmission lines has been constructed. This technology enables assisted prediction of external insulation status and intelligent safety management, significantly improving the efficiency of transmission line inspections and comprehensively enhancing the intelligence level of equipment and the reliability of power grid operation. However, with the field application of power equipment condition diagnosis systems based on hyperspectral imaging technology, the resulting interference from environmental factors in spectral image acquisition, the complex posture of insulating components, and mutual interference between adjacent towers and insulating components pose serious challenges to the detection accuracy of the spectral inversion model of insulation status of insulating components constructed under laboratory conditions.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of the present invention, and therefore may contain information that does not constitute prior art known to those skilled in the art in this country. Summary of the Invention

[0006] To address the problems existing in the prior art, this invention, based on mastering the pixel-level bidirectional reflection characteristics of external insulation components and constructing a reflectivity correction method that integrates spatial information, integrates three-dimensional imaging technology to achieve multispectral photometric three-dimensional reconstruction of insulation components. This enables the visualization detection and electrical performance evaluation of the insulation state of external insulation components under complex measurement environments, overcoming the fatal flaw of existing spectral detection technologies, which suffer from large measurement errors at close range.

[0007] The objective of this invention is achieved through the following technical solution: a hyperspectral visualization and stereoscopic reconstruction detection device for the insulation state of power equipment, characterized in that the device comprises: an outer insulation material sample of the insulation component, a bidirectional reflection characteristic testing system, a hyperspectral image acquisition system, a LiDAR system, a display unit, a data processing unit, and a spectrometer system;

[0008] The outer insulating material pattern of the insulating component is required to have a flat surface and uniform thickness.

[0009] The spectrometer system and the dichroic reflectance test system are used to collect reflectance data of the external insulating material sample of the insulating component in order to obtain a dichroic reflectance spectral library.

[0010] The hyperspectral image acquisition system is used to acquire image data of the outer insulating material of the insulating component and simultaneously obtain three-dimensional data of reflectance spectrum-image grayscale.

[0011] The LiDAR system is used to acquire LiDAR image data to obtain the three-dimensional coordinate information of the outer insulation material pattern of the insulating component;

[0012] The data processing unit is used to analyze the reflectance spectrum-image grayscale three-dimensional data and the LiDAR image data, and in conjunction with the bidirectional reflectance spectrum library, to perform a visual diagnosis of the external insulation status of the power equipment through the display unit.

[0013] Preferably, the LiDAR system is a radar system that uses laser beams to detect the position, velocity and other characteristics of a target. By emitting a laser beam at the target and then comparing the received signal reflected back from the target power equipment with the emitted signal, parameters such as the distance, azimuth, height, attitude and shape of the target power equipment can be obtained, thereby realizing pixel-level three-dimensional reconstruction of the power equipment.

[0014] Preferably, the data processing unit is connected to the LiDAR system to achieve pixel-level three-dimensional reconstruction of the power equipment, connected to the hyperspectral image acquisition system to achieve reflectivity data analysis of the power equipment, and combined with the bidirectional reflectivity spectral library to achieve pixel-level reflectivity data calibration, thereby realizing visualization of the external insulation status of the power equipment through hyperspectral photometric three-dimensional reconstruction.

[0015] Preferably, the spectrometer system comprises an optical fiber and a spectrometer, wherein the spectrometer acquires reflectance data with a band spacing of a first predetermined length within a first predetermined wavelength range; preferably, the spectral resolution of the spectrometer is used as the first predetermined length.

[0016] The reflectance data of the outer insulating material sample of the tested insulating component are collected by the spectrometer system and the dichroic reflectance characteristic testing system according to the traversal dichroic reflectance spectrum acquisition method, so as to obtain a dichroic reflectance spectrum library of the outer insulating material sample of the insulating component.

[0017] Preferably, the dichroic reflection characteristic testing system includes: a slide rail connecting block, a slide rod connecting block, an upper slip ring, a bottom slip ring, an optical fiber fixator, a light source, and a slide rod;

[0018] The bottom of the slide rail connecting block is connected to the bottom slip ring, and one side of the slide rail connecting block is connected to the upper slip ring.

[0019] One side of the slide bar connecting block is connected to the upper slip ring, and the other side of the slide bar connecting block is connected to the slide bar;

[0020] The fiber optic fixer has one end connected to a slide bar and the other end provided with a ring through which the optical fiber passes, so that the fiber optic fixer can fix the optical fiber.

[0021] The light source is fixed to the end of the slide bar.

[0022] Preferably, the optical fiber is connected to the dichroic reflection characteristic testing system via the optical fiber fixer.

[0023] Preferably, the traversal bidirectional reflectance spectral acquisition method refers to acquiring the reflectance of the outer insulating material sample of the tested insulating component by simultaneously changing different values ​​of the incident zenith angle, the reflected zenith angle, the incident-reflected ray azimuth angle, the light source distance, and the detection distance.

[0024] Preferably, the hyperspectral visualization stereoscopic reconstruction detection device for the insulation status of power equipment further includes: a power management module, a halogen lamp light source system, a central processing unit, and a data storage unit;

[0025] The power management module is used to realize power supply and distribution;

[0026] The halogen lamp light source system is used to emit halogen lamps with uniform intensity distribution within a predetermined wavelength range, and its brightness and on / off status are controlled by the central processing unit in groups.

[0027] The central processing unit is connected to the halogen lamp light source system, the hyperspectral image acquisition system, the LiDAR system, the data processing unit, the data storage unit, and the display unit.

[0028] The central processing unit is used to adjust the switching status and light source intensity of the halogen lamp light source system according to the distance from the target power equipment.

[0029] The central processing unit is also used to adjust the light source intensity of the halogen lamp light source system according to the distance to the target power equipment during the inspection process.

[0030] The central processing unit is also used to control the hyperspectral image acquisition system to acquire hyperspectral image data, and to control the data processing unit to further analyze the acquired hyperspectral image data.

[0031] The central processing unit is also used to control the LiDAR system to acquire three-dimensional LiDAR image data and to control the data processing unit to further analyze the acquired LiDAR images.

[0032] The central processing unit is also used to control the data storage unit to store data, so as to store the evaluation results of the external insulation status of the power equipment under test during the inspection process;

[0033] The central processing unit is also used to control the display unit to display the assessment results of the external insulation status of the power equipment.

[0034] Preferably, in the hyperspectral image acquisition system, spectral image data with more than 100 imaging bands is defined as a hyperspectral image, which acquires image data with a band interval of a second predetermined length within a second predetermined wavelength range and simultaneously obtains three-dimensional data of reflectance spectrum-image grayscale; preferably, the spectral resolution of the hyperspectral image acquisition system is used as the second predetermined length.

[0035] Preferably, both the hyperspectral image acquisition system and the spectrometer system can acquire reflectance spectral data. The difference is that the spectrometer has a higher spectral resolution (i.e., a first predetermined length), while the hyperspectral image acquisition system can both image and acquire spectral data, and its spectral resolution (i.e., a second predetermined length) is lower than that of the spectrometer.

[0036] Preferably, in the bidirectional reflectance characteristic testing system, considering that the spectral acquisition system needs to set conditions according to the bidirectional reflectance spectral acquisition method, and the slider system rotates and moves, while the hyperspectral imaging system requires a stable imaging platform, and since the insulating material pattern is small in size and has a flat surface, no imaging analysis is required, a spectrometer is used instead of a hyperspectral image acquisition system to carry out spectral data acquisition in the bidirectional reflectance characteristic testing system.

[0037] Preferably, in the subsequent acquisition of the surface condition of power equipment, since visualization analysis and inversion of the material surface condition inversion results are required, it is necessary to use imaging analysis methods to acquire reflectance spectral data, that is, to use a hyperspectral image acquisition system.

[0038] Preferably, the first predetermined acquisition wavelength range and the second predetermined acquisition wavelength range are the same, both being 400nm-1000nm, which is the typical spectral range of a visible-near-infrared spectrometer / hyperspectral imaging system; however, the predetermined lengths are different, with the "predetermined length" of the spectrometer being less than the "predetermined length" of the hyperspectral imaging system, i.e., the first predetermined length < the second predetermined length, or in other words, the spectral resolution of the spectrometer > the spectral resolution of the hyperspectral image acquisition system.

[0039] Preferably, the power equipment external insulation condition visualization detection device integrating hyperspectral photometric three-dimensional reconstruction further includes: a mechanical support module and a rotatable worktable;

[0040] The mechanical support module is used to provide mechanical support for the visual detection device for the external insulation status of the power equipment;

[0041] The rotatable worktable is used to place the target electrical equipment. The rotatable worktable is an electronically controlled device, and its rotation speed is controlled by a motor.

[0042] Preferably, the mechanical support module further includes an adjustment module, which is connected to the halogen lamp light source system, the hyperspectral image acquisition system and the LiDAR system, and adjusts the working angle and height of the halogen lamp light source system, the hyperspectral image acquisition system and the LiDAR system.

[0043] Preferably, the rotatable worktable is connected to the power management module to provide power and to the central processing unit to achieve controlled rotation.

[0044] The present invention also provides a hyperspectral visualization stereoscopic reconstruction detection device for the insulation status of power equipment, characterized in that the device includes: a bidirectional reflectance spectrum library acquisition module and a power equipment insulation status detection module;

[0045] The bidirectional reflectance spectral library acquisition module is used to acquire the bidirectional reflectance spectral library of the external insulation material pattern of the insulating component;

[0046] The power equipment insulation status detection module is used to achieve full-angle visualization of the fault status of the target power equipment. Preferably, the method for obtaining the bidirectional reflectance spectrum library includes the following steps:

[0047] Step S1: Prepare a typical insulating material sample for a power system, place it at the center of the workbench of the dichroic reflection characteristic testing system, and put the spectrometer system into operation and turn on the light source;

[0048] Step S2: Reset the dihedral reflectance spectrum acquisition conditions by adjusting the slide rail connecting block, slide rod connecting block, and slide rod;

[0049] Step S3: Collect the photoelectric response intensity of reflected light from the surface of the insulating material sample using a spectrometer system;

[0050] Step S4: Adjust one parameter of the bidirectional reflectance spectral acquisition conditions step by step, while keeping the other parameters unchanged;

[0051] Step S5: Repeat step S4 until the incident zenith angle θ is reached. i The zenith angle is 0°, and the reflected zenith angle is θ. o The incident-reflected ray azimuth angle φ is 180°, and the distance from the light source r is 0°. i The detection range is 1.5 meters, and the detection distance l is 1.5 meters.

[0052] Step S6: Adjust the dichroic reflectance spectral acquisition conditions, replace the typical insulation material sample of the power system with a calibration whiteboard, and acquire the photoelectric response intensity of the reflected light from the calibration whiteboard through a spectrometer system; preferably, the calibration whiteboard is a calibration whiteboard with 100% reflectivity;

[0053] Step S7: Close the optical fiber lens cover and collect the photoelectric response intensity in the dark state using a spectrometer system;

[0054] Step S8: Perform black and white calibration to obtain relative reflectance;

[0055] Step S9: Prepare insulation material samples with different insulation materials and different insulation fault states by simulation test method, and repeat S1-S8 to obtain a bidirectional reflectance spectrum library;

[0056] Step S10: In order to achieve the calibration of reflectance values ​​under different acquisition conditions, a neural network is established based on the bidirectional reflectance spectrum library, thereby establishing a nonlinear mapping relationship between reflectance, acquisition conditions and standard reflectance fault library.

[0057] Preferably, the power equipment insulation status detection module performs the following steps to achieve full-angle visualization of the fault status of the target power equipment:

[0058] Step S11: Place the target power equipment on a rotatable workbench, turn on the halogen lamp light source system to adjust the light intensity, turn on the hyperspectral image acquisition system and the LiDAR system, and adjust the acquisition parameters to ensure clear imaging;

[0059] Step S12: Using the line connecting the hyperspectral image acquisition system to the target power equipment as the normal, acquire hyperspectral image data and three-dimensional LiDAR image data within the range of -60° to 60° with the normal, according to the preset step.

[0060] Step S13: Control the rotatable worktable and repeat steps S11-S12 to complete the measurement of the remaining angles;

[0061] Step S14: Replace the target power equipment with a calibration whiteboard, adjust the acquisition conditions to standard acquisition conditions, acquire the photoelectric response intensity of the reflected light from the calibration whiteboard, and acquire the photoelectric response intensity in the dark state to complete the black and white calibration;

[0062] Step S15: The relative reflectance of hyperspectral images from different angles is decentered, the covariance matrix and its eigenvalues ​​and eigenvectors are extracted, and the hyperspectral reconstructed image is completed.

[0063] Step S16: Convert the 3D LiDAR image data to grayscale, select hyperspectral image data as the original image, and perform image matching and fusion;

[0064] Step S17: Establish a spherical coordinate system with the rotatable stage as the center, and complete the coordinate transformation in the LiDAR image data;

[0065] Step S18: Determine the acquisition conditions for each pixel and calibrate the relative reflectance in the hyperspectral image to the standard reflectance for measurement;

[0066] Step S19: Perform spectral matching between the measured standard reflectance of the target power equipment and the standard reflectance fault database to determine the fault status;

[0067] Step S20: Traverse and judge the fault status of each pixel of the target power equipment, mark it with different colors, and stitch together the diagnostic results of image data from different angles to achieve full-angle visualization of the fault status of the target power equipment.

[0068] A hyperspectral visualization and stereoscopic reconstruction detection method for the insulation state of power equipment, characterized in that the method includes the following steps:

[0069] S100: Collect reflectance data of the outer insulation material of the insulating component to obtain a dihedral reflectance spectral library;

[0070] S200: Collect image data of the outer insulation material of the insulating component and simultaneously obtain three-dimensional data of reflectance spectrum-image grayscale;

[0071] S300: Acquire LiDAR image data to obtain the three-dimensional coordinate information of the outer insulation material pattern of the insulating component;

[0072] S400: Analyze the three-dimensional data of the reflection spectrum-image grayscale and the LiDAR image data, and combine them with the bidirectional reflection spectrum library to perform visual diagnosis of the external insulation status of power equipment through the display unit. Compared with the prior art, the present invention has the following advantages: Light transmission in space follows the radiative transmission process, and the reflection spectrum of external insulation components with different insulation states has bidirectional reflection characteristics. Based on mastering the pixel-level bidirectional reflection characteristics of external insulation components and constructing a reflectivity correction method that integrates spatial information, the present invention integrates three-dimensional imaging technology to realize multispectral photometric three-dimensional reconstruction of insulation components, thereby realizing the visual detection and electrical performance evaluation of the insulation status of external insulation components under complex measurement environments. Attached Figure Description

[0073] Various other advantages and benefits of the present invention will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0074] In the attached diagram:

[0075] Figure 1 This is a schematic diagram of the structure of a hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to an embodiment of the present invention;

[0076] Figure 2 This is a schematic diagram of a bidirectional reflection characteristic testing system for a hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to an embodiment of the present invention. In the diagram, A1 and A2 are slide rail connecting blocks, A3 and A4 are slide rod connecting blocks, B1 and B2 are upper slip rings, B3 is a bottom slip ring, C is an optical fiber fixer, D is a light source, E1 and E2 are slide rods, G is a worktable, and F is a sample of the outer insulation material of the insulation component.

[0077] Figure 3This is a flowchart illustrating the acquisition of a bidirectional reflectance spectral library for a hyperspectral visualization and stereoscopic reconstruction detection device for the insulation state of power equipment, according to an embodiment of the present invention.

[0078] Figure 4 This is a physical diagram of a hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to an embodiment of the present invention; wherein, A is the mechanical support module of the hyperspectral image acquisition system and the LiDAR laser radar image acquisition system, B is the mechanical support module of the halogen lamp light source system, C is the hyperspectral image acquisition system, D is the LiDAR laser radar image acquisition system, F is the coarse adjustment module of the imaging angle of C and D, G is the fine adjustment module of the imaging angle of C and D, H is the power equipment under test, I is the rotatable worktable, E is the halogen lamp light source system, and J is the central processing unit;

[0079] Figure 5 This is a flowchart of the steps of the power equipment insulation status detection module in a hyperspectral visualization stereoscopic reconstruction detection device for power equipment insulation status according to an embodiment of the present invention.

[0080] Figure 6 This is a bidirectional reflectance spectrum library standard reflectance spectrum of tempered glass, ceramics, and high-temperature vulcanized silicone rubber materials under different pollution levels in a hyperspectral visualization stereoscopic reconstruction detection device and technology for the insulation state of power equipment according to an embodiment of the present invention.

[0081] Figure 7 This refers to the standard reflectance values ​​of tempered glass, ceramics, and high-temperature vulcanized silicone rubber materials at a wavelength of 750nm for different incident zenith angles, reflected zenith angles, and incident-reflected ray azimuth angles in a hyperspectral visualization stereoscopic reconstruction detection device and technology for the insulation state of power equipment according to an embodiment of the present invention.

[0082] Figures 8(a) to 8(c) show the nonlinear mapping relationship of tempered glass, ceramic, and high-temperature vulcanized silicone rubber materials at a wavelength of 750nm for different incident zenith angles, reflected zenith angles, and incident-reflected ray azimuth angles in a hyperspectral visualization stereoscopic reconstruction detection device and technology for the insulation state of power equipment according to an embodiment of the present invention.

[0083] Figure 9 This is the fusion result of hyperspectral images and LiDAR images of composite insulators in a hyperspectral visualization stereoscopic reconstruction detection device and technology for the insulation state of power equipment according to an embodiment of the present invention;

[0084] Figure 10 This is the pollution status assessment result of composite insulators in a hyperspectral visualization stereoscopic reconstruction detection device and technology for the insulation status of power equipment according to an embodiment of the present invention.

[0085] The present invention will be further explained below with reference to the accompanying drawings and embodiments. Detailed Implementation

[0086] The following will refer to the appendix. Figures 1 to 10 Specific embodiments of the invention will be described in more detail below. While specific embodiments of the invention are shown in the accompanying drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.

[0087] It should be noted that certain terms are used in the specification and claims to refer to specific components. Those skilled in the art will understand that different terms may be used to refer to the same component. This specification and claims do not distinguish components based on differences in terminology, but rather on differences in function. The terms "comprising" or "including" used throughout the specification and claims are open-ended and should be interpreted as "comprising but not limited to." The following descriptions are preferred embodiments for carrying out the invention; however, these descriptions are for the purpose of understanding the general principles of the specification and are not intended to limit the scope of the invention. The scope of protection of this invention is determined by the appended claims.

[0088] To facilitate understanding of the embodiments of the present invention, further explanations and descriptions will be provided below with reference to the accompanying drawings and specific embodiments. The accompanying drawings do not constitute a limitation on the embodiments of the present invention.

[0089] To better understand, such as Figure 1 As shown, a hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment is disclosed. The device includes:

[0090] The outer insulation material sample 1 is made from common power system insulation materials, such as high-temperature vulcanized silicone rubber, epoxy resin, ceramics, tempered glass, etc., cut into a standardized shape. The surface of the insulation material sample is required to be flat and the thickness uniform. Preferably, the insulation material sample is square, with a length, width and height of 8 cm, 8 cm and 1 cm respectively.

[0091] The spectrometer system 2 consists of a light-guiding optical fiber and a spectrometer. The light-guiding optical fiber is connected to the bidirectional reflection characteristic testing system 3 via an optical fiber fixer. The spectrometer collects reflectance data with a band spacing of a first predetermined length within a first predetermined wavelength range, wherein the spectral resolution of the spectrometer is used as the first predetermined length. The first predetermined wavelength range is 400nm-1000nm.

[0092] Dihedral reflection characteristic testing system 3, such as Figure 2As shown, it consists of slide rail connecting blocks A1 and A2, slide rod connecting blocks A3 and A4, upper slide rings B1 and B2, bottom slide ring B3, fiber optic fixer C, light source D, slide rods E1 and E2, and worktable G.

[0093] The bottom of the slide rail connecting blocks A1 and A2 is connected to the bottom slip ring B3 by a sliding fixing method, and one side of the slide rail connecting blocks A1 and A2 is fixedly connected to the upper slip rings B1 and B2. The upper slip rings B1 and B2 can slide 360° along the circumference on the bottom slip ring B3 through the slide rail connecting blocks A1 and A2.

[0094] The sliding rod connecting blocks A3 and A4 are respectively connected to the upper sliding rings B1 and B2 by a slidable fixing method on one side, and to the sliding rods E1 and E2 by a snap-fit ​​fixing method on the other side. The sliding rod connecting blocks A3 and A4 can respectively realize the sliding rods E1 and E2 sliding 90° along the circumference on the upper sliding rings B1 and B2. At the same time, the sliding rod connecting blocks A3 and A4 can respectively realize the adjustment of the distance between the sliding rods E1 and E2 and the worktable G located at the center of the bottom sliding ring B3.

[0095] The fiber optic fixer C has one end connected to the slide rod E1 using a snap-fit ​​fixing method, and the other end uses a ring design to pass the optical fiber through the ring and fix it.

[0096] The light source D emits halogen light with uniform intensity distribution within a predetermined wavelength range and is fixed to the end of the slide bar E2.

[0097] The slide bar E1 connects the slide bar connecting block A3 and the fiber optic fixer C;

[0098] The slide bar E2 connects the slide bar connecting block A4 and the light source D;

[0099] The worktable G is located at the center of the bottom slip ring B3 and is used to place the outer insulation material sample 1 of the insulating component to be tested. The bidirectional reflectance spectral library 4 is obtained by collecting reflectance data of the outer insulation material sample 1 of the insulating component to be tested using the spectrometer system 2 and the bidirectional reflectance characteristic testing system 3 according to a traversal bidirectional reflectance spectral acquisition method, thereby obtaining a bidirectional reflectance spectral library for the outer insulation material sample 1 of the insulating component. The traversal bidirectional reflectance spectral acquisition method refers to collecting the reflectance of the outer insulation material sample 1 of the insulating component to be tested by simultaneously changing different values ​​of the incident zenith angle, reflected zenith angle, incident-reflected ray azimuth angle, light source distance, and detection distance.

[0100] Among them, such as Figure 2As shown, the incident zenith angle refers to the angle θ between the incident ray from the light source D and the normal z-axis of the worktable G in the spherical coordinate system formed by the worktable G as the center point O. i ;

[0101] The reflected zenith angle refers to the angle θ between the reflected ray received by the optical fiber and the normal z-axis of the worktable G in a spherical coordinate system centered at point O on the worktable G. o ;

[0102] The incident-reflected ray azimuth angle refers to the angle φ between the projection line of the incident ray from the light source D onto the horizontal plane xOy of the worktable G in the spherical coordinate system centered at point O on the worktable G and the x-axis. i The angle between the projection line of the reflected light received by the optical fiber onto the horizontal plane xOy of the worktable and the x-axis is φ. o The angle between the incident ray from light source D and the reflected ray from the optical fiber on the horizontal plane xOy of the worktable G is the incident-reflected ray azimuth angle φ, where φ = φ i +φ o ;

[0103] The light source distance refers to the spatial distance r between the light source D and the center point of the surface of the outer insulating material sample 1 in the spherical coordinate system formed by the worktable G as the center point O. i ;

[0104] The detection distance refers to the spatial distance l between the optical fiber and the center point of the surface of the outer insulating material sample 1 of the insulating component in the spherical coordinate system formed by the worktable G as the center point O.

[0105] The power management module 5 is connected to the halogen lamp light source system 6, the hyperspectral image acquisition system 7, the LiDAR system 8, the central processing unit 9, the data processing unit 10, the data storage unit 11, and the display unit 12, and is used to realize power supply and distribution.

[0106] The halogen lamp light source system 6 consists of 6 groups of halogen lamps evenly distributed at both ends of the hyperspectral image acquisition system 7 and the LiDAR system 8. It emits halogen lamps with uniform intensity distribution within a predetermined wavelength range. Its brightness and on / off status can be controlled by the central processing unit 9.

[0107] The hyperspectral image acquisition system 7 acquires image data with a band interval of a second predetermined length within a second predetermined wavelength range and simultaneously obtains three-dimensional data of reflectance spectrum and image grayscale. Spectral image data with more than 100 imaging bands is defined as a hyperspectral image, and the spectral resolution of the hyperspectral image acquisition system is used as the second predetermined length. The second predetermined wavelength range is consistent with the first predetermined wavelength range.

[0108] The LiDAR system 8 is a radar system that uses laser beams to detect the position, velocity and other characteristics of a target. By emitting a laser beam at the target and then comparing the received signal reflected back from the target power equipment with the emitted signal, parameters such as the distance, azimuth, height, attitude and shape of the target power equipment can be obtained, thereby achieving pixel-level three-dimensional reconstruction of the power equipment.

[0109] Central processing unit 9 is connected to the halogen lamp light source system 6, the hyperspectral image acquisition system 7, the LiDAR system 8, the data processing unit 10, the data storage unit 11, and the display unit 12, wherein:

[0110] The central processing unit 9 is used to adjust the switching state and light source intensity of the halogen lamp light source system 6 according to the distance from the target power equipment;

[0111] The central processing unit 9 is also used to adjust the light source intensity of the halogen lamp light source system according to the distance to the target power equipment during the inspection process.

[0112] The central processing unit 9 is also used to control the hyperspectral image acquisition system 7 to acquire hyperspectral image data, and to control the data processing unit 10 to further analyze the acquired hyperspectral image data (specific steps are S12-S20).

[0113] The central processing unit 9 is also used to control the LiDAR system 8 to acquire three-dimensional LiDAR image data, and to control the data processing unit 10 to further analyze the acquired LiDAR images (specific steps are S12-S20).

[0114] The central processing unit 9 is also used to control the data storage unit 11 to perform data storage;

[0115] The central processing unit 9 is also used to control the display unit 12 to display the evaluation results of the external insulation status of the power equipment.

[0116] The data storage unit 11 is connected to the data processing unit 10 and the central processing unit 9 to store the evaluation results of the external insulation status of the power equipment under test during the inspection process.

[0117] Display unit 12 is connected to data processing unit 10 and central processing unit 9 to visualize the evaluation results of the external insulation status of power equipment.

[0118] The data processing unit 10 is connected to the LiDAR system 8 to realize pixel-level three-dimensional reconstruction of power equipment, connected to the hyperspectral image acquisition system 7 to realize reflectivity data analysis of power equipment (specific steps are S12-S20), and combined with the bidirectional reflectivity spectral library 4 to realize pixel-level reflectivity data calibration (specific steps are S14-S18), thereby realizing visualization of the external insulation status of power equipment by fusing hyperspectral photometric three-dimensional reconstruction.

[0119] In one embodiment, a hyperspectral visualization stereoscopic reconstruction detection device for the insulation status of power equipment is provided. The device includes: a bidirectional reflectance spectrum library acquisition module and a power equipment insulation status detection module.

[0120] The dihedral reflectance spectral library acquisition module is used to acquire a dihedral reflectance spectral library 4 of the external insulation material sample of the insulating component; wherein, the method for acquiring the dihedral reflectance spectral library 4 is as follows: Figure 3 As shown, the method includes the following steps:

[0121] Step S1: Prepare a typical insulation material sample for a power system. The insulation material sample should have a flat surface and uniform thickness. Place the insulation material sample to be tested in the center of the worktable of the dichroic reflection characteristic test system, and put the spectrometer system into working condition and turn on the light source.

[0122] Step S2: By adjusting the sliding rail connecting blocks A1 and A2, the sliding rod connecting blocks A3 and A4, and the sliding rods E1 and E2, the bidirectional reflection spectrum acquisition conditions are reset, i.e., the incident zenith angle θ. i The zenith angle is 90°, and the reflected zenith angle is θ. o The incident-reflected ray azimuth angle is 90°, the incident-reflected ray azimuth angle φ is 0°, and the distance from the light source is r. i The detection range is 0.5 meters, and the detection distance l is 0.5 meters.

[0123] Step S3: Collect the photoelectric response intensity of the reflected light from the surface of the insulating material sample using a spectrometer system. ;

[0124] Step S4: Adjust one parameter of the bidirectional reflectance spectral acquisition conditions step by step, while keeping the other parameters unchanged;

[0125] Step S5: Repeat step S4 until the incident zenith angle θ is reached. i The zenith angle is 0°, and the reflected zenith angle is θ. o The incident-reflected ray azimuth angle φ is 180°, and the distance from the light source r is 0°. i The detection range is 1.5 meters, and the detection distance l is 1.5 meters.

[0126] Step S6: Adjust the dihedral reflectance spectrum acquisition conditions to: incident zenith angle θ iThe angle is 45°, and the reflected zenith angle is θ. o The incident-reflected ray azimuth angle φ is 180°, and the distance from the light source r is 0°. i The detection distance l is 1 meter. A typical insulating material sample for the power system is replaced with a calibration whiteboard with 100% reflectivity. The photoelectric response intensity of the reflected light from the calibration whiteboard is collected using a spectrometer system. ;

[0127] Step S7: Close the optical fiber lens cover and collect the photoelectric response intensity in the dark state using the spectrometer system. ;

[0128] Step S8: Perform black and white calibration to obtain relative reflectance. , ;

[0129] Step S9: Prepare insulation material samples with different insulation materials and different insulation fault states by simulation test method, and repeat S1-S8 to obtain the bidirectional reflectance spectrum library 4;

[0130] Step S10: To calibrate reflectance values ​​under different acquisition conditions, a BP neural network is established based on the bidirectional reflectance spectral library 4, with each wavelength as the input. Relative reflectance at the following levels and collection conditions The output is a standard reflectivity fault library. Thus, the reflectivity is established. Data collection conditions With standard reflectivity fault library Nonlinear mapping relationship .

[0131] In another embodiment, the power equipment external insulation status visualization detection device integrating hyperspectral photometric stereoscopic reconstruction further includes: a mechanical support module 13 and a rotatable worktable 14;

[0132] Among them, the mechanical support module 13 is connected to the halogen lamp light source system 6, the hyperspectral image acquisition system 7, and the LiDAR system 8, providing mechanical support for the power equipment external insulation status visualization detection device that integrates hyperspectral photometric three-dimensional reconstruction. The mechanical support module also includes an adjustment module, which adjusts the working angle and height of the halogen lamp light source system 6, the hyperspectral image acquisition system 7, and the LiDAR system 8.

[0133] The rotatable worktable 14 is an electronic control device that is connected to the power management module 5 to provide power and to the central processing unit 9 to achieve controlled rotation and provide a placement platform for the target electrical equipment.

[0134] In another embodiment, a power equipment external insulation condition visualization detection device integrating hyperspectral photometric stereoscopic reconstruction, such as... Figure 5 As shown, the power equipment insulation status detection module performs the following steps to achieve full-angle visualization of the fault status of the target power equipment:

[0135] Step S11: Place the target power equipment on the rotatable worktable 14 and stop the rotatable worktable 14 from rotating; turn on the halogen lamp light source system 6 and adjust the light intensity according to the distance from the target power equipment to the power equipment using a power equipment external insulation state visualization detection device that integrates hyperspectral photometric stereoscopic reconstruction; turn on the hyperspectral image acquisition system 7 and the LiDAR system 8 and adjust the acquisition parameters to ensure clear imaging.

[0136] Step S12: Using the line connecting the hyperspectral image acquisition system 7 to the target power equipment as the normal, acquire hyperspectral image data within the range of -60° to 60° with the normal. ,in λ represents the pixel coordinates of the photoelectric converter, which correspond one-to-one with the spatial positions in the hyperspectral image, and λ represents the wavelength dimension of the photoelectric response intensity curve of the hyperspectral image acquisition system.

[0137] Furthermore, a rectangular coordinate system with the LiDAR system 8 as the origin is established, and the LiDAR system 8 is used to acquire three-dimensional LiDAR image data within a range of -60° to 60° with preset steps. ,in This represents the pixel coordinates of the photoelectric converter, and corresponds one-to-one with their spatial positions in the 3D reconstructed image. This represents the distance from the pixel to the vertical plane of the LiDAR system 8; the preset step can be set according to the accuracy requirements of the research, preferably 1°, 5°, or 10°, with 5° being recommended.

[0138] Step S13: Control the rotatable worktable 14 to rotate 120°, repeat steps S11-S12, and obtain the results respectively. and ;

[0139] Furthermore, continue to control the rotatable worktable 14 to rotate 120°, and repeat steps S11-S12 to obtain the results respectively. and ;

[0140] Step S14: Replace the target power equipment with a calibration whiteboard with 100% reflectivity. Adjust the acquisition conditions to standard acquisition conditions, i.e., adjust the distance between the hyperspectral image acquisition system 7 and the calibration whiteboard to 1 meter and the included angle to 90°, adjust the distance between the halogen lamp light source system 6 and the calibration whiteboard to 1 meter and the included angle to 45°, and acquire the photoelectric response intensity of the reflected light from the calibration whiteboard. ;

[0141] Furthermore, with the hyperspectral image acquisition system and lens 7 turned off, the photoelectric response intensity in the dark state was... ;

[0142] Perform black and white calibration to obtain relative reflectivity , , ,

[0143] in:

[0144] ,

[0145] ,

[0146] .

[0147] Step S15: Sequentially process any coordinate in different hyperspectral images from -60° to 60°, 60° to 180°, and 180° to 300°. relative reflectivity , , Decentralization is implemented to For example:

[0148] ,in, Represents any coordinate in a hyperspectral image The relative reflectivity of the m-th band after decentralization. Let represent the wavelength of the m-th band in the hyperspectral image, and P represent the total number of bands in the hyperspectral image.

[0149] Furthermore, the N bands Write in matrix form ,calculate covariance matrix , and its eigenvalue b and eigenvalue vector ;

[0150] Furthermore, select the largest eigenvalue. The corresponding eigenvector Using the coordinates as variables, the hyperspectral reconstructed image can be obtained by iterating sequentially from the base. , where P represents the total number of bands in the hyperspectral image;

[0151] Further, repeat step S14 to obtain respectively , .

[0152] Step S16: In order for hyperspectral image data and LiDAR image data to work synergistically, the two types of image data need to be fused so that the detection template pixels in the two types of image data can correspond one-to-one.

[0153] Specifically, the LiDAR image data were processed sequentially. , , After grayscale processing, LiDAR grayscale images were obtained. , and ;

[0154] Further, select respectively As the original image, Select as the target image As the original image, Select as the target image As the original image, As the target image, the Scale Invariant Feature Transform (SIFT) algorithm is applied for image matching and fusion. This transforms image matching into matching between feature point vectors, converting these stable, detailed features into feature vectors. Based on these feature vectors, feature matching is performed on the feature points, i.e., through spatial set transformation. ,in This represents the coordinate transformation operation performed by the SIFT algorithm;

[0155] Step S17: Establish a spherical coordinate system with the rotatable worktable 14 as the center, where the coordinates... , , , The test setup conditions are known; in LiDAR image data , , In the process, the coordinates of all points of the target power equipment can be read and recorded as a set. ;

[0156] Furthermore, through coordinate transformation, the Cartesian coordinate system formed by the vertical plane of the LiDAR system 8 and the ground focus can be converted into a spherical coordinate system with the rotatable worktable 14 as the center. Therefore, It can be converted into .

[0157] Step S18: Set the coordinates , , , as well as By substituting spherical coordinates, the acquisition conditions for each pixel in the LiDAR image can be clearly obtained. ;

[0158] Furthermore, readout from hyperspectral images Corresponding coordinate set The relative reflectance at each wavelength, and through Relationship calibration to measure standard reflectance .

[0159] Step S19: Measure the standard reflectance obtained from the target power equipment. and standard reflectivity fault library Viewed as a vector in a space with the same dimension and number of bands, the spectral angle of each pixel of the target power equipment is calculated sequentially. , ,in To measure standard reflectance , Standard reflectivity fault library ;

[0160] Furthermore, find the relationship between each fault state. The minimum is calculated. This allows us to determine the fault state of the pixel.

[0161] Step S20: Traverse and determine the fault status of each pixel of the target power equipment, and mark it with different colors to visualize the fault status of the target power equipment; for example, use light red to dark red to represent the aging status of the insulation material from slight to severe; use light blue to dark blue to represent the contamination status of the insulation material from slight to severe.

[0162] Furthermore, by stitching together the diagnostic results of the hyperspectral image data collected from different angles in step S20, the fault status of the target power equipment can be visualized from all angles.

[0163] Application Validation

[0164] 1. Figure 6 For a tempered glass, ceramic, or high-temperature vulcanized silicone rubber material with a contamination level of 0-IV under defect conditions, the sampling conditions are: incident zenith angle θ i 45°, reflected zenith angle θ o The incident-reflected ray azimuth angle φ is 90°, and the distance from the light source is r. i Example of reflectivity curve detection results after black and white calibration when the distance is 1 meter and the detection distance l is 1 meter. , , Meanwhile, it can be seen that when a contamination defect occurs, different levels of contamination will cause the reflectance value to increase in a regular manner. This regular change also provides a basis for spectral analysis for the qualitative and quantitative assessment of the severity of the defect. By changing the acquisition conditions, the reflectance curve detection results of different insulating materials, different defect states, and different acquisition conditions can be obtained.

[0165] 2. Figure 7 For a tempered glass, ceramic, or high-temperature vulcanized silicone rubber material with a pollution level of 0 under defect conditions, a fixed light source distance r is used. i When the distance l is 1 meter and the detection distance l is 1 meter, the incident zenith angle θ i 45°, reflected zenith angle θ o This is a case study of a black-and-white calibrated reflectivity intensity database at a wavelength of 750nm, with incident-reflected light azimuth angles φ ranging from 0° to 90° and from 0° to 180°. , , Continue to change the incident zenith angle θ i The distance from the light source is r i The detection distance l can obtain a standard reflectivity intensity database under different acquisition conditions at a wavelength of 750nm;

[0166] 3. Figure 8(a) shows the incident zenith angle θ at a wavelength of 750 nm for tempered glass, ceramics, and high-temperature vulcanized silicone rubber materials under defect conditions of contamination level 0. i The nonlinear mapping relationship between θ and the standard reflectivity intensity shows that... i It satisfies a negative quadratic polynomial relationship with the standard reflectivity intensity, that is:

[0167]

[0168] In the formula, x, c, and j are undetermined coefficients, which can be determined by changing θ. i After obtaining the measured values, least squares fitting is used to determine the final value. Taking tempered glass as an example, its expression can be written as:

[0169]

[0170] Figure 8(b) shows the reflection zenith angle θ at a wavelength of 750 nm for tempered glass, ceramics, and high-temperature vulcanized silicone rubber materials under defect conditions of contamination level 0. o The nonlinear mapping relationship between θ and the standard reflectivity intensity shows that... o It satisfies a cubic polynomial relationship with the standard reflectance intensity, that is:

[0171]

[0172] In the formula, q, w, y, and v are undetermined coefficients, which can be determined by changing θ. o After obtaining the measured values, least squares fitting is used to determine the final value. Taking tempered glass as an example, its expression can be written as:

[0173] .

[0174] Figure 8(c) shows the nonlinear mapping relationship between the incident-reflected ray azimuth angle φ and the standard reflectivity intensity at a wavelength of 750 nm for tempered glass, ceramics, and high-temperature vulcanized silicone rubber materials under a contamination level of 0. It can be seen that φ and the standard reflectivity intensity satisfy a linear relationship, i.e.:

[0175]

[0176] In the formula, h and t are undetermined coefficients, which can be determined by measuring φ and then performing least-squares fitting. Taking tempered glass as an example, its expression can be written as:

[0177]

[0178] By mastering the nonlinear empirical fitting relationship between the acquisition conditions and the standard reflectance intensity, we can provide prior knowledge for the standard reflectance under different acquisition conditions.

[0179] 4. Figure 9 This is an example of the fusion results of a hyperspectral image and a LiDAR image of a composite insulator. The results show that the detection template pixels in the two image data can be matched one-to-one, which shows that the fusion results of the device and method of the present invention are accurate and effective. Synergistic analysis can be achieved by fusing hyperspectral images and LiDAR images.

[0180] 5. Figure 10 As an example of the pollution status assessment results of a composite insulator, the colors from light to dark indicate the diagnostic results of different pollution levels, thereby realizing the visual detection of pollution distribution. The results show that the detection results of the device and method of the present invention are accurate and effective.

[0181] The above experimental results show that the device and method of the present invention can effectively realize multispectral photometric three-dimensional reconstruction of insulating components, thereby enabling the visualization detection and electrical performance evaluation of the insulation status of external insulating components under complex measurement environments.

[0182] Although embodiments of the present invention have been described above in conjunction with the accompanying drawings, the present invention is not limited to the specific embodiments and application fields described above. The specific embodiments described above are merely illustrative and instructive, and not restrictive. Those skilled in the art can make many other forms based on the guidance of this specification and without departing from the scope of protection of the claims of the present invention, and all of these are within the scope of protection of the present invention.

Claims

1. A hyperspectral visualization and stereoscopic reconstruction detection device for the insulation state of power equipment, characterized in that, The device includes: an outer insulation material sample for the insulating component, a dichroic reflection characteristic testing system, a hyperspectral image acquisition system, a LiDAR system, a display unit, a data processing unit, and a spectrometer system; The outer insulating material pattern of the insulating component is required to have a flat surface and uniform thickness. The spectrometer system and the dichroic reflectance test system are used to collect reflectance data of the external insulating material sample of the insulating component in order to obtain a dichroic reflectance spectral library. The hyperspectral image acquisition system is used to acquire image data of the outer insulating material of the insulating component and simultaneously obtain three-dimensional data of reflectance spectrum-image grayscale. The LiDAR system is used to acquire LiDAR image data to obtain the three-dimensional coordinate information of the outer insulation material pattern of the insulating component. The data processing unit is used to analyze the reflectance spectrum-image grayscale three-dimensional data and the LiDAR image data, and combine them with the bidirectional reflectance spectrum library to perform a visual diagnosis of the external insulation status of power equipment through the display unit. The spectrometer system includes an optical fiber and a spectrometer, wherein the spectrometer collects reflectance data with a band spacing of a first predetermined length within a first predetermined wavelength range; wherein the first predetermined length is the spectral resolution of the spectrometer. The reflectance data of the outer insulating material sample of the tested insulating component are collected by the spectrometer system and the dihedral reflectance characteristic testing system according to the traversal dihedral reflectance spectrum acquisition method, so as to obtain a dihedral reflectance spectrum library of the outer insulating material sample of the insulating component. The dihedral reflection characteristic testing system includes: a slide rail connecting block, a slide rod connecting block, an upper slip ring, a bottom slip ring, an optical fiber fixator, a light source, and a slide rod; The bottom of the slide rail connecting block is connected to the bottom slip ring, and one side of the slide rail connecting block is connected to the upper slip ring. One side of the slide bar connecting block is connected to the upper slip ring, and the other side of the slide bar connecting block is connected to the slide bar; The fiber optic fixer has one end connected to a slide bar and the other end provided with a ring through which the optical fiber passes, so that the fiber optic fixer can fix the optical fiber. The light source is fixed to the end of the slide bar.

2. The hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to claim 1, characterized in that, The traversal bidirectional reflectance spectral acquisition method includes acquiring the reflectance of the outer insulating material sample of the tested insulating component by simultaneously changing different values ​​of the incident zenith angle, reflected zenith angle, incident-reflected ray azimuth angle, light source distance, and detection distance.

3. The hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to claim 1, characterized in that, The device also includes: a power management module, a halogen lamp light source system, a central processing unit, and a data storage unit; The power management module is used to realize power supply and distribution; The halogen lamp light source system is used to emit halogen lamps with uniform intensity distribution within a predetermined wavelength range, and its brightness and on / off status are controlled by the central processing unit in groups. The central processing unit is connected to the halogen lamp light source system, the hyperspectral image acquisition system, the LiDAR system, the data processing unit, the data storage unit, and the display unit. The central processing unit is used to adjust the switching status and light source intensity of the halogen lamp light source system according to the distance from the target power equipment. The central processing unit is also used to adjust the light source intensity of the halogen lamp light source system according to the distance to the target power equipment during the inspection process. The central processing unit is also used to control the hyperspectral image acquisition system to acquire hyperspectral image data and to control the data processing unit to perform data analysis on the acquired hyperspectral image data. The central processing unit is also used to control the LiDAR system to acquire three-dimensional LiDAR image data and to control the data processing unit to perform data analysis on the acquired LiDAR images. The central processing unit is also used to control the data storage unit to store data, so as to store the evaluation results of the external insulation status of the power equipment under test during the inspection process; The central processing unit is also used to control the display unit to display the assessment results of the external insulation status of the power equipment.

4. The hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to claim 1, characterized in that, In the hyperspectral image acquisition system, spectral image data with more than 100 imaging bands is defined as a hyperspectral image. The system acquires image data with a band interval of a second predetermined length within a second predetermined wavelength range and simultaneously obtains three-dimensional data of reflectance spectrum and image grayscale. The second predetermined length is the spectral resolution of the hyperspectral image acquisition system.

5. The hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to claim 3, characterized in that, The device also includes: a mechanical support module and a rotatable worktable; The mechanical support module is used to provide mechanical support for the visual detection device for the external insulation status of the power equipment; the mechanical support module also includes an adjustment module, which is connected to the halogen lamp light source system, the hyperspectral image acquisition system and the LiDAR system, and adjusts the working angle and height of the halogen lamp light source system, the hyperspectral image acquisition system and the LiDAR system; The rotatable worktable is used to place the target electrical equipment. The rotatable worktable is an electronically controlled device, and its rotation speed is controlled by a motor. The rotatable worktable is connected to the power management module to provide power, and is connected to the central processing unit to achieve controlled rotation.

6. The hyperspectral visualization stereoscopic reconstruction detection device for insulation status of power equipment according to claim 5, characterized in that, The device also includes: a dihedral reflectance spectrum library acquisition module and a power equipment insulation status detection module; The bidirectional reflectance spectral library acquisition module is used to acquire a bidirectional reflectance spectral library of the external insulation material patterns of the insulating component; The power equipment insulation status detection module is used to collect and analyze the reflectance spectrum-image grayscale three-dimensional data and LiDAR image data of the target power equipment, and, in conjunction with the bidirectional reflectance spectrum library, realize the visual diagnosis of the external insulation status of the power equipment through the display unit.

7. The hyperspectral visualization stereoscopic reconstruction detection device for the insulation state of power equipment according to claim 6, characterized in that, The dihedral reflectance spectral library acquisition module performs the following steps to obtain the dihedral reflectance spectral library of the outer insulating material pattern of the insulating component: Step S1: Prepare a typical insulating material sample for a power system, place it at the center of the workbench of the dichroic reflection characteristic testing system, and put the spectrometer system into operation and turn on the light source; Step S2: Reset the dihedral reflectance spectrum acquisition conditions by adjusting the slide rail connecting block, slide rod connecting block, and slide rod; Step S3: Collect the photoelectric response intensity of reflected light from the surface of the insulating material sample using a spectrometer system; Step S4: Adjust one parameter of the bidirectional reflectance spectral acquisition conditions step by step, while keeping the other parameters unchanged; Step S5: Repeat step S4 until the incident zenith angle θ is reached. i The zenith angle is 0°, and the reflected zenith angle is θ. o The incident-reflected ray azimuth angle φ is 180°, and the distance from the light source r is 0°. i The detection range is 1.5 meters. l It is 1.5 meters; Step S6: Adjust the dichroic reflectance spectral acquisition conditions, replace the typical insulation material sample of the power system with a calibration whiteboard, and acquire the photoelectric response intensity of the reflected light from the calibration whiteboard through a spectrometer system; the calibration whiteboard is a calibration whiteboard with 100% reflectivity; Step S7: Close the optical fiber lens cover and collect the photoelectric response intensity in the dark state using a spectrometer system; Step S8: Perform black and white calibration to obtain relative reflectance; Step S9: Prepare insulation material samples with different insulation materials and different insulation fault states through simulation test method, and repeat S1-S8 to obtain a bidirectional reflectance spectral library. After the bidirectional reflectance spectral library is collected, it will be used as a spectral database. Step S10: In order to achieve the calibration of reflectance values ​​under different acquisition conditions, a neural network is established based on the bidirectional reflectance spectrum library, thereby establishing a nonlinear mapping relationship between reflectance, acquisition conditions and standard reflectance fault library.

8. The hyperspectral visualization stereoscopic reconstruction detection device for insulation status of power equipment according to claim 6, characterized in that, The power equipment insulation status detection module performs the following steps to achieve full-angle visualization of the fault status of the target power equipment: Step S11: Place the target power equipment on a rotatable workbench, turn on the halogen lamp light source system to adjust the light intensity, turn on the hyperspectral image acquisition system and the LiDAR system, and adjust the acquisition parameters to ensure clear imaging; Step S12: Using the line connecting the hyperspectral image acquisition system to the target power equipment as the normal, acquire hyperspectral image data and three-dimensional LiDAR image data within the range of -60° to 60° with the normal, according to the preset step. Step S13: Control the rotatable worktable and repeat steps S11-S12 to complete the measurement of the remaining angles; Step S14: Replace the target power equipment with a calibration whiteboard, adjust the acquisition conditions to standard acquisition conditions, acquire the photoelectric response intensity of the reflected light from the calibration whiteboard, and acquire the photoelectric response intensity in the dark state to complete the black and white calibration; Step S15: The relative reflectance of hyperspectral images from different angles is decentered, the covariance matrix and its eigenvalues ​​and eigenvectors are extracted, and the hyperspectral reconstructed image is completed. Step S16: Convert the 3D LiDAR image data to grayscale, select hyperspectral image data as the original image, and perform image matching and fusion; Step S17: Establish a spherical coordinate system with the rotatable stage as the center, and complete the coordinate transformation in the LiDAR image data; Step S18: Determine the acquisition conditions for each pixel and calibrate the relative reflectance in the hyperspectral image to the standard reflectance for measurement; Step S19: Perform spectral matching between the measured standard reflectance of the target power equipment and the standard reflectance fault database to determine the fault status; Step S20: Traverse and judge the fault status of each pixel of the target power equipment, mark it with different colors, and stitch together the diagnostic results of image data from different angles to achieve full-angle visualization of the fault status of the target power equipment.

Images