Method, device, storage medium and system for detecting health state of switch cabinet

Abstract

The invention provides a method, device, storage medium and system for detecting the health state of a switch cabinet, and the method comprises the steps: obtaining first detection information of a target switch cabinet, the detection information at least comprising a thermal imaging image; judging whether the first detection information comprises first partial discharge information or not; under the condition that the first detection information does not include the first partial discharge information, determining the health state of the target switch cabinet according to the first detection information; and under the condition that the first detection information comprises the first partial discharge information, fusing the first partial discharge information and the thermal imaging information by adopting a fusion algorithm to obtain second detection information, and determining the health state of the target switch cabinet according to the second detection information. The problem of low detection efficiency of the health state of the switch cabinet in the prior art is at least solved.

Description

Technical Field

[0001] The present application relates to the field of electrical equipment, and in particular, to a method for detecting the health status of a switch cabinet, an apparatus for detecting the health status of a switch cabinet, a computer-readable storage medium, and a system for detecting the health status of a switch cabinet. Background Art

[0002] GaN-based UV sensors have the advantages of high sensitivity, fast response and strong anti-interference ability, so they are widely used in partial discharge monitoring. This sensor can monitor the ultraviolet intensity around power equipment in real time to determine whether there is partial discharge. Once partial discharge is detected, the sensor will immediately send out an alarm signal to remind the operation and maintenance personnel to deal with it in time to avoid equipment failure. GaN ultraviolet partial discharge monitoring technology is mainly used in fault diagnosis and prevention of power equipment and systems. Partial discharge refers to the discharge phenomenon in a local range of the insulating medium under the action of the electric field in electrical equipment. This phenomenon may damage the insulation performance of the electrical equipment and cause equipment failure. Therefore, monitoring and early warning of partial discharge are of great significance to ensure the safe operation of power equipment. In addition to the power field, GaN ultraviolet partial discharge monitoring technology can also be applied to other fields that need to monitor partial discharge, such as aerospace, petrochemical, etc. In these fields, partial discharge may also cause equipment damage or safety accidents, so effective monitoring and early warning are also needed. In short, GaN ultraviolet partial discharge monitoring technology is an important equipment fault diagnosis and prevention technology with broad application prospects and important practical value.

[0003] When traditional GaN-based UV sensors perform thermal imaging, the response speed is slow, and users are unable to edit and adjust the thermal imaging images, which cannot meet people's needs for GaN-based UV sensors thermal imaging.

[0004] As one of the main electrical equipment commonly used in power supply and distribution network projects, electrical switchgear will inevitably generate heat in various parts or equipment due to various adverse factors during long-term operation, which not only seriously affects the normal operation of power supply and distribution, but also causes major safety accidents due to its heat and continuous temperature increase.

[0005] In switchgear, partial discharge refers to the local electrical discharge phenomenon caused by high voltage due to insulation defects or unevenness. This discharge usually does not immediately cause insulation breakdown of the entire system, but it will produce local high-energy discharge, leading to gradual damage of the insulation material.

[0006] As described above, there is an urgent need for a method that can efficiently detect partial discharge and overheating anomalies in switch cabinets. Summary of the invention

[0007] The main purpose of the present application is to provide a method for detecting the health status of a switch cabinet, an apparatus for detecting the health status of a switch cabinet, a computer-readable storage medium, and a system for detecting the health status of a switch cabinet, so as to at least solve the problem of low efficiency in detecting the health status of a switch cabinet in the prior art.

[0008] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for detecting the health status of a switch cabinet is provided, comprising: obtaining first detection information of a target switch cabinet, the detection information at least including a thermal imaging image; judging whether the first detection information includes first partial discharge information; when the first detection information does not include the first partial discharge information, determining the health status of the target switch cabinet according to the first detection information; when the first detection information includes the first partial discharge information, using a fusion algorithm to fuse the first partial discharge information and the thermal imaging image to obtain second detection information, and determining the health status of the target switch cabinet according to the second detection information.

[0009] Optionally, determining the health status of the target switch cabinet based on the first detection information includes: acquiring original data of multiple switch cabinets, the switch cabinets including the target switch cabinet; filtering the original data according to preset filtering conditions to determine the first detection information, the first detection information being the original data of the target switch cabinet.

[0010] Optionally, determining the health status of the target switch cabinet based on the first detection information includes: segmenting the thermal imaging image to obtain multiple thermal imaging sub-images; analyzing the thermal imaging sub-images using an analysis algorithm to obtain thermal imaging information; judging whether the thermal imaging information includes an abnormal temperature area; if the thermal imaging information includes an abnormal temperature area, determining that the health status of the target switch cabinet is: overheating abnormality.

[0011] Optionally, when the first detection information includes the first partial discharge information, the method further includes: determining a partial discharge image based on the first partial discharge information, wherein the partial discharge image includes ultraviolet light distribution information of the switch cabinet; segmenting the partial discharge image to obtain a plurality of partial discharge electronic images; analyzing the partial discharge electronic image using an analysis algorithm to obtain second partial discharge information of a first target component, wherein the second partial discharge information includes the ultraviolet light distribution information of the first target component, wherein the first target component is a component in the target switch cabinet that generates partial discharge abnormalities.

[0012] Optionally, the analysis algorithm includes a scale-invariant feature transformation algorithm, an accelerated robust feature algorithm, a rotation binary operator and a convolutional neural network.

[0013] Optionally, when the first detection information includes the first partial discharge information, it is determined that the health state of the target switchgear is abnormal discharge.

[0014] According to another aspect of the present application, a device for detecting the health status of a switch cabinet is provided, comprising: an acquisition unit, used to acquire first detection information of a target switch cabinet, the detection information at least comprising a thermal imaging image; a judgment unit, used to judge whether the first detection information includes first partial discharge information; a first determination unit, used to determine the health status of the target switch cabinet according to the first detection information when the first detection information does not include the first partial discharge information; and a second determination unit, used to fuse the first partial discharge information and the thermal imaging image using a fusion algorithm to obtain second detection information when the first detection information includes the first partial discharge information, and determine the health status of the target switch cabinet according to the second detection information.

[0015] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the processing methods for detecting the health status of a switch cabinet.

[0016] According to another aspect of the present application, a system for detecting the health status of a switch cabinet is provided, comprising: one or more processors, a memory, one or more programs, and an ultraviolet sensor, wherein the ultraviolet sensor is connected to the processor to control the ultraviolet sensor to obtain first detection information, the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a processing method for executing any one of the above-described methods for detecting the health status of the switch cabinet.

[0017] Optionally, the ultraviolet sensor is a gallium nitride-based ultraviolet sensor.

[0018] Applying the technical solution of the present application, according to obtaining the first detection information of the target switch cabinet, the detection information at least includes a thermal image; judging whether the first detection information includes the first partial discharge information; in the case where the first detection information does not include the first partial discharge information, determining the health state of the target switch cabinet according to the first detection information; in the case where the first detection information includes the first partial discharge information, using a fusion algorithm to fuse the first partial discharge information and the thermal imaging information to obtain the second detection information after the fusion of the first partial discharge information and the thermal imaging information, and determining the health state of the target switch cabinet according to the second detection information. In the above method, the detected information does not include partial discharge anomalies, and only overheating anomalies are detected for the switch cabinet. After the detector detects the partial discharge anomaly, after confirming the partial discharge anomaly, the overheating anomaly of the switch cabinet is detected and judged, thereby improving the efficiency of partial discharge detection and overheating anomaly detection for the switch cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for detecting a health status of a switch cabinet provided in an embodiment of the present application is shown;

[0021] Figure 2 A schematic flow chart of a method for detecting the health status of a switch cabinet provided according to an embodiment of the present application is shown;

[0022] Figure 3 A schematic flow chart of another method for detecting the health status of a switch cabinet provided according to an embodiment of the present application is shown;

[0023] Figure 4 A schematic diagram of the structure of a fusion system provided according to an embodiment of the present application is shown;

[0024] Figure 5 A schematic structural diagram of a partial discharge detection platform provided according to an embodiment of the present application is shown;

[0025] Figure 6 A schematic flow chart of a method for optimizing the collection material of a probe on a gallium nitride-based semiconductor ultraviolet detector provided according to an embodiment of the present application is shown;

[0026] Figure 7 A schematic structural diagram of an infrared thermal imaging platform provided according to an embodiment of the present application is shown;

[0027] Figure 8 A schematic diagram of an analysis process of an image analysis module provided according to an embodiment of the present application is shown;

[0028] Fig. 9 A schematic diagram of an evaluation process of an image evaluation module provided according to an embodiment of the present application is shown;

[0029] Fig.10 A schematic diagram of the structure of an information fusion platform provided according to an embodiment of the present application is shown;

[0030] Fig.11 A structural block diagram of a device for detecting the health status of a switch cabinet provided according to an embodiment of the present application is shown.

[0031] The above drawings include the following reference numerals:

[0032] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0033] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] As introduced in the background technology, electrical switchgear is one of the main electrical equipment commonly used in power supply and distribution network projects. In the long-term operation, the components or equipment in various parts will inevitably generate heat due to various adverse factors, which not only seriously affects the normal operation of power supply and distribution, but also causes major safety accidents due to its heating and continuous temperature increase. In the switchgear, partial discharge refers to the local electrical discharge phenomenon caused by high voltage due to insulation defects or unevenness. This discharge usually does not immediately cause insulation breakdown of the entire system, but will produce local high-energy discharge, resulting in gradual damage to the insulating material. There is an urgent need for a method that can detect partial discharge and overheating anomalies in switchgear. In order to solve the above technical problems, the present application provides a method for detecting the health status of a switchgear, a device for detecting the health status of a switchgear, a computer-readable storage medium, and a system for detecting the health status of a switchgear.

[0037] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal for detecting the health status of a switch cabinet according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0039] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for detecting the health status of the switch cabinet in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] In this embodiment, a method for detecting the health status of a switch cabinet is provided, which runs on a mobile terminal, a computer terminal or a similar computing device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] Figure 2 1 is a flow chart of a method for detecting the health status of a switch cabinet according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0042] Step S201, obtaining first detection information of a target switch cabinet, where the detection information at least includes a thermal imaging image;

[0043] Specifically, gallium nitride-based ultraviolet sensors have the advantages of high sensitivity, rapid response and strong anti-interference ability. The gallium nitride-based ultraviolet detector acquires information from the switch cabinet, which can increase the accuracy of thermal imaging images and make the temperature detection of the switch cabinet more precise, which is conducive to accurate health judgment of the switch cabinet.

[0044] Among them, the optimized ultraviolet detector can be used to optimize the image acquisition, and the optimization process of the ultraviolet detector includes: step S2011, substrate preparation: Si-NPA is prepared by hydrothermal corrosion method, and Si-NPA is used as substrate; step S2012, nano heterojunction array preparation: GaN / Si-NPA nano heterojunction array is prepared by CVD method by pre-depositing metal Pt as catalyst on it; step S2013, detector element preparation: ITO film and Ag film are deposited on the upper and lower surfaces of GaN / Si-NPA as transparent top electrode and bottom electrode respectively. The gallium nitride-based ultraviolet sensor prepared by the above optimization process is a prototype device of ultraviolet detector with ITO / Si-NPA / sc-Si / Ag structure, which avoids the problem that traditional silicon detectors are easily interfered by visible light signals, and must use matching filters to eliminate the noise generated by visible light. At the same time, there is also a disadvantage of short service life due to easy aging, so as to ensure the accuracy of information collection.

[0045] Step S202, determining whether the first detection information includes first partial discharge information;

[0046] Specifically, when local discharge occurs inside the switch cabinet, ultraviolet light distribution information is generated. These signals are captured by the gallium nitride-based semiconductor ultraviolet detector. The detector converts the captured ultraviolet light distribution information into electrical signals. Therefore, when the first detection information obtained by the gallium nitride-based ultraviolet detector includes ultraviolet radiation signals, it can be determined that the switch has a local discharge anomaly.

[0047] Step S203, when the first detection information does not include the first partial discharge information, determining the health state of the target switchgear according to the first detection information;

[0048] Specifically, the first detection information obtained by the gallium nitride-based semiconductor ultraviolet detector includes a thermal imaging image. Thermal imaging can generate a thermal image and a temperature value through the infrared energy emitted by the switch cabinet when it is working, thereby detecting overheating anomalies of the switch cabinet and further judging the health status of the switch cabinet.

[0049] Step S204, when the first detection information includes the first partial discharge information, a fusion algorithm is used to fuse the first partial discharge information and the thermal imaging information to obtain second detection information, and the health status of the target switch cabinet is determined according to the second detection information.

[0050] Through this embodiment, when the detected information does not include local discharge abnormality, only overheating abnormality detection is performed on the switch cabinet. After the detector detects the local discharge abnormality, the local discharge abnormality is confirmed and the overheating abnormality of the switch cabinet is detected and judged, thereby improving the efficiency of local discharge detection and overheating abnormality detection of the switch cabinet.

[0051] In some optional embodiments, determining the health status of a target switch cabinet according to the first detection information includes: obtaining raw data of a plurality of switch cabinets, the switch cabinets including the target switch cabinet; filtering the raw data by preset filtering conditions to determine the first detection information, the first detection information being the raw data of the target switch cabinet. When the ultraviolet detector detects and obtains detection information of the switch cabinet, a large amount of raw data will be included. Direct transmission and processing of the raw data will consume a large amount of resources. Preprocessing and compressing the raw data output by the ultraviolet detector to obtain the first detection information with a smaller amount of data reduces the data transmission and transmission time, increases the transmission efficiency, and reduces the consumption of resources.

[0052] Specifically, the ultraviolet radiation of the target object is detected by the ultraviolet detector module to obtain raw data, which includes the intensity and wavelength information of the ultraviolet radiation. The preprocessed and compressed data are processed and analyzed. This step ensures the rapid transmission of data and reduces the network burden. In the data processing and analysis module, the data of the visual image is received, processed and analyzed, which includes calculating the temperature and position information of the target object. The parallel processing module processes the data of multiple pixels at the same time to improve the processing efficiency. Finally, the processing and analysis module outputs the temperature and position information of the target object for further use or storage.

[0053] In some optional implementations, determining the health status of the target switch cabinet according to the first detection information includes: segmenting the thermal imaging image to obtain a plurality of thermal imaging sub-images; analyzing the thermal imaging sub-images using an analysis algorithm to obtain thermal imaging information; determining whether the thermal imaging information includes an abnormal temperature region; and determining the health status of the target switch cabinet as overheating abnormality when the thermal imaging information includes an abnormal temperature region. When the first detection information does not include the first partial discharge information, an abnormality judgment is made according to the thermal imaging image, and the switch cabinet is diagnosed with an overheating abnormality.

[0054] In the above implementation, the method of the embodiment of the present application further includes: in the case where the thermal imaging information includes a temperature abnormality area, determining the second temperature information of the first target component according to the thermal imaging information, wherein the first target component is a component in the target switch cabinet that generates a temperature abnormality. By dividing the thermal imaging image into a plurality of thermal imaging sub-images, the temperature of the temperature abnormality area in the target switch cabinet can be more accurately determined, and at the same time, the temperature distribution of each component in the switch cabinet can be confirmed, and whether the first component in the target switch cabinet has an overheating abnormality can be confirmed, further confirming the health status of the switch cabinet.

[0055] Specifically, as an electrical equipment, the external line of the switch cabinet first enters the main control switch in the cabinet, and then enters the branch control switch, and each branch is set according to its needs. Such as instruments, automatic control, motor magnetic switches, various AC contactors, etc., some also have high-voltage and low-voltage room switch cabinets, equipped with high-voltage busbars, such as power plants, etc., and some are also equipped with low-frequency load shedding to protect the main equipment. The main function of the switch cabinet is to open and close, control and protect electrical equipment during the process of power generation, transmission, distribution and power conversion in the power system. There are multiple components in the switch cabinet, mainly composed of circuit breakers, disconnectors, load switches, operating mechanisms, mutual inductors and various protection devices. Each component may have discharge anomalies and overheating anomalies, which will affect the life of the device. Through the thermal images detected by the ultraviolet detector, after confirming that the target switch cabinet has an overheating anomaly, the temperature and position of the first component in the target switch cabinet where the overheating anomaly occurred are further confirmed, thereby improving the efficiency of detecting anomalies, so that maintenance personnel can more accurately confirm the location of the overheating anomaly and perform repairs, while confirming the health status of the switch cabinet and improving the efficiency of abnormality handling.

[0056] In some optional embodiments, a partial discharge image is determined based on the first partial discharge information, wherein the partial discharge image includes ultraviolet light distribution information of the switch cabinet; the partial discharge image is segmented to obtain a plurality of partial discharge electronic images; the partial discharge electronic image is analyzed using an analysis algorithm to obtain second partial discharge information of the first target component, wherein the second partial discharge information includes ultraviolet light distribution information of the first target component, wherein the first target component is a component in the target switch cabinet that produces partial discharge anomalies.

[0057] Specifically, when a partial discharge anomaly occurs in the switch cabinet, ultraviolet light will be generated. The radiation generated by the ultraviolet light, and its distribution information can be used to detect and diagnose the partial discharge anomaly of the switch cabinet. By detecting the distribution information of the ultraviolet light emitted by the switch cabinet, it can help determine the location and degree of the partial discharge anomaly, that is, when the switch cabinet has a partial discharge anomaly, it will generate different degrees of ultraviolet light radiation, and its distribution information will show uneven and concentrated characteristics. By analyzing the distribution information of ultraviolet light, the fault of the switch cabinet can be discovered and repaired in time, which can improve the reliability and safety of the equipment.

[0058] Among them, the second partial discharge information is obtained through the first partial discharge information, which can not only diagnose the target switch cabinet where partial discharge occurs, but also further identify the components in the target switch cabinet where partial discharge abnormalities occur, which can improve the abnormal maintenance rate while ensuring the reliability and safety of the equipment.

[0059] In some optional embodiments, when the first detection information includes first partial discharge information, the method for detecting the health status of the switch cabinet further includes: determining a partial discharge image based on the first partial discharge information, wherein the first partial discharge information includes ultraviolet light distribution information of a first target component, and the first target component is a component that produces partial discharge abnormalities in the target switch cabinet; segmenting the partial discharge image to obtain a plurality of partial discharge electronic images; and analyzing the partial discharge electronic image using an analysis algorithm to obtain first temperature information of the first target component.

[0060] Specifically, when a partial discharge anomaly occurs in the target switch cabinet, that is, the first detection information includes the first partial discharge information, wherein the first partial discharge information is an electrical signal. The electrical signal is converted into a partial discharge image, and the partial discharge image is divided into a plurality of partial discharge electronic images, and the temperature and position of the second component in the target switch cabinet where the partial discharge anomaly occurs are confirmed through the partial discharge electronic image. While confirming that the switch cabinet has a partial discharge anomaly, the component that has caused the partial discharge anomaly is further confirmed, which can help maintenance personnel improve the maintenance efficiency.

[0061] In some optional embodiments, the analysis algorithm includes a scale-invariant feature transformation algorithm, an accelerated robust feature algorithm, a rotation binary operator, and a convolutional neural network.

[0062] Specifically, the Scale-invariant feature transform (SIFT) algorithm is a feature-based image recognition algorithm that extracts feature points from an image and describes and matches them. The core steps of the SIFT algorithm include spatial filtering of the image to reduce the impact of noise, extracting feature points, calculating the direction and intensity of feature points, describing feature points and generating feature descriptors, and finally performing feature matching. The Speeded Up Robust Features (SURF) algorithm is similar to the SIFT algorithm. The SURF algorithm is also used to extract feature points from an image and match them. The SURF algorithm is faster than the SIFT algorithm and is suitable for scenarios that require real-time processing. The Oriented FAST and Rotated BRIEF (ORB) algorithm combines FAST feature point detection and BRIEF descriptors, improves efficiency through rotation invariance and fast calculation, and is suitable for scenarios that require fast feature matching. Convolutional Neural Network With the development of deep learning technology, convolutional neural network has become the main method for image recognition tasks. CNN extracts features from images through convolution, pooling and fully connected layers. It is suitable for large-scale and high-complexity image tasks and accurately identifies the working position and working status of switchgear. The above algorithm can further confirm the location of overheating anomalies and / or partial discharge anomalies and the temperature of the abnormal area, and further confirm the health status of the switchgear.

[0063] In some optional implementations, when the first detection information includes first partial discharge information, it is determined that the health status of the target switchgear is abnormal discharge.

[0064] Specifically, when local discharge occurs inside the switch cabinet, ultraviolet light signals are generated. These signals are captured by the gallium nitride-based semiconductor ultraviolet detector. The detector converts the captured ultraviolet light signals into electrical signals, collects electrical signals and images, and extracts and merges the collected information, so that the measured thermal imaging data can be presented more quickly, the detection time is short, and the detection results are more accurate, meeting people's needs for abnormality confirmation.

[0065] In some optional embodiments, the health status of the target switch cabinet is determined based on the second detection information, including: confirming the first temperature of each component in the target switch cabinet based on the temperature information; judging whether the first temperature is greater than the temperature threshold; when the first temperature is greater than or equal to the temperature threshold, determining the health status of the target switch cabinet as: discharge abnormality and overheating abnormality.

[0066] Specifically, when the gallium nitride-based semiconductor ultraviolet detector detects the first partial discharge information, that is, a partial discharge abnormality occurs in the switch cabinet, the first partial discharge information and the thermal imaging information are fused to obtain the second detection information. The health status of the target switch cabinet is determined through the second detection information, so that personnel can better understand the health status of the switch cabinet and take timely measures to increase the service life of the switch cabinet.

[0067] Among them, the image of the switch cabinet is obtained by a gallium nitride-based semiconductor ultraviolet detector. Specifically, the ultraviolet light distribution information generated is used to realize the discharge phenomenon, which needs to be analyzed. This includes identifying hot spots, cold spots and temperature distribution in the image. By analyzing the image, it is determined whether the switch cabinet has overheating or cooling problems, and the severity of the problem.

[0068] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for detecting the health status of a switch cabinet of the present application will be described in detail below in combination with specific embodiments.

[0069] This embodiment relates to a specific method for detecting the health status of a switch cabinet, such as Figure 3 As shown, the following steps may be included:

[0070] Step S1: partial discharge information collection: the fusion system controls the gallium nitride-based semiconductor ultraviolet detector to collect partial discharge information of the switch cabinet;

[0071] Step S2: thermal imaging of the switch cabinet: the fusion system controls the gallium nitride-based semiconductor ultraviolet detector to collect thermal imaging of the switch cabinet;

[0072] Step S3: Information fusion: The fusion system fuses the switch cabinet partial discharge information and thermal imaging information collected by the GaN-based semiconductor ultraviolet detector to determine the health status of the switch cabinet, specifically whether there is a discharge phenomenon or an overheating phenomenon.

[0073] Specifically, Figure 4 As shown, the above fusion system may include a partial discharge monitoring platform, an infrared thermal imaging platform, an information fusion platform and a communication platform, and the partial discharge monitoring platform and the thermal infrared imaging platform are both connected to the information fusion platform. Among them, the partial discharge monitoring platform controls the gallium nitride-based semiconductor ultraviolet detector in real time to perform partial discharge monitoring on the switch cabinet; the infrared thermal imaging platform controls the gallium nitride-based semiconductor ultraviolet detector in real time to perform infrared thermal imaging on the switch cabinet; the information fusion platform fuses the partial discharge monitoring information and the infrared thermal imaging information to determine the health status of the switch cabinet; the communication platform establishes a control communication connection between the fusion system and the gallium nitride-based semiconductor ultraviolet detector.

[0074] The above-mentioned fusion system is equipped with a partial discharge monitoring platform and an infrared thermal imaging platform, which respectively drive the gallium nitride-based semiconductor ultraviolet detector to collect electrical signals and images. The collected information is extracted and merged through the information fusion platform, so that the measured thermal imaging data can be presented more quickly, the detection time is short, and the detection results are more accurate. Users can edit and adjust the thermal imaging images as needed, meeting people's needs for thermal imaging of gallium nitride-based ultraviolet sensors.

[0075] Furthermore, if Figure 5 As shown, the partial discharge monitoring platform may include a preparation module, a capture conversion module, a processing and analysis module and a first controller, wherein the preparation module, the capture conversion module and the processing and analysis module are all connected to the first controller, and the first controller controls the opening and closing of the gallium nitride-based semiconductor ultraviolet detector in real time; the preparation module prepares and optimizes the collection material of the probe on the gallium nitride-based semiconductor ultraviolet detector; the capture conversion module generates ultraviolet light distribution information when partial discharge occurs inside the switch cabinet, and these signals are captured by the gallium nitride-based semiconductor ultraviolet detector, and the detector converts the captured ultraviolet light distribution information into electrical signals; the processing and analysis module processes, compresses and analyzes the raw data of ultraviolet radiation output by the detector.

[0076] Specifically, first, the raw data output by the ultraviolet detector is preprocessed and compressed using a preprocessing and compression module. The purpose of this step is to reduce the amount of data and transmission time, because the raw data usually contains a large amount of information, and direct transmission and processing will consume a lot of resources. The ultraviolet radiation of the target object is detected by the ultraviolet detector module to obtain the raw data, which includes the intensity and wavelength information of the ultraviolet radiation; then, the preprocessed and compressed data is transmitted to the data processing and analysis module. This step ensures the rapid transmission of data and reduces the network burden. In the data processing and analysis module, the data of the visualization image is received, processed and analyzed, which includes calculating the temperature and position information of the target object. The parallel processing module processes the data of multiple pixels at the same time to improve the processing efficiency; finally, the processing and analysis module outputs the temperature and position information of the target object for further use or storage.

[0077] The preparation module prepares and optimizes the collection materials of the probe on the GaN-based semiconductor UV detector, such as Figure 6As shown, the optimization process may include: first, substrate preparation: controlling the corrosion equipment to prepare Si-NPA by hydrothermal corrosion method, with Si-NPA as the substrate; then, nano-heterojunction array preparation: controlling the chemical vapor deposition (CVD) equipment to pre-deposit metal Pt as a catalyst on the above substrate, and controlling the CVD equipment to prepare the GaN / Si-NPA nano-heterojunction array; finally, detector element preparation: controlling the CVD equipment to deposit ITO film and Ag film on and below GaN / Si-NPA as transparent top electrode and bottom electrode, respectively, to prepare a prototype ultraviolet detector device with a structure of ITO / Si-NPA / sc-Si / Ag. In order to avoid the traditional silicon detector being easily interfered by the visible light signal, a matching filter is used to eliminate the noise generated by the visible light, and there is also a disadvantage of a short service life due to easy aging, so as to ensure the accuracy of information collection.

[0078] Furthermore, if Figure 7 As shown, the infrared thermal imaging platform may include a second controller, an optimization preparation module, a performance test module, an image analysis module and an image evaluation module, wherein the optimization preparation module, the performance test module, the image analysis module and the image evaluation module are all connected to the second controller; the second controller controls the opening and closing of the gallium nitride-based semiconductor ultraviolet detector in real time; the optimization preparation module optimizes the acquisition material of the probe of the gallium nitride-based semiconductor ultraviolet detector, grows a high-quality gallium nitride epitaxial layer on a substrate such as sapphire and silicon, and designs and manufactures gallium nitride-based ultraviolet detectors with specific structures according to application requirements, such as metal-semiconductor-metal (MSM), Schottky and pin structures; the performance test module performs thermal imaging acquisition of the switch cabinet of the gallium nitride-based semiconductor ultraviolet detector; the image analysis module performs image analysis on the thermal infrared image acquired by the gallium nitride-based semiconductor ultraviolet detector; the image evaluation module compresses and crops the thermal infrared image acquired by the gallium nitride-based semiconductor ultraviolet detector and then evaluates the quality of the acquired image.

[0079] Specifically, Figure 8As shown, the analysis process of the image analysis module may include: the first step, image preprocessing: denoising and graying the image to improve the image quality and facilitate subsequent analysis. By using image denoising technology, such as median filtering, the noise interference in the image is reduced to make the image clearer; the second step, image segmentation: according to the characteristics of the infrared image, the image is segmented into different areas for easy identification and analysis; the third step, position image recognition: using image processing technology to identify mutual inductors and three-phase power equipment, a key step for accurate analysis of specific equipment in the image; the fourth step, temperature image recognition: based on the temperature distribution of the equipment, analyze the operating status of the equipment and identify whether there is overheating or other faults; the fifth step, analysis and processing: analyze the identified equipment and temperature data through the numerical value of the temperature image recognition, including calculating the temperature rise and temperature difference parameters, and evaluating the health status of the equipment through the relative temperature difference calculation formula; the sixth step, results and reports: according to the analysis results, interpret the operating status of the equipment, determine whether there are potential problems, and generate a report. The report should contain detailed information, temperature data, fault diagnosis and corresponding suggestions or action plans for the equipment.

[0080] Among them, denoising the image may include reducing noise interference in the image through image denoising technology, such as median filtering, to make the image clearer; dividing the image into different areas according to the characteristics of the infrared image for easy identification and analysis; using image processing technology to identify transformers and three-phase power equipment, which is a key step in accurately analyzing specific equipment in the image, and accurately identifying the location and status of the switch cabinet through specific algorithms and models; analyzing the operating status of the equipment based on the temperature distribution of the equipment, and identifying whether there is overheating or other faults; analyzing the identified equipment and temperature data, including calculating temperature rise and temperature difference parameters, and evaluating the health status of the equipment through the relative temperature difference calculation formula; based on the analysis results, interpreting the operating status of the equipment, judging whether there are potential problems, and generating a report, which should contain detailed information of the equipment, temperature data, fault diagnosis and corresponding suggestions or action plans, and performing image analysis on thermal infrared images collected by gallium nitride-based semiconductor ultraviolet detectors.

[0081] Specifically, Fig. 9As shown, the evaluation process of the image evaluation module may include: the first step, image acquisition: the image of the switch cabinet is acquired through the gallium nitride-based semiconductor ultraviolet detector, specifically the generated ultraviolet light distribution information is used to realize the discharge phenomenon; the second step, image analysis: the image needs to be analyzed, which includes identifying the hot spots, cold spots and temperature distribution in the image, and by analyzing the image, it is determined whether the switch cabinet has overheating or cooling problems, and the severity of the problem; the third step, data interpretation: according to the image analysis results, the data is interpreted, which includes identifying the location, size and shape of abnormal temperature areas, and the temperature difference between these areas and the normally operating switch cabinet, and by comparing the actual temperature with the standard temperature range, it is determined whether the switch cabinet is in a normal working state; the fourth step, evaluation conclusion: based on the results of image analysis and data interpretation, an evaluation conclusion is drawn, which includes determining whether there are potential safety hazards or performance problems, and whether further measures are needed, such as repairing or replacing parts; the fifth step, record and report: a report is generated for the evaluation process and conclusions, and the report includes the equipment used, measurement parameters, image analysis results and data interpretation, and measures, so as to facilitate subsequent tracking and management.

[0082] Furthermore, if Fig.10 As shown, the information fusion platform may include a database, a display module, a user interaction module, an information extraction module, an information merging module and an information proofreading module. The database stores switch cabinet related data, the display module displays the detection information of the GaN-based semiconductor ultraviolet detector, the user interaction module transmits user requirements to the fusion system, the information extraction module extracts information from the switch cabinet partial discharge information collected by the GaN-based semiconductor ultraviolet detector and the thermal imaging image collected by the GaN-based semiconductor ultraviolet detector, the information merging module merges the information collected by the GaN-based semiconductor ultraviolet detector, and the information proofreading module proofreads the information collected by the GaN-based semiconductor ultraviolet detector with the information stored in the database in real time.

[0083] In the present application, the fusion system controls the gallium nitride-based semiconductor ultraviolet detector to collect the partial discharge information of the switch cabinet; Si-NPA is prepared by hydrothermal corrosion method, and Si-NPA is used as the substrate; GaN / Si-NPA nanoheterojunction array is prepared by CVD method by pre-depositing metal Pt as a catalyst thereon; ITO film and Ag film are deposited on and below GaN / Si-NPA as transparent top electrode and bottom electrode respectively, and a prototype ultraviolet detector device with the structure of ITO / Si-NPA / sc-Si / Ag is prepared, and the capture conversion module generates ultraviolet light distribution information when partial discharge occurs inside the switch cabinet. These signals are captured by the gallium nitride-based semiconductor ultraviolet detector, and the detector converts the captured ultraviolet light distribution information into electrical signals The processing and analysis module processes, compresses and analyzes the raw data of the ultraviolet radiation output by the detector. The fusion system controls the gallium nitride-based semiconductor ultraviolet detector to collect thermal imaging of the switch cabinet. The second controller controls the opening and closing of the gallium nitride-based semiconductor ultraviolet detector in real time. The optimization and preparation module optimizes the collection material of the probe of the gallium nitride-based semiconductor ultraviolet detector, grows high-quality gallium nitride epitaxial layers on substrates such as sapphire and silicon, and designs and manufactures gallium nitride-based ultraviolet detectors with specific structures according to application requirements, such as metal-semiconductor-metal (MSM), Schottky or pin structures. The performance test module collects thermal imaging of the switch cabinet with the gallium nitride-based semiconductor ultraviolet detector. The image analysis module denoises and grayscales the image to improve the image quality for subsequent analysis.

[0084] Before the image assessment module starts the assessment, after acquiring the image of the switch cabinet through the gallium nitride-based semiconductor ultraviolet detector, it needs to be analyzed, which includes identifying the hot spots, cold spots and temperature distribution in the image, and judging whether the switch cabinet has overheating or cooling problems and the severity of the problem by analyzing the image; interpreting the data based on the image analysis results, which includes identifying the location, size and shape of abnormal temperature areas, and the temperature difference between these areas and the normally operating switch cabinet, and judging whether the switch cabinet is in normal working condition by comparing the actual temperature with the standard temperature range; drawing assessment conclusions based on the results of image analysis and data interpretation, which includes determining whether there are potential safety hazards or performance problems, and whether further measures are needed, such as repair or replacement of parts; recording the assessment process and conclusions in a report, including the equipment used, measurement parameters, image analysis results and data interpretation, so as to ensure the safety of the switch cabinet. and the suggestions and measures proposed; the report should be detailed and accurate to facilitate subsequent tracking and management, and the thermal infrared images collected by the GaN-based semiconductor ultraviolet detector shall be compressed and cropped to evaluate the quality of the collected images; the fusion system shall fuse the partial discharge information of the switch cabinet and the thermal imaging information collected by the GaN-based semiconductor ultraviolet detector to determine the health status of the switch cabinet, the database shall store the relevant data of the switch cabinet, the display module shall display the detection information of the GaN-based semiconductor ultraviolet detector, the user interaction module shall transmit the user's needs to the fusion system, the information extraction module shall extract the partial discharge information of the switch cabinet collected by the GaN-based semiconductor ultraviolet detector and the thermal imaging image collected by the GaN-based semiconductor ultraviolet detector, the information merging module shall merge the information collected by the GaN-based semiconductor ultraviolet detector, and the information proofreading module shall proofread the information collected by the GaN-based semiconductor ultraviolet detector with the information stored in the database in real time.

[0085] The embodiment of the present application also provides a device for detecting the health status of a switch cabinet. It should be noted that the device for detecting the health status of a switch cabinet in the embodiment of the present application can be used to execute the method for detecting the health status of a switch cabinet provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been described will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0086] The following is an introduction to the device for detecting the health status of a switch cabinet provided in an embodiment of the present application.

[0087] Fig.11 is a schematic diagram of a device for detecting the health status of a switch cabinet according to an embodiment of the present application. Fig.11 As shown, the device comprises:

[0088] An acquisition unit 10 is used to acquire first detection information of a target switch cabinet, where the detection information at least includes a thermal imaging image;

[0089] A judging unit 20, configured to judge whether the first detection information includes first partial discharge information;

[0090] A first determining unit 30, configured to determine a health state of a target switch cabinet according to the first detection information when the first detection information does not include the first partial discharge information;

[0091] The second determination unit 40 is used to fuse the first partial discharge information and the thermal imaging information using a fusion algorithm to obtain second detection information when the first detection information includes the first partial discharge information, and determine the health status of the target switch cabinet according to the second detection information.

[0092] In the above scheme, when the acquisition unit detects the information of the switch cabinet, and the judgment unit determines that the first detection information does not include local discharge abnormality, the first determination unit detects overheating abnormality on the switch cabinet. After the judgment unit determines that the local discharge abnormality is detected in the first detection information, the local discharge abnormality is confirmed and the overheating abnormality of the switch cabinet is detected and judged, thereby improving the efficiency of local discharge detection and overheating abnormality detection of the switch cabinet.

[0093] In one embodiment of the present application, the acquisition unit includes a first acquisition subunit and a first determination subunit, wherein the first acquisition subunit is used to acquire the original data of multiple switch cabinets, the switch cabinets including the target switch cabinet; the first determination subunit is used to filter the original data according to the preset filtering conditions to determine the first detection information, the first detection information is the original data of the target switch cabinet. The original data is preprocessed and compressed, and the first detection information of the target switch cabinet including the abnormality is filtered out, which reduces the data transmission and transmission time, increases the transmission efficiency, and reduces the resource consumption.

[0094] In the actual application process, in one embodiment of the present application, the first determination unit includes a first segmentation unit, a first analysis unit, a first judgment subunit and a second determination subunit, wherein the first segmentation unit is used to analyze the thermal imaging sub-image using an analysis algorithm to obtain thermal imaging information; the first analysis unit is used to analyze the thermal imaging sub-image using an analysis algorithm to obtain thermal imaging information; the first judgment subunit is used to determine whether the thermal imaging information includes an abnormal temperature area; the second determination subunit is used to determine that the health status of the target switch cabinet is: overheating abnormality when the thermal imaging information includes the abnormal temperature area. By segmenting the thermal imaging image into multiple thermal imaging sub-images, the temperature of the abnormal temperature area in the target switch cabinet can be more accurately determined, and at the same time, the temperature distribution of each component in the switch cabinet can be confirmed, and whether the first component in the target switch cabinet has an abnormal overheating abnormality can be confirmed, further confirming the health status of the switch cabinet.

[0095] In the case where the first detection information includes the first partial discharge information, the first determination unit includes a third determination subunit, a second segmentation unit and a second analysis unit, wherein the third determination subunit is used to determine the partial discharge image according to the first partial discharge information, wherein the partial discharge image includes the ultraviolet light distribution information of the switch cabinet; the second segmentation unit is used to segment the partial discharge image to obtain a plurality of partial discharge electronic images; the second analysis unit is used to analyze the partial discharge electronic image using an analysis algorithm to obtain the second partial discharge information of the first target component, wherein the second partial discharge information includes the ultraviolet light distribution information of the first target component, wherein the first target component is the component that generates partial discharge abnormality in the target switch cabinet. The temperature and position of the second component that has generated partial discharge abnormality in the target switch cabinet are confirmed by the partial discharge electronic image, and while confirming that the switch cabinet has generated partial discharge abnormality, the component that generated partial discharge abnormality is further confirmed, which can help the maintenance personnel improve the maintenance efficiency.

[0096] In the above embodiment, the analysis algorithm includes a scale-invariant feature transformation algorithm, an accelerated robust feature algorithm, a rotation binary operator and a convolutional neural network.

[0097] In another embodiment of the present application, the second determination unit includes a fourth determination subunit, wherein the fourth determination subunit is used to determine that the health state of the target switch cabinet is abnormal discharge when the first detection information includes the first partial discharge information. The first partial discharge information and the thermal imaging information are fused to obtain the second detection information, and the health state of the target switch cabinet is determined by the second detection information, so that personnel can better understand the health state of the switch cabinet and take timely measures to increase the service life of the switch cabinet.

[0098] The device for detecting the health status of a switch cabinet includes a processor and a memory, wherein the acquisition unit, the judgment unit, the first determination unit, the second determination unit, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0099] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the efficiency of partial discharge detection and overheating abnormality detection of the switch cabinet can be improved by adjusting the kernel parameters.

[0100] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0101] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, a device where the computer-readable storage medium is located is controlled to execute a method for detecting a health status of a switch cabinet.

[0102] Specifically, the method for detecting the health status of the switch cabinet includes:

[0103] Step S201, obtaining first detection information of a target switch cabinet, where the detection information at least includes a thermal imaging image;

[0104] Specifically, gallium nitride-based ultraviolet sensors have the advantages of high sensitivity, rapid response and strong anti-interference ability. The gallium nitride-based ultraviolet detector acquires information from the switch cabinet, which can increase the accuracy of thermal imaging images and make the temperature detection of the switch cabinet more precise, which is conducive to accurate health judgment of the switch cabinet.

[0105] Among them, the optimized ultraviolet detector can be used to optimize the image acquisition, and the optimization process of the ultraviolet detector is as follows: step S2011, substrate preparation: Si-NPA is prepared by hydrothermal etching method, and Si-NPA is used as substrate; step S2012, nano heterojunction array preparation: GaN / Si-NPA nano heterojunction array is prepared by CVD method by pre-depositing metal Pt as catalyst on it; step S2013, detector element preparation: ITO film and Ag film are deposited on the upper and lower surfaces of GaN / Si-NPA as transparent top electrode and bottom electrode respectively. The gallium nitride-based ultraviolet sensor prepared by the above optimization process is a prototype ultraviolet detector device with an ITO / Si-NPA / sc-Si / Ag structure, which avoids the problem that the traditional silicon detector is easily interfered by visible light signals, and must use a matching filter to eliminate the noise generated by visible light. At the same time, there is also a disadvantage of short service life due to easy aging, so as to ensure the accuracy of information collection.

[0106] Step S202, determining whether the first detection information includes first partial discharge information;

[0107] Specifically, when local discharge occurs inside the switch cabinet, ultraviolet light distribution information is generated. These signals are captured by the gallium nitride-based semiconductor ultraviolet detector. The detector converts the captured ultraviolet light distribution information into electrical signals. Therefore, when the first detection information obtained by the gallium nitride-based ultraviolet detector includes ultraviolet radiation signals, it can be determined that the switch has a local discharge anomaly.

[0108] Step S203, when the first detection information does not include the first partial discharge information, determining the health state of the target switchgear according to the first detection information;

[0109] Specifically, the first detection information obtained by the gallium nitride-based semiconductor ultraviolet detector includes a thermal imaging image. Thermal imaging can generate a thermal image and a temperature value through the infrared energy emitted by the switch cabinet when it is working, thereby detecting overheating anomalies of the switch cabinet and further judging the health status of the switch cabinet.

[0110] Step S204, when the first detection information includes the first partial discharge information, a fusion algorithm is used to fuse the first partial discharge information and the thermal imaging information to obtain second detection information, and the health status of the target switch cabinet is determined according to the second detection information.

[0111] Optionally, determining the health status of the target switch cabinet based on the first detection information includes: obtaining original data of multiple switch cabinets, the switch cabinets including the target switch cabinet; filtering the original data according to preset filtering conditions to determine the first detection information, the first detection information being the original data of the target switch cabinet.

[0112] Optionally, determining the health status of the target switch cabinet based on the first detection information includes: segmenting the thermal imaging image to obtain multiple thermal imaging sub-images; analyzing the thermal imaging sub-images using an analysis algorithm to obtain thermal imaging information; judging whether the thermal imaging information includes an abnormal temperature area; if the thermal imaging information includes an abnormal temperature area, determining the health status of the target switch cabinet as: overheating abnormality.

[0113] Optionally, when the first detection information includes first partial discharge information, the method further includes: determining a partial discharge image based on the first partial discharge information, wherein the partial discharge image includes ultraviolet light distribution information of the switch cabinet; segmenting the partial discharge image to obtain a plurality of partial discharge electronic images; analyzing the partial discharge electronic image using an analysis algorithm to obtain second partial discharge information of the first target component, the second partial discharge information includes ultraviolet light distribution information of the first target component, wherein the first target component is a component in the target switch cabinet that generates partial discharge anomalies.

[0114] Optionally, the analysis algorithms include a scale-invariant feature transformation algorithm, an accelerated robust feature algorithm, a rotation binary operator, and a convolutional neural network.

[0115] Optionally, when the first detection information includes first partial discharge information, it is determined that the health state of the target switchgear is abnormal discharge.

[0116] An embodiment of the present invention provides a system for detecting the health status of a switch cabinet, comprising: one or more processors, a memory, one or more programs, and an ultraviolet sensor, wherein the ultraviolet sensor is connected to the processor to control the ultraviolet sensor to obtain first detection information, and the one or more programs are stored in the memory and configured to be executed by the one or more processors, wherein the method for detecting the health status of the switch cabinet is executed when the program is running.

[0117] Specifically, the method for detecting the health status of the switch cabinet includes:

[0118] Step S201, obtaining first detection information of a target switch cabinet, where the detection information at least includes a thermal imaging image;

[0119] Specifically, gallium nitride-based ultraviolet sensors have the advantages of high sensitivity, rapid response and strong anti-interference ability. The gallium nitride-based ultraviolet detector acquires information from the switch cabinet, which can increase the accuracy of thermal imaging images and make the temperature detection of the switch cabinet more precise, which is conducive to accurate health judgment of the switch cabinet.

[0120] Among them, the optimized ultraviolet detector can be used to optimize the image acquisition, and the optimization process of the ultraviolet detector is as follows: step S2011, substrate preparation: Si-NPA is prepared by hydrothermal etching method, and Si-NPA is used as substrate; step S2012, nano heterojunction array preparation: GaN / Si-NPA nano heterojunction array is prepared by CVD method by pre-depositing metal Pt as catalyst on it; step S2013, detector element preparation: ITO film and Ag film are deposited on the upper and lower surfaces of GaN / Si-NPA as transparent top electrode and bottom electrode respectively. The gallium nitride-based ultraviolet sensor prepared by the above optimization process is a prototype ultraviolet detector device with an ITO / Si-NPA / sc-Si / Ag structure, which avoids the problem that the traditional silicon detector is easily interfered by visible light signals, and must use a matching filter to eliminate the noise generated by visible light. At the same time, there is also a disadvantage of short service life due to easy aging, so as to ensure the accuracy of information collection.

[0121] Step S202, determining whether the first detection information includes first partial discharge information;

[0122] Specifically, when local discharge occurs inside the switch cabinet, ultraviolet light distribution information is generated. These signals are captured by the gallium nitride-based semiconductor ultraviolet detector. The detector converts the captured ultraviolet light distribution information into electrical signals. Therefore, when the first detection information obtained by the gallium nitride-based ultraviolet detector includes ultraviolet radiation signals, it can be determined that the switch has a local discharge anomaly.

[0123] Step S203, when the first detection information does not include the first partial discharge information, determining the health state of the target switchgear according to the first detection information;

[0124] Specifically, the first detection information obtained by the gallium nitride-based semiconductor ultraviolet detector includes a thermal imaging image. Thermal imaging can generate a thermal image and a temperature value through the infrared energy emitted by the switch cabinet when it is working, thereby detecting overheating anomalies of the switch cabinet and further judging the health status of the switch cabinet.

[0125] Step S204, when the first detection information includes the first partial discharge information, a fusion algorithm is used to fuse the first partial discharge information and the thermal imaging information to obtain second detection information, and the health status of the target switch cabinet is determined according to the second detection information.

[0126] Optionally, determining the health status of the target switch cabinet based on the first detection information includes: obtaining original data of multiple switch cabinets, the switch cabinets including the target switch cabinet; filtering the original data according to preset filtering conditions to determine the first detection information, the first detection information being the original data of the target switch cabinet.

[0127] Optionally, in the case where the first detection information includes the first partial discharge information, the method includes: segmenting the thermal imaging image to obtain a plurality of thermal imaging sub-images; analyzing the thermal imaging sub-images using an analysis algorithm to obtain thermal imaging information; determining whether the thermal imaging information includes an abnormal temperature area; and in the case where the thermal imaging information includes an abnormal temperature area, determining that the health status of the target switch cabinet is: abnormal overheating.

[0128] Optionally, when the first detection information includes first partial discharge information, the method further includes: determining a partial discharge image based on the first partial discharge information, wherein the partial discharge image includes ultraviolet light distribution information of the switch cabinet; segmenting the partial discharge image to obtain a plurality of partial discharge electronic images; analyzing the partial discharge electronic image using an analysis algorithm to obtain second partial discharge information of the first target component, the second partial discharge information includes ultraviolet light distribution information of the first target component, wherein the first target component is a component in the target switch cabinet that generates partial discharge anomalies.

[0129] Optionally, the analysis algorithms include a scale-invariant feature transformation algorithm, an accelerated robust feature algorithm, a rotation binary operator, and a convolutional neural network.

[0130] Optionally, when the first detection information includes first partial discharge information, it is determined that the health state of the target switchgear is abnormal discharge.

[0131] Optionally, the ultraviolet sensor is a gallium nitride-based ultraviolet sensor.

[0132] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0133] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0134] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0137] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0138] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0139] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0140] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0141] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0142] 1) A method for detecting the health status of a switch cabinet of the present application, based on obtaining first detection information of a target switch cabinet, the detection information at least includes a thermal image; judging whether the first detection information includes the first partial discharge information; in the case where the first detection information does not include the first partial discharge information, determining the health status of the target switch cabinet according to the first detection information; in the case where the first detection information includes the first partial discharge information, using a fusion algorithm to fuse the first partial discharge information and the thermal imaging information to obtain second detection information after the fusion of the first partial discharge information and the thermal imaging information, and determining the health status of the target switch cabinet according to the second detection information. In the above method, the detected information does not include partial discharge anomalies, and only overheating anomalies are detected for the switch cabinet. After the detector detects the partial discharge anomaly, after confirming the partial discharge anomaly, the overheating anomaly of the switch cabinet is detected and judged, thereby improving the efficiency of partial discharge detection and overheating anomaly detection for the switch cabinet.

[0143] 2) A device for detecting the health status of a switch cabinet of the present application comprises: an acquisition unit, which is used to acquire first detection information of a target switch cabinet, wherein the detection information at least includes a thermal imaging image; a judgment unit, which is used to judge whether the first detection information includes the first partial discharge information; a first determination unit, which is used to determine the health status of the target switch cabinet according to the first detection information when the first detection information does not include the first partial discharge information; and a second determination unit, which is used to fuse the first partial discharge information and the thermal imaging information using a fusion algorithm when the first detection information includes the first partial discharge information, to obtain the second detection information after the first partial discharge information and the thermal imaging information are fused, and to determine the health status of the target switch cabinet according to the second detection information. When the acquisition unit detects the information of the switch cabinet, and the judgment unit judges that the first detection information does not include the partial discharge abnormality, the first determination unit performs overheating abnormality detection on the switch cabinet, and after the judgment unit judges that the partial discharge abnormality is detected in the first detection information, the judgment unit detects and judges the overheating abnormality of the switch cabinet after confirming the partial discharge abnormality, thereby improving the efficiency of partial discharge detection and overheating abnormality detection on the switch cabinet.

[0144] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting the health status of a switch cabinet, characterized in that: include: Acquire first detection information of a target switch cabinet, wherein the first detection information at least includes a thermal imaging image; determining whether the first detection information includes first partial discharge information; In a case where the first detection information does not include the first partial discharge information, determining a health state of the target switchgear according to the first detection information; In the case where the first detection information includes the first partial discharge information, a fusion algorithm is used to fuse the first partial discharge information and the thermal imaging image to obtain second detection information, and the health status of the target switchgear is determined based on the second detection information.

2. The method according to claim 1, characterized in that Determining the health status of the target switch cabinet according to the first detection information includes: Acquire original data of a plurality of switch cabinets, wherein the switch cabinets include the target switch cabinet; The original data is screened by a preset screening condition to determine the first detection information, where the first detection information is the original data of the target switch cabinet.

3. The method according to claim 1, characterized in that Determining the health status of the target switch cabinet according to the first detection information includes: Segmenting the thermal imaging image to obtain a plurality of thermal imaging sub-images; Analyzing the thermal imaging sub-image using an analysis algorithm to obtain thermal imaging information; Determining whether the thermal imaging information includes an abnormal temperature area; In the case where the thermal imaging information includes an abnormal temperature area, the health state of the target switch cabinet is determined to be: abnormal overheating.

4. The method according to claim 1, characterized in that In a case where the first detection information includes the first partial discharge information, the method further includes: Determining a partial discharge image according to the first partial discharge information, wherein the partial discharge image includes ultraviolet light distribution information of the switch cabinet; Segmenting the partial discharge image to obtain a plurality of partial discharge sub-images; The partial discharge electronic image is analyzed by using an analysis algorithm to obtain second partial discharge information of the first target component, wherein the second partial discharge information includes ultraviolet light distribution information of the first target component, wherein the first target component is a component in the target switch cabinet that generates partial discharge anomalies.

5. The method according to claim 3 or 4, characterized in that: The analysis algorithms include a scale-invariant feature transformation algorithm, an accelerated robust feature algorithm, a rotational binary operator, and a convolutional neural network.

6. The method according to claim 1, characterized in that In a case where the first detection information includes the first partial discharge information, it is determined that the health state of the target switchgear is abnormal discharge.

7. A device for detecting the health status of a switch cabinet, characterized in that: include: An acquisition unit, configured to acquire first detection information of a target switch cabinet, wherein the first detection information at least includes a thermal imaging image; A judging unit, configured to judge whether the first detection information includes first partial discharge information; a first determining unit, configured to determine a health state of the target switchgear according to the first detection information when the first detection information does not include the first partial discharge information; The second determination unit is used to fuse the first partial discharge information and the thermal imaging image using a fusion algorithm to obtain second detection information when the first detection information includes the first partial discharge information, and determine the health status of the target switchgear according to the second detection information.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for detecting the health status of a switch cabinet according to any one of claims 1 to 6.

9. A system for detecting the health status of a switch cabinet, characterized in that: include: One or more processors, a memory, one or more programs, and an ultraviolet sensor, wherein the ultraviolet sensor is connected to the processor to control the ultraviolet sensor to obtain first detection information, the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the health status of a switch cabinet as described in any one of claims 1 to 6.

10. The system according to claim 9, characterized in that The ultraviolet sensor is a gallium nitride-based ultraviolet sensor.

Images