Electrical hidden danger detection method and device and readable storage medium

Abstract

The invention provides an electrical hidden danger detection method and device and a readable storage medium, and relates to the technical field of electrical safety, and the method comprises the steps: detecting a plurality of parameters in an electrical hidden danger generation process through a duplex detection device disposed in each of a plurality of regions in a preset space, and carrying out the analog-to-digital conversion; fourier transform is carried out on the plurality of parameters after analog-to-digital conversion, and a frequency spectrum characteristic value of each parameter in a frequency domain is extracted; comparing and analyzing the frequency spectrum characteristic value corresponding to each parameter with a pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs by using AI to obtain an electrical hidden danger identification result corresponding to each parameter; and determining a final electrical hidden danger identification result of the corresponding area according to the electrical hidden danger identification result corresponding to each parameter. According to the method, the device and the readable storage medium, the problems that an existing electrical hidden danger detection method has certain limitation, hidden dangers cannot be found in time in the early stage, and the source of the hidden dangers cannot be accurately positioned can be solved.

Description

Technical Field

[0001] The present invention relates to the field of electrical safety technology, and in particular to a method and device for detecting electrical hidden dangers and a readable storage medium. Background Art

[0002] Communication buildings and data centers are very important electrical loads because they are equipped with a large number of communication and electronic equipment. In order to ensure that these important loads can operate normally without power outages, a large and stable power supply system must be configured to supply power to them. Common power supply systems are DC-48V system, 240V system, 336V system, and the most common AC 220V system protected by UPS (Uninterruptible Power Supply) equipment.

[0003] Communication power supply systems, especially in the power distribution link, often have problems due to power cable virtual connection, unreliable connection, intermittent arcing and eventually burning. This kind of failure is very likely to occur. We collectively refer to these as electrical hazards. The accident scene of existing electrical hazards is shown in the following figure Figure 1 and 2 As shown, its main characteristics are concealment, unpredictability and difficulty in positioning.

[0004] Therefore, the existing electrical hidden danger detection methods have certain limitations, and often cannot detect hidden dangers in time at an early stage, and cannot accurately locate the source of the hidden danger. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method, device and readable storage medium for detecting electrical hidden dangers in view of the above-mentioned shortcomings of the prior art, so as to solve the problem that the existing electrical hidden danger detection methods have certain limitations, often fail to detect hidden dangers in time at an early stage, and cannot accurately locate the source of hidden dangers.

[0006] In a first aspect, the present invention provides a method for detecting electrical hazards.

[0007] include:

[0008] Multiple parameters in the process of electrical hidden dangers occurring are detected by using a complex detection device arranged in each of multiple areas of a preset space, and analog-to-digital conversion is performed; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers occurring;

[0009] Perform Fourier transform on the multiple parameters after analog-to-digital conversion to extract the frequency spectrum characteristic value of each parameter in the frequency domain;

[0010] Artificial intelligence AI is used to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs, and the electrical hidden danger identification result corresponding to each parameter is obtained;

[0011] Determine the final electrical hazard identification result of the corresponding area according to the electrical hazard identification result corresponding to each parameter;

[0012] In response to the final electrical hazard identification result of a certain area being that there is an electrical hazard, an early warning signal is issued, and the specific location of the electrical hazard is determined according to the address code of the certain area.

[0013] Furthermore, before detecting multiple parameters during the occurrence of electrical hazards by using a complex detection device arranged in each of multiple areas of the preset space and performing analog-to-digital conversion, the method further includes:

[0014] Dividing the preset space into a plurality of areas, wherein each area has a unique address code;

[0015] The multiple detection device is arranged in each of the areas.

[0016] Furthermore, dividing the preset space into a plurality of areas specifically includes:

[0017] Divide the preset space into a grid matrix; or,

[0018] The preset space is divided into a honeycomb structure.

[0019] Furthermore, the complex detection device is formed by connecting a plurality of detection modules and their corresponding analog-to-digital conversion modules in parallel, and each detection module is used to detect one parameter among the plurality of parameters;

[0020] The multiple parameters include gas and at least one of the following: light, sound, and electromagnetic waves.

[0021] Furthermore, the method further comprises:

[0022] The number of the multiple parameters is adjusted by increasing or decreasing the detection modules and the corresponding analog-to-digital conversion modules in the complex detection device.

[0023] Furthermore, the artificial intelligence AI is used to compare and analyze the spectrum characteristic value corresponding to each parameter with the pre-stored spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs, and the electrical hidden danger identification result corresponding to each parameter is obtained, which specifically includes:

[0024] AI is used to perform a similarity comparison analysis between the frequency spectrum characteristic value corresponding to each parameter and the frequency spectrum characteristic value of the corresponding parameter when the pre-stored electrical hazard occurs to obtain a similarity result. If the similarity result is greater than or equal to a preset similarity threshold, the electrical hazard identification result corresponding to the parameter is judged to be the existence of an electrical hazard; otherwise, the electrical hazard identification result corresponding to the parameter is judged to be the absence of an electrical hazard.

[0025] Further, the final electrical hazard identification result of the corresponding area is determined according to the electrical hazard identification result corresponding to each parameter, specifically including:

[0026] If the electrical hazard identification result corresponding to any one of the multiple parameters is that an electrical hazard exists, then determining that the final electrical hazard identification result of the corresponding area is that an electrical hazard exists; or,

[0027] If the number of parameters whose identification results indicate that electrical hazards exist among the multiple parameters exceeds a preset number threshold, then the final electrical hazard identification result of the corresponding area is determined to be that electrical hazards exist; or,

[0028] If the identification results of all the parameters in the multiple parameters are that there is an electrical hazard, then the final electrical hazard identification result of the corresponding area is determined to be that there is an electrical hazard.

[0029] In a second aspect, the present invention provides a device for detecting electrical hidden dangers, the device comprising:

[0030] A parameter detection conversion module, used to detect multiple parameters in the process of electrical hidden dangers through a complex detection device arranged in each of multiple areas of a preset space, and perform analog-to-digital conversion; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers;

[0031] A Fourier transform module, connected to the parameter detection conversion module, is used to perform Fourier transform on the multiple parameters after analog-to-digital conversion to extract the frequency spectrum characteristic value of each parameter in the frequency domain;

[0032] A comparison and analysis module, connected to the Fourier transform module, is used to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs by using artificial intelligence AI, so as to obtain the electrical hidden danger identification result corresponding to each parameter;

[0033] An identification result determination module, connected to the comparison and analysis module, is used to determine the final electrical hazard identification result of the corresponding area according to the electrical hazard identification result corresponding to each parameter;

[0034] The early warning and positioning module is connected to the identification result determination module, and is used to respond to the final electrical hazard identification result of a certain area as the existence of electrical hazards, send out an early warning signal, and determine the specific location of the electrical hazard according to the address code of the certain area.

[0035] In a third aspect, the present invention provides an electrical hazard detection device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the electrical hazard detection method described in the first aspect.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting electrical hazards described in the first aspect above is implemented.

[0037] The present invention provides a detection method, device and readable storage medium for electrical hidden dangers. First, multiple parameters in the process of electrical hidden dangers are detected by a complex detection device arranged in each of multiple areas in a preset space, and analog-to-digital conversion is performed; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers; then the multiple parameters after analog-to-digital conversion are Fourier transformed to extract the spectrum characteristic value of each parameter in the frequency domain; and artificial intelligence AI is used to compare and analyze the spectrum characteristic value corresponding to each parameter with the spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs, so as to obtain the electrical hidden danger identification result corresponding to each parameter; then the final electrical hidden danger identification result of the corresponding area is determined according to the electrical hidden danger identification result corresponding to each parameter; finally, in response to the final electrical hidden danger identification result of a certain area being that there is an electrical hidden danger, an early warning signal is issued, and the specific location of the electrical hidden danger is determined according to the address code of the certain area. The present invention uses complex detection devices arranged in multiple areas in a preset space to monitor multiple physical and chemical parameters in the process of electrical hidden dangers in real time, and performs analog-to-digital conversion and Fourier transform to extract spectrum characteristic values, and then uses artificial intelligence AI to compare and analyze with the pre-stored spectrum characteristic values, so that electrical hidden dangers can be discovered in time. In addition, the electrical hidden danger situation in the corresponding area is comprehensively determined based on the identification results of each parameter, and a warning signal is issued when a hidden danger is confirmed. The source of the hidden danger is accurately located in combination with the address code, which significantly improves the early detection and accurate positioning capabilities of electrical hidden danger detection. It solves the problem that the existing electrical hidden danger detection methods have certain limitations, often fail to detect hidden dangers in time at an early stage, and fail to accurately locate the source of hidden dangers. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 For existing electrical hazards accident site Figure 1 ;

[0039] Figure 2 For existing electrical hazards accident site Figure 2 ;

[0040] Figure 3 This is a flow chart of a method for detecting electrical hidden dangers according to Embodiment 1 of the present invention;

[0041] Figure 4 A schematic diagram of a method for detecting electrical hazards according to an embodiment of the present invention;

[0042] Figure 5 This is a schematic diagram of the structure of a device for detecting electrical hidden dangers according to Embodiment 2 of the present invention;

[0043] Figure 6 This is a schematic diagram of the structure of an electrical hazard detection device according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solution of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0045] It should be understood that the specific embodiments and drawings described herein are only used to explain the present invention rather than to limit the present invention.

[0046] It can be understood that, in the absence of conflict, the various embodiments of the present invention and the various features in the embodiments can be combined with each other.

[0047] It can be understood that, for the convenience of description, the drawings of the present invention only show the parts related to the present invention, while the parts irrelevant to the present invention are not shown in the drawings.

[0048] It can be understood that each unit and module involved in the embodiments of the present invention may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.

[0049] It can be understood that the terms "first", "second", etc. in the embodiments of the present invention are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0050] It can be understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in an order different from that marked in the drawings.

[0051] It is understood that the flowcharts and block diagrams of the present invention illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present invention. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or may be implemented by a combination of hardware and computer instructions.

[0052] It can be understood that the units and modules involved in the embodiments of the present invention can be implemented by software or hardware. For example, the units and modules can be located in a processor.

[0053] Application Overview

[0054] At present, the existing electrical hidden danger detection methods have certain limitations:

[0055] 1) Failure to detect hidden dangers in the early stages:

[0056] At present, the detection methods for electrical hidden dangers are at a stage of helplessness: that is, when it is still at the stage of electrical hidden dangers, it is currently impossible to effectively predict and warn;

[0057] Only when electrical hidden dangers develop over a certain period of time and not too short a period of time, will they eventually evolve and mutate into electrical faults! Because the physical phenomenon of the fault is particularly obvious: generally the current suddenly increases sharply, the voltage decreases, etc. Therefore, through the monitoring of physical quantities such as current and voltage, measures can be taken in time to cut off the fault; this type of technology is generally called electrical safety and protection technology.

[0058] 2) Unable to accurately locate the source of hidden dangers:

[0059] After a hidden danger occurs, there are always certain characteristics and phenomena. However, due to the limitations of the current technical level, the specific location of the hidden danger cannot be accurately located, resulting in the inability to quickly deal with the hidden danger after it occurs. For example, when a cable has a partial discharge at the joint (commonly known as sparking), a short high-temperature arc burns the insulating material, which will emit a pungent smell. It is common sense that you can smell a distinct burnt smell.

[0060] However, because it is not easy to locate abnormal odors in a space, the simple special odor detection method is not practical.

[0061] In response to the above technical problems, the concept of this application is to provide a detection method, device and readable storage medium for electrical hidden dangers. Through the duplex detection devices arranged in multiple areas of the preset space, multiple physical and chemical parameters in the process of electrical hidden dangers are monitored in real time, and analog-to-digital conversion and Fourier transform are performed to extract spectrum feature values, and then artificial intelligence AI is used to compare and analyze the pre-stored spectrum feature values, so that electrical hidden dangers can be discovered in time. In addition, the electrical hidden danger situation in the corresponding area is comprehensively determined based on the identification results of each parameter, and a warning signal is issued when the hidden danger is confirmed. The source of the hidden danger is accurately located in combination with the address code, which significantly improves the early detection ability and accurate positioning ability of electrical hidden danger detection.

[0062] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0063] Embodiment 1:

[0064] This embodiment provides a method for detecting electrical hazards. Figure 3 As shown, the method includes:

[0065] Step S101: Detect multiple parameters during the occurrence of electrical hazards through a complex detection device arranged in each of multiple areas of a preset space, and perform analog-to-digital conversion; wherein the multiple parameters involve physical quantities and chemical quantities during the occurrence of electrical hazards.

[0066] In this embodiment, the preset space refers to a limited space where electrical facilities are located, such as a machine room or a power distribution room. The preset space includes multiple areas, each of which is arranged with a complex detection device. Since electrical hazards have certain physical and chemical characteristics, multiple parameters in the process of electrical hazards are detected by the arranged complex detection devices, and analog-to-digital conversion is performed. These parameters involve physical quantities and chemical quantities in the process of electrical hazards.

[0067] Optionally, before detecting multiple parameters during the occurrence of electrical hazards by using a complex detection device arranged in each of multiple areas of the preset space and performing analog-to-digital conversion, the method further includes:

[0068] Dividing the preset space into a plurality of areas, wherein each area has a unique address code;

[0069] The multiple detection device is arranged in each of the areas.

[0070] In this embodiment, in order to achieve accurate location determination, each area has a unique address code. When an electrical hazard occurs in a certain area, the specific location of the hazard can be immediately determined by corresponding to the address code.

[0071] Optionally, dividing the preset space into a plurality of areas specifically includes:

[0072] Divide the preset space into a grid matrix; or,

[0073] The preset space is divided into a honeycomb structure.

[0074] In this embodiment, the preset space can be divided into a grid matrix or a honeycomb structure. For example, the preset space is divided into a grid matrix, and each grid has a unique address code (i.e., a unique address code). Through the unique code of the grid matrix, it can be confirmed which grid matrix has an electrical hazard, so as to achieve accurate location judgment.

[0075] Optionally, the complex detection device is formed by connecting a plurality of detection modules and their corresponding analog-to-digital conversion modules in parallel, and each detection module is used to detect one parameter among the plurality of parameters;

[0076] The multiple parameters include gas and at least one of the following: light, sound, and electromagnetic waves.

[0077] In this embodiment, the multiple parameters preferably include gas, light, sound and electromagnetic waves. The complex detection device is composed of multiple detection modules and their corresponding analog-to-digital conversion modules in parallel. For example, the complex detection device may include an optical detection module and its corresponding analog-to-digital conversion module, an acoustic detection module and its corresponding analog-to-digital conversion module, an electromagnetic detection module and its corresponding analog-to-digital conversion module, a gas detection module and its corresponding analog-to-digital conversion module, and they are connected in parallel. Each detection module is specifically used to detect a specific parameter.

[0078] Optionally, the method further comprises:

[0079] The number of the multiple parameters is adjusted by increasing or decreasing the detection modules and the corresponding analog-to-digital conversion modules in the complex detection device.

[0080] In this embodiment, the complex detection device adopts an open structure, which can flexibly add new detection means and functional modules.

[0081] Step S102: Perform Fourier transform on the multiple parameters after analog-to-digital conversion to extract the frequency spectrum feature value of each parameter in the frequency domain.

[0082] In this embodiment, the key indicators extracted by the Fourier analysis method include characteristic values ​​of various spectra, for example, including:

[0083] Light spectrum: light is emitted during partial discharge and the spectrum has characteristic values;

[0084] Acoustic spectrum: sound is produced during partial discharge and the sound spectrum has characteristic values;

[0085] Electromagnetic spectrum: light is emitted during partial discharge, and electromagnetic waves have characteristic values;

[0086] Gas detection: burning of common insulating materials, leakage of gases and characteristic components during partial discharge.

[0087] Step S103: using AI (Artificial Intelligence) to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hazard occurs, to obtain the electrical hazard identification result corresponding to each parameter.

[0088] In this embodiment, the system has a large amount of basic data accumulated in the early stage, namely: the spectrum characteristic values ​​of light waves, sound waves, electromagnetic waves, etc. that accompany common electrical hazards (set as the initial values ​​of the AI ​​system in the system). When electrical hazards occur, i.e., partial discharge, the AI ​​compares and analyzes the aforementioned spectrum characteristic values ​​after Fourier transformation with the initial values ​​stored in the AI ​​system, and can effectively identify electrical hazards.

[0089] Optionally, the use of artificial intelligence AI to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs, to obtain the electrical hidden danger identification result corresponding to each parameter, specifically includes:

[0090] AI is used to perform a similarity comparison analysis between the frequency spectrum characteristic value corresponding to each parameter and the frequency spectrum characteristic value of the corresponding parameter when the pre-stored electrical hazard occurs to obtain a similarity result. If the similarity result is greater than or equal to a preset similarity threshold, the electrical hazard identification result corresponding to the parameter is judged to be the existence of an electrical hazard; otherwise, the electrical hazard identification result corresponding to the parameter is judged to be the absence of an electrical hazard.

[0091] In this embodiment, the similarity threshold can be set according to actual conditions. When the similarity result is greater than or equal to the preset similarity threshold, it is determined that a hidden danger has occurred.

[0092] Taking electromagnetic waves as an example, AI comparative analysis includes: there is a large amount of basic data accumulated in the system in the early stage, that is, the characteristic values ​​of the electromagnetic wave frequency domain accompanying common electrical hazards (set as the initial value of the AI ​​system in the system). When an electrical hazard occurs, that is, partial discharge, AI will compare the aforementioned frequency domain detection signal after Fourier transformation (that is, the spectrum characteristic value) with the initial value stored in the AI ​​system for similarity analysis. Among them, the system can flexibly set the similarity threshold of the comparative analysis: the comparison similarity ranges from 30% to 70%, etc., and can be selected at will. If the similarity between the on-site detection signal and the initial value in the system exceeds the threshold, the detection item is judged as a logical output 1 (that is, a hidden danger is determined to have occurred).

[0093] Step S104: determining the final electrical hazard identification result of the corresponding area according to the electrical hazard identification result corresponding to each parameter.

[0094] Specifically, if the electrical hazard identification result corresponding to any one of the multiple parameters is that an electrical hazard exists, then the final electrical hazard identification result of the corresponding area is determined to be that an electrical hazard exists; or, if the number of parameters among the multiple parameters whose identification results are that an electrical hazard exists exceeds a preset number threshold, then the final electrical hazard identification result of the corresponding area is determined to be that an electrical hazard exists; or, if the identification results of all the parameters among the multiple parameters are that an electrical hazard exists, then the final electrical hazard identification result of the corresponding area is determined to be that an electrical hazard exists.

[0095] In this embodiment, in order to avoid misjudgment and improve the accuracy of recognition, when the number of parameters among multiple parameters whose recognition results are that there are electrical hazards exceeds a preset threshold value (for example, 2 or 3), or the recognition results of all parameters among multiple parameters are that there are electrical hazards, the final electrical hazard recognition result of the corresponding area is determined to be that there are electrical hazards.

[0096] Step S105: In response to the final electrical hazard identification result of a certain area being that there is an electrical hazard, a warning signal is issued, and the specific location of the electrical hazard is determined according to the address code of the certain area.

[0097] In this embodiment, the warning may include a general warning and a strong warning. When the electrical hazard identification result corresponding to only one parameter is that there is an electrical hazard, a general warning may be issued. Otherwise, a strong warning may be issued to require the user to confirm and handle the situation on site as soon as possible.

[0098] It should be noted that the basic principle of the present invention is:

[0099] 1. We all have this common sense in our lives: when a socket is lit, there will be a "sizzling" sound, a noticeable arc light, a burning smell, etc. Common sense is life experience, but if you want to use industrial products to identify it, you must achieve the desired effect through the collection of physical and chemical characteristics, signal processing, and output results.

[0100] 2. Electrical hazards always have certain physical and chemical properties! However, how to identify them is the key issue! At present, the characterization indicators of electrical systems are mainly concentrated on basic electrical parameters such as current and voltage. Therefore, the key technology of the present invention is: through precise detection of physical phenomena such as light, sound, electromagnetic waves in the three-dimensional space where the electrical facilities are located, and then digital processing (A / D) of the physical analog quantity, and then through the Fourier analysis method to extract key indicators such as spectrum, and through AI technology and the database accumulated in the early stage, the electrical hazards can be effectively identified; at the same time, the smell of chemical phenomena and specific gas detection are carried out as one of the detection means; and as the database continues to grow and the experience data becomes more and more abundant, the recognition accuracy will increase rapidly, and it can increasingly meet the needs of precise detection!

[0101] It should be noted that the key indicators extracted by Fourier analysis method include the characteristic values ​​of various spectra, for example:

[0102] Light spectrum: light is emitted during partial discharge and the spectrum has characteristic values;

[0103] Acoustic spectrum: sound is produced during partial discharge and the sound spectrum has characteristic values;

[0104] Electromagnetic spectrum: light is emitted during partial discharge, and electromagnetic waves have characteristic values;

[0105] Gas detection: burning of common insulating materials, leakage of gases and characteristic components during partial discharge.

[0106] Taking electromagnetic waves as an example, AI comparative analysis includes: there is a large amount of basic data accumulated in the system in the early stage, that is, the characteristic values ​​of the electromagnetic wave frequency domain accompanying common electrical hazards (set as the initial value of the AI ​​system in the system). When an electrical hazard occurs, that is, partial discharge, AI will compare the aforementioned frequency domain detection signal after Fourier transformation (that is, the spectrum characteristic value) with the initial value stored in the AI ​​system for similarity analysis. Among them, the system can flexibly set the similarity threshold of the comparative analysis: the comparison similarity ranges from 30% to 70%, etc., and can be selected at will. If the similarity between the on-site detection signal and the initial value in the system exceeds the threshold, the detection item is judged as a logical output 1 (that is, a hidden danger is determined to have occurred).

[0107] 3. The recognition degree of a single detection method is not high, and the probability of misjudgment is high; however, if multiple detection methods are used together, that is, a duplex detection method is adopted, the recognition degree and accuracy of the system can be effectively improved;

[0108] It should be noted that complex testing refers to the simultaneous implementation of multiple testing methods and the final testing results through logical output.

[0109] 4. The coordination between multiple detection methods cannot be achieved by simple logic, and complex logic judgment must be achieved through AI;

[0110] 5. Open detection means: According to the continuous development of technology, new modules of detection means can be added to form a logic with the previous detection means, and the final output results can be obtained after AI judgment;

[0111] 6. In a specific space, the space is divided into a grid matrix (or honeycomb structure, the same effect), each grid has a unique address code (i.e., a unique address code), and a duplex detection device is arranged in each grid. When an electrical hazard occurs in a certain grid, an early warning signal is issued! By matching the detected signal with the address code, the specific location of the hazard can be immediately determined, so that the hazard can be located as quickly as possible, discovered and handled in a timely manner.

[0112] It should be noted that sound waves, electromagnetic waves, gases, etc., decay rapidly in space, or decay in a gradient manner. That is, the intensity is greatest at the signal source, and the closer to the signal source, the greater the intensity; the farther from the signal source, the faster the intensity decays to a very weak level. In a limited space, the attenuation of light with distance is not obvious; gas is not very accurate due to air flow. Therefore, the present invention adopts compound detection, which can not only improve the effectiveness of detection, but also avoid being detected by adjacent grids.

[0113] The specific implementation process is as follows: In each grid, when there are safety hazards such as minor discharge caused by poor contact of electrical equipment or even serious safety hazards such as arcing, multiple means of duplex detection will be carried out based on the physical phenomena at the time, such as sound, light, smell, electromagnetic characteristics, etc. If a single detection exceeds the limit, a general warning will be issued. If all duplex detection warnings are output in a strong warning related to the gate logic method, the maintenance personnel will be reminded to confirm on site in time, discover hidden dangers in time and deal with them according to actual conditions.

[0114] It should be noted that general warning refers to the situation in which a single item in a multiple-item detection method issues a logical 1 alarm, which is called a general warning. General warnings are mostly due to detection errors, and the probability of a real hidden danger is not high. A general warning signal is issued to the user, and when necessary, on-site inspections are conducted to confirm and handle the situation. Strong warning refers to the situation in which more than one item (for example, 3 items) in a multiple-item detection method issues an alarm, which is called a strong warning. In a strong warning, multiple indicators meet the warning conditions, so the accuracy of the detection is relatively high! Therefore, the probability of a real problem is basically 100%. Users are required to confirm and handle the situation on site as soon as possible.

[0115] Among them, the principle block diagram is as follows Figure 4 As shown, based on Figure 4 The schematic diagram shown, a detection case is as follows:

[0116] a) Occurrence: In a power distribution room or a room with power distribution facilities, point A experiences partial discharge due to electrical insulation breakdown. (In this case, normal power supply will not be affected for a short period of time. It is a potential safety hazard and needs to be dealt with in a timely manner. Because the hidden danger will continue to develop and eventually lead to a serious accident.)

[0117] b) Startup: Partial discharge is accompanied by physical and chemical phenomena such as visible light, sound, radio waves, and odor. The above phenomena will have different intensities and time sequences due to different discharge conditions. At the same time, the detection signal is strongest at the discharge point, and the intensity gradually decreases at other locations in the room as the distance from the discharge point increases.

[0118] The various detection devices of the complex detection device will detect their own physical and chemical properties, strength, etc.

[0119] The machine room is divided into different grid matrices on a two-dimensional plane, and a multiple detection device is arranged in each grid matrix. In this way, the specific location of the partial discharge can be determined based on the detected signal strength (the range is determined within the grid matrix).

[0120] c) Fourier analysis: frequency domain analysis

[0121] The signals detected by the aforementioned detection devices in each grid matrix are in the most original format of analog physical quantities (light, sound, electromagnetic waveforms, gas composition, etc.), which are facilitated by analog-to-digital conversion (A / D) for later processing.

[0122] Fourier analysis transforms time domain signals such as light waves, sound waves, and electromagnetic waves into frequency domain signals, which is a basic integral transform.

[0123] d) AI comparative analysis:

[0124] The system has a large amount of basic data accumulated in the early stage, namely: the characteristic values ​​of the frequency domain of physical quantities such as light waves, sound waves, and electromagnetic waves that accompany common electrical hazards (set them as the initial values ​​of the AI ​​system in the system). When an electrical hazard occurs, that is, partial discharge, AI will compare and analyze the similarity of the aforementioned frequency domain detection signal after Fourier transformation with the initial value stored in the AI ​​system. The system can flexibly set the threshold for comparative analysis: the comparison similarity ranges from 30% to 70%, etc., and you can choose it yourself. If the on-site detection signal and the similarity with the initial value in the system exceed the threshold, the detection item is judged as logical output 1 (that is, it is determined that a hidden danger has occurred).

[0125] It should be noted that AI comparison is a centralized comparison. The signal input into AI contains unique grid matrix address coding information. Therefore, the comparison result can also output address information, which can accurately tell where the hidden dangers are.

[0126] e) Result output:

[0127] The system result is the judgment output of the compound detection, and the "OR" logic is performed to output the final result. That is, when any of the multiple detection methods of the compound detection outputs logic 1, the logic 1 is output to the user, and the hidden danger is finally determined, and the user is notified to conduct on-site inspection and processing in a timely manner.

[0128] It should be noted that the electrical hidden danger detection method provided by the present invention has the following characteristics:

[0129] 1. Use a compound detection method that detects both physical quantities (sound, light, electricity, etc.) and chemical quantities (specific trace gases) during the occurrence of electrical hazards;

[0130] 2. The system structure adopts an open structure and AND gate logic, which can flexibly add new technologies, detection methods and functional modules;

[0131] 3. In the digital architecture, the collected physical and chemical quantities are converted into analog-to-digital (A / D) quantities to facilitate the subsequent AI logic analysis;

[0132] 4. Use digital Fourier analysis algorithm and spectrum analysis technology to extract key detection information;

[0133] 5. The grid matrix structure (or honeycomb structure) encodes the address and achieves precise positioning;

[0134] 6. Perform logical analysis and output results based on AI.

[0135] The detection method of electrical hidden dangers provided by the embodiment of the present invention first detects multiple parameters in the process of electrical hidden dangers through a complex detection device arranged in each of multiple areas of a preset space, and performs analog-to-digital conversion; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers; then the multiple parameters after analog-to-digital conversion are Fourier transformed to extract the spectrum characteristic value of each parameter in the frequency domain; and the spectrum characteristic value corresponding to each parameter is compared and analyzed with the spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs by using artificial intelligence AI to obtain the electrical hidden danger identification result corresponding to each parameter; then the final electrical hidden danger identification result of the corresponding area is determined according to the electrical hidden danger identification result corresponding to each parameter; finally, in response to the final electrical hidden danger identification result of a certain area being that there is an electrical hidden danger, an early warning signal is issued, and the specific location of the electrical hidden danger is determined according to the address code of the certain area. The present invention monitors multiple physical and chemical parameters in the process of electrical hidden dangers in real time through complex detection devices arranged in multiple areas of a preset space, performs analog-to-digital conversion and Fourier transform to extract spectrum characteristic values, and then uses artificial intelligence AI to compare and analyze with the pre-stored spectrum characteristic values, so that electrical hidden dangers can be discovered in time. In addition, the electrical hidden danger situation in the corresponding area is comprehensively determined based on the identification results of each parameter, and a warning signal is issued when a hidden danger is confirmed. The source of the hidden danger is accurately located in combination with the address code, which significantly improves the early detection and accurate positioning capabilities of electrical hidden danger detection. It solves the problem that the existing electrical hidden danger detection methods have certain limitations, often fail to detect hidden dangers in time at an early stage, and fail to accurately locate the source of hidden dangers.

[0136] Embodiment 2:

[0137] like Figure 5 As shown, this embodiment provides an electrical hidden danger detection device, which is used to execute the above-mentioned electrical hidden danger detection method, including:

[0138] The parameter detection conversion module 11 is used to detect multiple parameters in the process of electrical hidden dangers through the duplex detection device arranged in each of the multiple areas of the preset space, and perform analog-to-digital conversion; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers;

[0139] A Fourier transform module 12, connected to the parameter detection conversion module 11, is used to perform Fourier transform on the multiple parameters after analog-to-digital conversion, and extract the frequency spectrum characteristic value of each parameter in the frequency domain;

[0140] The comparison and analysis module 13 is connected to the Fourier transform module 12 and is used to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs by using artificial intelligence AI to obtain the electrical hidden danger identification result corresponding to each parameter;

[0141] The identification result determination module 14 is connected to the comparison and analysis module 13 and is used to determine the final electrical hazard identification result of the corresponding area according to the electrical hazard identification result corresponding to each parameter;

[0142] The warning and positioning module 15 is connected to the identification result determination module 14, and is used to respond to the final electrical hazard identification result of a certain area as the existence of electrical hazards, send out a warning signal, and determine the specific location of the electrical hazard according to the address code of the certain area.

[0143] Optionally, the electrical hidden danger detection device further includes:

[0144] A space division module, used to divide the preset space into a plurality of areas, wherein each area has a unique address code;

[0145] The detection device arrangement module is used to arrange the multiple detection devices in each of the areas.

[0146] Optionally, the space division module is specifically used to:

[0147] Divide the preset space into a grid matrix; or,

[0148] The preset space is divided into a honeycomb structure.

[0149] Optionally, the complex detection device is formed by connecting a plurality of detection modules and their corresponding analog-to-digital conversion modules in parallel, and each detection module is used to detect one parameter among the plurality of parameters;

[0150] The multiple parameters include gas and at least one of the following: light, sound, and electromagnetic waves.

[0151] Optionally, the electrical hidden danger detection device further includes:

[0152] The parameter adjustment module is used to adjust the number of the multiple parameters by increasing or decreasing the detection modules and the corresponding analog-to-digital conversion modules in the complex detection device.

[0153] Optionally, the comparison and analysis module 13 is specifically used for:

[0154] AI is used to perform a similarity comparison analysis between the frequency spectrum characteristic value corresponding to each parameter and the frequency spectrum characteristic value of the corresponding parameter when the pre-stored electrical hazard occurs to obtain a similarity result. If the similarity result is greater than or equal to a preset similarity threshold, the electrical hazard identification result corresponding to the parameter is judged to be the existence of an electrical hazard; otherwise, the electrical hazard identification result corresponding to the parameter is judged to be the absence of an electrical hazard.

[0155] Optionally, the recognition result determination module 14 is specifically used for:

[0156] If the electrical hazard identification result corresponding to any one of the multiple parameters is that an electrical hazard exists, then determining that the final electrical hazard identification result of the corresponding area is that an electrical hazard exists; or,

[0157] If the number of parameters whose identification results indicate that electrical hazards exist among the multiple parameters exceeds a preset number threshold, then the final electrical hazard identification result of the corresponding area is determined to be that electrical hazards exist; or,

[0158] If the identification results of all the parameters in the multiple parameters are that there is an electrical hazard, then the final electrical hazard identification result of the corresponding area is determined to be that there is an electrical hazard.

[0159] Embodiment 3:

[0160] refer to Figure 6 This embodiment provides an electrical hazard detection device, including a memory 21 and a processor 22. The memory 21 stores a computer program, and the processor 22 is configured to run the computer program to execute the electrical hazard detection method in Example 1.

[0161] The memory 21 is connected to the processor 22. The memory 21 may be a flash memory, a read-only memory or other memory. The processor 22 may be a central processing unit or a single-chip microcomputer.

[0162] Embodiment 4:

[0163] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for detecting electrical hazards in the above-mentioned embodiment 1 is implemented.

[0164] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0165] In summary, the detection method, device and readable storage medium of electrical hidden dangers provided by the embodiments of the present invention first detect multiple parameters in the process of electrical hidden dangers through the duplex detection device arranged in each of the multiple areas of the preset space, and perform analog-to-digital conversion; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers; then perform Fourier transform on the multiple parameters after analog-to-digital conversion to extract the spectrum characteristic value of each parameter in the frequency domain; and use artificial intelligence AI to compare and analyze the spectrum characteristic value corresponding to each parameter with the spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs, so as to obtain the electrical hidden danger identification result corresponding to each parameter; then determine the final electrical hidden danger identification result of the corresponding area according to the electrical hidden danger identification result corresponding to each parameter; finally, in response to the final electrical hidden danger identification result of a certain area being that there is an electrical hidden danger, an early warning signal is issued, and the specific location of the electrical hidden danger is determined according to the address code of the certain area. The present invention monitors multiple physical and chemical parameters in the process of electrical hidden dangers in real time through the duplex detection devices arranged in multiple areas of the preset space, performs analog-to-digital conversion and Fourier transform to extract the spectrum characteristic value, and then uses artificial intelligence AI to compare and analyze with the pre-stored spectrum characteristic value, so as to timely discover electrical hidden dangers. In addition, the electrical hidden danger situation in the corresponding area is comprehensively determined based on the identification results of each parameter, and a warning signal is issued when a hidden danger is confirmed. The source of the hidden danger is accurately located in combination with the address code, which significantly improves the early detection and accurate positioning capabilities of electrical hidden danger detection. It solves the problem that the existing electrical hidden danger detection methods have certain limitations, often fail to detect hidden dangers in time at an early stage, and fail to accurately locate the source of hidden dangers.

[0166] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present invention, but the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A method for detecting electrical hazards, characterized in that: The method comprises: Multiple parameters in the process of electrical hidden dangers occurring are detected by using a complex detection device arranged in each of multiple areas of a preset space, and analog-to-digital conversion is performed; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers occurring; Perform Fourier transform on the multiple parameters after analog-to-digital conversion to extract the frequency spectrum characteristic value of each parameter in the frequency domain; Artificial intelligence AI is used to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs, and the electrical hidden danger identification result corresponding to each parameter is obtained; Determine the final electrical hazard identification result of the corresponding area according to the electrical hazard identification result corresponding to each parameter; In response to the final electrical hazard identification result of a certain area being that there is an electrical hazard, an early warning signal is issued, and the specific location of the electrical hazard is determined according to the address code of the certain area.

2. The method according to claim 1, characterized in that Before detecting multiple parameters in the process of electrical hidden dangers by using a complex detection device arranged in each of the multiple areas of the preset space and performing analog-to-digital conversion, the method further includes: Dividing the preset space into a plurality of areas, wherein each area has a unique address code; The multiple detection device is arranged in each of the areas.

3. The method according to claim 2, characterized in that The dividing the preset space into a plurality of areas specifically includes: Divide the preset space into a grid matrix; or, The preset space is divided into a honeycomb structure.

4. The method according to claim 1, characterized in that: The complex detection device is formed by connecting a plurality of detection modules and their corresponding analog-to-digital conversion modules in parallel, and each detection module is used to detect one parameter among the plurality of parameters; The multiple parameters include gas and at least one of the following: light, sound, and electromagnetic waves.

5. The method according to claim 4, characterized in that The method further comprises: The number of the multiple parameters is adjusted by increasing or decreasing the detection modules and the corresponding analog-to-digital conversion modules in the complex detection device.

6. The method according to claim 1, characterized in that The method of using artificial intelligence AI to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs, and obtaining the electrical hidden danger identification result corresponding to each parameter, specifically includes: AI is used to perform a similarity comparison analysis between the frequency spectrum characteristic value corresponding to each parameter and the frequency spectrum characteristic value of the corresponding parameter when the pre-stored electrical hazard occurs to obtain a similarity result. If the similarity result is greater than or equal to a preset similarity threshold, the electrical hazard identification result corresponding to the parameter is judged to be the existence of an electrical hazard; otherwise, the electrical hazard identification result corresponding to the parameter is judged to be the absence of an electrical hazard.

7. The method according to claim 1, characterized in that Determining the final electrical hazard identification result of the corresponding area according to the electrical hazard identification result corresponding to each parameter specifically includes: If the electrical hazard identification result corresponding to any one of the multiple parameters is that an electrical hazard exists, then determining that the final electrical hazard identification result of the corresponding area is that an electrical hazard exists; or, If the number of parameters whose identification results indicate that electrical hazards exist among the multiple parameters exceeds a preset number threshold, then the final electrical hazard identification result of the corresponding area is determined to be that electrical hazards exist; or, If the identification results of all the parameters in the multiple parameters are that there is an electrical hazard, then the final electrical hazard identification result of the corresponding area is determined to be that there is an electrical hazard.

8. A device for detecting electrical hazards, characterized in that: The device comprises: A parameter detection conversion module, used to detect multiple parameters in the process of electrical hidden dangers through a complex detection device arranged in each of multiple areas of a preset space, and perform analog-to-digital conversion; wherein the multiple parameters involve physical quantities and chemical quantities in the process of electrical hidden dangers; A Fourier transform module, connected to the parameter detection conversion module, is used to perform Fourier transform on the multiple parameters after analog-to-digital conversion to extract the frequency spectrum characteristic value of each parameter in the frequency domain; A comparison and analysis module, connected to the Fourier transform module, is used to compare and analyze the frequency spectrum characteristic value corresponding to each parameter with the pre-stored frequency spectrum characteristic value of the corresponding parameter when the electrical hidden danger occurs by using artificial intelligence AI, so as to obtain the electrical hidden danger identification result corresponding to each parameter; An identification result determination module, connected to the comparison and analysis module, is used to determine the final electrical hazard identification result of the corresponding area according to the electrical hazard identification result corresponding to each parameter; The early warning and positioning module is connected to the identification result determination module, and is used to respond to the final electrical hazard identification result of a certain area as the existence of electrical hazards, send out an early warning signal, and determine the specific location of the electrical hazard according to the address code of the certain area.

9. A device for detecting electrical hazards, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the method for detecting electrical hazards according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting electrical hazards according to any one of claims 1 to 7 is implemented.

Images