A switchgear system having an abnormal condition monitoring function using sound and temperature

Abstract

The present invention is characterized by comprising a switchboard (100), a temperature sensor (150), a microphone array (200), an abnormality diagnosis module (300), and a display (400), which can identify abnormal conditions such as partial discharge, arc discharge, corona discharge, and mechanical abnormalities by utilizing the internal temperature of the switchboard, which is a power facility, and acoustic signal data generated inside the switchboard to identify abnormal conditions occurring inside the switchboard quickly and accurately, and can generate and display abnormal occurrence event information regarding the switchboard component that caused the abnormal condition and the cause of the abnormal condition using artificial intelligence, thereby enabling prompt necessary measures to be taken regarding the switchboard component that caused the abnormal condition and the cause of the abnormal condition, and thus providing the effect of preventing safety accidents of the switchboard in advance.

Description

Technology Field

[0001] The present invention relates to a switchgear system having an abnormality monitoring function using sound and temperature. More specifically, it relates to a switchgear system that monitors abnormalities in a switchgear by utilizing the internal temperature of the switchgear, which is a power facility, and audible / inaudible sound signal data generated inside the switchgear to identify the occurrence of abnormal conditions such as partial discharge, arc discharge, corona discharge, and mechanical abnormalities, and by displaying abnormality event information regarding the switchgear component that caused the abnormal condition and the cause thereof. Background Technology

[0003] Recently, various safety accidents occurring in industrial sites are causing enormous social and economic damage, and among them, safety accidents in power facilities are resulting in problems such as loss of not only human lives but also the loss of expensive industrial equipment.

[0004] In particular, switchgear, a type of power equipment installed at industrial sites, is a core facility of the power system that distributes electricity supplied from power plants or substations to demand centers, and various electrical components for power distribution are installed inside.

[0005] If aging or mechanical / electrical defects occur in the electrical components installed in the switchgear, abnormal phenomena such as abnormal temperature rise, partial discharge, arc discharge, corona discharge, and abnormal mechanical noise occur. If these phenomena persist, they eventually lead to the failure of the electrical components, resulting in serious accidents such as fires or the interruption of power supply to consumers, which causes industrial facilities to cease operation.

[0006] Therefore, the core of switchgear safety management lies in detecting abnormal conditions early on before they persist and lead to an accident, identifying the switchgear component responsible for the detected abnormality and its cause, and ensuring that necessary measures are taken.

[0007] Conventionally, various detection technologies utilizing infrared cameras, single microphones, vibration sensors, acoustic cameras, and ultrasonic sensors have been used to detect abnormal conditions in switchgear. However, single microphone and vibration sensor methods are unable to track the directionality and location of noise; ultrasonic methods are effective for high-frequency discharge noise but have limitations in detecting low-frequency mechanical noise; acoustic camera methods provide high-resolution images but are very expensive, leading to installation cost issues and reduced reliability due to reflection and interference caused by the complex internal structure of switchgear; and infrared camera methods have limitations in diagnosing mechanical noise or partial discharge occurring in the early stages of a fault.

[0008] Furthermore, the aforementioned conventional technology has problems such as difficulty in accurately locating noise sources and identifying their causes, significant technical limitations in terms of real-time diagnosis of abnormalities, difficulty in immediate utilization in situations requiring emergency response due to the long time required to provide analysis results, and difficulty in precisely detecting abnormalities occurring in the complex wiring structure inside switchgear due to high-cost equipment or insufficient spatial resolution.

[0009] Therefore, it is necessary to develop switchgear safety management technology that can detect abnormal conditions early and at low cost before they persist and lead to an accident, and accurately identify the switchgear component and cause of the detected abnormality within a short period of time so that necessary measures can be taken promptly.

[0010] This invention addresses the problem and necessity described above and proposes a technology for a switchgear system that monitors abnormalities in power distribution panels by utilizing the internal temperature of the power distribution panel, audible / inaudible acoustic signal data generated within the panel, and artificial intelligence to identify abnormal conditions such as partial discharge, arc discharge, corona discharge, and mechanical anomalies, and by displaying abnormal occurrence event information regarding the switchgear component that caused the abnormal condition and the cause thereof. The following are prior art related to this. Prior art literature

[0012] 1. Republic of Korea Published Patent Application No. 10-2014-0118425 2. Republic of Korea Registered Patent Application No. 10-2287399 3. Republic of Korea Published Patent Application No. 10-2025-0062321 4. Republic of Korea Published Patent Application No. 10-2025-0094082

[0013] 1. Analysis of Acoustic Signals Generated by Corona and Series Arc Discharge (Journal of the Korean Institute of Electrical and Electronic Materials, v.25 no.2, 2012) 2. Condition Monitoring Technology for Heating Cables by Discharge Signal Detection (Journal of the Korean Institute of Electrical and Electronic Materials, v.34 no.2, 2021) The problem to be solved

[0014] The present invention aims to identify the occurrence of abnormal conditions, such as partial discharge, arc discharge, corona discharge, and mechanical abnormalities, by utilizing the internal temperature of a power distribution panel and audible / inaudible acoustic signal data generated inside the panel.

[0015] In addition, the present invention aims to display abnormal occurrence event information regarding the switchgear component that caused the abnormal condition and the cause of the occurrence. means of solving the problem

[0017] The switchgear system having an abnormal monitoring function using sound and temperature according to the present invention for solving the above problem is,

[0018] A power distribution panel (100) that receives electricity from an external source, distributes it to a load, and performs a warning alarm when a door is opened;

[0019] A temperature sensor (150) installed inside the switchboard (100) to detect temperature and provide the detected temperature information to an abnormality diagnosis module (300) and a display (400);

[0020] A microphone array (200) installed inside the power distribution panel (100) to collect acoustic signal data generated from the power distribution panel at multiple locations and to provide the collected acoustic signal data to an abnormality diagnosis module (300);

[0021] An abnormality diagnosis module (300) installed inside the power distribution panel (100) to frequency analyze multiple acoustic signal data provided by a microphone array (200) to identify the occurrence of an abnormal state in the power distribution panel and to display abnormality event information regarding the occurred abnormal state on a display (400);

[0022] It is characterized by including a display (400) installed on the outside of the switchboard (100) to display internal temperature information of the switchboard and abnormal occurrence event information. Effects of the invention

[0024] The present invention utilizes the internal temperature of a power distribution panel and acoustic signal data generated inside the panel to identify the occurrence of abnormal conditions such as partial discharge, arc discharge, corona discharge, and mechanical abnormalities, thereby providing the effect of quickly and accurately identifying abnormal conditions occurring inside the distribution panel.

[0025] In addition, the present invention can generate and display abnormal occurrence event information regarding the switchgear component that caused the abnormal condition and the cause of the abnormal condition using artificial intelligence, thereby enabling prompt necessary measures to be taken regarding the switchgear component that caused the abnormal condition and the cause, and thus providing the effect of preventing safety accidents of the switchgear in advance. Brief explanation of the drawing

[0027] FIG. 1 is an overall configuration diagram of the present invention. FIG. 2 is a configuration diagram of the switchboard, temperature sensor, and microphone array of the present invention. FIG. 3 is a functional block diagram of the present invention FIG. 4 is an explanatory diagram of acoustic signal data related to an abnormal state of the present invention. FIGS. 5, 6, and 7 are explanatory diagrams of abnormal occurrence event information of the present invention. Specific details for implementing the invention

[0028] Embodiments of the present invention will be described in detail with reference to the attached drawings.

[0029] The present invention, a switchboard system having an abnormal monitoring function using sound and temperature (hereinafter, the present invention), is an invention that can identify the occurrence of abnormal conditions such as partial discharge, arc discharge, corona discharge, and mechanical abnormalities by utilizing the internal temperature of the switchboard, which is a power facility, and acoustic signal data generated inside the switchboard, thereby providing the effect of quickly and accurately identifying abnormal conditions occurring inside the switchboard, and can generate and display abnormal occurrence event information regarding the switchboard component that caused the abnormal condition and the cause of the abnormal condition using artificial intelligence, so that necessary measures can be taken quickly regarding the switchboard component that caused the abnormal condition and the cause of the abnormal condition, thereby providing the effect of preventing safety accidents of the switchboard in advance. As shown in FIG. 1, it is characterized by being configured to include a switchboard (100), a temperature sensor (150), a microphone array (200), an abnormal diagnosis module (300), and a display (400).

[0031] Specifically, the switchgear system having an abnormal monitoring function using sound and temperature according to the present invention, as illustrated in FIG. 1,

[0032] A power distribution panel (100) that receives electricity from an external source, distributes it to a load, and performs a warning alarm when a door is opened;

[0033] A temperature sensor (150) installed inside the switchboard (100) to detect temperature and provide the detected temperature information to an abnormality diagnosis module (300) and a display (400);

[0034] A microphone array (200) installed inside the power distribution panel (100) to collect acoustic signal data generated from the power distribution panel at multiple locations and to provide the collected acoustic signal data to an abnormality diagnosis module (300);

[0035] An abnormality diagnosis module (300) installed inside the power distribution panel (100) to frequency analyze multiple acoustic signal data provided by a microphone array (200) to identify the occurrence of an abnormal state in the power distribution panel and to display abnormality event information regarding the occurred abnormal state on a display (400);

[0036] It is characterized by including a display (400) installed on the outside of the switchboard (100) to display internal temperature information of the switchboard and abnormal occurrence event information.

[0038] The above-mentioned switchboard (100) is configured to receive electricity from the outside and distribute it to a load, and to perform a warning alarm when the door is opened. As shown in FIG. 1, a display (400) that displays abnormal event information is installed on the outside of the switchboard (100), and on the inside, a microphone array (200) for collecting acoustic signal data and an abnormal diagnosis module (300) that analyzes the collected data using artificial intelligence are installed.

[0039] Generally, a switchboard is a core power facility that ensures the safe distribution and supply of electricity in the power system to each consumer (load). It receives power from external power sources, such as power plants, substations, or pole-mounted transformers, and then stably distributes it to various loads (e.g., distribution panels, power-consuming devices) installed at diverse power demand sites, such as factories, buildings, plants, and data centers. A distribution panel, on the other hand, is a facility that stably distributes the power supplied by the switchboard to various loads (e.g., distribution panels, power-consuming devices).

[0040] In addition, as shown in FIG. 2, various electrical components for power distribution, such as circuit breakers, transformers, measuring instruments, protective relays, insulating switches, busbars, electronic contactors, cable terminals, bus ducts, insulators, and mechanical coupling members, are installed inside the switchboard, and the switchboard performs functions such as power distribution, overcurrent and leakage current interruption, insulation maintenance, and electrical system protection and control.

[0041] In particular, recently, control devices and communication modules for automation and remote monitoring are being installed in switchboards, enabling advancements in intelligent power management.

[0042] The term "switchboard" used in the present invention is a term that includes a conventional switchboard and a distribution board. The present invention comprises a switchboard (100) that performs the above-mentioned functions, a temperature sensor (150) that detects the internal temperature of the switchboard (100), a microphone array (200) that collects abnormal acoustic signals generated by electrical / mechanical defects in real time, and the internal temperature of the switchboard and

[0043] An abnormality diagnosis module (300) and a display (400) are installed to diagnose / indicate whether an abnormality has occurred early through analysis of collected abnormal sound signals using artificial intelligence.

[0045] Meanwhile, the above-mentioned switchboard (100) may cause electric shock safety accidents due to the characteristics of the equipment, in which high-voltage electricity flows inside. Therefore, an alarm function is required to warn the worker that the switchboard is in a live state with high voltage flowing when the switchboard door is opened.

[0046] To this end, the above switchboard (100) is, as shown in FIG. 2,

[0047] A door sensor (110) that detects the opening of the switchboard door, and

[0048] It is characterized by including an alarm device (120) that warns, by at least one of an auditory method and a visual method, that the switchboard is in a live state when the openness of the switchboard door is detected by the door sensor (110).

[0049] The door sensor (110) provides a detection signal to the alarm device (120) when the opening of the switchboard door is detected, and the alarm device (120) performs a warning in at least one of an auditory method and a visual method when the detection signal is received.

[0050] At this time, the auditory method may be to output a voice warning message such as “High voltage is flowing through the switchboard, so do not operate it,” and the visual method may be to turn on or flash a warning light.

[0052] The above temperature sensor (150) is installed inside the power distribution board (100) to detect the temperature and is configured to provide the detected temperature information to the abnormal diagnosis module (300) and the display (400).

[0053] The temperature information provided by the temperature sensor (150) is displayed on the display (400) so that the internal temperature of the switchboard can be determined from the outside. In addition, the temperature information provided by the temperature sensor (150) to the abnormality diagnosis module (300) is used as verification information to determine whether the identified risk level is accurate when the abnormality diagnosis module (300) identifies the risk level of the abnormal state, and this will be described later.

[0055] The microphone array (200) is configured to be installed inside the power distribution board (100) to collect acoustic signal (audible / inaudible acoustic signal) data generated from the power distribution board at multiple locations and to provide the collected acoustic signal data to an abnormality diagnosis module (300). As shown in FIG. 2, it includes multiple MEMS microphones (210) that provide the collected acoustic signal data to the abnormality diagnosis module (300) along with their own identification information, and the multiple MEMS microphones (210) are installed inside the power distribution board (100).

[0056] The plurality of MEMS microphones (210) can be installed in the inner space of the switchboard (100) (see FIG. 2) or on the inner surface of the switchboard (100) door (not shown), as shown in FIG. 3, each MEMS microphone (210) transmits collected acoustic signal data along with its identification information (e.g., #01, #02) to an abnormality diagnosis module (300), so that the abnormality diagnosis module (300) can use artificial intelligence to diagnose / analyze abnormal conditions occurring at various locations inside the switchboard (100) from multiple angles.

[0057] At this time, the plurality of MEMS microphones (210) are installed inside the switchboard (100) as shown in FIG. 2 so as to collect acoustic signal data in the audible band (about 20Hz to 20kHz) as well as the inaudible band (including ultrasound), and are installed in a number suitable for the size of the internal space of the switchboard (100).

[0058] Since multiple MEMS microphones (210) are installed inside the switchboard (100), acoustic signal data can be collected from multiple angles in three dimensions, enabling accurate spatial tracking of the sound source. As a result, the direction and location of the sound source inside the switchboard, where reflection and interference easily occur due to electrical components and structures, can be accurately identified. Additionally, the microphones can be arranged three-dimensionally while maintaining uniform spacing, thereby improving the performance of collecting acoustic signal data across the entire frequency band from low to high frequencies.

[0059] Accordingly, the diagnostic accuracy of the abnormality diagnosis module (300), which diagnoses the occurrence of an abnormal state by analyzing acoustic signal data provided by the microphone array (200) including MEMS microphones (210) using artificial intelligence, is improved.

[0061] The above abnormality diagnosis module (300) is configured to use artificial intelligence to frequency analyze multiple acoustic signal data provided by a microphone array (200) installed inside the power distribution panel (100) to identify the occurrence of an abnormal state in the power distribution panel and to display abnormality event information regarding the occurred abnormal state on the display (400).

[0062] To this end, the above abnormality diagnosis module (300) is, as shown in FIG. 3,

[0063] A preprocessing unit (310) that performs noise removal and amplification preprocessing on multiple acoustic signal data provided from a microphone array (200), and

[0064] An intelligent abnormal state diagnosis unit (320) that uses artificial intelligence to frequency analyze multiple pre-processed acoustic signal data to identify the type / risk level / source location of an abnormal state occurring in a power distribution panel (100), generates analysis result information regarding the type / risk level / source location of the abnormal state, and provides it to an intelligent control unit (330);

[0065] The intelligent control unit (330) generates abnormal occurrence event information regarding the abnormal state that has occurred using the analysis result information provided by the intelligent abnormal state diagnosis unit (320) and artificial intelligence, and displays it on the display (400), wherein the types of the abnormal state include partial discharge, corona discharge, arc discharge, and mechanical abnormal noise.

[0067] The above preprocessing unit (310) is configured to perform noise removal and amplification preprocessing on a plurality of acoustic signal data provided from a microphone array (200), thereby removing noise included in the plurality of acoustic signal data and performing amplification processing to increase the diagnostic accuracy of the intelligent abnormal state diagnosis unit (320) to be described later.

[0068] At this time, the preprocessing unit (310) may use an adaptive noise cancellation technique or other noise cancellation technique for noise removal, and may use a 60dB gain preamplifier or other gain preamplifier for signal amplification. The noise removal or signal amplification process of the preprocessing unit (310) is a general technique, so a detailed description is omitted.

[0070] The above-described intelligent abnormal state diagnosis unit (320) is configured to use artificial intelligence to frequency analyze multiple pre-processed acoustic signal data to identify the type / risk level / source location of an abnormal state occurring in the power distribution panel (100), and then generate analysis result information regarding the type / risk level / source location of the abnormal state and provide it to the intelligent control unit (330). The types of abnormal states include partial discharge, corona discharge, arc discharge, and mechanical abnormal noise.

[0071] Specifically, the intelligent abnormal state diagnosis unit (320) is,

[0072] Using artificial intelligence that has learned the frequency characteristics of acoustic signal data regarding abnormal conditions that may occur in the switchboard (100), frequency analysis is performed on multiple preprocessed acoustic signal data to identify the type and risk level of the abnormal conditions that have occurred.

[0073] The method is characterized by identifying MEMS microphones (210) that provided acoustic signal data having frequency characteristics of an abnormal state among a plurality of MEMS microphones (210) constituting a microphone array (200), and identifying the source location within the switchboard that caused the abnormal state by using the installation location information of the identified MEMS microphones (210) and the reception time information of the acoustic signal data having frequency characteristics of an abnormal state.

[0075] As illustrated in FIG. 3, the intelligent abnormal state diagnosis unit (320) uses artificial intelligence to perform frequency analysis on a plurality of pre-processed acoustic signal data to identify the type and risk level of the abnormal state that occurred.

[0076] At this time, the artificial intelligence used to identify the type and risk of abnormal conditions is an artificial intelligence that has learned the frequency characteristics of acoustic signal data regarding abnormal conditions that may occur in the switchboard (100). When specific acoustic signal data is given as input, the artificial intelligence is an artificial intelligence in which a learning diagnostic model is established to diagnose whether the specific acoustic signal data given as input is acoustic signal data related to partial discharge, acoustic signal data related to corona discharge, acoustic signal data related to arc discharge, or acoustic signal data related to mechanical abnormal noise, by utilizing the learning results.

[0078] As exemplified in A of Figure 4, the above artificial intelligence identifies the type of abnormal condition that has occurred as partial discharge if the frequency band characteristics of the preprocessed acoustic signal data have a band of several kHz to tens of MHz and the frequency waveform characteristics have a pulse wave in the form of an instantaneous peak that is repeated at a specific phase of the power frequency, and identifies it as a partial discharge at a warning level if the amplitude of the frequency waveform is less than a preset value and as a partial discharge at a dangerous level if it is greater than the preset value.

[0079] As exemplified in Figure 4B, the artificial intelligence identifies the type of abnormal condition that has occurred as corona discharge if the frequency band characteristics of the preprocessed acoustic signal data have a band of several kHz to several hundred kHz and the frequency waveform characteristics are such that a continuous pulse wave is stably repeated every half-cycle of the power frequency, and identifies it as a warning level corona discharge if the amplitude of the frequency waveform is below a preset value and identifies it as a dangerous level corona discharge if it is above the preset value.

[0080] As exemplified in Figure 4C, the above artificial intelligence identifies the type of abnormal condition that has occurred as arc discharge if the frequency band characteristics of the preprocessed acoustic signal data have a DC to several MHz band and the frequency waveform characteristics rise sharply in a specific frequency band and then gradually fall, and identifies it as a warning level arc discharge if the amplitude of the frequency waveform is below a preset value and as a dangerous level arc discharge if it is above the preset value.

[0081] As exemplified in D of Fig. 4, the above artificial intelligence identifies the type of abnormal condition that has occurred as mechanical vibration if the frequency band characteristics of the preprocessed acoustic signal data include a fundamental frequency of 100 Hz or 200 Hz and harmonic components that are multiples thereof, and the frequency waveform characteristics have irregular pitch. If the amplitude of the frequency waveform is less than a preset value, it identifies it as mechanical vibration at a warning level, and if it is greater than a preset value, it identifies it as mechanical vibration at a danger level.

[0083] Additionally, the intelligent abnormal state diagnosis unit (320) identifies the source location of the abnormal state within the switchgear. Specifically, among the plurality of MEMS microphones (210) constituting the microphone array (200), it identifies the MEMS microphones (210) that provided acoustic signal data having the frequency characteristics of the abnormal state. By using the installation location information of the identified MEMS microphones (210) and the reception time information of the acoustic signal data having the frequency characteristics of the abnormal state, it identifies the source location within the switchgear that caused the abnormal state.

[0084] The above intelligent abnormal state diagnosis unit (320) may use pre-stored microphone installation information and TDOA (Time Difference of Arrival) technology to identify the location of the source of the abnormal state within the switchboard. The pre-stored microphone installation information is information regarding the installation locations of microphones within the switchboard, and the TDOA (Time Difference of Arrival) technology is a technology that identifies the location of the sound wave source by triangulation through the analysis of the time difference of arrival times of multiple sound waves. Since this is a conventionally known general technology, a detailed explanation is omitted.

[0085] Therefore, since the source causing the abnormal condition is located at a specific location within the switchboard and acoustic signal data regarding the abnormal condition caused by the source is collected by MEMS microphones (210) installed in a helical structure within the switchboard and provided to the abnormal diagnosis module (300) at different time intervals, the intelligent abnormal condition diagnosis unit (320) can identify the location of the source causing the abnormal condition within the switchboard using pre-stored microphone installation information and TDOA (Time Difference of Arrival) technology.

[0086] Using the example of a case where partial discharge occurs due to the aging of an insulator at a specific location within a switchboard, we explain how to identify the location of the source within the switchboard that caused the abnormal condition.

[0087] The above intelligent abnormal state diagnosis unit (320) identifies MEMS microphones (210) that provide acoustic signal data with frequency characteristics corresponding to partial discharge among a plurality (e.g., 10) of MEMS microphones (210). For example, among the 10 MEMS microphones (210), if the MEMS microphones (210) that provide acoustic signal data with frequency characteristics corresponding to partial discharge are #1, #6, #7, and #10 MEMS microphones (210), then #1, #6, #7, and #10 MEMS microphones (210) are identified as MEMS microphones (210) that provide acoustic signal data with frequency characteristics corresponding to partial discharge. Of course, if all 10 MEMS microphones (210) provide acoustic signal data with frequency characteristics corresponding to partial discharge, then MEMS microphones (210) that provide acoustic signal data with frequency characteristics corresponding to partial discharge are identified as #1 to #10 MEMS microphones (210). Since the MEMS microphones (210) provide their own identification information along with acoustic signal data, it is possible to determine which of the 10 MEMS microphones (210) provided acoustic signal data having frequency characteristics corresponding to partial discharge.

[0088] The installation locations of the identified #1, #6, #7, and #10 MEMS microphones (210) are identified using pre-stored microphone installation information (information regarding the installation locations of microphones within the switchboard), and the Time Difference of Arrival (TDOA) technique is applied to the reception time information of acoustic signal data having the frequency characteristics of partial discharge provided by the #1, #6, #7, and #10 MEMS microphones (210) to determine the reception time difference of the acoustic signal data having the frequency characteristics of partial discharge. Then, by using the installation location information and time difference information of the identified #1, #6, #7, and #10 MEMS microphones (210) within the switchboard, the location of the insulator within the switchboard that caused the partial discharge can be identified.

[0089] When the type / risk level / location of the source of an abnormal condition occurring within the switchboard is identified through the process described above, the intelligent abnormal condition diagnosis unit (320) generates analysis result information regarding the type / risk level / location of the source of the abnormal condition and provides it to the intelligent control unit (330).

[0091] Meanwhile, as shown in FIG. 5, the risk level of an abnormal state identified by the intelligent abnormal state diagnosis unit (320) is displayed on the display (400) for verification by the manager, so the identification of the risk level of the abnormal state must be accurate. That is, the identified risk level of the abnormal state must be reliable.

[0092] To this end, the intelligent abnormal state diagnosis unit (320) is,

[0093] When determining the risk of an abnormal state, the risk is determined using the amplitude of the frequency waveform of the acoustic signal, and the final risk is determined using the temperature information provided by the temperature sensor (150) as risk verification information.

[0094] After initially identifying the risk of an abnormal state using the amplitude of the frequency waveform of the acoustic signal, if the internal temperature of the switchgear based on temperature information is within the temperature range corresponding to the initially identified risk of the abnormal state, the initially identified risk of the abnormal state is determined as the final risk.

[0095] It is characterized by first identifying the risk of an abnormal state using the frequency waveform amplitude of an acoustic signal, and if the internal temperature of the switchgear based on temperature information is not within the temperature range corresponding to the risk of the abnormal state identified in the first, identifying the risk of the abnormal state in the second, and if the risk of the abnormal state identified in the second matches the risk of the abnormal state identified in the first, determining the risk of the abnormal state identified in the first as the final risk, and if the risk of the abnormal state identified in the second differs from the risk of the abnormal state identified in the first, determining the risk of the abnormal state identified in the second as the final risk.

[0097] As described above, the intelligent abnormal state diagnosis unit (320) performs frequency analysis on a plurality of pre-processed acoustic signal data to determine the risk level of an abnormal state that has occurred. When determining the risk level of an abnormal state, if the amplitude of the frequency waveform is less than a preset value, the risk level is determined to be at a warning level, and if it is greater than the preset value, the risk level is determined to be at a danger level.

[0098] At this time, if the risk is determined solely by the amplitude of the frequency waveform of the acoustic signal, there is a possibility of inaccuracy. To ensure accuracy in determining the risk, the temperature information provided by the temperature sensor (150) is used as risk verification information to determine the final risk.

[0099] Specifically, after first identifying the risk of an abnormal state using the amplitude of the frequency waveform of the acoustic signal, if the internal temperature of the switchgear based on temperature information is within a temperature range corresponding to the risk of the abnormal state identified in the first, the risk of the abnormal state identified in the first is determined as the final risk.

[0100] For example, if the risk level initially identified using the frequency waveform amplitude of the acoustic signal is identified as a risk level and the internal temperature of the switchboard based on the temperature information provided by the temperature sensor (150) is in a temperature range corresponding to the risk level (e.g., 50℃ or higher), the risk level of the abnormal state initially identified is determined to be accurate and the risk level is determined as the final risk level.

[0101] However, after first identifying the risk of an abnormal condition using the amplitude of the frequency waveform of the acoustic signal, if the internal temperature of the switchgear based on temperature information is not within the temperature range corresponding to the risk of the abnormal condition identified in the first step, the risk of the abnormal condition is identified in the second step.

[0102] For example, if the risk level initially identified using the frequency waveform amplitude of the acoustic signal is identified as a risk level and the internal temperature of the switchgear based on the temperature information provided by the temperature sensor (150) is not in the temperature range corresponding to the risk level (e.g., less than 50℃), the risk level of the abnormal state initially identified is determined to be inaccurate, and the risk level of the abnormal state is identified secondarily using the frequency waveform amplitude of the acoustic signal.

[0103] If the risk level of the second identified abnormal state matches the risk level of the first identified abnormal state, the risk level of the first identified abnormal state is determined as the final risk level.

[0104] For example, if the risk level of the first identified abnormal state was at a dangerous level, and it is determined that the risk level of the second identified abnormal state is still at a dangerous level based on temperature information, the temperature information used for verification is ignored, and the risk level of the first identified abnormal state is determined as the final risk level.

[0105] However, if the risk of the second abnormal state identified is different from the risk of the first abnormal state identified, the risk of the second abnormal state identified is determined as the final risk.

[0106] For example, if the risk level of the first identified abnormal state is at a dangerous level and is judged to be inaccurate based on temperature information and the risk level of the second identified abnormal state is at a warning level, the risk level of the first identified abnormal state is judged to be an incorrect risk level and the warning level of the second identified abnormal state is determined as the final risk level.

[0107] As described above, using the internal temperature of the switchgear as verification information when assessing risk can reduce errors that may occur when using only the amplitude of the frequency waveform of the acoustic signal for risk assessment, thereby improving the reliability of the risk assessment for abnormal conditions.

[0109] The above intelligent control unit (330) is configured to generate abnormal occurrence event information regarding the abnormal state that occurred by using the analysis result information provided by the intelligent abnormal state diagnosis unit (320) and artificial intelligence, and to display it on the display (400). The manager can identify what abnormal state has occurred, what the source of the abnormal state (e.g., insulator) is, and what the cause of the abnormal state (e.g., insulator aging) is through the abnormal occurrence event information displayed on the display (400), and then take necessary measures (e.g., confirming through precision diagnostic equipment whether the abnormal state occurred due to insulator aging and then taking measures to repair the insulator).

[0111] Specifically, the intelligent control unit (330) uses the analysis result information including the type / risk level / location of the source of the abnormal state provided by the intelligent abnormal state diagnosis unit (320), the 3D-based external image information of the switchgear, and the 2D-based internal design drawing information of the switchgear, and artificial intelligence to generate a first abnormal event information, which is basic information regarding the abnormal state that occurred, and a second abnormal event information, which is detailed information regarding the abnormal state that occurred. After the generated first abnormal event information is displayed on the display (400), if there is a user touch on the first display icon included in the first abnormal event information, the generated second abnormal event information is displayed on the display (400).

[0112] The above first abnormal occurrence event information is information displayed at a point on a 3D-based external image of a switchboard corresponding to the location of the source of the abnormal condition, wherein a first display icon is displayed in a color reflecting the risk level of the abnormal condition and information on the type of the abnormal condition is also displayed, and the above second abnormal occurrence event information is information displayed at a point on a 2D-based internal design drawing of a switchboard corresponding to the location of the source of the abnormal condition, wherein a second display icon is displayed in combination with information on the switchboard component expected to be the source of the abnormal condition, information on the expected cause of the abnormal condition, and information on diagnostic equipment capable of precisely diagnosing the expected cause of the abnormal condition.

[0114] The intelligent control unit (330) uses the analysis result information including the type / risk level / location of the source of the abnormal state provided by the intelligent abnormal state diagnosis unit (320), the 3D-based external image information of the switchgear, and the 2D-based design drawing information of the switchgear, and artificial intelligence to generate the first abnormal occurrence event information, which is basic information regarding the abnormal state that occurred, and the second abnormal occurrence event information, which is detailed information regarding the abnormal state that occurred.

[0115] The above analysis result information includes information on the type, risk level, and source location of an abnormal condition that occurred within the switchgear. For example, the type of abnormal condition may be partial discharge, the risk level of the abnormal condition may be a warning level, and the source location that caused the abnormal condition may be point a within the switchgear.

[0116] The artificial intelligence installed in the intelligent control unit (330) generates a first abnormal occurrence event information using the analysis result information provided by the intelligent abnormal state diagnosis unit (320) and the pre-stored 3D-based external image information of the power distribution panel. The first abnormal occurrence event information is characterized by being information displayed at a point on the 3D-based external image of the power distribution panel corresponding to the source location of the abnormal state, with a first display icon that is displayed in a color reflecting the risk level of the abnormal state and information on the type of abnormal state.

[0117] For example, if it is confirmed through analysis result information that the type of abnormal condition that occurred is partial discharge, the risk level of partial discharge is a warning level, and the location of the source that caused the partial discharge is point a within the switchboard, the artificial intelligence mounted on the intelligent control unit (330) generates first abnormal occurrence event information as illustrated in A of FIG. 5, in which a first display icon, which is displayed in orange (meaning the risk level is a warning level) and has information on the type of abnormal condition called partial discharge, is displayed at a point on the 3D-based external image of the switchboard corresponding to point a within the switchboard, which is the location of the source that caused the partial discharge.

[0119] In addition, the artificial intelligence installed in the intelligent control unit (330) generates second abnormal occurrence event information using the analysis result information provided by the intelligent abnormal state diagnosis unit (320) and the previously stored 2D-based internal design drawing information of the switchboard. The second abnormal occurrence event information is characterized by being information displayed at a point on the 2D-based internal design drawing of the switchboard corresponding to the location of the source of the abnormal state, wherein the second display icon is combined with information on the switchboard component expected to be the source of the abnormal state, information on the expected cause of the abnormal state, and information on the diagnostic equipment capable of precisely diagnosing the expected cause of the abnormal state.

[0120] Specifically, the intelligent control unit (330) is,

[0121] Using artificial intelligence, identify switchgear components suspected to be the source of the abnormal condition, identify the suspected cause of the abnormal condition, identify diagnostic equipment, and generate information on secondary abnormal occurrence events,

[0122] The artificial intelligence mounted on the intelligent control unit (330) identifies the switchgear component located at a point on the internal design drawing of the switchgear corresponding to the source location included in the analysis result information as the switchgear component expected to be the source causing the abnormal condition,

[0123] The artificial intelligence mounted on the intelligent control unit (330) identifies possible causes of an abnormal state that has occurred by using pre-stored cause information for each abnormal state and type information of abnormal states included in the analysis result information, and among the identified possible causes, if there is a possible cause related to a switchboard component identified as the expected source of occurrence, the possible cause is identified as the expected cause of the abnormal state.

[0124] The artificial intelligence mounted on the intelligent control unit (330) identifies a diagnostic device capable of precisely diagnosing the expected cause of the identified abnormal state, and

[0125] The artificial intelligence mounted on the intelligent control unit (330) is characterized by generating second abnormal occurrence event information using switchboard component information expected to be the source of the identified abnormal state, information on the expected cause of the abnormal state, information on diagnostic equipment, and information on the internal design drawing of the switchboard.

[0127] For example, if it is confirmed through analysis result information that the location of the source causing the abnormal condition is point a within the switchgear, the artificial intelligence mounted on the intelligent control unit (330) uses 2D-based internal design drawing information of the switchgear to identify the switchgear component at point a within the switchgear as the switchgear component expected to be the source causing the abnormal condition. For example, if the switchgear component at point a within the switchgear is an insulator, the insulator is identified as the switchgear component expected to be the source causing the abnormal condition.

[0128] In addition, the artificial intelligence mounted on the intelligent control unit (330) identifies possible causes of the abnormal state that occurred by using pre-stored cause information for each abnormal state and type information of the abnormal state included in the analysis result information. For example, if it is confirmed that the type of abnormal state is partial discharge, it identifies possible causes of partial discharge by using pre-stored cause information for each abnormal state, and possible causes can be identified as internal cracks in the insulator, aging of the insulator, generation of bubbles inside the insulator, defects in the joint between the conductor and the insulator.

[0129] In addition, the artificial intelligence mounted on the intelligent control unit (330) identifies, among the identified possible causes, if there is a possible cause related to the insulator, which is a switchboard component identified as the expected source, that possible cause is identified as the expected cause of partial discharge. For example, when possible causes such as internal cracks in the insulator, aging of the insulator, generation of bubbles inside the insulator, and defects in the joint between the conductor and the insulator are identified, the possible causes related to the insulator, which is a switchboard component identified as the expected source are internal cracks in the insulator, aging of the insulator, and generation of bubbles inside the insulator, so internal cracks in the insulator, aging of the insulator, and generation of bubbles inside the insulator are identified as the expected causes of partial discharge.

[0130] In addition, when the artificial intelligence mounted on the intelligent control unit (330) identifies the expected cause of partial discharge, it identifies diagnostic equipment information capable of precisely diagnosing the identified expected cause by referring to the pre-stored diagnostic equipment information by cause of abnormal condition. For example, if the identified expected cause is an internal crack in the insulator, an insulator aging, or an internal bubble formation in the insulator, the insulator internal crack diagnosis device of Company A, the insulator aging measurement device of Company B, and the insulator internal bubble formation detection device of Company C can be identified as diagnostic equipment capable of precisely diagnosing the expected cause.

[0131] When a switchgear component (e.g., insulator) suspected of being the source of partial discharge, the suspected cause of partial discharge (e.g., internal crack in the insulator, aging in the insulator, generation of bubbles inside the insulator), and a diagnostic device capable of precisely diagnosing the suspected cause of partial discharge (e.g., an insulator internal crack measuring device of Company A, an insulator aging measuring device of Company B, an insulator internal bubble generation measuring device of Company C) are identified, the artificial intelligence mounted on the intelligent control unit (330) generates second abnormal occurrence event information as illustrated in Fig. 5B, in which a second display icon containing information on the switchgear component suspected of being the source of partial discharge, information on the suspected cause of partial discharge, and information on the diagnostic device capable of precisely diagnosing the suspected cause of partial discharge is displayed at a point on the 2D-based switchgear internal design drawing corresponding to point a within the switchgear, which is the location of the source of partial discharge (e.g., insulator).

[0132] When the generation of the first and second abnormal occurrence event information is completed, the artificial intelligence mounted on the intelligent control unit (330) causes the first abnormal occurrence event information to be displayed on the display (400) as shown in A of FIG. 5, so that through the first abnormal occurrence event information displayed on the display (400), the manager can intuitively know what abnormal condition has occurred in the power distribution panel, what the level of risk of the abnormal condition is, and where the source that caused the abnormal condition is located within the power distribution panel.

[0133] After displaying the first abnormal event information, if there is a user touch on the first display icon included in the first abnormal event information, the artificial intelligence mounted on the intelligent control unit (330) causes the generated second abnormal event information to be displayed on the display (400) as shown in Fig. 5B, so that through the second abnormal event information displayed on the display (400), the manager can know what switchboard component caused the abnormal condition, where the component is located, what the cause of the abnormal condition is, and what equipment can precisely diagnose the cause.

[0134] Afterwards, the manager uses diagnostic equipment identified through the second abnormal event information to perform a precise diagnosis of the switchgear component that caused the abnormal condition, and if the diagnosis result finally confirms that the switchgear component is abnormal, repair or replacement work is performed on the switchgear component.

[0135] That is, by detecting an abnormal state of the intelligent control unit (330) as described above → notifying of the occurrence of an abnormal state → identifying the source and cause of the abnormal state → providing diagnostic equipment information, the administrator is guided to quickly recognize the situation of an abnormal occurrence, identify the exact cause, and perform rapid maintenance.

[0137] Meanwhile, in terms of switchgear management, it is necessary to enable the manager to identify the abnormal conditions that have occurred to date and the locations of their sources in chronological order, thereby allowing for the understanding of the history of abnormal conditions regarding which conditions occurred in the switchgear and in what chronological order.

[0138] To this end, the intelligent control unit (330) uses artificial intelligence and previously generated first abnormal occurrence event information to generate third abnormal occurrence event information that can identify abnormal states that have occurred up to now in chronological order and displays it on the display (400).

[0139] The above third abnormal occurrence event information is characterized by the fact that a plurality of third indicator icons, each containing information on the type of abnormal state, are displayed at points on an external image of a 3D-based switchboard corresponding to the location of the source of the abnormal state, and the plurality of third indicator icons are connected by arrows so as to indicate the order of occurrence of the abnormal state. That is, the third abnormal occurrence event information is information that provides the temporal and spatial directionality of the occurrence of the abnormal state.

[0140] As described above, the first abnormal occurrence event information is information in which a first indicator icon, which includes information on the type of abnormal state, is displayed at a point on the external image of the 3D-based switchboard corresponding to the location of the source of the abnormal state. By using the previously generated first abnormal occurrence event information, the abnormal state that has occurred so far and the location of the source that caused the abnormal state can be identified in chronological order.

[0141] The artificial intelligence mounted on the intelligent control unit (330) uses the previously generated first abnormal occurrence event information to display a plurality of third display icons, which have information on the type of abnormal state, at points on the external image of the 3D-based power distribution panel corresponding to the location of the source of the abnormal state. The plurality of third display icons generate third abnormal occurrence event information, such as that shown in FIG. 6, which is information connected by arrows to indicate the order of occurrence of the abnormal state, and display it on the display (400), thereby enabling the manager to identify the temporal and spatial direction of the abnormal state that has occurred so far in chronological order from the perspective of power distribution panel management.

[0143] Furthermore, in terms of switchgear maintenance, it is necessary to enable managers to identify the switchgear components that have caused abnormal conditions to date, their locations, and the causes of the abnormal conditions in chronological order, thereby allowing them to understand the history of switchgear component failures and determine which components caused the abnormal conditions.

[0144] To this end, the intelligent control unit (330) uses artificial intelligence and previously generated second abnormal occurrence event information to generate fourth abnormal occurrence event information that can identify switchgear components presumed to be the source of the abnormal state that has occurred so far in chronological order, and displays it on the display (400).

[0145] The above-mentioned fourth abnormal occurrence event information is characterized by the fact that a plurality of fourth indicator icons, each containing information on switchgear components expected to be the source of the abnormal condition and information on the expected cause of the abnormal condition, are displayed at points on a 2D-based internal design drawing of the switchgear corresponding to the location of the source of the abnormal condition, and the plurality of fourth indicator icons are information connected by arrows so as to indicate the sequence of failures of the switchgear components. That is, the fourth abnormal occurrence event information is information that provides the temporal and spatial directionality of the failure of switchgear components.

[0146] As described above, the second abnormal occurrence event information is information in which a second display icon is displayed at a point on the 2D-based internal design drawing of the switchgear corresponding to the location of the source of the abnormal condition, in which switchgear component information expected to be the source of the abnormal condition, information on the expected cause of the abnormal condition, and information on diagnostic equipment capable of precisely diagnosing the expected cause of the abnormal condition are combined. By using the previously generated second abnormal occurrence event information, the switchgear component that has caused the abnormal condition so far, the location of the component, and the cause of the abnormal condition can be identified in chronological order.

[0147] The artificial intelligence installed in the intelligent control unit (330) uses the previously generated second abnormal occurrence event information to display a plurality of fourth display icons, which include information on switchboard components expected to be the source of the abnormal condition and information on the expected cause of the abnormal condition, at points on the 2D-based internal design drawing of the switchboard corresponding to the location of the source of the abnormal condition. The plurality of fourth display icons generate fourth abnormal occurrence event information, such as that shown in FIG. 7, which is information connected by arrows to indicate the order of failure of switchboard components, and display it on the display (400), thereby enabling the manager to identify the temporal and spatial direction of the switchboard components that have caused the abnormal condition in chronological order from the perspective of switchboard maintenance / repair.

[0149] The above-described first to fourth abnormal occurrence event information is information displayed on the display (400), so the manager must move to the switchboard (100) installed at the site to check the abnormal occurrence event information. If the manager is not at the site where the switchboard (100) is installed at the time the abnormal condition occurs, the occurrence of the abnormal condition cannot be immediately recognized, and as a result, it is difficult to identify the switchboard component that caused the abnormal condition immediately upon the occurrence of the abnormal condition.

[0150] Accordingly, to solve the above problem, the intelligent control unit (330) is characterized by using artificial intelligence to generate abnormal state occurrence notification information including second abnormal occurrence event information, as shown in FIG. 3, and providing it to an administrator terminal.

[0151] That is, the artificial intelligence installed in the intelligent control unit (330) generates abnormal state occurrence notification information including the second abnormal occurrence event information when generating second abnormal occurrence event information and provides it to the administrator terminal.

[0152] Information regarding the second abnormal occurrence event is displayed on the display (400) but is also provided to the manager, so that even if the manager is not at the site where the power distribution panel (100) is installed, the manager can check the information regarding the power distribution panel component expected to be the source of the abnormal condition, the information regarding the expected cause of the abnormal condition, and the information regarding the diagnostic equipment capable of precisely diagnosing the expected cause of the abnormal condition through the information regarding the second abnormal occurrence event displayed on the manager terminal.

[0154] The above display (400) is configured to be installed on the outside of the switchboard (100) to display internal temperature information of the switchboard and abnormal occurrence event information. As shown in FIGS. 5, 6, and 7, the display (400) displays information on the first to fourth abnormal occurrence events and internal temperature information of the switchboard (e.g., 45°C), so that the manager can check information on the abnormal condition that occurred, information related to the switchboard component that caused the abnormal condition, temporal / spatial history information of the abnormal condition, temporal / spatial history information of the switchboard component that caused the abnormal condition, and the internal temperature of the switchboard.

[0156] Meanwhile, when an abnormal condition occurs, it is necessary to notify the surroundings of the abnormal condition through visual and auditory methods. To this end, the intelligent control unit (330) is characterized by controlling an alarm device (120) installed in a power distribution panel to notify of the occurrence of an abnormal condition through at least one of an auditory method and a visual method when an abnormal condition occurs.

[0157] At this time, the auditory notification method may be a voice message, a warning sound, a siren, etc., and the visual notification method may be a flashing light. After the manager recognizes that an abnormal condition has occurred in the power distribution panel through the auditory / visual notification of the alarm device (120), the manager checks the information on the first to fourth abnormal occurrence events described above through the display (400).

[0159] Although the technical concept of the present invention has been described above together with the accompanying drawings, this is merely an illustrative description of preferred embodiments of the present invention and is not intended to limit the invention. It is obvious that the scope of the rights of the present invention is not limited to the embodiments but includes modifications made by those skilled in the art within the scope of the technical concept of the present invention. Explanation of the symbols

[0161] 100 : Switchboard 150: Temperature sensor 200: Microphone Array 300: Anomaly Diagnosis Module 400 : Display

Claims

Claim 1 In a power distribution system having an abnormality monitoring function using sound and temperature, the system comprises: a power distribution panel (100) that receives electricity from the outside and distributes it to a load, and performs a warning alarm when a door is opened; a temperature sensor (150) installed inside the power distribution panel (100) to detect temperature and provide the detected temperature information to an abnormality diagnosis module (300) and a display (400); a microphone array (200) installed inside the power distribution panel (100) to collect sound signal data generated in the power distribution panel from multiple locations and provide the collected multiple sound signal data to an abnormality diagnosis module (300); an abnormality diagnosis module (300) installed inside the power distribution panel (100) to frequency analyze the multiple sound signal data provided by the microphone array (200) to identify the occurrence of an abnormal state in the power distribution panel and to display abnormality event information regarding the abnormal state on the display (400); and an abnormality diagnosis module installed outside the power distribution panel (100) to display internal temperature information of the power distribution panel and abnormality event information. The abnormality diagnosis module (300) includes a display (400), and the abnormality diagnosis module (300) includes a preprocessing unit (310) that performs noise removal and amplification preprocessing on a plurality of acoustic signal data provided from a microphone array (200), an intelligent abnormality diagnosis unit (320) that uses artificial intelligence to frequency analyze the preprocessed plurality of acoustic signal data to identify the type / risk level / source location of an abnormality state occurring in the switchboard (100), generates analysis result information regarding the type / risk level / source location of the abnormality state, and provides it to an intelligent control unit (330), and an intelligent control unit (330) that uses the analysis result information provided by the intelligent abnormality diagnosis unit (320) and artificial intelligence to generate abnormality occurrence event information regarding the abnormality state that occurred and displays it on the display (400), wherein the types of abnormalities include partial discharge, corona discharge, arc discharge, and mechanical abnormal noise, and the intelligent abnormality diagnosis unit (320), when identifying the risk level of the abnormality state,The method is characterized by determining the risk level using the frequency waveform amplitude of an acoustic signal, and determining the final risk level using temperature information provided by a temperature sensor (150) as risk verification information, wherein after determining the risk level of an abnormal state first using the frequency waveform amplitude of the acoustic signal, if the internal temperature of the switchboard based on the temperature information is within the temperature range corresponding to the risk level of the abnormal state determined first, the risk level of the abnormal state determined first is determined as the final risk level, and after determining the risk level of an abnormal state first using the frequency waveform amplitude of the acoustic signal, if the internal temperature of the switchboard based on the temperature information is not within the temperature range corresponding to the risk level of the abnormal state determined first, the risk level of the abnormal state determined second, and if the risk level of the abnormal state determined second matches the risk level of the abnormal state determined first, the risk level of the abnormal state determined first is determined as the final risk level, and if the risk level of the abnormal state determined second differs from the risk level of the abnormal state determined first, the risk level of the abnormal state determined second is determined as the final risk level. Switchgear system with monitoring function. Claim 2 A switchboard system having an abnormal monitoring function using sound and temperature, wherein the switchboard (100) comprises a door sensor (110) that detects the opening of the switchboard door, and an alarm device (120) that warns, by at least one of an auditory method and a visual method, that the switchboard is in a live state when the opening of the switchboard door is detected by the door sensor (110). Claim 3 A switchboard system having an abnormality monitoring function using sound and temperature, wherein, in claim 1, the microphone array (200) includes a plurality of MEMS microphones (210) that provide collected acoustic signal data along with their identification information to an abnormality diagnosis module (300), and the plurality of MEMS microphones (210) are installed inside a switchboard (100). Claim 4 delete Claim 5 delete Claim 6 In claim 1, the intelligent abnormal state diagnosis unit (320) is characterized by using artificial intelligence that has learned the frequency characteristics of acoustic signal data regarding an abnormal state that may occur in a switchboard (100), performing frequency analysis on a plurality of preprocessed acoustic signal data to identify the type and risk level of the abnormal state that has occurred, identifying MEMS microphones (210) that have provided acoustic signal data having the frequency characteristics of the abnormal state that has occurred among a plurality of MEMS microphones (210) constituting a microphone array (200), and identifying the location of the source of the abnormal state within the switchboard that has occurred by using the installation location information of the identified MEMS microphones (210) and the reception time information of the acoustic signal data having the frequency characteristics of the abnormal state that has occurred. Claim 7 In claim 1, the intelligent control unit (330) generates first abnormal occurrence event information, which is basic information regarding the abnormal state, and second abnormal occurrence event information, which is detailed information regarding the abnormal state, by using artificial intelligence with analysis result information including the type / risk level / location of the source of the abnormal state provided by the intelligent abnormal state diagnosis unit (320), 3D-based external image information of the switchboard, and 2D-based internal design drawing information of the switchboard, and causes the generated first abnormal occurrence event information to be displayed on the display (400), and then causes the generated second abnormal occurrence event information to be displayed on the display (400) when there is a user touch on the first display icon included in the first abnormal occurrence event information, wherein the first abnormal occurrence event information is information displayed at a point on the 3D-based external image of the switchboard corresponding to the location of the source of the abnormal state, where the first display icon is displayed in a color reflecting the risk level of the abnormal state and the type information of the abnormal state is also included, and the second abnormal occurrence event information is information including switchboard component information expected to be the source that caused the abnormal state and the expected abnormal state A switchgear system having an abnormality monitoring function using sound and temperature, characterized in that a second display icon, which includes cause information and diagnostic equipment information capable of precisely diagnosing the expected cause of the abnormal condition, is information displayed at a point on a 2D-based internal design drawing of the switchgear corresponding to the location of the source of the abnormal condition. Claim 8 In claim 7, the intelligent control unit (330) uses artificial intelligence to identify a switchboard component presumed to be the source of the abnormal state, identify the presumed cause of the abnormal state, identify diagnostic equipment, and generate second abnormal occurrence event information, wherein the artificial intelligence identifies a switchboard component located at a point on the internal design drawing of the switchboard corresponding to the source location included in the analysis result information as the switchboard component presumed to be the source of the abnormal state, the artificial intelligence identifies a possible cause of the abnormal state using pre-stored cause information for each abnormal state and type information of the abnormal state included in the analysis result information, and among the identified possible causes, if there is a possible cause related to the switchboard component identified as the presumed source, the corresponding possible cause is identified as the presumed cause of the abnormal state, the artificial intelligence identifies diagnostic equipment capable of precisely diagnosing the identified presumed cause of the abnormal state, and the artificial intelligence generates second abnormal occurrence event information using the switchboard component information presumed to be the source of the identified abnormal state, the presumed cause information of the abnormal state, the diagnostic equipment information, and the switchboard internal design drawing information. System. Claim 9 In claim 7, the intelligent control unit (330) generates third abnormal event information that can identify abnormal states that have occurred up to now in chronological order using artificial intelligence and existing first abnormal event information, and displays it on a display (400), wherein the third abnormal event information is characterized in that a plurality of third display icons, each having information on the type of abnormal state, are displayed at points on a 3D-based external image of a power distribution board corresponding to the location of the source of the abnormal state, and the plurality of third display icons are information connected by arrows so as to know the order of occurrence of the abnormal state. Claim 10 In claim 7, the intelligent control unit (330) generates a fourth abnormal event information that can identify, in chronological order, switchgear components presumed to be the source of the abnormal state that has occurred so far using artificial intelligence and previously generated second abnormal event information, and displays it on a display (400); wherein the fourth abnormal event information is characterized in that a plurality of fourth display icons, in which switchgear component information presumed to be the source of the abnormal state and information on the presumed cause of the abnormal state are combined, are displayed at points on a 2D-based switchgear internal design drawing corresponding to the location of the source of the abnormal state, and the plurality of fourth display icons are information connected by arrows so as to know the order of failure of switchgear components. Claim 11 A switchgear system having an abnormality monitoring function using sound and temperature, wherein, in claim 7, the intelligent control unit (330) generates abnormal state occurrence notification information including second abnormal occurrence event information using artificial intelligence and provides it to an administrator terminal. Claim 12 A switchboard system having an abnormality monitoring function using sound and temperature, wherein, in claim 1, the intelligent control unit (330) controls an alarm device (120) installed in the switchboard to notify of the occurrence of an abnormal state by at least one of an auditory method and a visual method when an abnormal state occurs.

Images