Intelligent lightning arrester detection method and device

Abstract

The invention provides an intelligent lightning arrester detection method and device. The method comprises the steps that in response to monitoring that a lightning arrester fails to complete lightning protection operation, multi-modal data of the lightning arrester are acquired, and the multi-modal data comprise temperature and humidity data, power data and mechanical state data; obtaining a three-dimensional model of the lightning arrester; inputting the three-dimensional model and the multi-modal data into a reasoning model, so that the reasoning model performs lightning protection simulation on the three-dimensional model according to the multi-modal data; and inputting the multi-modal data and process data generated by lightning protection simulation into a classification model in real time to enable the classification model to monitor the process data, and outputting a lightning arrester fault type based on the multi-modal data and abnormal data under the condition that the abnormal data is monitored. The invention provides an intelligent detection scheme for the lightning arrester, and fault detection and fault type notification can be realized under the condition that the lightning arrester does not complete lightning protection operation.

Description

Technical Field

[0001] The present application relates to the field of electrical data processing, and in particular to an intelligent lightning arrester detection method and device. Background Art

[0002] With the continuous development of the power system, the demand for protection of power facilities is increasing. As an important protective equipment in the power system, the reliability and effectiveness of lightning arresters are directly related to the safe and stable operation of the power system.

[0003] Traditional arrester fault detection methods mainly rely on manual inspections and basic electrical tests. This method is not only inefficient, but also easy to miss hidden dangers in complex and changeable operating environments. Especially in areas with frequent thunderstorms, the health of the arrester directly affects the safety of the power grid. In addition, with the development of smart grid technology, higher requirements are placed on the real-time monitoring and intelligent diagnosis of arresters. Traditional detection methods cannot meet the needs of modern power systems for early detection and timely handling of arrester faults.

[0004] Therefore, the present application provides an intelligent lightning arrester detection method and device to solve one of the above technical problems. Summary of the invention

[0005] The purpose of this application is to provide an intelligent lightning arrester detection method and device, which can solve at least one of the above-mentioned technical problems. The specific solution is as follows: According to a specific implementation of the present application, in a first aspect, the present application provides an intelligent lightning arrester detection method, comprising: In response to monitoring that a lightning arrester fails to complete a lightning protection operation, multimodal data of the lightning arrester is obtained, the multimodal data including temperature and humidity data, power data, and mechanical status data; a three-dimensional model of the lightning arrester is obtained; the three-dimensional model and the multimodal data are input into an inference model, so that the inference model performs a lightning protection simulation on the three-dimensional model according to the multimodal data; the multimodal data and process data generated by the lightning protection simulation are input into a classification model in real time, so that the classification model monitors the process data, and when abnormal data is detected, the lightning arrester fault type is output based on the multimodal data and the abnormal data.

[0006] In one embodiment, the temperature and humidity data include ambient temperature, ambient humidity and internal temperature of the arrester, and the arrester fault type includes a first fault type characterizing equipment overheating; the classification model refers to at least one of the following data to output the first fault type: working state characterization data of the arrester in the abnormal data; the temperature difference between the internal temperature and the ambient temperature; equipment temperature rise coefficient; wherein the equipment temperature rise coefficient is used to characterize the temperature change rate of the arrester from the current moment to the next moment, and the equipment temperature rise coefficient is obtained based on a preset functional relationship between the ambient humidity, the power data and the equipment temperature rise coefficient.

[0007] In one implementation, the preset functional relationship is expressed by the following formula: Trate =k1·H+k2·P+k3; where Δ Trate It represents the temperature rise coefficient of the equipment, H represents the ambient humidity, P represents the power data, and k1, k2 and k3 represent different coefficients.

[0008] In one embodiment, the arrester fault type includes a second fault type that characterizes an electrical fault; the classification model refers to at least one of the following data to output the second fault type: a working state of the arrester represented by the abnormal data; an expected power deviation value; wherein the expected power deviation value is the difference between the power value represented by the abnormal data and the power value represented by the power data.

[0009] In one embodiment, the mechanical state data includes the posture adjustment response and vibration condition of the lightning arrester, and the lightning arrester fault type includes a third fault type characterizing mechanical damage; the classification model refers to at least one of the following data to output the third fault type: the three-dimensional model; the posture adjustment response of the lightning arrester; the vibration condition of the lightning arrester.

[0010] According to a specific implementation of the present application, in a second aspect, the present application provides an intelligent lightning arrester detection device, comprising: An acquisition unit, in response to monitoring that a lightning arrester fails to complete a lightning protection operation, acquires multimodal data of the lightning arrester, the multimodal data including temperature and humidity data, power data, and mechanical state data; and is used to acquire a three-dimensional model of the lightning arrester; a processing unit, for inputting the three-dimensional model and the multimodal data into an inference model so that the inference model performs a lightning protection simulation on the three-dimensional model according to the multimodal data; and for inputting the multimodal data and process data generated by the lightning protection simulation into a classification model in real time so that the classification model monitors the process data and, when abnormal data is detected, outputs a lightning arrester fault type based on the multimodal data and the abnormal data.

[0011] In one embodiment, the temperature and humidity data include ambient temperature, ambient humidity and internal temperature of the arrester, and the arrester fault type includes a first fault type characterizing equipment overheating; the classification model refers to at least one of the following data to output the first fault type: working state characterization data of the arrester in the abnormal data; the temperature difference between the internal temperature and the ambient temperature; equipment temperature rise coefficient; wherein the equipment temperature rise coefficient is used to characterize the temperature change rate of the arrester from the current moment to the next moment, and the equipment temperature rise coefficient is obtained based on a preset functional relationship between the ambient humidity, the power data and the equipment temperature rise coefficient.

[0012] In one implementation, the preset functional relationship is expressed by the following formula: Trate =k1·H+k2·P+k3; where Δ Trate It represents the temperature rise coefficient of the equipment, H represents the ambient humidity, P represents the power data, and k1, k2 and k3 represent different coefficients.

[0013] In one embodiment, the arrester fault type includes a second fault type that characterizes an electrical fault; the classification model refers to at least one of the following data to output the second fault type: a working state of the arrester represented by the abnormal data; an expected power deviation value; wherein the expected power deviation value is the difference between the power value represented by the abnormal data and the power value represented by the power data.

[0014] In one embodiment, the mechanical state data includes the posture adjustment response and vibration condition of the lightning arrester, and the lightning arrester fault type includes a third fault type characterizing mechanical damage; the classification model refers to at least one of the following data to output the third fault type: the three-dimensional model; the posture adjustment response of the lightning arrester; the vibration condition of the lightning arrester.

[0015] Compared with the prior art, the above-mentioned scheme of the embodiment of the present application has at least the following beneficial effects: the present application obtains multimodal data (temperature and humidity data, power data, mechanical status data), a three-dimensional model, and inputs it into the inference model for lightning protection simulation, and then inputs the simulation results and actual data into the classification model to detect the fault type. This method can comprehensively consider various factors and improve the accuracy and efficiency of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of an intelligent lightning arrester detection method according to an embodiment of the present application is shown; Figure 2 A unit block diagram of an intelligent lightning arrester detection device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0018] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0019] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0020] It should be understood that although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0021] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0022] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0023] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0024] The optional embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0025] The embodiment provided in this application is an embodiment of an intelligent lightning arrester detection method.

[0026] Combine the following Figure 1 The embodiments of the present application are described in detail.

[0027] Figure 1 A flow chart of an intelligent lightning arrester detection method according to an embodiment of the present application is shown. Figure 1 As shown, the following steps are included.

[0028] Step S101, in response to monitoring that a lightning arrester fails to complete a lightning protection operation, multimodal data of the lightning arrester is acquired.

[0029] Among them, multimodal data includes temperature and humidity data, power data, and mechanical status data.

[0030] Step S102, obtaining a three-dimensional model of the arrester.

[0031] Step S103: input the three-dimensional model and the multimodal data into the inference model, so that the inference model performs lightning protection simulation on the three-dimensional model according to the multimodal data.

[0032] Step S104, inputting the multimodal data and process data generated by the lightning protection simulation into the classification model in real time, so that the classification model monitors the process data, and outputs the arrester fault type based on the multimodal data and the abnormal data when abnormal data is detected.

[0033] In the present application, the arrester fails to complete the lightning protection operation, for example, in the following situations. The arrester is overloaded or overheated. The current that the arrester bears during a lightning strike exceeds its design capacity, causing the internal components to overheat or even melt, and it can no longer provide protection. The arrester has an electrical failure. A short circuit or open circuit occurs inside the arrester, causing it to be unable to conduct the lightning current normally, thereby exposing the protected equipment to overvoltage. The arrester has a power regulation failure or a control circuit failure, causing the arrester to be unable to adjust its working state as required. The arrester is mechanically damaged. The arrester is physically impacted or vibrated, causing damage to its internal structure, affecting its normal operation. The posture adjustment mechanism fails, causing the arrester to be unable to properly align with the lightning path. Communication failure. The communication between the arrester and the monitoring system is interrupted, resulting in the inability to remotely monitor its status or receive control instructions.

[0034] In a lightning protection operation scenario, a plurality of lightning arresters are usually arranged in an area to work together. When one or several lightning arresters fail to complete the lightning protection operation, the above step S101 is triggered to execute, and then fault detection is performed on the one or several lightning arresters that failed to complete the lightning protection operation respectively, so as to quickly know the arrester fault type when it is determined that the arrester has a fault.

[0035] In this application, by acquiring multimodal data including temperature and humidity data, power data, and mechanical status data, and combining it with a three-dimensional model of the arrester, a lightning protection simulation is performed using an inference model. This method can fully reflect the working status of the arrester under different environmental conditions, monitor the data generated during the simulation in real time through a classification model, and accurately determine the fault type when an abnormality is found. This method improves the accuracy and timeliness of fault detection, helps prevent potential equipment failures, and ensures the stable operation of the power system.

[0036] In one implementation, the temperature and humidity data include the ambient temperature, the ambient humidity, and the internal temperature of the arrester, and the arrester fault type includes a first fault type indicating overheating of the device.

[0037] The classification model refers to at least one of the following data to output a first fault type: Data 1: Characterization data of the working status of the lightning arrester in abnormal data.

[0038] Data 2: The temperature difference between the internal temperature and the ambient temperature.

[0039] Data 3: Equipment temperature rise coefficient.

[0040] Among them, the data representing the working status of the arrester in the abnormal data include various indicators reflecting the abnormal operation of the arrester, such as the abnormal temperature difference between the internal temperature and the ambient temperature, the abnormal increase of the equipment temperature rise coefficient, etc. These data can help identify whether the arrester is in an overheated state. The equipment temperature rise coefficient is used to characterize the temperature change rate of the arrester from the current moment to the next moment. The equipment temperature rise coefficient is obtained based on the preset functional relationship between the ambient humidity, power data and the equipment temperature rise coefficient.

[0041] In an embodiment of the present application, by including temperature and humidity data of ambient temperature, ambient humidity and internal temperature of the arrester, combined with the working status characterization data of the arrester, the temperature difference between the internal temperature and the ambient temperature and the temperature rise coefficient of the equipment, the operating status of the arrester can be comprehensively monitored and the type of overheating fault can be accurately identified. This method can timely detect and warn of overheating problems of the arrester, improve the accuracy and response speed of fault detection, and thus ensure the safe and stable operation of the power system.

[0042] For example, the preset functional relationship adopts the formula Δ Trate =k1·H+k2·P+k3.

[0043] Among them, Δ Trate It represents the temperature rise coefficient of the equipment, H represents the ambient humidity, P represents the power data, and k1, k2 and k3 represent different coefficients.

[0044] In the embodiment of the present application, the preset functional relationship of the temperature rise coefficient of the equipment is exemplified. By quantitatively analyzing the relationship between the ambient humidity, power data and the temperature rise coefficient of the equipment, the thermal performance of the arrester can be more accurately evaluated, thereby improving the accuracy and reliability of overheating fault detection. In addition, other functions that can realize relationship representation can also be used, which are not described in detail in this application.

[0045] In the present application, the arrester fault type includes a second fault type representing an electrical fault.

[0046] In a feasible implementation manner, the classification model refers to at least one of the following data to output the second fault type.

[0047] Data 1: The working status of the arrester represented by abnormal data.

[0048] Data 2: Expected power deviation value.

[0049] In the present application, the arrester working state represented by the abnormal data includes the deviation of the arrester working state mark, and the data reflects the electrical fault problem that may occur in the arrester. The power expected deviation value is the difference between the power value represented by the abnormal data and the power value represented by the power data.

[0050] Among them, it should be noted that the power value in the abnormal data usually refers to the power measurement value that is found to be beyond the normal range or does not conform to the expected pattern during the monitoring process, which indicates that the lightning arrester has some form of failure or abnormal behavior. The power data is a general power measurement value monitored under normal operating conditions, which represents the power characteristics that the lightning arrester should have in a fault-free state. The deviation between the power value in the abnormal data and the normal power data is called the power expected deviation value, which can be used to identify whether there is an electrical fault in the lightning arrester. Therefore, the difference between the power values ​​in the abnormal data and the conventional power data is that they reflect whether the operating state of the lightning arrester deviates from the normal operating range. Therefore, the introduction of the power expected deviation value improves the accuracy of electrical fault detection.

[0051] In addition, the working state of the arrester represented by abnormal data mainly refers to the deviation of the arrester working state mark. This type of data directly reflects the abnormal changes in the arrester working state, such as overheating, poor electrical connection, etc., while the power expected deviation value refers to the difference between the actual measured power value and the expected power value. This deviation value is used to measure whether the arrester has reached its expected power level in actual operation, and is one of the important bases for judging the electrical fault of the arrester. In short, the former focuses on the changes in the working state of the arrester, while the latter focuses on evaluating the consistency between the actual power performance of the arrester and the expected one. Referring to the above two types of data is conducive to the realization of high-precision arrester electrical fault detection, so as to output the second fault type in the event of an electrical fault in the arrester.

[0052] In an embodiment of the present application, by analyzing the working status of the lightning arrester and the expected power deviation value represented by the abnormal data, it is possible to promptly detect whether there is an electrical fault in the lightning arrester. This method helps to quickly identify electrical anomalies and avoid larger-scale system failures caused by electrical problems, thereby improving the overall safety and stability of the power system.

[0053] In the present application, the mechanical state data includes the posture adjustment response and vibration conditions of the arrester, and the arrester fault type includes a third fault type that characterizes mechanical damage.

[0054] In one feasible implementation, the classification model refers to at least one of the following data to output the third fault type: Data 1: Three-dimensional model.

[0055] Data 2: Arrester position adjustment response.

[0056] Data 3: Vibration condition of lightning arrester.

[0057] In the present application, the posture adjustment response of the arrester and the vibration of the arrester are obtained through sensors. The posture adjustment response can be known based on the response speed and accuracy of the arrester to external control instructions, for example, after receiving the adjustment command, whether the arrester can reach the specified position within the specified time. The vibration condition can be measured by an accelerometer or other vibration sensor to evaluate whether the arrester is vibrating due to external factors such as wind, earthquake or internal factors such as mechanical wear.

[0058] In an embodiment of the present application, the presence of mechanical damage is determined by monitoring the posture adjustment response and vibration of the arrester. This method can effectively identify mechanical failures, ensure the normal operation of the arrester in a complex environment, extend the service life of the equipment, and reduce maintenance costs.

[0059] In addition to the above data, the present application can also further analyze the arrester mode through other useful data to achieve other types of fault detection, such as electric field strength detection, partial discharge detection, communication stability detection, etc. Some feasible detection methods are shown below.

[0060] For example, an electric field strength detector can be used to detect changes in the surrounding electric field. If the electric field strength is abnormally high, it means that a thunderstorm is about to occur. At this time, the monitoring of the lightning arrester should be strengthened and necessary protective measures should be taken.

[0061] For example, partial discharge detection can be achieved through high-frequency pulse current detection or ultra-high frequency detection. For example, the high-frequency pulse current method is used to detect whether there is partial discharge inside the lightning arrester. If an abnormal high-frequency pulse current is detected, it may mean that partial discharge has occurred inside the lightning arrester and further inspection is required. For another example, ultra-high frequency (UHF) technology is used to monitor whether there is partial discharge inside the lightning arrester. This method can capture the electromagnetic wave signal generated by partial discharge and help locate the problem area.

[0062] For example, the wireless communication module of the lightning arrester can be tested for communication stability to ensure that data transmission and control command reception are not interfered with. In addition, the delay time and packet loss rate of data transmission by the lightning arrester can also be monitored to ensure the quality of the communication channel.

[0063] The detection methods mentioned in the embodiments of the present application can be combined with the aforementioned detection methods to further expand the fault types, such as the fourth fault type characterizing partial discharge, and the fifth fault type characterizing unstable communication.

[0064] The intelligent lightning arrester detection method provided in the present application can be applied to lightning arrester fault detection in a variety of different power usage scenarios.

[0065] For example, in a wind farm, multimodal data of the wind turbine tower base is collected in real time by installing temperature and humidity sensors, vibration sensors, power monitoring devices, etc., and the overall layout of the wind farm is obtained by using drone aerial photography technology to establish a three-dimensional model of the wind turbine and its lightning arrester. These data and models are imported into the intelligent detection system, and the lightning protection simulation is performed using the inference model. The data changes during the simulation process are monitored in real time through the classification model. Once abnormal data is found, the system determines the fault type based on multimodal data analysis and sends alarm information to the operation and maintenance personnel through the wireless communication module.

[0066] For example, for urban high-rise buildings, temperature and humidity sensors, vibration sensors, power monitoring devices, etc. can be installed on the top and around the building to collect multimodal data in real time, and use architectural drawings and 3D modeling software to build a three-dimensional model of the building and its lightning protection system. Import the data and model into the intelligent detection system, use the inference model to perform lightning protection simulation, and use the classification model to monitor data changes in the simulation process in real time. When abnormal data is detected, the system determines the type of fault based on multimodal data analysis and sends an alarm message to the property management personnel through the wireless communication module.

[0067] For another example, in a smart park, temperature and humidity sensors, vibration sensors, power monitoring devices, etc. can be installed around each power facility to collect multimodal data in real time, and a three-dimensional model of the power facility and its lightning protection system can be established using the park planning map and 3D modeling software. These data and models are imported into the intelligent detection system, and the lightning protection simulation is performed using the inference model. The data changes during the simulation are monitored in real time through the classification model. Once abnormal data is found, the system determines the fault type based on multimodal data analysis and sends an alarm message to the park management platform through the wireless communication module.

[0068] This application collects multimodal data in real time and combines it with a three-dimensional model to perform lightning protection simulation, and uses a classification model to monitor abnormal data during the simulation process, so as to accurately determine the fault type of the lightning arrester, including overheating, electrical failure, and mechanical damage. This method not only improves the accuracy and timeliness of fault detection, but also enhances the overall safety and stability of the power system, ensures the normal operation of power facilities in complex environments, and further ensures the reliable operation of the system by optimizing communication quality and enhancing anti-interference capabilities.

[0069] The present application also provides an apparatus embodiment that is consistent with the above embodiment, which is used to implement the method steps of the above embodiment. The explanation based on the same name meaning is the same as the above embodiment, and has the same technical effect as the above embodiment, which will not be repeated here.

[0070] like Figure 2 As shown, the present application provides an intelligent lightning arrester detection device 200, comprising: The acquisition unit 201, in response to monitoring that there is a lightning arrester that fails to complete the lightning protection operation, obtains the multimodal data of the lightning arrester, and the multimodal data includes temperature and humidity data, power data, and mechanical state data. And is used to obtain a three-dimensional model of the lightning arrester. The processing unit 202 is used to input the three-dimensional model and the multimodal data into the reasoning model so that the reasoning model performs lightning protection simulation on the three-dimensional model according to the multimodal data. And it is used to input the process data generated by the multimodal data and the lightning protection simulation into the classification model in real time, so that the classification model monitors the process data, and outputs the lightning arrester fault type based on the multimodal data and the abnormal data when abnormal data is monitored.

[0071] In one embodiment, the temperature and humidity data include the ambient temperature, the ambient humidity, and the internal temperature of the arrester, and the arrester fault type includes a first fault type characterizing the overheating of the device. The classification model refers to at least one of the following data to output the first fault type: data characterizing the working state of the arrester in the abnormal data. The temperature difference between the internal temperature and the ambient temperature. The temperature rise coefficient of the device. Among them, the temperature rise coefficient of the device is used to characterize the temperature change rate of the arrester from the current moment to the next moment, and the temperature rise coefficient of the device is obtained based on a preset functional relationship between the ambient humidity, the power data, and the temperature rise coefficient of the device.

[0072] In one implementation, the preset functional relationship is expressed by the following formula: Trate =k1·H+k2·P+k3. Among them, Δ Trate It represents the temperature rise coefficient of the equipment, H represents the ambient humidity, P represents the power data, and k1, k2 and k3 represent different coefficients.

[0073] In one embodiment, the arrester fault type includes a second fault type representing an electrical fault. The classification model refers to at least one of the following data to output the second fault type: an arrester operating state represented by the abnormal data. A power expected deviation value. The power expected deviation value is a difference between a power value represented by the abnormal data and a power value represented by the power data.

[0074] In one embodiment, the mechanical state data includes the posture adjustment response and vibration of the arrester, and the arrester fault type includes a third fault type characterizing mechanical damage. The classification model refers to at least one of the following data to output the third fault type: a three-dimensional model, a posture adjustment response of the arrester, and a vibration of the arrester.

[0075] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0076] In some embodiments, the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, any of the methods described above is performed.

[0077] In some embodiments, the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, any of the methods described above is performed.

[0078] Although operations are described in a particular order in the drawings, this should not be understood as requiring that the operations be performed in the particular order shown or in serial order, or that all shown operations be performed to achieve desired results. In certain circumstances, multitasking and parallel processing may be advantageous.

[0079] The methods and devices of the present application can be implemented using standard programming techniques, using rule-based logic or other logic to implement various method steps. It should also be noted that the words "device" and "module" used herein and in the claims are intended to include implementations using one or more lines of software code and / or hardware implementations and / or devices for receiving input.

[0080] Any steps, operations or procedures described herein may be performed or implemented using one or more hardware or software modules, either alone or in combination with other devices. In one embodiment, the software module is implemented using a computer program product including a computer-readable medium containing computer program code, which can be executed by a computer processor to perform any or all of the described steps, operations or procedures.

[0081] The foregoing description of the implementation of the present application has been given for the purpose of illustration and description. The foregoing description is not exhaustive nor is it intended to limit the present application to the exact form disclosed, and various variations and modifications may exist according to the above teachings or may be obtained from the practice of the present application. These embodiments are selected and described in order to illustrate the principles of the present application and its practical application, so that those skilled in the art can utilize the present application in various embodiments and various modifications suitable for the specific purpose contemplated.

[0082] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0083] It can be further understood that, unless otherwise specified, “connection” includes a direct connection without other components between the two, and also includes an indirect connection with other components between the two.

[0084] It is further understood that, although the operations are described in a specific order in the drawings in the embodiments of the present application, it should not be understood as requiring the operations to be performed in the specific order or serial order shown, or requiring the execution of all the operations shown to obtain the desired results. In certain environments, multitasking and parallel processing may be advantageous.

[0085] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to encompass any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the field of the present application that are not disclosed in the present application. The specification and embodiments are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following scope of rights.

[0086] It should be understood that the present application is not limited to the precise structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the scope of the appended claims.

[0087] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting an intelligent lightning arrester, characterized in that: include: In response to monitoring that a lightning arrester fails to complete a lightning protection operation, multimodal data of the lightning arrester is acquired, wherein the multimodal data includes temperature and humidity data, power data, and mechanical state data; Obtaining a three-dimensional model of the arrester; Inputting the three-dimensional model and the multimodal data into a reasoning model, so that the reasoning model performs a lightning protection simulation on the three-dimensional model according to the multimodal data; The multimodal data and the process data generated by the lightning protection simulation are input into the classification model in real time, so that the classification model monitors the process data, and outputs the arrester fault type based on the multimodal data and the abnormal data when abnormal data is detected.

2. The intelligent lightning arrester detection method according to claim 1, characterized in that: The temperature and humidity data include the ambient temperature, the ambient humidity and the internal temperature of the arrester, and the arrester fault type includes a first fault type indicating overheating of the device; The classification model refers to at least one of the following data to output the first fault type: The working state characterization data of the arrester in the abnormal data; a temperature difference between the internal temperature and the ambient temperature; Equipment temperature rise coefficient; The device temperature rise coefficient is used to characterize the temperature change rate of the arrester from the current moment to the next moment, and the device temperature rise coefficient is obtained based on a preset functional relationship between the ambient humidity, the power data and the device temperature rise coefficient.

3. The intelligent lightning arrester detection method according to claim 2, characterized in that: The preset functional relationship is expressed by the following formula: Δ Trate =k1·H+k2·P+k3; Among them, Δ Trate It represents the temperature rise coefficient of the equipment, H represents the ambient humidity, P represents the power data, and k1, k2 and k3 represent different coefficients.

4. The intelligent lightning arrester detection method according to claim 1, characterized in that: The arrester fault type includes a second fault type characterizing an electrical fault; The classification model refers to at least one of the following data to output the second fault type: The working state of the arrester represented by the abnormal data; Power expected deviation value; The expected power deviation value is the difference between the power value represented by the abnormal data and the power value represented by the power data.

5. The intelligent lightning arrester detection method according to claim 1, characterized in that: The mechanical state data includes the posture adjustment response and vibration of the arrester, and the arrester fault type includes a third fault type representing mechanical damage; The classification model refers to at least one of the following data to output the third fault type: the three-dimensional model; The posture adjustment response of the arrester; The vibration condition of the lightning arrester.

6. An intelligent lightning arrester detection device, characterized in that: include: an acquisition unit, in response to monitoring that a lightning arrester fails to complete a lightning protection operation, acquiring multimodal data of the lightning arrester, wherein the multimodal data includes temperature and humidity data, power data, and mechanical state data; and for obtaining a three-dimensional model of the arrester; A processing unit, configured to input the three-dimensional model and the multimodal data into a reasoning model, so that the reasoning model performs a lightning protection simulation on the three-dimensional model according to the multimodal data; And it is used to input the multimodal data and the process data generated by the lightning protection simulation into the classification model in real time, so that the classification model monitors the process data, and outputs the lightning arrester fault type based on the multimodal data and the abnormal data when abnormal data is monitored.

7. The intelligent lightning arrester detection device according to claim 6, characterized in that: The temperature and humidity data include the ambient temperature, the ambient humidity and the internal temperature of the arrester, and the arrester fault type includes a first fault type indicating overheating of the device; The classification model refers to at least one of the following data to output the first fault type: The working state characterization data of the arrester in the abnormal data; a temperature difference between the internal temperature and the ambient temperature; Equipment temperature rise coefficient; The device temperature rise coefficient is used to characterize the temperature change rate of the arrester from the current moment to the next moment, and the device temperature rise coefficient is obtained based on a preset functional relationship between the ambient humidity, the power data and the device temperature rise coefficient.

8. The intelligent lightning arrester detection device according to claim 7, characterized in that: The preset functional relationship is expressed by the following formula: Δ Trate =k1·H+k2·P+k3; Among them, Δ Trate It represents the temperature rise coefficient of the equipment, H represents the ambient humidity, P represents the power data, and k1, k2 and k3 represent different coefficients.

9. The intelligent lightning arrester detection device according to claim 6, characterized in that: The arrester fault type includes a second fault type characterizing an electrical fault; The classification model refers to at least one of the following data to output the second fault type: The working state of the arrester represented by the abnormal data; Power expected deviation value; The expected power deviation value is the difference between the power value represented by the abnormal data and the power value represented by the power data.

10. The intelligent lightning arrester detection device according to claim 6, characterized in that: The mechanical state data includes the posture adjustment response and vibration of the arrester, and the arrester fault type includes a third fault type representing mechanical damage; The classification model refers to at least one of the following data to output the third fault type: the three-dimensional model; The posture adjustment response of the arrester; The vibration condition of the lightning arrester.

Images