High and low voltage distribution box fault diagnosis method and system based on Internet of Things

Abstract

The invention relates to a high-low voltage distribution box fault diagnosis method and system based on the Internet of Things, and relates to the technical field of fault diagnosis. The method comprises the following steps: acquiring historical fault information, sound waveform data, equipment vibration data, image feature data and equipment temperature data of the high-low voltage distribution box, performing data information association construction on the historical fault information, sound waveform data, equipment vibration data, image feature data and equipment temperature data according to time sequence nodes, and selecting association data information after association construction according to a preset time interval to obtain multi-dimensional data, carrying out training test on the fault diagnosis model based on the multi-dimensional data to obtain a test result, judging whether the test result meets a preset test result standard, and if yes, carrying out fault diagnosis; if yes, real-time waveform data, real-time vibration data, real-time characteristic data, real-time temperature data and working parameter data of the high-low voltage distribution box are collected and input into the trained fault diagnosis model, and fault diagnosis information of the high-low voltage distribution box is obtained. According to the invention, the fault diagnosis efficiency of the high-low voltage distribution box is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and in particular to a method and system for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things. Background Art

[0002] With the rapid development of the economy, the power system plays an extremely critical role in social production and life. As the core component of the power system, the operation status of high and low voltage distribution boxes is directly related to the stability and safety of the power supply system. However, due to the complexity of the power equipment and system operating environment, equipment failures and accidents occur frequently, posing a serious threat to the stable operation of the power system.

[0003] Traditional fault diagnosis methods for high and low voltage distribution boxes mainly include visual inspection and electrical parameter measurement. The visual inspection method relies on the technicians to carefully observe the electrical components inside the distribution box, and some obvious physical damage or connection problems can be found. The electrical parameter measurement method uses tools such as voltmeters, ammeters, and resistance meters to measure the electrical parameters of the distribution box to determine the working status of the electrical components.

[0004] Although these methods have achieved certain results in practical applications, they still have many limitations. First, the visual inspection method is limited by the experience and subjective judgment of technicians, and may miss some hidden or subtle faults. Secondly, although the electrical parameter measurement method can provide some quantitative data, the measurement process is cumbersome and requires professional technicians to operate. In addition, with the emergence of abnormal conditions such as aging or failure of the equipment for detecting electrical parameters, the electrical parameters measured by the electrical parameter measurement method have accuracy problems. Therefore, the prior art has the defect of low efficiency in fault diagnosis of high and low voltage distribution boxes. Summary of the invention

[0005] In order to solve at least one of the above technical problems, the present application provides a high and low voltage distribution box fault diagnosis method and system based on the Internet of Things.

[0006] In the first aspect, the present application provides a method for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things, which adopts the following technical solutions: A high and low voltage distribution box fault diagnosis method based on the Internet of Things, comprising: Obtain historical fault information of high and low voltage distribution boxes and sound waveform data, equipment vibration data, image feature data and equipment temperature data of the high and low voltage distribution boxes each time a fault occurs in the historical fault information, wherein the historical fault information is the working parameter change information and fault details of the high and low voltage distribution boxes when they present a fault state within a historical period, and the equipment vibration data and the equipment temperature data are vibration data and temperature data corresponding to nodes at different positions of the high and low voltage distribution boxes, respectively; The historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data are associated with each other according to time series nodes, and the associated data information after the association is constructed is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; Performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; Performing training and testing on the fault diagnosis model based on the processed multi-dimensional data to obtain test results; Determine whether the test result meets the preset test result standard. If so, collect the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data of the high and low voltage distribution box, and input the real-time waveform data, the real-time vibration data, the real-time feature data, the real-time temperature data and the working parameter data into the trained fault diagnosis model to obtain the fault diagnosis information of the high and low voltage distribution box.

[0007] By adopting the above technical solution, comprehensive historical fault information and sound waveforms, equipment vibration, image features, and equipment temperature of high and low voltage distribution boxes are obtained. These data not only cover the detailed parameter changes at the time of the fault, but also take into account the vibration and temperature differences of nodes at different locations, making the fault characteristics more three-dimensional and accurate. The multi-dimensional data is associated and constructed according to the time series nodes, and the data of different time nodes are selected, which effectively avoids data redundancy, while retaining the timeline of fault development, so that fault diagnosis can trace the history. It makes subsequent analysis more efficient and targeted. The multi-dimensional data is preprocessed to remove noise and interference, improve data quality, and provide a reliable foundation for the training of subsequent fault diagnosis models. It helps the model to capture fault characteristics more accurately. The fault diagnosis model is trained based on the processed multi-dimensional data, and the accuracy of the model is verified by the test results. It ensures that the model can accurately identify the fault type of the high and low voltage distribution box, and improves the efficiency and accuracy of fault diagnosis. When the test results meet the preset standards, the multi-dimensional data of the high and low voltage distribution box is collected in real time and input into the trained fault diagnosis model to obtain fault diagnosis information immediately. It greatly shortens the fault response time, improves the stability and safety of the power system, and thus improves the fault diagnosis efficiency of high and low voltage distribution boxes.

[0008] In a preferred example, the present application may be further configured as follows: the training and testing of the fault diagnosis model based on the processed multi-dimensional data includes: Select and segment the multi-dimensional data to obtain a training data set and a test data set; Inputting the training data set into the fault diagnosis model for training to obtain a trained fault diagnosis model; The test data set is input into the trained fault diagnosis model to perform a model verification test to obtain a test result.

[0009] In a preferred example, the present application can be further configured as follows: the historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data are associated with each other according to time series nodes, and the associated data information after the association is constructed is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes, including: Determine the operating current data, operating voltage data, fault type and fault duration at different time nodes according to the historical fault information; Creating a multidimensional data coordinate system, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions; Bind the image feature data, the fault type, and the fault duration to the time node of the X-axis in the multidimensional data coordinate system, and import the sound waveform data, the equipment vibration data, the equipment temperature data, the operating current data, and the operating voltage data into the multidimensional data coordinate system, respectively, to obtain a waveform change curve corresponding to the sound waveform data, a vibration change curve corresponding to the equipment vibration data, a temperature change curve corresponding to the equipment temperature data, a current change curve corresponding to the operating current data, and a voltage change curve corresponding to the operating voltage data; Performing change amplitude detection on the voltage change curve and the current change curve to determine a first time node at which the voltage change curve and the current change curve change by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the waveform change curve, the vibration change curve, and the temperature change curve to determine a second time node at which the waveform change curve, the vibration change curve, and the temperature change curve change by a second preset amplitude; Determine a sequential relationship between the first time node and the second time node, and detect the image feature data based on the sequential relationship to determine a third time node at which an abnormal change in the image feature data occurs; According to the time correspondence between the first time node, the second time node and the third time node, the historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data are associated with each other to obtain a plurality of associated data groups; Performing key data group screening on the multiple associated data groups to obtain a representative data group; The associated data in the representative data group are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.

[0010] In a preferred example, the present application may be further configured as follows: the key data group screening of the multiple associated data groups to obtain the representative data group includes: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as a first data group; if so, performing secondary matching on the at least two associated data groups according to the amplitude ratio coefficient and a preset coefficient matching condition to obtain a data group matching result; Determine, according to the data group matching result, whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data groups are defined as the third data group; The first data group, the second data group and the third data group are aggregated to obtain a representative data group.

[0011] In a preferred example, the present application may be further configured as follows: the associated data in the representative data group is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes, and the above also includes: Acquire a time interval definition standard, and use the fault type and fault duration as screening conditions to match the time interval definition standard, to obtain a first preset time interval corresponding to the first data group, a second preset time interval corresponding to the second data group, and a third preset time interval corresponding to the third data group; Determine whether the interval duration difference between the first preset time interval, the second preset time interval and the third preset time interval meets a preset duration range, and if so, calculate the average value of the first preset time interval, the second preset time interval and the third preset time interval to obtain a preset time interval; If not, determine the time interval with the shortest interval duration among the first preset time interval, the second preset time interval and the third preset time interval, and define the time interval as the preset time interval.

[0012] In a preferred example, the present application may be further configured as follows: performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data includes: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.

[0013] In a preferred example, the present application can be further configured as follows: the method further includes: Determine whether there is human activity in the preset area of ​​the high and low voltage distribution box according to the image feature data, and if there is human activity in the preset area, determine the time interval before and after the human activity when the high and low voltage distribution box fails; If the time intervals before and after meet the preset interval conditions, the personnel activity is regarded as a fault inducing factor, and the fault inducing factor is added to the fault diagnosis information to obtain the added fault diagnosis information.

[0014] In the second aspect, the present application provides a high and low voltage distribution box fault diagnosis system based on the Internet of Things, which adopts the following technical solutions: A high and low voltage distribution box fault diagnosis system based on the Internet of Things, comprising: An information acquisition module, used to acquire historical fault information of high and low voltage distribution boxes and sound waveform data, equipment vibration data, image feature data and equipment temperature data of the high and low voltage distribution boxes each time a fault occurs in the historical fault information, wherein the historical fault information is the working parameter change information and fault details of the high and low voltage distribution boxes when they present a fault state within a historical period, and the equipment vibration data and the equipment temperature data are vibration data and temperature data corresponding to nodes at different positions of the high and low voltage distribution boxes respectively; An association construction module is used to associate the historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data according to time series nodes, and select the associated data information after the association construction according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; A data processing module, used for performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; A training and testing module, used to train and test the fault diagnosis model based on the processed multi-dimensional data to obtain a test result; The data diagnosis module is used to determine whether the test result meets the preset test result standard. If so, the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data of the high and low voltage distribution box are collected, and the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data are input into the trained fault diagnosis model to obtain fault diagnosis information of the high and low voltage distribution box.

[0015] In a possible implementation, when the training and testing module performs training and testing on the fault diagnosis model based on the processed multi-dimensional data, it is specifically used to: Select and segment the multi-dimensional data to obtain a training data set and a test data set; Inputting the training data set into the fault diagnosis model for training to obtain a trained fault diagnosis model; The test data set is input into the trained fault diagnosis model to perform a model verification test to obtain a test result.

[0016] In another possible implementation, when the association construction module performs data information association construction on the historical fault information, the sound waveform data, the equipment vibration data, the image feature data, and the equipment temperature data according to time series nodes, and selects the associated data information after the association construction according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes, it is specifically used to: Determine the operating current data, operating voltage data, fault type and fault duration at different time nodes according to the historical fault information; Creating a multidimensional data coordinate system, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions; Bind the image feature data, the fault type, and the fault duration to the time node of the X-axis in the multidimensional data coordinate system, and import the sound waveform data, the equipment vibration data, the equipment temperature data, the operating current data, and the operating voltage data into the multidimensional data coordinate system, respectively, to obtain a waveform change curve corresponding to the sound waveform data, a vibration change curve corresponding to the equipment vibration data, a temperature change curve corresponding to the equipment temperature data, a current change curve corresponding to the operating current data, and a voltage change curve corresponding to the operating voltage data; Performing change amplitude detection on the voltage change curve and the current change curve to determine a first time node at which the voltage change curve and the current change curve change by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the waveform change curve, the vibration change curve, and the temperature change curve to determine a second time node at which the waveform change curve, the vibration change curve, and the temperature change curve change by a second preset amplitude; Determine a sequential relationship between the first time node and the second time node, and detect the image feature data based on the sequential relationship to determine a third time node at which an abnormal change in the image feature data occurs; According to the time correspondence between the first time node, the second time node and the third time node, the historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data are associated with each other to obtain a plurality of associated data groups; Performing key data group screening on the multiple associated data groups to obtain a representative data group; The associated data in the representative data group are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.

[0017] In another possible implementation, when the association building module performs key data group screening on the multiple associated data groups to obtain a representative data group, it is specifically used to: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as a first data group; if so, performing secondary matching on the at least two associated data groups according to the amplitude ratio coefficient and a preset coefficient matching condition to obtain a data group matching result; Determine, according to the data group matching result, whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data groups are defined as the third data group; The first data group, the second data group and the third data group are aggregated to obtain a representative data group.

[0018] In another possible implementation, the system further includes: a matching module, a first spacing module, and a second spacing module, wherein: The matching module is used to obtain a time interval definition standard, and use the fault type and fault duration as screening conditions to match the time interval definition standard, so as to obtain a first preset time interval corresponding to the first data group, a second preset time interval corresponding to the second data group, and a third preset time interval corresponding to the third data group; The first interval module is used to determine whether the interval duration difference between the first preset time interval, the second preset time interval and the third preset time interval meets a preset duration range, and if so, calculate the average value of the first preset time interval, the second preset time interval and the third preset time interval to obtain the preset time interval; The second interval module is used to determine the time interval with the shortest interval duration among the first preset time interval, the second preset time interval and the third preset time interval when the condition is not satisfied, and define the time interval as the preset time interval.

[0019] In another possible implementation, when the data processing module performs data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data, it is specifically used to: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.

[0020] In another possible implementation, the system further includes: a personnel monitoring module and an information updating module, wherein: The personnel monitoring module is used to determine whether there is personnel activity in the preset area of ​​the high and low voltage distribution box according to the image feature data, and if there is personnel activity in the preset area, determine the time interval before and after the personnel activity when the high and low voltage distribution box fails; The information updating module is used to take the personnel activity as a fault inducing factor when the time intervals meet a preset interval condition, and add the fault inducing factor to the fault diagnosis information to obtain the added fault diagnosis information.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for diagnosing high and low voltage distribution box faults based on the Internet of Things are implemented.

[0022] In a fourth aspect, the present application provides a computer storage medium, as follows: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned high and low voltage distribution box fault diagnosis method based on the Internet of Things are implemented.

[0023] In summary, this application has the following beneficial technical effects: The comprehensive historical fault information of high and low voltage distribution boxes and sound waveforms, equipment vibration, image features, and equipment temperature were obtained. These data not only cover the detailed parameter changes at the time of the fault, but also take into account the vibration and temperature differences of nodes at different locations, making the fault characteristics more three-dimensional and accurate. The multi-dimensional data is associated and constructed according to the time series nodes, and the data of different time nodes are selected, which effectively avoids data redundancy and retains the timeline of fault development, so that fault diagnosis can trace the history. This makes subsequent analysis more efficient and targeted. The multi-dimensional data is preprocessed to remove noise and interference, improve data quality, and provide a reliable foundation for the training of subsequent fault diagnosis models. It helps the model capture fault characteristics more accurately. The fault diagnosis model is trained based on the processed multi-dimensional data, and the accuracy of the model is verified by the test results. It ensures that the model can accurately identify the fault type of the high and low voltage distribution box, and improves the efficiency and accuracy of fault diagnosis. When the test results meet the preset standards, the multi-dimensional data of the high and low voltage distribution box is collected in real time and input into the trained fault diagnosis model to obtain fault diagnosis information immediately. It greatly shortens the fault response time, improves the stability and safety of the power system, and thus improves the fault diagnosis efficiency of high and low voltage distribution boxes. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a high and low voltage distribution box fault diagnosis method based on the Internet of Things in one of the embodiments of the present application.

[0025] Figure 2 It is a structural schematic diagram of a high and low voltage distribution box fault diagnosis system based on the Internet of Things in one embodiment of the present application.

[0026] Figure 3 It is a principle block diagram of an electronic device in one embodiment of the present application. DETAILED DESCRIPTION

[0027] The following is combined with Figure 1 To Attachment Figure 3 This application is described in further detail.

[0028] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] In addition, the term "and / or" 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, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0031] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0032] The embodiment of the present application provides a high and low voltage distribution box fault diagnosis method based on the Internet of Things, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected through wired or wireless communication. The embodiment of the present application does not limit this. Figure 1 As shown, the method includes: Step S10: Acquire historical fault information of the high and low voltage distribution boxes and sound waveform data, equipment vibration data, image feature data and equipment temperature data of the high and low voltage distribution boxes each time a fault occurs in the historical fault information.

[0033] Among them, the historical fault information is the working parameter change information and fault details when the high and low voltage distribution boxes are in a fault state during the historical period. The equipment vibration data and equipment temperature data are the vibration data and temperature data corresponding to the nodes at different positions of the high and low voltage distribution boxes respectively.

[0034] For the embodiments of the present application, historical fault information refers to the record of all fault events that have occurred in the high and low voltage distribution boxes in the past, including the time, type, cause, fault manifestation data, etc. of the fault. Sound waveform data is used to represent the waveform characteristics of the sound signal generated by the high and low voltage distribution boxes when a fault occurs. Equipment vibration data refers to the vibration information generated by its various components due to current, mechanical movement, etc. when the high and low voltage distribution boxes are in operation. Image feature data refers to the key features in the image information of the area where the high and low voltage distribution boxes are located captured by devices such as cameras. Equipment temperature data indicates the temperature conditions of different parts of the high and low voltage distribution boxes during operation. Among them, different position nodes refer to specific detection points or components on the high and low voltage distribution boxes.

[0035] In the embodiment of the present application, based on the Internet of Things technology, sensors and cameras installed on high and low voltage distribution boxes are used to monitor and record sound, vibration, image and temperature data in real time. Secondly, when the system detects a fault, the data preservation mechanism is immediately triggered to save the relevant data before and after the fault to the database. Finally, these data are extracted regularly or as needed to form a historical fault information data set.

[0036] Step S11: historical fault information, sound waveform data, equipment vibration data, image feature data and equipment temperature data are associated with each other according to time series nodes, and associated data information after the association is constructed is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.

[0037] For the embodiment of the present application, the operating current data, operating voltage data, fault type and fault duration at different time nodes are determined according to the historical fault information, and then a multidimensional data coordinate system is created, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is the data unit parameter of different dimensions. The image feature data, fault type and fault duration are bound to the time nodes of the X-axis in the multidimensional data coordinate system, and the sound waveform data, equipment vibration data, equipment temperature data, operating current data and operating voltage data are respectively imported into the multidimensional data coordinate system to obtain a waveform change curve corresponding to the sound waveform data, a vibration change curve corresponding to the equipment vibration data, a temperature change curve corresponding to the equipment temperature data, a current change curve corresponding to the operating current data and a voltage change curve corresponding to the operating voltage data. Then, the voltage change curve and the current change curve are subjected to a change amplitude detection to determine the first time node at which the voltage change curve and the current change curve undergo a first preset amplitude change. The first time node is defined as the starting time node, and the waveform change curve, vibration change curve, and temperature change curve are amplitude-detected to determine the second time node at which the waveform change curve, vibration change curve, and temperature change curve undergo a second preset amplitude change. The sequence relationship between the first time node and the second time node is determined, and the image feature data is detected based on the sequence relationship to determine the third time node at which the image feature data undergoes an abnormal change. According to the time correspondence between the first time node, the second time node, and the third time node, the historical fault information, sound waveform data, equipment vibration data, image feature data, and equipment temperature data are associated and constructed to obtain multiple associated data groups. Then, the multiple associated data groups are screened for key data groups to obtain representative data groups. The associated data in the representative data group is selected according to the preset time interval to obtain multi-dimensional data corresponding to different time nodes.

[0038] In the embodiment of the present application, the first preset amplitude change and the second preset amplitude change are both amplitude changes preset by the staff according to the application conditions and fault conditions of the high and low voltage distribution boxes.

[0039] Specifically, the data amplitude difference and amplitude change time interval corresponding to each associated data group are determined according to multiple associated data groups, and the data amplitude difference and amplitude change time interval are calculated by ratio, so as to obtain the amplitude proportional coefficient corresponding to each associated data group. Then, the initial data set of each associated data group at the moment before the data amplitude occurs is collected, and the initial data set corresponding to each associated data group is matched to determine whether there are at least two initial data sets corresponding to the associated data groups that match each other. If not, the associated data group is defined as the first data group. If so, the at least two associated data groups are matched twice according to the amplitude proportional coefficient and the preset coefficient matching condition to obtain the data group matching result. According to the data group matching result, it is determined whether there are at least two associated data groups whose corresponding amplitude proportional coefficients meet the preset coefficient matching condition. If so, the initial time node corresponding to the initial data set of the at least two associated data groups is determined, and the associated data group whose initial time node is close to the current time node is taken as the second data group. If there are not at least two associated data groups whose corresponding amplitude proportion coefficients satisfy the preset coefficient matching condition, the associated data group is defined as the third data group, and the first data group, the second data group and the third data group are aggregated to obtain a representative data group.

[0040] In the embodiment of the present application, the time interval definition standard is obtained, and the fault type and the duration of the fault are used as screening conditions to match the time interval definition standard, and a first preset time interval corresponding to the first data group, a second preset time interval corresponding to the second data group, and a third preset time interval corresponding to the third data group are obtained. It is determined whether the interval duration difference between the first preset time interval, the second preset time interval, and the third preset time interval meets the preset duration range. If it meets, the average value of the first preset time interval, the second preset time interval, and the third preset time interval is calculated to obtain the preset time interval. If it does not meet, the time interval with the smallest interval duration among the first preset time interval, the second preset time interval, and the third preset time interval is determined, and the time interval is defined as the preset time interval.

[0041] Step S12: performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data.

[0042] In the embodiment of the present application, data cleaning is performed on the multi-dimensional data to obtain cleaned multi-dimensional data, and then data standardization is performed on the cleaned multi-dimensional data to obtain processed multi-dimensional data.

[0043] For the embodiments of the present application, data cleaning processing refers to a series of preprocessing operations on the original data to correct or delete errors, duplications, missing data, etc. to ensure the accuracy and consistency of the data. The multi-dimensional data after cleaning processing represents a data set with improved quality after cleaning. Data standardization processing is used to represent the conversion of data of different dimensions or value ranges to the same standard to facilitate subsequent data analysis and processing.

[0044] Step S13: training and testing the fault diagnosis model based on the processed multi-dimensional data to obtain test results.

[0045] Specifically, the multi-dimensional data is selected and segmented to obtain a training data set and a test data set, the training data set is input into the fault diagnosis model for training to obtain a trained fault diagnosis model, and the test data set is input into the trained fault diagnosis model for model verification testing to obtain test results.

[0046] For the embodiments of the present application, the steps of data selection and segmentation usually play an important role in data analysis or machine learning tasks. Before training the machine learning model, we need to divide the training data set and the test data set from the original multi-dimensional data. This step is performed after data preprocessing (such as data cleaning and standardization). Specifically, the purpose of data selection and segmentation is to ensure that the model does not overfit during the training process, and at the same time, good generalization performance can be obtained on the test data set. In order to achieve this goal, we need to ensure that the training data set and the test data set are consistent in data distribution, and the test data set should be large enough to accurately evaluate the performance of the model.

[0047] In the embodiments of the present application, the fault diagnosis model is taken as an example of a neural network model, including but not limited to a neural network model, and the specific model type can be selected according to the actual situation.

[0048] Step S14: Determine whether the test result meets the preset test result standard. If so, collect the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data of the high and low voltage distribution boxes, and input the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data into the trained fault diagnosis model to obtain fault diagnosis information of the high and low voltage distribution boxes.

[0049] In the embodiment of the present application, the comprehensive historical fault information and sound waveform, equipment vibration, image features, and equipment temperature of the high and low voltage distribution box are obtained. These data not only cover the detailed parameter changes at the time of the fault, but also take into account the vibration and temperature differences of nodes at different positions, making the fault characteristics more three-dimensional and accurate. The multi-dimensional data is associated and constructed according to the time series nodes, and the data of different time nodes are selected, which effectively avoids data redundancy, while retaining the timeline of the fault development, so that the fault diagnosis can trace the history. Make the subsequent analysis more efficient and targeted. Preprocess the multi-dimensional data, remove noise and interference, improve data quality, and provide a reliable basis for the training of subsequent fault diagnosis models. It helps the model to capture fault characteristics more accurately. The fault diagnosis model is trained based on the processed multi-dimensional data, and the accuracy of the model is verified by the test results. It ensures that the model can accurately identify the fault type of the high and low voltage distribution box, and improves the efficiency and accuracy of fault diagnosis. When the test results meet the preset standards, the multi-dimensional data of the high and low voltage distribution box is collected in real time and input into the trained fault diagnosis model to obtain fault diagnosis information immediately. It greatly shortens the fault response time, improves the stability and safety of the power system, and thus improves the fault diagnosis efficiency of high and low voltage distribution boxes.

[0050] Furthermore, it is determined based on the image feature data whether there is human activity in the preset area of ​​the high and low voltage distribution box. If there is human activity in the preset area, the time interval before and after the human activity when the high and low voltage distribution box fails is determined. If the time interval meets the preset interval condition, the human activity is regarded as a fault inducing factor, and the fault inducing factor is added to the fault diagnosis information to obtain the added fault diagnosis information.

[0051] The above embodiment introduces a high and low voltage distribution box fault diagnosis method based on the Internet of Things from the perspective of method flow. The following embodiment introduces a high and low voltage distribution box fault diagnosis system based on the Internet of Things from the perspective of virtual module or virtual unit. For details, please see the following embodiment.

[0052] The present application embodiment provides a high and low voltage distribution box fault diagnosis system 20 based on the Internet of Things, such as Figure 2 As shown, Figure 2 A schematic diagram of a high and low voltage distribution box fault diagnosis system based on the Internet of Things provided in an embodiment of the present application. The system 20 may specifically include: The information acquisition module 21 is used to obtain the historical fault information of the high and low voltage distribution boxes and the sound waveform data, equipment vibration data, image feature data and equipment temperature data of the high and low voltage distribution boxes each time a fault occurs in the historical fault information. The historical fault information is the working parameter change information and fault details of the high and low voltage distribution boxes when they present a fault state in a historical period. The equipment vibration data and equipment temperature data are the vibration data and temperature data corresponding to the nodes at different positions of the high and low voltage distribution boxes respectively. The association construction module 22 is used to associate the historical fault information, sound waveform data, equipment vibration data, image feature data and equipment temperature data according to the time series nodes, and select the associated data information after the association construction according to the preset time interval to obtain the multi-dimensional data corresponding to different time nodes; The data processing module 23 is used to perform data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; A training and testing module 24 is used to train and test the fault diagnosis model based on the processed multi-dimensional data to obtain a test result; The data diagnosis module 25 is used to determine whether the test results meet the preset test result standards. If so, the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data of the high and low voltage distribution boxes are collected, and the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data are input into the trained fault diagnosis model to obtain fault diagnosis information of the high and low voltage distribution boxes.

[0053] In a possible implementation of the embodiment of the present application, when the training and testing module 24 performs training and testing on the fault diagnosis model based on the processed multi-dimensional data, it is specifically used to: Select and segment the multi-dimensional data to obtain training data sets and test data sets; Inputting the training data set into the fault diagnosis model for training to obtain a trained fault diagnosis model; The test data set is input into the trained fault diagnosis model for model validation testing to obtain the test results.

[0054] In another possible implementation of the embodiment of the present application, the association construction module 22 is specifically used to: associate historical fault information, sound waveform data, equipment vibration data, image feature data, and equipment temperature data according to time series nodes, and select the associated data information after the association construction according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes. Determine the operating current data, operating voltage data, fault type and fault duration at different time nodes based on historical fault information; Create a multidimensional data coordinate system, the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is the data unit parameters of different dimensions; The image feature data, the fault type and the fault duration are bound to the time nodes of the X-axis in the multidimensional data coordinate system, and the sound waveform data, the equipment vibration data, the equipment temperature data, the operating current data and the operating voltage data are respectively imported into the multidimensional data coordinate system to obtain a waveform change curve corresponding to the sound waveform data, a vibration change curve corresponding to the equipment vibration data, a temperature change curve corresponding to the equipment temperature data, a current change curve corresponding to the operating current data and a voltage change curve corresponding to the operating voltage data; Performing change amplitude detection on the voltage change curve and the current change curve to determine a first time node at which the voltage change curve and the current change curve change by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the waveform change curve, the vibration change curve, and the temperature change curve to determine a second time node at which the waveform change curve, the vibration change curve, and the temperature change curve change by a second preset amplitude; Determine the chronological relationship between the first time node and the second time node, and detect the image feature data based on the chronological relationship to determine a third time node at which an abnormal change in the image feature data occurs; According to the time correspondence between the first time node, the second time node and the third time node, historical fault information, sound waveform data, equipment vibration data, image feature data and equipment temperature data are associated and constructed to obtain multiple associated data groups; Performing key data group screening on multiple related data groups to obtain representative data groups; The associated data in the representative data group are selected according to the preset time interval to obtain multi-dimensional data corresponding to different time nodes.

[0055] In another possible implementation of the embodiment of the present application, when the association construction module 22 performs key data group screening on multiple associated data groups to obtain a representative data group, it is specifically used to: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as the first data group; if so, performing secondary matching on at least two associated data groups according to the amplitude ratio coefficient and the preset coefficient matching condition to obtain a data group matching result; Determine whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition according to the data group matching result; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data group is defined as a third data group; The first data group, the second data group and the third data group are aggregated to obtain a representative data group.

[0056] In another possible implementation of the embodiment of the present application, the system 20 further includes: a matching module, a first spacing module and a second spacing module, wherein: a matching module, configured to obtain a time interval definition standard, and match the time interval definition standard by using the fault type and the fault duration as screening conditions, to obtain a first preset time interval corresponding to the first data group, a second preset time interval corresponding to the second data group, and a third preset time interval corresponding to the third data group; A first interval module, used to determine whether the interval duration difference between the first preset time interval, the second preset time interval and the third preset time interval meets the preset duration range, and if so, calculate the average value of the first preset time interval, the second preset time interval and the third preset time interval to obtain the preset time interval; The second interval module is used to determine the time interval with the shortest interval duration among the first preset time interval, the second preset time interval and the third preset time interval when the condition is not satisfied, and define the time interval as the preset time interval.

[0057] In another possible implementation of the embodiment of the present application, when the data processing module 23 performs data preprocessing on the multi-dimensional data to obtain the processed multi-dimensional data, it is specifically used to: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.

[0058] In another possible implementation of the embodiment of the present application, the system 20 further includes: a personnel monitoring module and an information updating module, wherein: A personnel monitoring module is used to determine whether there is human activity in the preset area of ​​the high and low voltage distribution box based on the image feature data, and if there is human activity in the preset area, determine the time interval before and after the human activity when the high and low voltage distribution box fails; The information updating module is used to take the human activity as the fault inducing factor when the current and subsequent time intervals meet the preset interval conditions, and add the fault inducing factor to the fault diagnosis information to obtain the added fault diagnosis information.

[0059] Technical personnel in the relevant field can clearly understand that, for the convenience and simplicity of description, the specific working process of the high and low voltage distribution box fault diagnosis system 20 based on the Internet of Things described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0060] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0061] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0062] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0063] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0064] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0065] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0066] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0067] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0068] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A high and low voltage distribution box fault diagnosis method based on the Internet of Things, characterized in that: include: Obtain historical fault information of the high and low voltage distribution boxes and the sound waveform data, equipment vibration data, image feature data and equipment temperature data of the high and low voltage distribution boxes each time a fault occurs in the historical fault information, wherein the historical fault information is the working parameter change information and fault details of the high and low voltage distribution boxes when they present a fault state within a historical period, and the equipment vibration data and the equipment temperature data are respectively the vibration data and temperature data corresponding to nodes at different positions of the high and low voltage distribution boxes; The historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data are associated with each other according to time series nodes, and the associated data information after the association is constructed is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; Performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; Performing training and testing on the fault diagnosis model based on the processed multi-dimensional data to obtain test results; Determine whether the test result meets the preset test result standard. If so, collect the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data of the high and low voltage distribution box, and input the real-time waveform data, the real-time vibration data, the real-time feature data, the real-time temperature data and the working parameter data into the trained fault diagnosis model to obtain the fault diagnosis information of the high and low voltage distribution box.

2. According to a method for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things according to claim 1, it is characterized in that: The training and testing of the fault diagnosis model based on the processed multi-dimensional data includes: Select and segment the multi-dimensional data to obtain a training data set and a test data set; Inputting the training data set into the fault diagnosis model for training to obtain a trained fault diagnosis model; The test data set is input into the trained fault diagnosis model to perform a model verification test to obtain a test result.

3. According to a method for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things in claim 1, it is characterized in that: The historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data are associated with each other according to time series nodes, and the associated data information after the association is constructed is selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes, including: Determine the operating current data, operating voltage data, fault type and fault duration at different time nodes according to the historical fault information; Creating a multidimensional data coordinate system, wherein the X-axis of the multidimensional data coordinate system is different time nodes, and the Y-axis of the multidimensional data coordinate system is data unit parameters of different dimensions; Bind the image feature data, the fault type, and the fault duration to the time node of the X-axis in the multidimensional data coordinate system, and import the sound waveform data, the equipment vibration data, the equipment temperature data, the operating current data, and the operating voltage data into the multidimensional data coordinate system, respectively, to obtain a waveform change curve corresponding to the sound waveform data, a vibration change curve corresponding to the equipment vibration data, a temperature change curve corresponding to the equipment temperature data, a current change curve corresponding to the operating current data, and a voltage change curve corresponding to the operating voltage data; Performing change amplitude detection on the voltage change curve and the current change curve to determine a first time node at which the voltage change curve and the current change curve change by a first preset amplitude; The first time node is defined as a starting time node, and amplitude detection is performed on the waveform change curve, the vibration change curve, and the temperature change curve to determine a second time node at which the waveform change curve, the vibration change curve, and the temperature change curve change by a second preset amplitude; Determining a sequential relationship between the first time node and the second time node, and detecting the image feature data based on the sequential relationship to determine a third time node at which an abnormal change in the image feature data occurs; According to the time correspondence between the first time node, the second time node and the third time node, the historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data are associated with each other to obtain a plurality of associated data groups; Performing key data group screening on the multiple associated data groups to obtain a representative data group; The associated data in the representative data group are selected according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes.

4. According to the method for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things in claim 3, it is characterized in that: The step of screening the multiple associated data groups for key data groups to obtain representative data groups includes: Determine the data amplitude difference and amplitude change time interval corresponding to each associated data group according to the plurality of associated data groups; Calculate the ratio of the data amplitude difference and the amplitude change time interval to obtain the amplitude proportional coefficient corresponding to each associated data group; Collecting the initial data set of each associated data group at a time before the data amplitude occurs, and matching the initial data set corresponding to each associated data group to determine whether there is a situation where the initial data sets corresponding to at least two associated data groups match each other; if not, defining the associated data group as a first data group; if so, performing secondary matching on the at least two associated data groups according to the amplitude ratio coefficient and a preset coefficient matching condition to obtain a data group matching result; Determine, according to the data group matching result, whether there are at least two associated data groups whose amplitude ratio coefficients meet the preset coefficient matching condition; if so, determine the initial time node corresponding to the initial data set of the at least two associated data groups, and take the associated data group whose initial time node is close to the current time node as the second data group; If there are no at least two associated data groups whose corresponding amplitude ratio coefficients satisfy the preset coefficient matching condition, the associated data groups are defined as the third data group; The first data group, the second data group and the third data group are aggregated to obtain a representative data group.

5. According to the method for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things in claim 4, it is characterized in that: The step of selecting the associated data in the representative data group according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes also includes: Acquire a time interval definition standard, and use the fault type and fault duration as screening conditions to match the time interval definition standard, to obtain a first preset time interval corresponding to the first data group, a second preset time interval corresponding to the second data group, and a third preset time interval corresponding to the third data group; Determine whether the interval duration difference between the first preset time interval, the second preset time interval and the third preset time interval meets a preset duration range, and if so, calculate the average value of the first preset time interval, the second preset time interval and the third preset time interval to obtain a preset time interval; If not, determine the time interval with the shortest interval duration among the first preset time interval, the second preset time interval and the third preset time interval, and define the time interval as the preset time interval.

6. The method for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things according to claim 1 is characterized in that: The performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data includes: Performing data cleaning on the multi-dimensional data to obtain cleaned multi-dimensional data; The cleaned multi-dimensional data is subjected to data standardization processing to obtain processed multi-dimensional data.

7. The method for diagnosing faults of high and low voltage distribution boxes based on the Internet of Things according to claim 1 is characterized in that: The method further comprises: Determine whether there is human activity in the preset area of ​​the high and low voltage distribution box according to the image feature data, and if there is human activity in the preset area, determine the time interval before and after the human activity when the high and low voltage distribution box fails; If the time intervals before and after meet the preset interval conditions, the personnel activity is regarded as a fault inducing factor, and the fault inducing factor is added to the fault diagnosis information to obtain the added fault diagnosis information.

8. A high and low voltage distribution box fault diagnosis system based on the Internet of Things, characterized in that: include: An information acquisition module, used to acquire historical fault information of high and low voltage distribution boxes and sound waveform data, equipment vibration data, image feature data and equipment temperature data of the high and low voltage distribution boxes each time a fault occurs in the historical fault information, wherein the historical fault information is the working parameter change information and fault details of the high and low voltage distribution boxes when they present a fault state within a historical period, and the equipment vibration data and the equipment temperature data are vibration data and temperature data corresponding to nodes at different positions of the high and low voltage distribution boxes respectively; An association construction module is used to associate the historical fault information, the sound waveform data, the equipment vibration data, the image feature data and the equipment temperature data according to time series nodes, and select the associated data information after the association construction according to a preset time interval to obtain multi-dimensional data corresponding to different time nodes; A data processing module, used for performing data preprocessing on the multi-dimensional data to obtain processed multi-dimensional data; A training and testing module, used to train and test the fault diagnosis model based on the processed multi-dimensional data to obtain a test result; The data diagnosis module is used to determine whether the test result meets the preset test result standard. If so, the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data of the high and low voltage distribution box are collected, and the real-time waveform data, real-time vibration data, real-time feature data, real-time temperature data and working parameter data are input into the trained fault diagnosis model to obtain fault diagnosis information of the high and low voltage distribution box.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a high- and low-voltage distribution box fault diagnosis method based on the Internet of Things as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute a high and low voltage distribution box fault diagnosis method based on the Internet of Things as claimed in any one of claims 1 to 7.

Images