Power distribution equipment fault prediction method and system based on multi-dimensional data of Internet of Things

Abstract

The invention relates to a power distribution equipment fault prediction method and system based on multi-dimensional data of the Internet of Things, and relates to the technical field of fault prediction, and the method comprises the steps: obtaining region image information and power distribution equipment information, planning the region image information according to a building application type, obtaining a building region image, and storing the building region image; and carrying out fault hidden danger analysis on the power distribution equipment information to obtain a hidden danger evaluation standard, and carrying out position corresponding binding on the hidden danger evaluation standard and the building area image to obtain a hidden danger evaluation image. And determining to-be-monitored application data of each power distribution device, binding the to-be-monitored application data with the hidden danger evaluation image to obtain a real-time monitoring image, and performing fault hidden danger pre-diagnosis on the to-be-monitored application data and a hidden danger evaluation standard to obtain a device hidden danger score. And if the equipment hidden danger score exceeds the preset hidden danger score, binding and labeling the to-be-diagnosed fault information and the real-time monitoring image to obtain a fault prediction image. The fault diagnosis efficiency of the power distribution equipment is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fault prediction, and in particular to a method and system for predicting faults of power distribution equipment based on multi-dimensional data of the Internet of Things. Background Art

[0002] With the rapid development of education, the demand for power supply in modern campuses is increasing. As a core component of campus energy supply, the stability and reliability of the power distribution system are directly related to the normal operation of teaching, scientific research, daily life, and other activities. However, traditional methods for predicting power distribution equipment failures, such as experience-based regular inspections and manual troubleshooting, suffer from low prediction accuracy, slow response speed, and high maintenance costs. These methods are no longer able to meet the current campus demand for efficient and intelligent power distribution system management.

[0003] In recent years, the rapid development of technologies such as the Internet of Things (IoT), big data, and artificial intelligence has provided new insights and approaches for predicting power distribution equipment failures. Particularly on campuses, the application of these technologies not only enables real-time monitoring of power distribution equipment status but also, through data analysis and model prediction, proactively identifies potential equipment failures. This provides timely and accurate warnings to operations and maintenance personnel, effectively avoiding or minimizing the occurrence of failures and ensuring the stability and security of campus power supply.

[0004] Then, although the existing technology can detect hidden dangers of equipment failure in advance, it is difficult to accurately locate the equipment failure. This means that after the operation and maintenance personnel receive the fault warning information and arrive at the predetermined location, they need to spend time to determine the cause of the fault. Only after the specific cause of the fault is determined can subsequent maintenance work be carried out, thereby reducing the fault diagnosis efficiency of the distribution equipment. Summary of the Invention

[0005] In order to solve at least one of the above technical problems, the present application provides a distribution equipment fault prediction method and system based on multi-dimensional data of the Internet of Things.

[0006] In the first aspect, the present application provides a method for predicting power distribution equipment failures based on multi-dimensional data of the Internet of Things, which adopts the following technical solutions: A method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things, comprising: Acquire regional image information of the campus and information about power distribution equipment, wherein the regional image information is an overall three-dimensional image of the campus area and application information of different buildings in the overall three-dimensional image; Planning the campus area image information according to the building application type to obtain a building area image; Analyzing the potential faults of the power distribution equipment to obtain potential fault evaluation standards for different power distribution equipment; Determining the installation and application location of each power distribution device according to the power distribution device information, and binding the hidden danger assessment standard and the building area image in a position-corresponding manner based on the installation and application location to obtain a hidden danger assessment image; Determine the application data to be monitored corresponding to each power distribution device between the current time node and the preset time node, and bind the application data to be monitored with the hidden danger assessment image according to the installation application location to obtain a real-time monitoring image; Based on the real-time monitoring image, the application data to be monitored at the same location is compared with the hidden danger assessment standard to perform fault hidden danger pre-diagnosis to obtain the equipment hidden danger score; Determine whether the equipment hidden danger score exceeds the preset hidden danger score. If so, determine the fault information to be diagnosed according to the hidden danger assessment standard, and bind and mark the fault information to be diagnosed with the corresponding position in the real-time monitoring image to obtain a fault prediction image.

[0007] By employing this technical solution, campus regional image information is first acquired, including an overall 3D image and information about different building applications, providing a detailed visual foundation for campus management. Subsequently, images are organized according to building application type, resulting in building area images, making the campus layout clear at a glance and facilitating subsequent management. This not only improves information visualization but also provides a spatial reference for power distribution equipment management. Through in-depth analysis of power distribution equipment information, hidden danger assessment criteria are derived, helping to proactively identify potential faults and reduce the occurrence of sudden failures. These hidden danger assessment criteria are then associated with the location of building area images to create a hidden danger assessment image. By identifying the application data to be monitored for power distribution equipment and binding it to the hidden danger assessment image, a real-time monitoring image is generated, enabling dynamic tracking of the power distribution equipment status. This improves the real-time and accuracy of monitoring and provides reliable data support for pre-diagnosis of fault hazards. Pre-diagnosis of fault hazards is performed based on the real-time monitoring image, resulting in a device hidden danger score. By determining whether the device hidden danger score exceeds a preset value, the system identifies and annotates the fault information to be diagnosed, generating a fault prediction image. It not only improves the timeliness of fault handling, but also intuitively displays the fault location through image annotation, making it easier for managers to quickly locate and take corresponding measures, effectively improving the fault diagnosis efficiency of power distribution equipment.

[0008] In a preferred example, the present application may be further configured as follows: performing fault hidden danger analysis on the power distribution equipment information to obtain hidden danger evaluation standards for different power distribution equipment includes: Determine historical performance data of each power distribution device based on the power distribution device information, wherein the historical performance data is application performance parameter data of different power distribution devices from the installation time node to the current time node; Filter the historical performance data to obtain equipment monitoring data before and after the power distribution equipment fails, and equipment failure data at the time of the failure; Filtering the equipment monitoring data and the equipment fault data to obtain natural monitoring data and natural fault data; The natural monitoring data and the natural fault data are analyzed for hidden dangers of equipment failures to obtain hidden danger evaluation standards for different power distribution equipment.

[0009] In a preferred example, the present application may be further configured as follows: filtering the device monitoring data and the device fault data to obtain natural monitoring data and natural fault data includes: Determining a fault occurrence node and a fault end node according to the device fault data, and segmenting the device monitoring data based on the fault occurrence node and the fault end node to obtain pre-sequence monitoring data, mid-sequence monitoring data, and post-sequence monitoring data; Determine a first data change ratio of the power distribution equipment application parameter according to the preceding monitoring data, determine a second data change ratio of the power distribution equipment application parameter according to the mid-sequence monitoring data, and determine a third data change ratio of the power distribution equipment application parameter according to the subsequent monitoring data; Determining a first ratio difference range based on the first data change ratio and the second data change ratio; determining a second ratio difference range based on the second data change ratio and the third data change ratio; determining whether the first ratio difference range and / or the second ratio difference range conform to a preset difference range; if not, marking the device monitoring data and device fault data corresponding to the first ratio difference range and / or the second ratio difference range as a human-induced fault; The data containing the artificially caused fault label in the equipment monitoring data and equipment fault data are filtered out to obtain natural monitoring data and natural fault data.

[0010] In a preferred example, the present application may be further configured as follows: performing equipment failure hidden danger analysis on the natural monitoring data and the natural fault data to obtain hidden danger evaluation standards for different power distribution equipment includes: Binding and fusing the natural monitoring data with the natural fault data, and determining the device application data sequence and the device environment data sequence of each power distribution device during each fault period based on the natural analysis data obtained from the data binding and fusion; Integrate and analyze the equipment application data sequence and the equipment environment data sequence to obtain a hidden danger score for each power distribution equipment; The equipment application data sequence, the equipment environment data sequence and the hidden danger scores are sorted according to time nodes to obtain hidden danger evaluation standards for different power distribution equipment.

[0011] In a preferred example, the present application may be further configured as follows: determining the device application data sequence and device environment data sequence of each power distribution device during each fault period according to the natural analysis data obtained through data binding and fusion, including: Performing primary data division on the natural analysis data according to data categories to obtain device application data and device environment data; Performing secondary data division on the device application data and the device environment data based on the fault period of each power distribution device to obtain multiple application data segments and multiple environment data segments; Arranging the data of each application data segment in a time sequence to obtain a device application data sequence of each power distribution device during each fault period; The data of each environmental data segment in the multiple environmental data segments are arranged in time sequence to obtain a device environmental data sequence of each power distribution device during each fault period.

[0012] In a preferred example, the present application may be further configured as follows: performing integrated analysis on the device application data sequence and the device environment data sequence to obtain a hidden danger score for each power distribution device includes: Create a device application coordinate system and a device environment coordinate system, where the X-axis of the device application coordinate system represents the time nodes before and after each failure in the historical period, and the Y-axis of the device application coordinate system represents different types of device application parameter data. The X-axis of the device environment coordinate system is the same as the X-axis of the device application coordinate system, and the Y-axis of the device environment coordinate system represents the environmental parameter data of the device. Importing the device application data sequence into the device application coordinate system to obtain different types of application data curves; Importing the device environment data sequence into the device environment coordinate system to obtain different types of environment data curves; Calculating a first slope value of each of the application data curves respectively, and performing cumulative mean calculation on each of the first slope values to obtain a first data score; Calculating the second slope value of each of the environmental data curves respectively, and performing cumulative mean calculation on each of the second slope values to obtain a second data score; The first data score and the second data score are summed according to the time nodes before and after the fault occurs to obtain the hidden danger score of each power distribution equipment.

[0013] In a preferred example, the present application may be further configured as follows: performing fault hidden danger pre-diagnosis on the application data to be monitored at the same location and the hidden danger assessment standard based on the real-time monitoring image to obtain the equipment hidden danger score, including: Arrange the application data to be monitored according to the time series to obtain a monitoring application data sequence and a monitoring environment data sequence; Performing data segment matching on the monitoring application data sequence and the equipment data sequence in the hidden danger assessment standard to obtain a sequence matching degree; Performing data segment matching on the equipment environment data sequence and the environment data sequence in the hidden danger assessment standard to obtain an environment matching degree; The product of the sequence matching degree, the environment matching degree and the hidden danger score is calculated to obtain a device hidden danger score.

[0014] In a second aspect, the present application provides a distribution equipment fault prediction system based on multi-dimensional data of the Internet of Things, which adopts the following technical solutions: A power distribution equipment fault prediction system based on multi-dimensional data of the Internet of Things, comprising: An information acquisition module is used to acquire regional image information of the campus and information about power distribution equipment. The regional image information is an overall three-dimensional image of the campus area and application information of different buildings in the overall three-dimensional image. An image planning module is used to plan the campus area image information according to the building application type to obtain a building area image; A hidden danger analysis module is used to analyze the fault hidden dangers of the power distribution equipment information and obtain hidden danger evaluation standards for different power distribution equipment; an information binding module, configured to determine the installation and application location of each power distribution device according to the power distribution device information, and to bind the hidden danger assessment standard to the building area image in a position-corresponding manner based on the installation and application location to obtain a hidden danger assessment image; A data binding module is used to determine the application data to be monitored corresponding to each power distribution device between the current time node and the preset time node, and bind the application data to be monitored with the hidden danger assessment image according to the installation application location to obtain a real-time monitoring image; A hidden danger pre-diagnosis module is used to pre-diagnose fault hidden dangers by comparing the application data to be monitored at the same location with the hidden danger assessment standard based on the real-time monitoring image to obtain an equipment hidden danger score; The fault binding module is used to determine whether the equipment hidden danger score exceeds the preset hidden danger score. If it exceeds, the fault information to be diagnosed is determined according to the hidden danger assessment standard, and the fault information to be diagnosed is bound and marked with the corresponding position in the real-time monitoring image to obtain a fault prediction image.

[0015] In a possible implementation, when the hidden danger analysis module performs fault hidden danger analysis on the power distribution equipment information and obtains hidden danger evaluation standards for different power distribution equipment, it is specifically configured to: Determine historical performance data of each power distribution device based on the power distribution device information, wherein the historical performance data is application performance parameter data of different power distribution devices from the installation time node to the current time node; Filter the historical performance data to obtain equipment monitoring data before and after the power distribution equipment fails, and equipment failure data at the time of the failure; Filtering the equipment monitoring data and the equipment fault data to obtain natural monitoring data and natural fault data; The natural monitoring data and the natural fault data are analyzed for hidden dangers of equipment failures to obtain hidden danger evaluation standards for different power distribution equipment.

[0016] In another possible implementation, when the hidden danger analysis module filters the equipment monitoring data and the equipment failure data to obtain natural monitoring data and natural failure data, it is specifically configured to: Determining a fault occurrence node and a fault end node according to the device fault data, and segmenting the device monitoring data based on the fault occurrence node and the fault end node to obtain pre-sequence monitoring data, mid-sequence monitoring data, and post-sequence monitoring data; Determine a first data change ratio of the power distribution equipment application parameter according to the preceding monitoring data, determine a second data change ratio of the power distribution equipment application parameter according to the mid-sequence monitoring data, and determine a third data change ratio of the power distribution equipment application parameter according to the subsequent monitoring data; Determining a first ratio difference range based on the first data change ratio and the second data change ratio; determining a second ratio difference range based on the second data change ratio and the third data change ratio; determining whether the first ratio difference range and / or the second ratio difference range conform to a preset difference range; if not, marking the device monitoring data and device fault data corresponding to the first ratio difference range and / or the second ratio difference range as a human-induced fault; The data containing the artificially caused fault label in the equipment monitoring data and equipment fault data are filtered out to obtain natural monitoring data and natural fault data.

[0017] In another possible implementation, when the hidden danger analysis module performs equipment failure hidden danger analysis on the natural monitoring data and the natural fault data to obtain hidden danger evaluation standards for different power distribution equipment, it is specifically configured to: Binding and fusing the natural monitoring data with the natural fault data, and determining the device application data sequence and the device environment data sequence of each power distribution device during each fault period based on the natural analysis data obtained from the data binding and fusion; Integrate and analyze the equipment application data sequence and the equipment environment data sequence to obtain a hidden danger score for each power distribution equipment; The equipment application data sequence, the equipment environment data sequence and the hidden danger scores are sorted according to time nodes to obtain hidden danger evaluation standards for different power distribution equipment.

[0018] In another possible implementation, when the hidden danger analysis module determines the device application data sequence and the device environment data sequence of each power distribution device during each fault period based on the natural analysis data obtained through data binding and fusion, it is specifically configured to: Performing primary data division on the natural analysis data according to data categories to obtain device application data and device environment data; Performing secondary data division on the device application data and the device environment data based on the fault period of each power distribution device to obtain multiple application data segments and multiple environment data segments; Arranging the data of each application data segment in a time sequence to obtain a device application data sequence of each power distribution device during each fault period; The data of each environmental data segment in the multiple environmental data segments are arranged in time sequence to obtain a device environmental data sequence of each power distribution device during each fault period.

[0019] In another possible implementation, when the hidden danger analysis module integrates and analyzes the device application data sequence and the device environment data sequence to obtain the hidden danger score of each power distribution device, it is specifically configured to: Create a device application coordinate system and a device environment coordinate system, where the X-axis of the device application coordinate system represents the time nodes before and after each failure in the historical period, and the Y-axis of the device application coordinate system represents different types of device application parameter data. The X-axis of the device environment coordinate system is the same as the X-axis of the device application coordinate system, and the Y-axis of the device environment coordinate system represents the environmental parameter data of the device. Importing the device application data sequence into the device application coordinate system to obtain different types of application data curves; Importing the device environment data sequence into the device environment coordinate system to obtain different types of environment data curves; Calculating a first slope value of each of the application data curves respectively, and performing cumulative mean calculation on each of the first slope values to obtain a first data score; Calculating the second slope value of each of the environmental data curves respectively, and performing cumulative mean calculation on each of the second slope values to obtain a second data score; The first data score and the second data score are summed according to the time nodes before and after the fault occurs to obtain the hidden danger score of each power distribution equipment.

[0020] In another possible implementation, when the hidden danger diagnosis module performs fault hidden danger pre-diagnosis based on the real-time monitoring image and compares the application data to be monitored at the same location with the hidden danger assessment standard to obtain the equipment hidden danger score, it is specifically configured to: Arrange the application data to be monitored according to the time series to obtain a monitoring application data sequence and a monitoring environment data sequence; Performing data segment matching on the monitoring application data sequence and the equipment data sequence in the hidden danger assessment standard to obtain a sequence matching degree; Performing data segment matching on the equipment environment data sequence and the environment data sequence in the hidden danger assessment standard to obtain an environment matching degree; The product of the sequence matching degree, the environment matching degree and the hidden danger score is calculated to obtain a device hidden danger score.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device includes 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 predicting power distribution equipment faults based on multi-dimensional data of the Internet of Things are implemented.

[0022] In a fourth aspect, the present application provides a computer storage medium, including the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for predicting distribution equipment faults based on multi-dimensional data of the Internet of Things.

[0023] In summary, this application has the following beneficial technical effects: First, regional image information of the campus is acquired, including an overall 3D image and information about the different applications within the buildings. This provides a detailed visual foundation for campus management. Subsequently, the images are organized according to building application type, resulting in building area images, making the campus layout clear at a glance and facilitating subsequent management. This not only improves information visualization but also provides a spatial reference for distribution equipment management. Through in-depth analysis of distribution equipment information, hidden danger assessment criteria are derived, helping to proactively identify potential faults and reduce the occurrence of sudden failures. These hidden danger assessment criteria are then associated with the location of the building area image to create a hidden danger assessment image. By identifying the application data to be monitored for distribution equipment and binding it to the hidden danger assessment image, a real-time monitoring image is generated, enabling dynamic tracking of the distribution equipment status. This improves the real-time and accuracy of monitoring and provides reliable data support for pre-diagnosis of fault hazards. Pre-diagnosis of fault hazards is performed based on the real-time monitoring images, resulting in equipment hidden danger scores. By determining whether the equipment hidden danger score exceeds a preset value, the system identifies and annotates the fault information to be diagnosed, creating a fault prediction image. It not only improves the timeliness of fault handling, but also intuitively displays the fault location through image annotation, making it easier for managers to quickly locate and take corresponding measures, effectively improving the fault diagnosis efficiency of power distribution equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flowchart of a method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things in one embodiment of the present application.

[0025] Figure 2 This is a structural diagram of a distribution equipment fault prediction system based on multi-dimensional data of the Internet of Things in one embodiment of the present application.

[0026] Figure 3 This 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 the attached 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 non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0029] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0030] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0031] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0032] The embodiment of the present application provides a method for predicting power distribution equipment failures based on multi-dimensional data of 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, a server cluster or a 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 thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes: Step S10: Acquire campus area image information and power distribution equipment information.

[0033] The regional image information is the overall three-dimensional image of the campus area and application information of different buildings in the overall three-dimensional image.

[0034] For the embodiment of the present application, the regional image information of the campus represents visual information about the overall spatial layout of the area where the campus is located. The overall three-dimensional image refers to a three-dimensional image generated using three-dimensional modeling technology that can display the campus and its surrounding environment. The application information of different buildings is used to indicate the functions or uses of each building on campus, such as teaching buildings, libraries, dormitories, etc. The power distribution equipment information represents detailed information about the power distribution system on campus, including but not limited to the location of the distribution room, transformer specifications, line layout, electrical equipment, etc.

[0035] Step S11: planning the campus area image information according to the building application type to obtain a building area image.

[0036] In this embodiment, computer vision technology is used to automatically identify buildings in an image and extract their outlines and location information. The application type of each building is then determined by comparing its appearance characteristics with a database of known building application types. Finally, the buildings are divided into different areas based on their application type, and image processing software is used to generate images of the corresponding building areas.

[0037] Step S12: Analyze the potential fault hazards of the power distribution equipment to obtain potential fault hazard assessment standards for different power distribution equipment.

[0038] Specifically, historical performance data for each distribution device is determined based on the distribution device information. This historical performance data consists of application performance parameter data for different distribution devices from the time of installation to the current time. This historical performance data is then filtered to obtain device monitoring data before and after a distribution device failure, as well as device failure data at the time of the failure. This device monitoring data and failure data are filtered to obtain natural monitoring data and natural failure data. This natural monitoring data and failure data are then used to analyze equipment failure hazards, yielding hazard assessment criteria for different distribution devices.

[0039] For the present embodiment, power distribution equipment information represents a series of detailed information about the power distribution equipment on campus, including but not limited to the equipment model, specifications, installation location, rated power, operating status, etc. Historical performance data refers to various parameter data displayed by the equipment during its use from the time the power distribution equipment was installed to the current time. This data can reflect the equipment's operating status, performance changes, and operating environment, such as current, voltage, power factor, and temperature.

[0040] In the embodiments of the present application, screening refers to the process of selecting and processing historical performance data. The purpose is to remove data without equipment failures and retain data related to distribution equipment failures that occurred during the historical period, that is, data that is valuable for subsequent analysis. Data filtering refers to further processing of monitoring data and fault data to eliminate distribution equipment failures caused by human factors. Natural monitoring data and natural fault data refer to filtered monitoring data and fault data, respectively.

[0041] For example, suppose the historical performance data for a power distribution device includes installation time, maintenance records, and daily monitoring data. Daily monitoring data includes application performance parameters such as current, voltage, and temperature. By filtering this data, we can obtain monitoring data before and after a specific failure, as well as specific data at the time of the failure. This data is then filtered to remove outliers caused by human error, resulting in natural monitoring data and natural failure data. Finally, based on this data, we analyze the potential risks of equipment failures and derive the potential risk assessment criteria for the equipment.

[0042] In an embodiment of the present application, data filtering is performed on equipment monitoring data and equipment failure data to obtain natural monitoring data and natural failure data, including: determining a fault occurrence node and a fault end node according to the equipment failure data, and segmenting the equipment monitoring data based on the fault occurrence node and the fault end node to obtain pre-sequence monitoring data, mid-sequence monitoring data, and post-sequence monitoring data. A first data change ratio of a distribution equipment application parameter is determined according to the pre-sequence monitoring data, a second data change ratio of a distribution equipment application parameter is determined according to the mid-sequence monitoring data, and a third data change ratio of a distribution equipment application parameter is determined according to the post-sequence monitoring data. A first proportional difference range is determined based on the first data change ratio and the second data change ratio. A second proportional difference range is determined based on the second data change ratio and the third data change ratio. It is determined whether the first proportional difference range and / or the second proportional difference range meet the preset difference range. If not, the equipment monitoring data and equipment failure data corresponding to the first proportional difference range and / or the second proportional difference range are marked as artificially caused failures. Data containing artificially caused failure labels in the equipment monitoring data and equipment failure data are filtered and screened out to obtain natural monitoring data and natural failure data.

[0043] In the embodiment of the present application, the preset difference range is a pre-set proportional difference range, which is used to determine the proportional difference range of data changes caused by human factors.

[0044] In an embodiment of the present application, an equipment failure hidden danger analysis is performed on natural monitoring data and natural fault data to obtain hidden danger evaluation standards for different power distribution equipment, including: data binding and fusion of natural monitoring data and natural fault data, and determining the equipment application data sequence and equipment environment data sequence of each power distribution equipment during each fault period based on the natural analysis data obtained by data binding and fusion. The equipment application data sequence and equipment environment data sequence are integrated and analyzed to obtain a hidden danger score for each power distribution equipment. The equipment application data sequence, equipment environment data sequence and hidden danger score are sorted according to time nodes to obtain hidden danger evaluation standards for different power distribution equipment.

[0045] In this embodiment, the hazard assessment standard actually organizes the device application data sequence, the device environment data sequence, and the hazard score into a table. The resulting data table is the hazard assessment standard. Specifically, a blank data table is created with the device application data sequence in the first column, the device environment data sequence in the second column, and the hazard score in the third column. These data are then imported horizontally into the table to form the hazard data table, i.e., the hazard assessment standard.

[0046] Determining the device application data sequence and device environment data sequence for each power distribution device during each fault period based on the natural analysis data obtained through data binding and fusion includes: performing a primary data segmentation on the natural analysis data according to data category to obtain device application data and device environment data; performing a secondary data segmentation on the device application data and device environment data based on the fault period of each power distribution device to obtain multiple application data segments and multiple environment data segments; arranging the data of each application data segment in a time series to obtain the device application data sequence for each power distribution device during each fault period; and arranging the data of each environment data segment in a time series to obtain the device environment data sequence for each power distribution device during each fault period.

[0047] The integrated analysis of the equipment application data sequence and the equipment environment data sequence to obtain the hidden danger score of each distribution device includes: creating an equipment application coordinate system and an equipment environment coordinate system, where the X-axis of the equipment application coordinate system represents the time nodes before and after each failure in the historical period, the Y-axis of the equipment application coordinate system represents different types of equipment application parameter data, the X-axis of the equipment environment coordinate system is the same as the X-axis of the equipment application coordinate system, and the Y-axis of the equipment environment coordinate system represents the environmental parameter data of the device. The equipment application data sequence is imported into the equipment application coordinate system to obtain different types of application data curves, and the equipment environment data sequence is imported into the equipment environment coordinate system to obtain different types of environmental data curves. The first slope value of each application data curve is calculated separately, and each first slope value is cumulatively averaged to obtain a first data score. The second slope value of each environmental data curve is calculated separately, and each second slope value is cumulatively averaged to obtain a second data score. The first data score and the second data score are summed according to the time nodes before and after the failure to obtain the hidden danger score of each distribution device.

[0048] Step S13: Determine the installation and application location of each power distribution device according to the power distribution device information, and bind the hidden danger assessment standard and the building area image in a positional correspondence based on the installation and application location to obtain a hidden danger assessment image.

[0049] In this embodiment of the application, a power distribution equipment information management system is used to input and store detailed information about the power distribution equipment, including installation locations. Then, the hidden danger assessment criteria for the power distribution equipment are programmatically associated with the installation locations in the image to generate a hidden danger assessment image. Finally, the generated image is reviewed and verified to ensure that all information is accurate. This makes it easier for personnel inspecting a building to directly and clearly view the hidden dangers that occurred in the power distribution equipment within that building over the historical period.

[0050] Step S14: Determine the application data to be monitored corresponding to each power distribution equipment between the current time node and the preset time node, and bind the application data to be monitored with the hidden danger assessment image according to the installation application location to obtain a real-time monitoring image.

[0051] In an embodiment of the present application, the preset time node is the initial time node of an operation monitoring cycle of the distribution equipment. For example, the operation monitoring cycle of the distribution equipment is from 0:00 to 12:00 every day, and then from 12:00 to 0:00 the next day. If the current time node is 11:00, the preset time node is 0:00.

[0052] For the embodiment of the present application, the data and image binding method in this step is consistent with the data and image binding method in step S13 and will not be repeated here. This application binds the application data to be monitored with the hidden danger assessment image to facilitate personnel to view and monitor the operating conditions and operating environment of different power distribution equipment in each different building.

[0053] Step S15: Based on the real-time monitoring image, the application data to be monitored at the same location is compared with the hidden danger assessment standard to perform fault hidden danger pre-diagnosis to obtain the equipment hidden danger score.

[0054] Specifically, the application data to be monitored is organized according to time series to obtain a monitoring application data sequence and a monitoring environment data sequence. The monitoring application data sequence is then segment-matched with the equipment data sequence in the hidden danger assessment standard to obtain a sequence matching degree. The equipment environment data sequence is segment-matched with the environment data sequence in the hidden danger assessment standard to obtain an environmental matching degree. The product of the sequence matching degree, the environmental matching degree, and the hidden danger score is calculated to obtain the equipment hidden danger score.

[0055] For the embodiments of the present application, the monitoring application data sequence refers to the application data to be monitored that has been sorted and arranged in a time series, which clearly shows the changing trend of the data over time. The monitoring environment data sequence refers to the environmental condition data corresponding to the monitoring application data, such as temperature, humidity, air pressure, etc., which are also sorted in a time series. The sequence matching degree and the environment matching degree respectively represent the matching degree between the monitoring application data sequence and the device data sequence, and the monitoring environment data sequence and the environmental data sequence, and are expressed in percentage form in the embodiments of the present application.

[0056] Step S16: Determine whether the equipment hidden danger score exceeds the preset hidden danger score. If so, determine the fault information to be diagnosed according to the hidden danger assessment standard, and bind and mark the fault information to be diagnosed with the corresponding position in the real-time monitoring image to obtain a fault prediction image.

[0057] In the embodiment of the present application, the preset hidden danger score is a pre-set threshold value used to determine whether the equipment hidden danger score reaches or exceeds the level that requires attention. This threshold value is usually manually set based on factors such as the type of equipment, operating environment, and safety standards.

[0058] In an embodiment of the present application, regional image information of the campus is obtained, including an overall three-dimensional image and information about different applications within the building, providing a detailed visual foundation for campus management. Subsequently, the image is planned according to the building application type to obtain a building area image, making the campus layout clear at a glance and facilitating subsequent management. This not only improves the visualization of information but also provides a spatial reference for the management of distribution equipment. By in-depth analysis of distribution equipment information, hidden danger assessment standards are derived, which helps to identify potential faults in advance and reduce the occurrence of sudden faults. The hidden danger assessment standards are bound to the corresponding building area image locations to form a hidden danger assessment image. By determining the application data to be monitored for the distribution equipment and binding it to the hidden danger assessment image, a real-time monitoring image is obtained, enabling dynamic tracking of the distribution equipment status. This improves the real-time and accuracy of monitoring and provides reliable data support for pre-diagnosis of fault hidden dangers. Pre-diagnosis of fault hidden dangers is performed based on the real-time monitoring image to obtain an equipment hidden danger score. By determining whether the equipment hidden danger score exceeds the preset hidden danger score, if so, the fault information to be diagnosed is determined and marked to obtain a fault prediction image. It not only improves the timeliness of fault handling, but also intuitively displays the fault location through image annotation, making it easier for managers to quickly locate and take corresponding measures, effectively improving the fault diagnosis efficiency of power distribution equipment.

[0059] The above embodiment introduces a distribution equipment fault prediction method based on multi-dimensional data of the Internet of Things from the perspective of method flow. The following embodiment introduces a distribution equipment fault prediction system based on multi-dimensional data of the Internet of Things from the perspective of virtual modules or virtual units. For details, please see the following embodiments.

[0060] The present application embodiment provides a distribution equipment fault prediction system 20 based on multi-dimensional data of the Internet of Things, such as Figure 2 As shown, Figure 2 This is a schematic diagram of a power distribution equipment fault prediction system based on multi-dimensional data of the Internet of Things provided in an embodiment of the present application. The system 20 may specifically include: An information acquisition module 21 is used to acquire regional image information of the campus and information about power distribution equipment. The regional image information is an overall three-dimensional image of the campus area and application information of different buildings in the overall three-dimensional image. An image planning module 22 is used to plan campus area image information according to building application types to obtain building area images; The hidden danger analysis module 23 is used to analyze the fault hidden dangers of the power distribution equipment information and obtain the hidden danger evaluation standards of different power distribution equipment; An information binding module 24 is configured to determine the installation and application location of each power distribution device based on the power distribution device information, and to bind the hidden danger assessment standard to the building area image based on the installation and application location to obtain a hidden danger assessment image; The data binding module 25 is used to determine the application data to be monitored corresponding to each power distribution device between the current time node and the preset time node, and bind the application data to be monitored with the hidden danger assessment image according to the installation application location to obtain a real-time monitoring image; The hidden danger pre-diagnosis module 26 is used to pre-diagnose the hidden dangers of the equipment by comparing the application data to be monitored at the same location with the hidden danger assessment standard based on the real-time monitoring image, and obtain the hidden danger score of the equipment; The fault binding module 27 is used to determine whether the equipment hidden danger score exceeds the preset hidden danger score. If it exceeds, the fault information to be diagnosed is determined according to the hidden danger assessment standard, and the fault information to be diagnosed is bound and marked with the corresponding position in the real-time monitoring image to obtain a fault prediction image.

[0061] In one possible implementation of the embodiment of the present application, the hidden danger analysis module 23 performs fault hidden danger analysis on the power distribution equipment information to obtain hidden danger evaluation standards for different power distribution equipment, specifically for: Determine the historical performance data of each power distribution device based on the power distribution device information. The historical performance data is the application performance parameter data of different power distribution devices from the installation time node to the current time node. Filter historical performance data to obtain equipment monitoring data before and after the power distribution equipment failure, as well as equipment failure data at the time of the failure; Filter the equipment monitoring data and equipment failure data to obtain natural monitoring data and natural failure data; Equipment failure hidden danger analysis is performed on natural monitoring data and natural fault data to obtain hidden danger evaluation standards for different distribution equipment.

[0062] In another possible implementation of the embodiment of the present application, when the hidden danger analysis module 23 filters the equipment monitoring data and the equipment failure data to obtain the natural monitoring data and the natural failure data, it is specifically used to: Determine the fault occurrence node and the fault end node according to the equipment fault data, and segment the equipment monitoring data based on the fault occurrence node and the fault end node to obtain the pre-sequence monitoring data, the mid-sequence monitoring data, and the post-sequence monitoring data; Determine a first data change ratio of the application parameter of the power distribution equipment according to the preceding monitoring data, determine a second data change ratio of the application parameter of the power distribution equipment according to the mid-sequence monitoring data, and determine a third data change ratio of the application parameter of the power distribution equipment according to the subsequent monitoring data; Determine a first ratio difference range based on the first data change ratio and the second data change ratio; Determine a second ratio difference range based on the second data change ratio and the third data change ratio; Determine whether the first ratio difference range and / or the second ratio difference range conform to a preset difference range; if not, mark the device monitoring data and device fault data corresponding to the first ratio difference range and / or the second ratio difference range as a human-induced fault; The equipment monitoring data and equipment failure data containing data with human-induced failure labels are filtered out to obtain natural monitoring data and natural failure data.

[0063] In another possible implementation of the embodiment of the present application, the hidden danger analysis module 23 performs equipment failure hidden danger analysis on natural monitoring data and natural fault data to obtain hidden danger evaluation standards for different power distribution equipment, specifically for: Bind and fuse the natural monitoring data with the natural fault data, and determine the equipment application data sequence and equipment environment data sequence of each distribution equipment during each fault period based on the natural analysis data obtained from the data binding and fusion; Integrate and analyze the equipment application data series and equipment environment data series to obtain the hidden danger score of each power distribution equipment; The equipment application data series, equipment environment data series and hidden danger scores are sorted according to time nodes to obtain the hidden danger evaluation standards for different power distribution equipment.

[0064] In another possible implementation of the embodiment of the present application, the hidden danger analysis module 23 is specifically configured to: The natural analysis data is divided into primary data according to data categories to obtain device application data and device environment data; Performing secondary data division on the device application data and the device environment data based on the fault period of each power distribution device to obtain multiple application data segments and multiple environment data segments; Arranging the data of each application data segment in a time sequence of the plurality of application data segments to obtain a device application data sequence of each power distribution device during each fault period; The data of each environmental data segment in the multiple environmental data segments are arranged in time sequence to obtain a device environmental data sequence of each power distribution device during each fault period.

[0065] In another possible implementation of the embodiment of the present application, the hidden danger analysis module 23 performs integrated analysis on the device application data sequence and the device environment data sequence to obtain the hidden danger score of each power distribution device, specifically for: Create a device application coordinate system and a device environment coordinate system. The X-axis of the device application coordinate system represents the time nodes before and after each failure in the historical period, and the Y-axis represents the application parameter data of different types of devices. The X-axis of the device environment coordinate system is the same as the X-axis of the device application coordinate system, and the Y-axis of the device environment coordinate system represents the parameter data of the environment in which the device is located. Import the device application data sequence into the device application coordinate system to obtain different types of application data curves; Import the device environment data sequence into the device environment coordinate system to obtain different types of environment data curves; Calculate the first slope value of each application data curve respectively, and perform cumulative mean calculation on each first slope value to obtain a first data score; Calculate the second slope value of each environmental data curve respectively, and perform cumulative mean calculation on each second slope value to obtain a second data score; The first data score and the second data score are summed according to the time nodes before and after the failure occurs to obtain the hidden danger score of each distribution equipment.

[0066] In another possible implementation of the embodiment of the present application, the hidden danger pre-diagnosis module 26 performs a fault hidden danger pre-diagnosis based on the real-time monitoring image and compares the application data to be monitored at the same location with the hidden danger assessment standard to obtain the equipment hidden danger score, specifically for: Arrange the monitoring application data according to the time series to obtain the monitoring application data series and the monitoring environment data series; Perform data segment matching on the monitoring application data sequence and the equipment data sequence in the hidden danger assessment standard to obtain the sequence matching degree; Perform data segment matching on the equipment environment data sequence and the environment data sequence in the hidden danger assessment standard to obtain the degree of environment matching; The product of the sequence matching degree, the environment matching degree and the hidden danger score is calculated to obtain the equipment hidden danger score.

[0067] Technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the distribution equipment fault prediction system 20 based on multi-dimensional data of the Internet of Things described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0068] 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 3The electronic device 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the number of transceivers 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.

[0069] Processor 301 can 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 device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 can 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.

[0070] Bus 302 may include a path for transmitting information between the above components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or one type of bus.

[0071] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device 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 compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0072] The memory 303 is used to store 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 content shown in the above method embodiment.

[0073] 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), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. They may also include servers, etc. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0074] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0075] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed 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 some of the steps in the flowcharts 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 portion of the sub-steps or stages of other steps.

[0076] The above are only some of the 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 method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things, characterized in that: include: Acquire regional image information of the campus and information about power distribution equipment, wherein the regional image information is an overall three-dimensional image of the campus area and application information of different buildings in the overall three-dimensional image; Planning the campus area image information according to the building application type to obtain a building area image; Analyzing the potential faults of the power distribution equipment to obtain potential fault evaluation standards for different power distribution equipment; Determining the installation and application location of each power distribution device according to the power distribution device information, and binding the hidden danger assessment standard and the building area image in a position-corresponding manner based on the installation and application location to obtain a hidden danger assessment image; Determine the application data to be monitored corresponding to each power distribution device between the current time node and the preset time node, and bind the application data to be monitored with the hidden danger assessment image according to the installation application location to obtain a real-time monitoring image; Based on the real-time monitoring image, the application data to be monitored at the same location is compared with the hidden danger assessment standard to perform fault hidden danger pre-diagnosis to obtain the equipment hidden danger score; Determine whether the equipment hidden danger score exceeds the preset hidden danger score. If so, determine the fault information to be diagnosed according to the hidden danger assessment standard, and bind and mark the fault information to be diagnosed with the corresponding position in the real-time monitoring image to obtain a fault prediction image.

2. The method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things according to claim 1, characterized in that: The performing of fault hidden danger analysis on the power distribution equipment information to obtain hidden danger evaluation standards for different power distribution equipment includes: Determine historical performance data of each power distribution device based on the power distribution device information, wherein the historical performance data is application performance parameter data of different power distribution devices from the installation time node to the current time node; Filter the historical performance data to obtain equipment monitoring data before and after the power distribution equipment fails, and equipment failure data at the time of the failure; Filtering the equipment monitoring data and the equipment fault data to obtain natural monitoring data and natural fault data; The natural monitoring data and the natural fault data are analyzed for hidden dangers of equipment failures to obtain hidden danger evaluation standards for different power distribution equipment.

3. The method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things according to claim 2, characterized in that: The filtering of the equipment monitoring data and the equipment fault data to obtain natural monitoring data and natural fault data includes: Determining a fault occurrence node and a fault end node according to the device fault data, and segmenting the device monitoring data based on the fault occurrence node and the fault end node to obtain pre-sequence monitoring data, mid-sequence monitoring data, and post-sequence monitoring data; Determine a first data change ratio of the power distribution equipment application parameter according to the preceding monitoring data, determine a second data change ratio of the power distribution equipment application parameter according to the mid-sequence monitoring data, and determine a third data change ratio of the power distribution equipment application parameter according to the subsequent monitoring data; Determining a first ratio difference range based on the first data change ratio and the second data change ratio; determining a second ratio difference range based on the second data change ratio and the third data change ratio; determining whether the first ratio difference range and / or the second ratio difference range conform to a preset difference range; if not, marking the device monitoring data and device fault data corresponding to the first ratio difference range and / or the second ratio difference range as a human-induced fault; The data containing the artificially caused fault label in the equipment monitoring data and equipment fault data are filtered out to obtain natural monitoring data and natural fault data.

4. The method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things according to claim 2, characterized in that: The performing of equipment failure hidden danger analysis on the natural monitoring data and the natural fault data to obtain hidden danger evaluation standards for different power distribution equipment includes: Binding and fusing the natural monitoring data with the natural fault data, and determining the device application data sequence and the device environment data sequence of each power distribution device during each fault period based on the natural analysis data obtained from the data binding and fusion; Integrate and analyze the equipment application data sequence and the equipment environment data sequence to obtain a hidden danger score for each power distribution equipment; The equipment application data sequence, the equipment environment data sequence and the hidden danger scores are sorted according to time nodes to obtain hidden danger evaluation standards for different power distribution equipment.

5. The method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things according to claim 4, characterized in that: The method of determining the device application data sequence and the device environment data sequence of each power distribution device during each fault period based on the natural analysis data obtained through data binding and fusion includes: Performing primary data division on the natural analysis data according to data categories to obtain device application data and device environment data; Performing secondary data division on the device application data and the device environment data based on the fault period of each power distribution device to obtain multiple application data segments and multiple environment data segments; Arranging the data of each application data segment in a time sequence to obtain a device application data sequence of each power distribution device during each fault period; The data of each environmental data segment in the multiple environmental data segments are arranged in time sequence to obtain a device environmental data sequence of each power distribution device during each fault period.

6. The method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things according to claim 4, characterized in that: The integrated analysis of the equipment application data sequence and the equipment environment data sequence to obtain a hidden danger score for each power distribution equipment includes: Create a device application coordinate system and a device environment coordinate system, where the X-axis of the device application coordinate system represents the time nodes before and after each failure in the historical period, and the Y-axis of the device application coordinate system represents different types of device application parameter data. The X-axis of the device environment coordinate system is the same as the X-axis of the device application coordinate system, and the Y-axis of the device environment coordinate system represents the environmental parameter data of the device. Importing the device application data sequence into the device application coordinate system to obtain different types of application data curves; Importing the device environment data sequence into the device environment coordinate system to obtain different types of environment data curves; Calculating a first slope value of each of the application data curves respectively, and performing cumulative mean calculation on each of the first slope values to obtain a first data score; Calculating the second slope value of each of the environmental data curves respectively, and performing cumulative mean calculation on each of the second slope values to obtain a second data score; The first data score and the second data score are summed according to the time nodes before and after the fault occurs to obtain the hidden danger score of each power distribution equipment.

7. The method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things according to claim 4, characterized in that: The method of performing fault hidden danger pre-diagnosis on the application data to be monitored at the same location and the hidden danger assessment standard according to the real-time monitoring image to obtain the equipment hidden danger score includes: Arrange the application data to be monitored according to the time series to obtain a monitoring application data sequence and a monitoring environment data sequence; Performing data segment matching on the monitoring application data sequence and the equipment data sequence in the hidden danger assessment standard to obtain a sequence matching degree; Performing data segment matching on the equipment environment data sequence and the environment data sequence in the hidden danger assessment standard to obtain an environment matching degree; The product of the sequence matching degree, the environment matching degree and the hidden danger score is calculated to obtain a device hidden danger score.

8. A power distribution equipment fault prediction system based on multi-dimensional data of the Internet of Things, characterized in that: include: An information acquisition module is used to acquire regional image information of the campus and information about power distribution equipment. The regional image information is an overall three-dimensional image of the campus area and application information of different buildings in the overall three-dimensional image. An image planning module is used to plan the campus area image information according to the building application type to obtain a building area image; A hidden danger analysis module is used to analyze the fault hidden dangers of the power distribution equipment information and obtain hidden danger evaluation standards for different power distribution equipment; an information binding module, configured to determine the installation and application location of each power distribution device according to the power distribution device information, and to bind the hidden danger assessment standard to the building area image in a position-corresponding manner based on the installation and application location to obtain a hidden danger assessment image; A data binding module is used to determine the application data to be monitored corresponding to each power distribution device between the current time node and the preset time node, and bind the application data to be monitored with the hidden danger assessment image according to the installation application location to obtain a real-time monitoring image; A hidden danger pre-diagnosis module is used to pre-diagnose fault hidden dangers by comparing the application data to be monitored at the same location with the hidden danger assessment standard based on the real-time monitoring image to obtain an equipment hidden danger score; The fault binding module is used to determine whether the equipment hidden danger score exceeds the preset hidden danger score. If it exceeds, the fault information to be diagnosed is determined according to the hidden danger assessment standard, and the fault information to be diagnosed is bound and marked with the corresponding position in the real-time monitoring image to obtain a fault prediction image.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed by the method for predicting power distribution equipment faults based on multi-dimensional data of the Internet of Things as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer program is stored which can be loaded by a processor and executes a method for predicting power distribution equipment failure based on multi-dimensional data of the Internet of Things as claimed in any one of claims 1 to 7.

Images