Intelligent power distribution room management method, system and equipment based on Internet of Things, and medium

Abstract

The invention relates to the technical field of the Internet of Things, in particular to an intelligent power distribution room management method, system and device based on the Internet of Things and a medium. The method comprises the following steps: firstly, performing real-time monitoring on power distribution equipment by a multi-type sensor deployed by an intelligent terminal equipment layer at a configurable sampling frequency, performing preprocessing and feature extraction on acquired data by an intelligent gateway layer through an edge computing technology, and dividing equipment states into different abnormal levels; the grading information is transmitted to a networking management platform layer, and a platform calculates a fault risk value and generates a standardized maintenance instruction sequence based on the fault risk value; and finally, the instructions are issued to field intelligent terminal equipment to execute specific maintenance operation. According to the invention, intelligent upgrading of power distribution room management is realized, the accuracy of anomaly detection and risk assessment is improved, and manual intervention is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of the Internet of Things, and in particular to a smart power distribution room management method, system, equipment and medium based on the Internet of Things. Background Art

[0002] With the continuous advancement of smart grid construction, the intelligent and automated level of distribution room, as an important node of the power system, needs to be improved urgently. The development of Internet of Things technology provides new technical support for remote monitoring and intelligent operation and maintenance of distribution room equipment, and promotes the development of distribution room management towards digitalization, networking and intelligence.

[0003] At present, most of the domestic power distribution room construction has not yet realized intelligent application, and the inspection and control of the equipment in the power distribution room still rely on manual inspections in each power distribution room on a regular basis, which is inefficient. Although some power distribution rooms have installed basic monitoring devices, the monitoring data has not been effectively utilized due to the lack of systematic data analysis and intelligent decision-making mechanisms; this situation needs to be further improved. Summary of the invention

[0004] In order to solve the problem that the existing distribution room management relies on manual regular inspections, is inefficient, and lacks systematic data analysis and intelligent decision-making mechanisms, the present application provides an intelligent distribution room management method, system, device and medium based on the Internet of Things, which adopts the following technical solutions: In a first aspect, the present application provides an intelligent power distribution room management method based on the Internet of Things, which is applied to an intelligent power distribution room integrated management system. The system includes an intelligent terminal device layer, an intelligent gateway layer, and a network management platform layer. The method includes the following steps: The operating parameters of the equipment in the power distribution room are collected through the intelligent terminal device layer to obtain the real-time status data of the equipment; Processing the real-time status data of the device through the intelligent gateway layer to obtain the abnormal status level of the device; Transmitting the abnormal status level of the equipment to the network management platform layer for analysis to obtain a fault risk value; Generate maintenance instructions based on the fault risk value through the networking management platform layer; The intelligent terminal device layer receives and executes the maintenance instruction to complete the device maintenance.

[0005] By adopting the above technical solutions, in order to solve the problems of low efficiency of manual inspection, delayed fault detection, and untimely maintenance in traditional distribution room management, it is urgent to establish an intelligent distribution room management system; this application proposes a three-layer architecture intelligent distribution room management method based on the Internet of Things. First, multiple types of sensors deployed by the intelligent terminal device layer monitor the distribution equipment in real time with a configurable sampling frequency. The intelligent gateway layer uses edge computing technology to pre-process and extract features of the collected data, and divides the equipment status into different abnormal levels; these classification information are transmitted to the network management platform layer, and the platform calculates the fault risk value, and generates a standardized maintenance instruction sequence based on the fault risk value; finally, these instructions are sent to the on-site intelligent terminal equipment to perform specific maintenance operations; the intelligent upgrade of distribution room management is realized, the accuracy of abnormality detection and risk assessment is improved, and manual intervention is reduced.

[0006] Optionally, the real-time status data of the device is processed by the intelligent gateway layer to obtain the abnormal status level of the device, which specifically includes the following steps: Preprocessing the real-time status data of the device through the intelligent gateway layer to obtain valid data; Calculate the change trend of the equipment operation parameters according to the effective data to obtain the parameter trend characteristics; Matching the parameter trend feature with a preset abnormal feature library to obtain an abnormal matching degree; The abnormal state level of the device is determined according to the numerical range of the abnormal matching degree.

[0007] By adopting the above technical scheme, the existing substation monitoring system adopts a simple threshold judgment method, which is unable to accurately identify the gradual abnormality of the equipment vibration frequency, resulting in the gradual deterioration of key components in the normal operating range, and ultimately causing sudden failure of the whole machine; the present application first performs pre-processing such as noise reduction and normalization on the collected original data to eliminate invalid data interference; then adopts an improved time series analysis algorithm to extract the changing trend characteristics of the equipment operating parameters, intelligently matches the extracted trend characteristics with the pre-established abnormal feature library, and calculates the abnormal matching degree; finally, according to the numerical range of the matching degree, the equipment status is divided into abnormal status levels, which can capture the gradual trend of the equipment parameters and realize accurate matching and grading of abnormal status.

[0008] Optionally, calculating the change trend of the equipment operation parameters according to the valid data to obtain the parameter trend characteristics specifically includes the following steps: According to the valid data, obtaining the time series variation characteristics of the equipment operation parameters; Obtain the benchmark parameters on the grid side and establish a grid operation benchmark curve; Comparing the time series variation characteristics with the grid operation benchmark curve to identify abnormal fluctuations of the equipment itself; According to the time series distribution and amplitude characteristics of the abnormal fluctuations of the device itself, the parameter trend characteristics are obtained.

[0009] By adopting the above technical scheme, in order to solve the problem that it is difficult to distinguish the fluctuations in the operating parameters of the equipment in the distribution room from the fluctuations in the power grid, resulting in the inability to accurately identify the abnormalities of the equipment itself, the present application first uses an improved time series analysis algorithm to extract the time series change characteristics of the equipment operating parameters from the effective data; by collecting benchmark parameters such as voltage and frequency on the power grid side, a power grid operation benchmark curve is constructed; then, the time series change characteristics of the equipment operating parameters are compared with the power grid benchmark curve to identify the abnormal fluctuations of the equipment itself; finally, according to the time series distribution law and amplitude change characteristics of the abnormal fluctuations, accurate parameter trend characteristics are generated; the technical problem that it is difficult to distinguish the abnormalities of the equipment itself from the fluctuations in the power grid is solved, and the accurate identification of equipment failures is achieved.

[0010] Optionally, the abnormal state level of the device is transmitted to the network management platform layer for analysis to obtain a fault risk value, which specifically includes the following steps: Transmitting the abnormal state level of the device to the network management platform layer, performing a correlation analysis of multiple devices in the region on the abnormal state level of the device to obtain a correlation impact factor; Performing weighted calculation on the abnormal state level of the equipment based on the associated influencing factors to obtain a comprehensive abnormal value of the equipment; Comparing the comprehensive abnormal value of the equipment with the historical fault data to obtain the fault similarity; A fault risk value is obtained according to the fault similarity and the equipment importance.

[0011] By adopting the above technical scheme, in order to solve the problem that the traditional distribution room management system only performs fault analysis on a single device, for example, multiple distribution equipment in an industrial park have abnormalities one after another. Due to the lack of correlation analysis between devices, the hidden dangers of systemic faults cannot be discovered in time, and eventually cause chain failures in the entire area; this application first performs correlation analysis on the abnormal states of multiple devices in the area, and calculates the impact factors between devices; the correlation impact factors are used as weights to perform weighted calculations on the abnormal states of the equipment to obtain a comprehensive abnormal value; then, the current abnormal characteristics are intelligently matched with the historical fault database to calculate the fault similarity; finally, combined with the importance of the equipment in the system, the fault risk value is comprehensively evaluated; considering the mutual influence between devices, a fault similarity calculation model based on historical data is established, which improves the accuracy of risk assessment and significantly improves the safe operation level of the distribution system.

[0012] Optionally, performing a correlation analysis of multiple devices in a region on the abnormal status level of the device to obtain a correlation impact factor specifically includes the following steps: Calling a pre-established regional device topology structure model, wherein the device topology structure model includes physical connection relationships and electrical connection relationships of devices in the region; Determine the hierarchical transmission path between the devices according to the device topology structure, and obtain the transmission coefficient; A cascade analysis is performed on the abnormal state level of the equipment based on the transfer coefficient to obtain the cascade influence degree, and a correlation influence factor is determined according to the cascade influence degree.

[0013] By adopting the above technical solution, the present application first calls the pre-established regional equipment topology model, which includes both the physical layout connection between the devices and the electrical circuit connection relationship; the hierarchical transmission path and transmission coefficient between the devices are calculated based on the topological structure; finally, through the innovative cascade analysis algorithm, the transmission impact of the abnormal state of the equipment is evaluated to obtain the correlation impact factor; the physical connection and electrical connection are dual-modeled, and the quantitative evaluation of the fault transmission effect is realized through hierarchical transmission analysis, which effectively solves the problem of fault correlation analysis between devices.

[0014] Optionally, obtaining a fault risk value according to the fault similarity and the device importance may specifically include the following steps: Obtain user type information of the power supply circuit where the equipment is located and determine the load level weight; Calculate the equipment importance coefficient based on the load level weight and the equipment online time; Performing a weighted combination of the fault similarity and the equipment importance coefficient to obtain an initial risk value; The initial risk value is dynamically modified according to the current power supply load situation to obtain a fault risk value.

[0015] By adopting the above technical solution, the present application first determines the load level weight according to the power supply circuit user type; secondly, calculates the importance coefficient in combination with the online time of the equipment; then, performs a weighted combination of the fault similarity and the importance coefficient to obtain the initial risk value; finally, dynamically corrects the risk value according to the current real-time load level, thereby realizing real-time dynamic adjustment of risk assessment.

[0016] Optionally, generating a maintenance instruction based on the fault risk value through the networking management platform layer specifically includes the following steps: Determining maintenance task priorities based on the fault risk value through the networking management platform layer, wherein the maintenance task priorities include emergency maintenance and regular maintenance; Allocate maintenance resources based on the maintenance task priority, check the availability of maintenance resources, and generate a task dispatch order; Matching the task dispatch order with a preset standard operation instruction library, filtering out the corresponding operation instruction set, and forming a maintenance instruction sequence; The maintenance instruction sequence is decomposed into basic operation instructions and sent to the corresponding intelligent terminal device.

[0017] By adopting the above technical scheme, the resource scheduling is unreasonable, the operation instructions are not standardized, and the execution efficiency is low in the process of generating maintenance instructions in traditional distribution rooms; this application first divides the two priority levels of emergency maintenance and regular maintenance according to the fault risk value; reasonably allocates maintenance resources based on the priority, and generates task dispatch orders; then, calls the preset standard operation instruction library and matches the corresponding operation instruction set; finally, decomposes the maintenance instruction sequence into basic operation instructions and issues them for execution; combines the risk assessment results with the maintenance resource scheduling, establishes a standardized operation instruction system, and realizes the full process intelligent conversion from risk assessment to specific operation instructions.

[0018] In a second aspect, the present application provides an intelligent power distribution room management system based on the Internet of Things, comprising: The intelligent terminal equipment layer is used to collect the operating parameters of the equipment in the power distribution room to obtain the real-time status data of the equipment, and to receive and execute maintenance instructions to complete equipment maintenance; The intelligent gateway layer is used to process the real-time status data of the device to obtain the abnormal status level of the device; The network management platform layer is used to receive the abnormal state level of the equipment and analyze it to obtain a fault risk value, and generate a maintenance instruction based on the fault risk value; Wherein, the intelligent terminal device layer, the intelligent gateway layer and the networking management platform layer are connected via a communication network.

[0019] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for managing an intelligent power distribution room based on the Internet of Things when executing the computer program.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned smart distribution room management method based on the Internet of Things are implemented.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: This application proposes a three-layer architecture intelligent power distribution room management method based on the Internet of Things. First, the multi-type sensors deployed by the intelligent terminal device layer monitor the power distribution equipment in real time with a configurable sampling frequency. The intelligent gateway layer pre-processes and extracts features of the collected data through edge computing technology, and divides the equipment status into different abnormal levels; these classification information are transmitted to the network management platform layer, and the platform calculates the fault risk value and generates a standardized maintenance instruction sequence based on the fault risk value; finally, these instructions are sent to the on-site intelligent terminal equipment to perform specific maintenance operations; the intelligent upgrade of power distribution room management is realized, the accuracy of abnormal detection and risk assessment is improved, and manual intervention is reduced; The existing substation monitoring system uses a simple threshold judgment method, which cannot accurately identify the gradual abnormality of the vibration frequency of the equipment, resulting in the gradual degradation of key components in the normal operating range, and ultimately causing sudden failures of the entire machine; the present application first performs pre-processing such as noise reduction and normalization on the collected raw data to eliminate invalid data interference; then uses an improved time series analysis algorithm to extract the change trend characteristics of the equipment operation parameters, intelligently matches the extracted trend characteristics with the pre-established abnormal feature library, and calculates the abnormal matching degree; finally, according to the numerical range of the matching degree, the equipment status is divided into abnormal status levels, which can capture the gradual trend of the equipment parameters and realize accurate matching and classification of abnormal states; In order to solve the problem that it is difficult to distinguish the fluctuations in the operating parameters of the equipment in the distribution room from the fluctuations in the power grid, resulting in the inability to accurately identify the abnormalities of the equipment itself, the present application first uses an improved time series analysis algorithm to extract the time series change characteristics of the equipment operating parameters from the effective data; by collecting benchmark parameters such as voltage and frequency on the power grid side, a power grid operation benchmark curve is constructed; then, the time series change characteristics of the equipment operating parameters are compared with the power grid benchmark curve to identify the abnormal fluctuations of the equipment itself; finally, according to the time series distribution law and amplitude change characteristics of the abnormal fluctuations, accurate parameter trend characteristics are generated; the technical problem that it is difficult to distinguish the abnormalities of the equipment itself from the fluctuations in the power grid is solved, and the accurate identification of equipment failures is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a smart power distribution room management method based on the Internet of Things according to an embodiment of the present application; Figure 2 It is a flowchart of step S200 in a smart power distribution room management method based on the Internet of Things in an embodiment of the present application; Figure 3 It is a flowchart of step S220 in a smart power distribution room management method based on the Internet of Things in an embodiment of the present application; Figure 4 It is a flowchart of step S300 in a smart power distribution room management method based on the Internet of Things in an embodiment of the present application; Figure 5 It is a flowchart of step S310 in a smart power distribution room management method based on the Internet of Things in an embodiment of the present application; Figure 6 It is a flowchart of step S340 in a smart power distribution room management method based on the Internet of Things in an embodiment of the present application; Figure 7 It is a flowchart of step S400 in a smart power distribution room management method based on the Internet of Things in an embodiment of the present application; Figure 8 This is a module diagram of an intelligent power distribution room management system based on the Internet of Things according to an embodiment of the present application; Fig. 9 It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0024] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0025] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0026] In the first aspect, the present application provides an intelligent distribution room management method based on the Internet of Things, which is applied to the intelligent distribution room comprehensive management system. The system includes an intelligent terminal device layer, an intelligent gateway layer and a network management platform layer. Figure 1 , the method comprises the following steps: S100. Collect operating parameters of the equipment in the power distribution room through the intelligent terminal device layer to obtain real-time status data of the equipment.

[0027] In this embodiment, the intelligent power distribution room integrated management system adopts a three-layer architecture, including an intelligent terminal device layer, an intelligent gateway layer, and a network management platform layer. Among them, the intelligent terminal device layer includes a variety of monitoring equipment, mainly composed of primary equipment (switch cabinets, transformers, PT, CT, etc.), secondary equipment (relays, online monitoring, etc.) and dynamic environment equipment (temperature and humidity, access control, cameras, etc.). These devices collect data through intelligent equipment such as RFID temperature measurement, partial discharge sensors, intelligent dehumidification, and monitoring terminals.

[0028] Specifically, various sensors collect data according to the preset sampling period. For example, the temperature sensor collects the surface temperature of the equipment every 5 minutes, the partial discharge sensor monitors the partial discharge signal in real time, and the intelligent dehumidification equipment monitors the ambient humidity and automatically controls it. The collected data includes equipment operating parameters (such as voltage, current, power, etc.), environmental parameters (such as temperature, humidity, etc.) and equipment status parameters (such as switch status, alarm information, etc.).

[0029] S200. Process the real-time status data of the device through the intelligent gateway layer to obtain the abnormal status level of the device.

[0030] Among them, the intelligent gateway layer uses intelligent gateway devices for data processing, which has the functions of "fast access, convenient maintenance, security and stability, remote management, edge computing, and efficient processing". The gateway device can identify different communication protocols and realize unified access and management of devices.

[0031] Specifically, the intelligent gateway pre-processes the collected data, including data format conversion, outlier filtering, data compression, etc. For example, when it is detected that the temperature of a switch cabinet exceeds the warning threshold, the gateway will immediately issue a level 1 alarm and transmit the abnormal data to the upper platform first. At the same time, the gateway has edge computing capabilities and can complete some data analysis tasks locally.

[0032] S300, transmitting the abnormal status level of the equipment to the network management platform layer for analysis to obtain a fault risk value.

[0033] The network management platform layer adopts the "big data + cloud computing" architecture, including functional modules such as massive data storage, deep processing and situational awareness. The platform uses image recognition technology and equipment status assessment models to achieve intelligent analysis of equipment operating status.

[0034] Specifically, the platform uses cloud servers to conduct in-depth data analysis, including dynamic grid planning, real-time warning of equipment health status, and intelligent grid operation and maintenance. By establishing a predictive maintenance model for equipment, the system can detect potential faults in advance and provide risk level assessment results.

[0035] S400. Generate maintenance instructions based on the fault risk value through the network management platform layer.

[0036] The network management platform generates corresponding maintenance instructions based on the analysis results. The platform provides 24 / 7 online monitoring, fault classification alarm notification, rapid dispatch of emergency repairs and other functions to achieve comprehensive management of the power distribution system.

[0037] Specifically, when the system detects an abnormality in the equipment, the platform automatically generates a work order based on the fault level and assigns the work order to a professional operation and maintenance team through a standardized service system. The maintenance instructions contain detailed operating steps, safety precautions, and a list of required tools to ensure the standardized execution of maintenance work.

[0038] S500: The intelligent terminal device layer receives and executes the maintenance instruction to complete device maintenance.

[0039] The intelligent terminal device layer includes various controllable devices and actuators, which can receive and execute control instructions from the platform. The system has established a standardized service system, and a professional operation and maintenance team is responsible for on-site operations.

[0040] Specifically, the operation and maintenance personnel receive maintenance instructions through mobile terminals and perform equipment maintenance according to the instructions. For example, they perform equipment inspections, replace faulty parts, adjust operating parameters, etc. After the maintenance is completed, the terminal device will feed back the execution results to the platform, realizing closed-loop management of maintenance work.

[0041] In one embodiment, referring to Figure 2 In step S200, the real-time status data of the device is processed by the intelligent gateway layer to obtain the abnormal status level of the device, which specifically includes the following steps: S210. Preprocess the real-time status data of the device through the intelligent gateway layer to obtain valid data.

[0042] The preprocessing of the real-time status data of the equipment includes three steps: data validity verification, data standardization and data compensation. Data validity verification mainly determines whether the data is within a reasonable range and eliminates obviously erroneous data; data standardization converts data of different dimensions into a unified standard; and data compensation processes data missing in the collection process.

[0043] Specifically, the intelligent gateway uses the sliding time window method to preprocess the data. For example, for the temperature data of a switch cabinet, a 5-minute time window is set. When the temperature value is detected to be outside the normal range (such as -20℃~80℃), the system automatically marks the data as invalid data. In the case of missing data, the system uses linear interpolation to supplement it to ensure the continuity of the data. The processed valid data will be timestamped and stored in the local cache.

[0044] S220. Calculate the change trend of the equipment operation parameters according to the effective data to obtain parameter trend characteristics.

[0045] The calculation of parameter trend characteristics adopts a sliding average algorithm of multiple time scales, including short-term (5 minutes), medium-term (1 hour) and long-term (24 hours). The system identifies abnormal change trends by comparing parameter changes at different time scales.

[0046] Specifically, taking transformer oil temperature as an example, the system calculates the rate of change and acceleration of the oil temperature. When the oil temperature is detected to rise rapidly in a short period of time, the system extracts the temperature curve characteristics of that period, including rising slope, fluctuation amplitude, and duration.

[0047] S230: Match the parameter trend feature with a preset abnormal feature library to obtain an abnormal matching degree.

[0048] Among them, the abnormal feature library stores the characteristic patterns of typical faults of various types of equipment, using a matching algorithm based on a combination of rules and pattern recognition. The abnormal patterns in the feature library include multiple dimensions such as time domain characteristics, frequency domain characteristics, and correlation characteristics of equipment parameters.

[0049] Specifically, the system uses an improved fuzzy pattern matching algorithm to calculate the abnormal matching degree. For example, when the vibration characteristics of the circuit breaker operating mechanism are detected, the system calculates the similarity between the extracted vibration waveform and the standard fault waveform in the feature library to obtain a matching value between 0 and 1. The closer the matching degree is to 1, the higher the similarity with a certain fault characteristic.

[0050] S240: Determine the abnormal state level of the device according to the numerical range of the abnormal matching degree.

[0051] In this embodiment, the abnormal status of the device is divided into four levels: normal, slight abnormality, moderate abnormality and severe abnormality (matching degree ≥ 0.8). Different levels correspond to different processing strategies and alarm methods.

[0052] Specifically, the system automatically determines the abnormality level based on the calculated abnormality matching degree. For example, if the matching degree between the contact temperature characteristics of a switchgear and the poor contact fault is 0.75, the system will determine it as a moderate abnormality, generate a yellow alarm, and recommend inspection and maintenance within 24 hours. At the same time, the system will record the abnormality level determination process to provide a basis for subsequent maintenance decisions.

[0053] In one embodiment, referring to Figure 3 In step S220, the change trend of the equipment operation parameters is calculated according to the effective data to obtain the parameter trend characteristics, which specifically includes the following steps: S221. Obtain the time series variation characteristics of the equipment operation parameters according to the valid data.

[0054] Among them, the time series change characteristics include two aspects: trend change and periodic change of parameters. Trend change reflects the overall change direction and rate of the parameters, and periodic change reflects the regular fluctuation characteristics of the parameters. The system uses the time series analysis method to arrange the continuously collected data in chronological order and extract the characteristic values.

[0055] Specifically, taking the load current of the distribution transformer as an example, the system collects data every 5 minutes and continuously collects data for 24 hours to form a time series. The basic characteristics of current changes are obtained by calculating the moving average and standard deviation. At the same time, the fast Fourier transform (FFT) is used to analyze the frequency domain characteristics of current fluctuations to identify periodic characteristics such as daily load change patterns and load differences between weekdays and holidays. For sudden current changes, the system will also record the duration and amplitude of the changes.

[0056] S222. Obtain benchmark parameters on the grid side and establish a grid operation benchmark curve.

[0057] The grid-side benchmark parameters refer to the typical operating parameters of the normally operating equipment in the same area. The system collects historical operating data of the same type of equipment in the area and establishes a standard operating mode library. The benchmark curve reflects the regular characteristics of equipment parameters changing over time under normal operating conditions.

[0058] Specifically, the system establishes benchmark curves for different time periods and weather conditions based on statistical analysis of historical data. For example, for a 10kV distribution transformer, the system establishes load curves for working days and rest days, and temperature curves for summer and winter. The benchmark curve includes a mean curve and a fluctuation range. The mean curve represents the expected value of the parameter, and the fluctuation range defines the normal variation range of the parameter.

[0059] S223. Compare the time series variation characteristics with the grid operation benchmark curve to identify abnormal fluctuations of the equipment itself.

[0060] Specifically, when it is detected that the contact temperature of a distribution switch exceeds the normal range of the reference curve, the system calculates the duration and degree of temperature deviation. For example, if the temperature exceeds the reference value by more than 20% for 30 minutes and is not caused by changes in ambient temperature or increased load, it is considered to be an abnormal fluctuation of the device itself. The system also considers changes in related parameters, such as whether the current value is synchronously abnormal, to improve the accuracy of the judgment.

[0061] S224. Obtain parameter trend characteristics based on the time series distribution and amplitude characteristics of the abnormal fluctuation of the device itself.

[0062] Among them, the parameter trend characteristics include the characteristic descriptions of the time dimension and the amplitude dimension. The time dimension describes the temporal relationship of the abnormality, such as the first occurrence time, duration, repetition cycle, etc.; the amplitude dimension describes the severity of the abnormality, such as the maximum deviation, average deviation, fluctuation range, etc.

[0063] In one embodiment, referring to Figure 4 In step S300, the abnormal status level of the equipment is transmitted to the network management platform layer for analysis to obtain the fault risk value, which specifically includes the following steps: S310, transmitting the abnormal status level of the equipment to the network management platform layer, performing correlation analysis on the abnormal status level of the equipment for multiple devices in the region, and obtaining correlation influencing factors.

[0064] Among them, the correlation analysis of multiple devices in the region uses the device topology diagram and the operation status correlation matrix. The topology diagram describes the physical connection relationship and electrical connection between devices, and the operation status correlation matrix reflects the degree of mutual influence of the operating parameters between devices. The system establishes a correlation model between devices based on the principle of power system flow analysis.

[0065] Specifically, taking a 10kV distribution line as an example, when a transformer is detected to have an abnormal temperature, the system automatically analyzes all devices connected to the transformer, including upstream incoming line cabinets, downstream distribution cabinets, etc. By analyzing the operating data of these devices, the degree of correlation between the devices is calculated. For example, if there is a significant correlation between the abnormal temperature of the transformer and the overload of a certain outgoing line circuit, the system will quantify this correlation as a correlation influencing factor.

[0066] S320. Perform weighted calculation on the abnormal status level of the equipment based on the associated influencing factors to obtain a comprehensive abnormal value of the equipment.

[0067] Among them, weight factors include multiple dimensions such as physical distance between devices, electrical connection relationship, and correlation of operating parameters. The system establishes a weight calculation model based on expert experience and historical data and dynamically adjusts the weight coefficient.

[0068] S330. Compare the comprehensive abnormal value of the equipment with the historical fault data to obtain the fault similarity.

[0069] Specifically, the system matches the comprehensive abnormal values ​​of the current equipment with historical cases. For example, if an operating mechanism of a circuit breaker is abnormal, the system extracts its abnormal features (such as extended operation time, abnormal mechanism vibration, etc.) and compares them with the features in the historical fault case library.

[0070] S340. Obtain a fault risk value according to the fault similarity and the equipment importance.

[0071] Among them, the importance of equipment is divided into four levels: core equipment (weight 1.0), important equipment (weight 0.8), general equipment (weight 0.6) and auxiliary equipment (weight 0.4). The system determines the importance of equipment based on factors such as the location of the equipment in the distribution network, the power supply range and the importance of the user.

[0072] In one embodiment, referring to Figure 5 In step S310, a correlation analysis of multiple devices in the region is performed on the abnormal status level of the device to obtain a correlation impact factor, which specifically includes the following steps: S311. Call a pre-established regional device topology structure model, where the device topology structure model includes physical connection relationships and electrical connection relationships of devices in the region.

[0073] The regional equipment topology model is constructed using graph theory, and the equipment topology diagram is used to represent the connection relationship between equipment. The nodes in the model represent various types of equipment (such as transformers, switch cabinets, lines, etc.), and the edges represent the connection method between equipment. The physical connection relationship describes the actual installation location and connection method of the equipment, and the electrical connection relationship describes the power transmission path and control relationship between equipment.

[0074] S312. Determine the hierarchical transmission path between the devices according to the device topology structure, and obtain the transmission coefficient.

[0075] The hierarchical transmission path is determined based on the breadth-first search algorithm, and the shortest and second shortest paths from the abnormal device to the related devices are calculated. The transmission coefficient takes into account factors such as path length, connection type, and impedance characteristics, and uses the attenuation function model to calculate the energy transfer effect. The system quantifies the diffusion effect of the abnormal state in the device network based on the size of the transmission coefficient.

[0076] S313. Perform cascade analysis on the abnormal status level of the equipment based on the transfer coefficient to obtain the cascade impact degree, and determine the associated impact factor according to the cascade impact degree.

[0077] Among them, the propagation characteristics of the abnormal state level of the equipment in the network are considered. The system establishes a cascading failure model based on the probability of equipment state transition, and determines the degree of influence of the abnormal state on each level of equipment through iterative calculation. The correlation impact factor is a normalized representation of the degree of cascading influence, reflecting the strength of fault correlation between equipment.

[0078] In one embodiment, referring to Figure 6 In step S340, a fault risk value is obtained according to the fault similarity and the equipment importance, which specifically includes the following steps: S341. Obtain user type information of the power supply circuit where the device is located, and determine the load level weight.

[0079] Among them, user type information is divided into special users (such as hospitals and data centers), first-level users (such as industrial enterprises), second-level users (such as commercial areas) and third-level users (such as ordinary residential areas). The system has established a hierarchical user weight assessment system based on the power supply reliability requirements and social impact of each type of user.

[0080] S342. Calculate the equipment importance coefficient based on the load level weight and the equipment online time.

[0081] Among them, in addition to the load level weight, the equipment importance coefficient also considers factors such as equipment operation time, maintenance record, replacement cycle, etc. The system establishes an equipment status assessment model based on fuzzy evaluation to dynamically calculate the equipment importance coefficient.

[0082] Specifically, the calculation formula for the equipment importance coefficient is: importance coefficient = load level weight * (1 + operating time coefficient) * maintenance status coefficient.

[0083] S343. Perform a weighted combination of the fault similarity and the equipment importance coefficient to obtain an initial risk value.

[0084] Among them, the system sets the benchmark weight ratio of fault similarity and importance coefficient, and dynamically adjusts it according to actual operating experience.

[0085] S344. Dynamically correct the initial risk value according to the current power supply load situation to obtain a fault risk value.

[0086] Specifically, the system uses time-based correction coefficients to adjust the initial risk value. For example, during peak power consumption (load rate exceeds 80%), the risk correction coefficient is 1.2; under extreme weather conditions (such as high temperature warnings), the correction coefficient can reach 1.3. Assuming that the initial risk value of a transformer is 75, and it is currently at peak power consumption and the weather is hot, the final fault risk value needs to be multiplied by the comprehensive correction coefficient of 1.5. Risk values ​​exceeding 100 will trigger the emergency warning mechanism, and the system will automatically generate processing suggestions and plans.

[0087] In one embodiment, referring to Figure 7 In step S400, a maintenance instruction is generated based on the fault risk value through the network management platform layer, which specifically includes the following steps: S410. Determine maintenance task priorities based on the fault risk value through the network management platform layer, where the maintenance task priorities include emergency maintenance and regular maintenance.

[0088] The system sets the emergency maintenance threshold of the fault risk value to 85 points and the regular maintenance threshold to 60 points. At the same time, combined with the trend analysis of equipment operation status, a time series-based early warning upgrade mechanism is established to dynamically adjust the maintenance priority.

[0089] S420: Allocate maintenance resources based on maintenance task priorities, check availability of maintenance resources, and generate task dispatch orders.

[0090] Among them, maintenance resource allocation adopts intelligent scheduling algorithm, which comprehensively considers factors such as professional qualifications, geographical location, workload, etc. of maintenance personnel. The system has established a maintenance resource pool management mechanism, including real-time status monitoring of resources such as personnel, vehicles, spare parts, etc., to ensure the rationality and efficiency of resource allocation.

[0091] Specifically, taking the maintenance task of a substation in a certain area as an example, the system first checks the currently available maintenance teams. Assuming that circuit breaker maintenance is required, the system will screen the teams with high-voltage switch maintenance qualifications and calculate the time cost of each team to arrive at the site. If the nearest qualified team has other urgent tasks, the system will compare task priorities and reallocate resources. At the same time, the system checks the inventory of required spare parts. If it finds that the inventory of key spare parts is insufficient, it will immediately trigger the spare parts allocation process to ensure the smooth progress of maintenance work.

[0092] S430: Match the task dispatch sheet with a preset standard operation instruction library, filter out the corresponding operation instruction set, and form a maintenance instruction sequence.

[0093] The standard operation instruction library adopts a hierarchical and classified knowledge base structure, which contains multi-dimensional information such as equipment type, fault type, operation steps, etc. The system uses an improved pattern matching algorithm to match the characteristics of the current maintenance task with the standard template in the instruction library to generate the optimal combination of operation instructions.

[0094] S440: Decompose the maintenance instruction sequence into basic operation instructions, and send them to the corresponding intelligent terminal device.

[0095] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0096] In the second aspect, the present application provides an intelligent distribution room management system based on the Internet of Things. The intelligent distribution room management system based on the Internet of Things of the present application is described below in combination with the above-mentioned intelligent distribution room management method based on the Internet of Things.

[0097] Reference Figure 8 , an intelligent distribution room management system based on the Internet of Things, comprising: The intelligent terminal equipment layer is used to collect the operating parameters of the equipment in the power distribution room to obtain the real-time status data of the equipment, and to receive and execute maintenance instructions to complete equipment maintenance; The intelligent gateway layer is used to process the real-time status data of the equipment and obtain the abnormal status level of the equipment; The network management platform layer is used to receive the abnormal status level of the equipment and analyze it to obtain the fault risk value, and generate maintenance instructions based on the fault risk value; Among them, the intelligent terminal device layer, the intelligent gateway layer and the network management platform layer are connected through a communication network.

[0098] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a smart distribution room management method based on the Internet of Things is implemented.

[0099] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0100] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0101] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0102] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A smart distribution room management method based on the Internet of Things, characterized in that: Applied in the integrated management system of intelligent power distribution room, the system includes an intelligent terminal device layer, an intelligent gateway layer and a network management platform layer, and the method includes the following steps: The operating parameters of the equipment in the power distribution room are collected through the intelligent terminal device layer to obtain the real-time status data of the equipment; Processing the real-time status data of the device through the intelligent gateway layer to obtain the abnormal status level of the device; Transmitting the abnormal status level of the equipment to the network management platform layer for analysis to obtain a fault risk value; Generate maintenance instructions based on the fault risk value through the networking management platform layer; The intelligent terminal device layer receives and executes the maintenance instruction to complete the device maintenance.

2. The method for managing an intelligent power distribution room based on the Internet of Things according to claim 1 is characterized in that: The real-time status data of the device is processed by the intelligent gateway layer to obtain the abnormal status level of the device, which specifically includes the following steps: Preprocessing the real-time status data of the device through the intelligent gateway layer to obtain valid data; Calculate the change trend of the equipment operation parameters according to the effective data to obtain the parameter trend characteristics; Matching the parameter trend feature with a preset abnormal feature library to obtain an abnormal matching degree; The abnormal state level of the device is determined according to the numerical range of the abnormal matching degree.

3. The method for managing an intelligent power distribution room based on the Internet of Things according to claim 2 is characterized in that: Calculating the change trend of the equipment operation parameters according to the effective data to obtain the parameter trend characteristics specifically includes the following steps: According to the valid data, obtaining the time series variation characteristics of the equipment operation parameters; Obtain the benchmark parameters on the grid side and establish a grid operation benchmark curve; Comparing the time series variation characteristics with the grid operation benchmark curve to identify abnormal fluctuations of the equipment itself; According to the time series distribution and amplitude characteristics of the abnormal fluctuations of the device itself, the parameter trend characteristics are obtained.

4. The method for managing an intelligent power distribution room based on the Internet of Things according to claim 1, characterized in that: The abnormal state level of the equipment is transmitted to the network management platform layer for analysis to obtain a fault risk value, which specifically includes the following steps: Transmitting the abnormal state level of the device to the network management platform layer, performing a correlation analysis of multiple devices in the region on the abnormal state level of the device to obtain a correlation impact factor; Performing weighted calculation on the abnormal state level of the equipment based on the associated influencing factors to obtain a comprehensive abnormal value of the equipment; Comparing the comprehensive abnormal value of the equipment with the historical fault data to obtain the fault similarity; A fault risk value is obtained according to the fault similarity and the equipment importance.

5. The method for managing an intelligent power distribution room based on the Internet of Things according to claim 4 is characterized in that: Performing a correlation analysis of multiple devices in a region on the abnormal status level of the device to obtain a correlation influencing factor specifically includes the following steps: Calling a pre-established regional device topology structure model, wherein the device topology structure model includes physical connection relationships and electrical connection relationships of devices in the region; Determine the hierarchical transmission path between the devices according to the device topology structure, and obtain the transmission coefficient; A cascade analysis is performed on the abnormal state level of the equipment based on the transfer coefficient to obtain the cascade influence degree, and a correlation influence factor is determined according to the cascade influence degree.

6. The method for managing an intelligent power distribution room based on the Internet of Things according to claim 4 is characterized in that: According to the fault similarity and the importance of the equipment, a fault risk value is obtained, which specifically includes the following steps: Obtain user type information of the power supply circuit where the equipment is located and determine the load level weight; Calculate the equipment importance coefficient based on the load level weight and the equipment online time; Performing a weighted combination of the fault similarity and the equipment importance coefficient to obtain an initial risk value; The initial risk value is dynamically modified according to the current power supply load situation to obtain a fault risk value.

7. The method for managing an intelligent power distribution room based on the Internet of Things according to claim 1, characterized in that: Generating maintenance instructions based on the fault risk value through the networking management platform layer specifically includes the following steps: Determining maintenance task priorities based on the fault risk value through the networking management platform layer, wherein the maintenance task priorities include emergency maintenance and regular maintenance; Allocate maintenance resources based on the maintenance task priority, check the availability of maintenance resources, and generate a task dispatch order; Matching the task dispatch order with a preset standard operation instruction library, filtering out the corresponding operation instruction set, and forming a maintenance instruction sequence; The maintenance instruction sequence is decomposed into basic operation instructions and sent to the corresponding intelligent terminal device.

8. An intelligent power distribution room management system based on the Internet of Things, characterized in that: include: The intelligent terminal equipment layer is used to collect the operating parameters of the equipment in the power distribution room to obtain the real-time status data of the equipment, and to receive and execute maintenance instructions to complete equipment maintenance; The intelligent gateway layer is used to process the real-time status data of the device to obtain the abnormal status level of the device; The network management platform layer is used to receive the abnormal state level of the equipment and analyze it to obtain a fault risk value, and generate a maintenance instruction based on the fault risk value; Wherein, the intelligent terminal device layer, the intelligent gateway layer and the networking management platform layer are connected via a communication network.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for managing an intelligent power distribution room based on the Internet of Things described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the smart distribution room management method based on the Internet of Things described in any one of claims 1 to 7 are implemented.

Images