Power distribution equipment intelligent management system based on Internet of Things

Abstract

The utility model provides a power distribution equipment intelligent management system based on the Internet of Things, the power distribution equipment intelligent management system based on the Internet of Things comprises an equipment layer, an edge layer and a cloud platform layer, specifically, the equipment layer comprises power distribution equipment and a sensor array arranged on the power distribution equipment; the edge layer preprocesses the operation data collected by the sensor array to obtain preprocessed data, and sends the preprocessed data to the cloud platform layer; and the cloud platform layer analyzes the preprocessed data and generates abnormal evaluation data, load optimization data and reactive compensation data. The system realizes comprehensive management of real-time monitoring, predictive maintenance, energy efficiency analysis, intelligent alarm and the like of the power distribution equipment, is suitable for complex operation environments, can effectively cope with severe working conditions of high humidity, large temperature difference, strong vibration and the like, ensures safe and stable operation, and improves the automation level and operation reliability of the power supply equipment.

Description

Technical Field

[0001] This application relates to the field of power equipment technology, and in particular to an intelligent management system for power distribution equipment based on the Internet of Things. Background Technology

[0002] Power distribution equipment, especially low-voltage switchgear, plays an irreplaceable role in modern industrial production and commercial operations. As a key infrastructure device in the power system, its operating status directly affects the reliability and security of the entire power supply system. With the continuous improvement of the level of intelligent industrial production, higher requirements are placed on the operation and maintenance management of power distribution systems. However, the current operation and maintenance management of power distribution equipment still faces severe challenges. Statistics from the State Grid Corporation of China show that the direct economic losses caused by power distribution system failures to industrial enterprises in my country exceed 1 billion yuan annually, a large portion of which stems from improper equipment maintenance or failure to detect faults in a timely manner. Against the backdrop of continuously rising energy costs, improving the operating efficiency and energy-saving level of power distribution systems has become an urgent need for enterprises. These practical problems are driving the development of power distribution equipment towards intelligence and networking.

[0003] Current technological advancements in smart power distribution primarily manifest in several aspects. For instance, existing technologies utilize temperature and humidity sensors deployed within distribution cabinets to monitor equipment operating status. RS485 bus is used for communication, transmitting the collected data to a local controller for processing. When monitored parameters exceed preset ranges, the system issues an alarm. While this approach achieves basic status monitoring, it lacks precise measurement of electrical parameters and comprehensive monitoring of critical internal components. Furthermore, its relatively simple implementation and simplistic data analysis methods, relying on single or limited sensors for status monitoring and fault diagnosis based primarily on threshold values ​​for single parameters, fail to comprehensively perceive the equipment's operating status, thus hindering the identification of complex fault modes and the prediction of potential equipment failures.

[0004] To address this, existing technologies incorporate Mahalanobis distance algorithms for fault feature identification. By establishing a fault feature database based on historical data, preliminary identification of abnormal states is achieved. The system possesses remote monitoring capabilities, supporting remote access to and basic analysis of equipment operation data. However, such systems still fall short in data preprocessing and feature extraction, failing to fully utilize the rich information contained in equipment operation data, especially the influence of dynamic characteristics and environmental factors. The system's data preprocessing capabilities are weak, and the feature extraction methods are overly simplistic, unable to effectively extract and utilize fault feature information. Furthermore, the assessment of equipment operating status is overly simplistic, completely lacking energy efficiency management functions, failing to help users achieve energy conservation and consumption reduction goals, and thus failing to meet the demands of modern industrial production for precise equipment management.

[0005] In the international market, mainstream electrical equipment manufacturers' smart power distribution solutions also suffer from similar limitations. While these solutions employ modular designs and provide basic network communication functions, enabling simple energy consumption monitoring and remote operation, the processing of various monitoring data is fragmented, lacking the ability to fuse and analyze multi-source data. They fail to fully explore the correlations between data points and remain relatively weak in deeper applications such as predictive maintenance and intelligent diagnostics. Specifically, they cannot accurately assess the health status of equipment, predict the development trend of potential faults, or implement refined load optimization and energy-saving control strategies, resulting in low energy utilization efficiency. Furthermore, alarm mechanisms are relatively simple, prone to false alarms and missed alarms, severely impacting the efficiency of operation and maintenance. Therefore, existing products generally lack systematic management capabilities throughout the entire equipment lifecycle, making it difficult to meet users' deeper needs for intelligent and refined equipment management. Utility Model Content

[0006] In view of this, the present application provides an intelligent management system for power distribution equipment based on the Internet of Things to solve the technical defects existing in the prior art.

[0007] According to a first aspect of the embodiments of this application, an intelligent management system for power distribution equipment based on the Internet of Things is provided, including a device layer, an edge layer, and a cloud platform layer, wherein...

[0008] The equipment layer includes power distribution equipment and a sensor array arranged on the power distribution equipment;

[0009] The edge layer preprocesses the operational data collected by the sensor array to obtain preprocessed data, and then sends the preprocessed data to the cloud platform layer.

[0010] The cloud platform layer analyzes the preprocessed data to generate anomaly assessment data, load optimization data, and reactive power compensation data.

[0011] Optionally, the sensor array includes a temperature sensor array, an electrical parameter monitoring sensor, and an environmental parameter sensor, wherein,

[0012] The temperature sensor array is arranged at the cable connection location of the power distribution equipment;

[0013] The electrical parameter monitoring sensors are arranged at the electrical parameter sampling locations of the power distribution equipment;

[0014] The environmental parameter sensors are arranged at the environmental parameter sampling locations of the power distribution equipment.

[0015] Optionally, the cable connection locations include busbar connections, circuit breaker contact locations, and cable joints.

[0016] Optionally, the environmental parameter sensor includes a humidity sensor and uses ultrasonic detection to perform partial discharge detection inside the power distribution equipment.

[0017] Optionally, the edge layer's preprocessing of the operational data collected by the sensor array includes:

[0018] The noise in the running data is removed by an improved Kalman filter algorithm to obtain denoised running data.

[0019] The denoised running data is processed using a preset compression algorithm based on differential coding to obtain the preprocessed data.

[0020] Optionally, the cloud platform layer's process of analyzing the preprocessed data and generating anomaly assessment data, load optimization data, and reactive power compensation data includes:

[0021] Extract the time-domain features, frequency-domain features, and time-frequency features of the preprocessed data;

[0022] By using a feature selection algorithm, redundant features in the time-domain features, the frequency-domain features, and the time-frequency features are removed to obtain the target time-domain features associated with the time-domain features, the target frequency-domain features associated with the frequency-domain features, and the target time-frequency features associated with the time-frequency features.

[0023] Based on the long short-term memory neural network model, the target time-domain features, target frequency-domain features, and target time-frequency features are processed to obtain the anomaly assessment data, the load optimization data, and the reactive power compensation data.

[0024] Optionally, the cloud platform layer further includes an anomaly assessment module, wherein,

[0025] The anomaly assessment module generates an equipment maintenance plan based on the anomaly assessment data; it calls the equipment parameters and historical maintenance data of the power distribution equipment, and also calls the historical work records of the maintenance personnel associated with the power distribution equipment; it generates plan allocation information based on the equipment parameters, the historical maintenance data, and the historical work records; and it allocates the equipment maintenance plan to the maintenance personnel based on the plan allocation information.

[0026] Optionally, the cloud platform layer further includes a load optimization module, wherein,

[0027] The load optimization module generates a load control command based on the load optimization data; in response to the load control command, the power distribution equipment adjusts the load parameters.

[0028] Optionally, the cloud platform layer further includes a reactive power compensation module, wherein,

[0029] The reactive power compensation module determines a reactive power compensation command based on a preset predictive compensation algorithm and the reactive power compensation data; in response to the reactive power compensation command, the power distribution equipment adjusts its power parameters.

[0030] Optionally, the IoT-based intelligent management system for power distribution equipment further includes a communication layer, wherein,

[0031] The communication layer is used for information interaction between the edge layer and the cloud platform layer.

[0032] This application provides an IoT-based intelligent management system for power distribution equipment, comprising a device layer, an edge layer, and a cloud platform layer. The device layer includes power distribution equipment and a sensor array deployed on the equipment. The edge layer preprocesses the operational data collected by the sensor array to obtain preprocessed data and sends this data to the cloud platform layer. The cloud platform layer analyzes the preprocessed data to generate anomaly assessment data, load optimization data, and reactive power compensation data. This system enables comprehensive management of power distribution equipment, including real-time monitoring, predictive maintenance, energy efficiency analysis, and intelligent alarms. It is suitable for complex operating environments, effectively coping with harsh conditions such as high humidity, large temperature differences, and strong vibrations, ensuring safe and stable operation, and improving the automation level and operational reliability of power supply equipment. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a schematic diagram of the structure of an intelligent management system for power distribution equipment based on the Internet of Things, provided in one embodiment of this application;

[0035] Figure 2 This is a system architecture diagram of an IoT-based intelligent management system for power distribution equipment provided in one embodiment of this application;

[0036] Figure 3 This is a schematic diagram of sensor arrangement for an IoT-based intelligent management system for power distribution equipment, provided in one embodiment of this application.

[0037] Figure 4 This is a software functional architecture diagram of an Internet of Things-based intelligent management system for power distribution equipment provided in one embodiment of this application;

[0038] Figure 5This is a flowchart illustrating the predictive maintenance process of an IoT-based intelligent management system for power distribution equipment, provided in one embodiment of this application. Detailed Implementation

[0039] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0040] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0041] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first.

[0042] This application provides an intelligent management system for power distribution equipment based on the Internet of Things, which will be described in detail in the following embodiments.

[0043] Figure 1 This diagram illustrates the structure of an IoT-based intelligent management system for power distribution equipment according to an embodiment of this application, specifically including a device layer, an edge layer, and a cloud platform layer.

[0044] The equipment layer includes power distribution equipment and a sensor array arranged on the power distribution equipment;

[0045] The edge layer preprocesses the operational data collected by the sensor array to obtain preprocessed data, and then sends the preprocessed data to the cloud platform layer.

[0046] The cloud platform layer analyzes the preprocessed data to generate anomaly assessment data, load optimization data, and reactive power compensation data.

[0047] The power distribution equipment includes distribution cabinets and distribution boxes. Sensor arrays are deployed at the data acquisition points of the power distribution equipment. These data acquisition points represent the locations where data needs to be collected from the power distribution equipment and are determined by the equipment's structure. The sensor array consists of a large number and various types of sensors. Therefore, based on the structure of the power distribution equipment, the locations where data collection is required are determined, and sensors are deployed at these locations to collect the equipment's operational data. After preprocessing at the edge layer, the preprocessed data is sent to the cloud computing platform at the cloud platform layer. The cloud computing platform analyzes this data to determine anomaly assessment data, load optimization data, and reactive power compensation data. The anomaly assessment data is used for anomaly warning, the load optimization data is used to optimize the load on the power distribution equipment, and the reactive power compensation data is used to adjust the power factor of the power distribution equipment.

[0048] Based on this, such as Figure 2 The system architecture diagram of an IoT-based intelligent management system for power distribution equipment is provided. Adopting a hierarchical design, it uses three layers—device layer, edge layer, and cloud platform layer—as the main execution layers. At the device layer, on the power distribution equipment side, a sensor array is deployed, including a temperature sensor array, current transformers, voltage acquisition modules, and environmental monitoring modules. At the edge layer, on the edge computing nodes, data acquisition and processing modules, local analysis modules, and communication management modules are deployed. Considering the special requirements of the industrial environment, the selected hardware ensures heat dissipation performance and anti-interference capabilities, while the software uses the Linux operating system to ensure the real-time performance and reliability of data processing. At the cloud platform layer, a microservice architecture is adopted, decoupling complex system functions into multiple independent service modules. LSTM (Long Short-Term Memory) neural network is used as the core algorithm. Specifically, it includes a distributed database, a health assessment module, a predictive analysis module, and an energy efficiency optimization module. The processing results are displayed through a web management platform, mobile applications, and API interface services.

[0049] Furthermore, the sensor array includes a temperature sensor array, an electrical parameter monitoring sensor, and an environmental parameter sensor, wherein the temperature sensor array is arranged at the cable connection location of the power distribution equipment; the electrical parameter monitoring sensor is arranged at the electrical parameter sampling location of the power distribution equipment; and the environmental parameter sensor is arranged at the environmental parameter sampling location of the power distribution equipment.

[0050] Furthermore, cable connection locations include busbar connections, circuit breaker contact locations, and cable joints.

[0051] Furthermore, the environmental parameter sensors include a humidity sensor, which uses ultrasonic detection to perform partial discharge detection inside the power distribution equipment.

[0052] Among them, the "matrix" temperature monitoring solution achieves accurate monitoring of equipment temperature distribution by deploying high-precision digital temperature sensors at key locations in the power distribution equipment. For example... Figure 2 The provided system architecture diagram for an IoT-based intelligent management system for power distribution equipment shows that the temperature sensor array utilizes the latest TMP117 digital temperature chip, boasting an ultra-high measurement accuracy of ±0.5℃ and a monitoring range covering a wide temperature range from -40℃ to 125℃, meeting the monitoring needs of power distribution equipment under various operating conditions. Furthermore, the matrix layout design combined with hyperbolic interpolation algorithms enables accurate reconstruction of the internal temperature field of the power distribution equipment. This monitoring method not only significantly improves the accuracy of temperature monitoring but also expands the monitoring coverage, providing a more reliable data foundation for equipment condition assessment.

[0053] Specifically, by deploying multiple high-precision digital temperature sensors at key locations on the power distribution equipment—the data acquisition points—and employing a hyperboloid interpolation algorithm for temperature field reconstruction, the temperature monitoring accuracy is improved to ±0.5℃, a five-fold increase. Simultaneously, the matrix layout expands the temperature monitoring coverage to 95% of the critical areas inside the equipment, a significant improvement over the original 30% coverage. This high-precision, wide-area monitoring capability enables the system to promptly detect early signs of faults such as localized overheating.

[0054] The sensors installed at busbar connections are primarily used to monitor the heat distribution generated during current transmission. These sensors, arranged in a specific spatial pattern, can accurately capture temperature changes at the busbar connection points and reflect the contact status of the connection points through temperature distribution characteristics. Sensors positioned at circuit breaker contacts focus on monitoring contact heating, which is crucial for early detection of faults such as poor contact. Sensors at cable joints primarily monitor temperature changes at the cable ends; real-time monitoring can effectively prevent dangerous faults caused by loose joints.

[0055] In addition, such as Figure 2 The provided system architecture diagram for an IoT-based intelligent management system for power distribution equipment shows that the electrical parameter monitoring sensors include current transformers and voltage acquisition modules. Specifically, the current transformers are 0.2-class high-precision current transformers with a Rogowski coil structure, exhibiting excellent linearity and temperature stability. This not only ensures measurement accuracy but also effectively suppresses external magnetic field interference. The voltage acquisition module employs a precise resistor voltage divider network and a temperature compensation design, achieving high-precision measurement across the entire temperature range. A high sampling frequency of 12.8kHz ensures accurate measurement of the fundamental frequency parameter and supports detailed analysis of harmonics up to the 25th order, providing a reliable basis for assessing power quality.

[0056] And, as Figure 2 The system architecture diagram of an IoT-based intelligent management system for power distribution equipment shows that the environmental monitoring module, or environmental parameter sensor, includes a humidity sensor. This humidity sensor employs a high-precision digital sensing element, covering a measurement range of 0-100% RH with an accuracy of ±2% RH. The sensor's installation location, i.e., the environmental parameter sampling location, ensures that the sensor accurately reflects the humidity status inside the cabinet without being directly affected by internal heat generation. The environmental parameter sensor also features partial discharge monitoring, using ultrasonic detection to detect early-stage degradation of equipment insulation performance. This non-destructive testing method does not affect normal equipment operation and can promptly identify potential safety hazards.

[0057] Specifically, in one embodiment, the sensor array is arranged as follows: Figure 3 A schematic diagram of the sensor layout for an IoT-based intelligent management system for power distribution equipment is provided. Wireless temperature sensors collect temperature data from the busbars, wired temperature sensors collect temperature data from the circuit breaker terminals, and ambient temperature sensors collect ambient temperature data. Data collected by current transformers, along with data collected by the wired / wireless temperature sensors, are sent to a smart meter. Data collected by the ambient temperature and humidity sensors are sent to a temperature and humidity controller, and all data is uploaded via network devices.

[0058] Furthermore, in step S106, the edge layer performs preprocessing on the operational data collected by the sensor array. In this embodiment, the specific implementation is as follows:

[0059] The noise in the running data is removed by an improved Kalman filter algorithm to obtain denoised running data; the denoised running data is then processed by a preset compression algorithm based on differential coding to obtain preprocessed data.

[0060] The edge layer includes edge computing nodes. These nodes are equipped with industrial-grade ARM processors as their core, clocked at 1.6GHz, and featuring 4GB of RAM and 64GB of industrial-grade storage. The processor selection meets the specific requirements of the industrial environment, offering excellent heat dissipation and reliable anti-interference capabilities. On the software side, a real-time Linux operating system is used. Through system configuration and optimization, the real-time performance and reliability of data processing are ensured.

[0061] Therefore, the primary task of edge computing nodes is data preprocessing. An improved Kalman filter algorithm is employed, which effectively removes noise from the running data by adaptively adjusting filter parameters while preserving the rapid changes in the signal. For data compression, a differential coding-based intelligent compression algorithm is used. This algorithm automatically adjusts the compression strategy according to data characteristics, achieving a compression rate of over 80% while maintaining data accuracy.

[0062] Furthermore, the edge computing nodes deploy an innovative, lightweight deep learning model. Developed based on the TensorFlow Lite framework, this model, through pruning and quantization optimization, keeps its size below 10MB while maintaining high analytical accuracy. Employing a pipelined processing mechanism, the model's single inference time is kept below 100ms, meeting the demands of real-time analysis. It also supports online model updates, allowing for continuous optimization of model parameters based on actual operational data, thereby constantly improving analytical accuracy.

[0063] Furthermore, the cloud platform layer analyzes the preprocessed data to generate anomaly assessment data, load optimization data, and reactive power compensation data. In this embodiment, the specific implementation method is as follows:

[0064] Extract the time-domain features, frequency-domain features, and time-frequency features of the preprocessed data; use a feature selection algorithm to remove redundant features from the time-domain features, frequency-domain features, and time-frequency features to obtain the target time-domain features associated with the time-domain features, the target frequency-domain features associated with the frequency-domain features, and the target time-frequency features associated with the time-frequency features; based on a long short-term memory neural network model, process the target time-domain features, target frequency-domain features, and target time-frequency features to obtain the anomaly assessment data, the load optimization data, and the reactive power compensation data.

[0065] Furthermore, the cloud platform layer also includes an anomaly assessment module, wherein the anomaly assessment module generates an equipment maintenance plan based on the anomaly assessment data; calls the equipment parameters and historical maintenance data of the power distribution equipment, and calls the historical work records of the maintenance personnel associated with the power distribution equipment; generates plan allocation information based on the equipment parameters, the historical maintenance data, and the historical work records; and allocates the equipment maintenance plan to the maintenance personnel based on the plan allocation information.

[0066] Furthermore, the cloud platform layer also includes a load optimization module, wherein the load optimization module generates a load control command based on the load optimization data; in response to the load control command, the power distribution equipment adjusts the load parameters.

[0067] Furthermore, the cloud platform layer also includes a reactive power compensation module, wherein the reactive power compensation module determines a reactive power compensation command based on a preset predictive compensation algorithm and the reactive power compensation data; in response to the reactive power compensation command, the power distribution equipment adjusts its power parameters.

[0068] Among them, such as Figure 4 The provided software functional architecture diagram of an IoT-based intelligent management system for power distribution equipment shows that data is collected through the device layer, data filtering, outlier cleaning and data formatting are performed through the edge layer, and feature extraction is performed through the cloud platform layer, extracting time-domain features, frequency-domain features, temperature features and electrical features. Through feature fusion, health status assessment is performed, and then fault prediction and risk assessment are performed through a deep learning model. Finally, it is determined whether maintenance is required. If maintenance is required, maintenance suggestions are generated and pushed to the mobile terminal. If maintenance is not required, health monitoring continues.

[0069] Based on this, the cloud computing platform constructs a unified data center and intelligent analytics platform. The platform adopts a microservice architecture, decoupling complex system functions into multiple independent service modules. This architecture not only improves system maintainability but also facilitates future functional expansion. For data storage, the distributed time-series database InfluxDB is selected as the core storage engine. This database is specifically optimized for time-series data, boasting excellent write performance, capable of processing 500,000 data points per second, meeting the needs of large-scale equipment monitoring. Through efficient data compression algorithms, a compression rate of over 90% is achieved, significantly reducing storage costs. The database supports multi-level storage strategies, storing data on different storage media based on data importance and usage frequency, ensuring both data access efficiency and optimized storage costs.

[0070] It should be noted that the anomaly assessment module includes a health assessment module, a predictive analysis module, an intelligent alarm system, and an operation and maintenance management system, such as... Figure 2 The system architecture diagram of an IoT-based intelligent management system for power distribution equipment is provided. In terms of equipment anomaly assessment, the health assessment module utilizes a deep learning-based intelligent analysis platform for analysis and modeling. This platform employs LSTM (Long Short-Term Memory) neural network as its core algorithm. This network structure is naturally well-suited for processing time-series data, effectively capturing the dynamic changes in equipment status. First, feature engineering is performed on the raw data, extracting multi-dimensional features including time-domain features, frequency-domain features, and time-frequency features. These features are then optimized using feature selection algorithms to remove redundant and irrelevant features, improving the model's training efficiency and prediction accuracy.

[0071] like Figure 2The system architecture diagram of an IoT-based intelligent management system for power distribution equipment is provided. In terms of equipment anomaly assessment, the predictive analysis module performs predictive maintenance based on an equipment health assessment model, achieving early warning of faults. By analyzing historical operating data of the power distribution equipment, a multi-dimensional health assessment model incorporating electrical, temperature, and environmental characteristics is established. The model employs an improved LSTM network structure, considering the impact of historical states at each time step. This design enables the model to accurately capture the gradual changes in equipment status. By comparing real-time monitoring data with the standard model, abnormal states are detected promptly, and potential fault risks are predicted, reducing the average fault warning time to 72 hours.

[0072] Furthermore, in terms of equipment anomaly assessment, it also includes intelligent alarm and operation and maintenance management. The intelligent alarm system, based on the concept of "multi-dimensional feature correlation analysis," breaks through the limitations of traditional single-threshold alarms. In the construction of the alarm model, a multi-dimensional feature benchmark for the normal operating status of the equipment is first established. This benchmark not only includes the standard range of each monitoring parameter but also considers the correlation between parameters. When an anomaly is detected, feature correlation analysis is first performed. By calculating the correlation coefficient matrix between features, the root cause of the alarm is identified. This analysis method effectively avoids alarm storms and greatly reduces the false alarm rate.

[0073] In terms of alarm handling mechanisms, a tiered processing strategy is adopted. A complete alarm level assessment system is established through in-depth analysis of historical alarm data. This assessment system not only considers the severity of the fault but also incorporates information from multiple dimensions such as equipment importance and the speed of fault development. Alarms are divided into four levels, each configured with corresponding processing procedures and response strategies. For alarms of different levels, the appropriate notification method and processing procedure are automatically selected to ensure that alarm information is delivered to relevant responsible persons in a timely manner, such as... Figure 2 The system architecture diagram of the IoT-based intelligent management system for power distribution equipment is shown, in which alarm information is sent to the Web management platform, mobile application and API port service.

[0074] The operation and maintenance management system is implemented through an intelligent operation and maintenance task management platform. This platform automatically generates maintenance plans based on equipment health assessment results. During task allocation, factors such as the professional skills, workload, and geographical location of maintenance personnel are comprehensively considered to achieve intelligent task assignment. During maintenance, detailed operation guidance is provided to maintenance personnel via mobile terminals, including equipment parameters, historical maintenance records, and standard operating procedures. After maintenance is completed, key data from the maintenance process is automatically recorded, and a maintenance quality assessment is performed.

[0075] like Figure 5The provided flowchart of a predictive maintenance process for an IoT-based intelligent management system for power distribution equipment shows that data is collected through current monitoring, voltage monitoring, power monitoring, and temperature monitoring. The collected data is then subjected to power analysis, power factor analysis, spectrum analysis, and temperature distribution analysis, followed by load optimization and reactive power compensation. This results in an energy-saving strategy that is achieved through automatic adjustment, real-time compensation, and load transfer. Energy consumption is compared to obtain the energy-saving effect, and the economic benefits are confirmed to achieve an effect evaluation.

[0076] Specifically, the load optimization module is responsible for energy efficiency management, employing "multi-dimensional energy efficiency analysis" technology. Through in-depth analysis of power consumption data from each circuit of the power distribution equipment, a load characteristic model is established. This model not only considers the time-varying characteristics of the load but also incorporates the impact of environmental factors and production plans, enabling accurate prediction of future power demand. Based on the load characteristic model, a load optimization scheme is automatically generated, avoiding localized overload or uneven load distribution through reasonable load allocation. The reactive power compensation module is responsible for reactive power compensation, employing a dynamic response intelligent compensation strategy. By monitoring the power factor of the power distribution equipment in real time and combining it with load characteristic analysis, the required compensation capacity is calculated. The control strategy uses a predictive compensation algorithm to predict changes in reactive power demand, enabling the early switching of compensation devices. This design controls the power factor response time to within 20 milliseconds, significantly outperforming traditional compensation schemes. Through continuous optimization control, the power factor can be stably maintained above 0.98, effectively reducing reactive power losses.

[0077] In summary, based on the "device-edge-cloud" three-layer collaborative architecture design, and through the deep integration of IoT, edge computing and artificial intelligence technologies, this architecture successfully solves key problems such as insufficient data processing capabilities and slow response speed in traditional systems by organically combining intelligent sensor arrays, edge computing units and cloud platforms. It realizes intelligent management of the entire process of data collection, processing and analysis, and intelligent management of the entire life cycle of power distribution equipment.

[0078] In practical applications, the system's deployment in a large industrial park has led to a comprehensive improvement in the operation and maintenance management of power distribution equipment. Regarding predictive maintenance, the system successfully issued early warnings for multiple critical equipment failures, effectively preventing unplanned power outages. Statistical analysis of six months of operational data shows that the equipment failure rate decreased by 40% compared to before the upgrade, and annual maintenance costs were reduced by approximately 30%. Furthermore, the accuracy rate of the intelligent alarm reached over 95%, significantly reducing false alarms. This high-precision alarm mechanism significantly improved the work efficiency of maintenance personnel, reducing the average fault response time from 2 hours to less than 30 minutes. More importantly, the system's early warning function allows maintenance personnel to take preventative measures before faults occur, effectively avoiding production losses caused by equipment failures. In terms of energy efficiency management, the system reduced the park's overall energy consumption by 15% through optimized load distribution and intelligent reactive power compensation. The power factor of the power distribution system remained consistently above 0.98, significantly reducing reactive power losses. Calculations show that electricity cost savings alone can save users approximately 500,000 yuan annually.

[0079] Furthermore, the IoT-based intelligent management system for power distribution equipment also includes a communication layer, which is used for information interaction between the edge layer and the cloud platform layer.

[0080] Specifically, such as Figure 2 The system architecture diagram of an IoT-based intelligent management system for power distribution equipment is provided. In the communication layer, the communication management module, during the process of sending pre-processed data from the edge computing node to the cloud computing platform, utilizes a multi-layered network architecture. For wired communication, it supports 10 / 100 / 1000Mbps adaptive industrial Ethernet interfaces and uses VLAN technology to achieve logical isolation of business data, ensuring real-time transmission of critical data. Wireless communication supports 4G / 5G and Wi-Fi dual-mode access, with mutual backup between the two communication methods, significantly improving reliability. For existing RS485 equipment in the field, a smart protocol conversion gateway enables seamless integration of new and old equipment, fully protecting the user's existing investment.

[0081] The IoT-based intelligent management system for power distribution equipment provided in this application determines data acquisition points based on the structure of the power distribution equipment and arranges sensor arrays according to these points. The sensor arrays collect operational data from the power distribution equipment. Preprocessing of the operational data using preset edge computing nodes yields preprocessed data. The preprocessed data is then sent to a cloud computing platform, which analyzes the data to generate anomaly assessment data, load optimization data, and reactive power compensation data. This system enables comprehensive management of power distribution equipment, including real-time monitoring, predictive maintenance, energy efficiency analysis, and intelligent alarms. It is suitable for complex operating environments and can effectively cope with harsh conditions such as high humidity, large temperature differences, and strong vibrations, ensuring safe and stable operation and improving the automation level and operational reliability of power supply equipment.

[0082] Furthermore, the components in the system embodiments should be understood as functional modules necessary to implement each step of the power distribution equipment maintenance and management, and these functional modules are not actual functional divisions or separations. The system claims defined by such a set of functional modules should be understood as a functional module architecture that primarily implements the solution through the computer program described in the specification, and not as a physical device that primarily implements the solution through hardware.

[0083] Furthermore, the operation and maintenance management of power distribution equipment through the IoT-based intelligent management system also involves a computing device. The components of this computing device include, but are not limited to, a memory and a processor. The processor and memory are connected via a bus, and a database is used to store data.

[0084] The computing device also includes access devices that enable the computing device to communicate via one or more networks. Examples of such networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. Access devices may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) interface, a Wi-MAX interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0085] In one embodiment of this application, other components of the computing device not shown above may also be interconnected, for example, via a bus. The computing device can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device can also be a mobile or stationary server.

[0086] The processor 720 is used to execute computer-executable instructions for each step of the IoT-based intelligent management system for power distribution equipment. An embodiment of this application also provides a computer-readable storage medium storing computer instructions, which, when executed by the processor, are used to implement the IoT-based intelligent management system for power distribution equipment, and to perform each step in the operation and maintenance management process of the power distribution equipment. An embodiment of this application also provides a chip storing a computer program, which, when executed by the chip, implements the IoT-based intelligent management system for power distribution equipment, and to perform each step in the operation and maintenance management process of the power distribution equipment.

[0087] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0089] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0090] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0091] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent management system for power distribution equipment based on the Internet of Things, characterized in that, It includes the device layer, the edge layer, and the cloud platform layer, among which, The equipment layer includes power distribution equipment and a sensor array arranged on the power distribution equipment; The edge layer preprocesses the operational data collected by the sensor array to obtain preprocessed data, and then sends the preprocessed data to the cloud platform layer. The cloud platform layer analyzes the preprocessed data to generate anomaly assessment data, load optimization data, and reactive power compensation data.

2. The system of claim 1, wherein, The sensor array includes a temperature sensor array, electrical parameter monitoring sensors, and environmental parameter sensors, wherein... The temperature sensor array is arranged at the cable connection location of the power distribution equipment; The electrical parameter monitoring sensors are arranged at the electrical parameter sampling locations of the power distribution equipment; The environmental parameter sensors are arranged at the environmental parameter sampling locations of the power distribution equipment.

3. The system of claim 2, wherein, The cable connection locations include busbar connections, circuit breaker contact locations, and cable joints.

4. The system of claim 2, wherein, The environmental parameter sensor includes a humidity sensor and uses ultrasonic detection to detect partial discharge inside the power distribution equipment.

5. The system of claim 1, wherein, The edge layer performs preprocessing on the operational data collected by the sensor array, including: The noise in the running data is removed by an improved Kalman filter algorithm to obtain denoised running data. The denoised running data is processed using a preset compression algorithm based on differential coding to obtain the preprocessed data.

6. The system of claim 1, wherein, The cloud platform layer's process of analyzing the preprocessed data and generating anomaly assessment data, load optimization data, and reactive power compensation data includes: Extract the time-domain features, frequency-domain features, and time-frequency features of the preprocessed data; By using a feature selection algorithm, redundant features in the time-domain features, the frequency-domain features, and the time-frequency features are removed to obtain the target time-domain features associated with the time-domain features, the target frequency-domain features associated with the frequency-domain features, and the target time-frequency features associated with the time-frequency features. Based on the long short-term memory neural network model, the target time-domain features, target frequency-domain features, and target time-frequency features are processed to obtain the anomaly assessment data, the load optimization data, and the reactive power compensation data.

7. The system of claim 1, wherein, The cloud platform layer also includes an anomaly assessment module, wherein, The anomaly assessment module generates an equipment maintenance plan based on the anomaly assessment data; it calls the equipment parameters and historical maintenance data of the power distribution equipment, and also calls the historical work records of the maintenance personnel associated with the power distribution equipment; it generates plan allocation information based on the equipment parameters, the historical maintenance data, and the historical work records; and it allocates the equipment maintenance plan to the maintenance personnel based on the plan allocation information.

8. The system of claim 1, wherein, The cloud platform layer also includes a load optimization module, wherein... The load optimization module generates a load control command based on the load optimization data; in response to the load control command, the power distribution equipment adjusts the load parameters.

9. The system of claim 1, wherein, The cloud platform layer also includes a reactive power compensation module, wherein, The reactive power compensation module determines a reactive power compensation command based on a preset predictive compensation algorithm and the reactive power compensation data; in response to the reactive power compensation command, the power distribution equipment adjusts its power parameters.

10. The system according to claim 1, characterized in that, The power distribution equipment intelligent management system based on the Internet of Things further comprises a communication layer, wherein The communication layer is used for information interaction between the edge layer and the cloud platform layer.

Images