Transformer substation management system and method based on Internet of Things technology

Abstract

The invention relates to the technical field of power system automation, in particular to a substation management system and method based on the Internet of Things technology, and the system comprises a ubiquitous Internet of Things sensing matrix, an electric power intelligence brain evolution center, a space-time fusion twin module, a nonlinear optimization decision module, and a multi-level vibration risk management and control model. Wherein the ubiquitous internet-of-things sensing matrix acquires substation equipment, environment and power grid data in real time; the electric power intelligence brain evolution center carries out health assessment, life prediction and abnormity positioning on the equipment; the space-time fusion twinborn module constructs a digital twinborn body, fuses equipment space-time data and historical data, and performs operation and maintenance simulation and fault reproduction; the nonlinear optimization decision-making module is used for generating a response regulation and control strategy aiming at the nonlinear and uncertain problems in the operation of the power grid; and the multi-level vibration risk management and control model carries out dynamic assessment and strategy optimization on equipment faults, power grid safety and environmental risks. Therefore, the problems of low inspection efficiency, high false detection risk, poor transmission stability and the like in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and in particular to a substation management system and method based on Internet of Things technology. Background Art

[0002] With the advancement of smart grid construction and the continued growth of electricity demand, substations, as the core hubs of the power system, face a direct impact on grid stability and power supply reliability through intelligent and efficient operation and management. Currently, the power industry is accelerating its digital transformation, placing higher demands on real-time monitoring, fault warnings, and optimized resource allocation of substation equipment. In this context, building a substation management system based on IoT technology—enabling full-scenario status awareness and refined control of substations through device interconnection, data sharing, and intelligent analysis—is becoming a key path to improving power system O&M efficiency and reducing operating costs.

[0003] However, traditional substation management models primarily rely on manual inspections and decentralized monitoring systems, presenting significant technical bottlenecks. On the one hand, manual inspections are inefficient and time-consuming, making it difficult to detect potential equipment failures. Furthermore, due to limitations in personnel experience and environmental conditions, the risk of missed or false detections is high. Decentralized monitoring systems, such as transformer oil chromatography monitoring and switchgear partial discharge detection, generate independent data, lacking unified integrated analysis and forming a comprehensive picture of equipment operation. Furthermore, existing systems often utilize single sensors or wired communication technologies. Faced with complex electromagnetic environments and dynamic equipment changes, data transmission suffers from poor stability and real-time performance. These "data silos" create weak capabilities for predicting equipment failures and enabling coordinated control. Furthermore, traditional fault diagnosis algorithms rely on fixed thresholds and empirical rules, making them difficult to adapt to complex operating conditions such as aging equipment and fluctuating environments. Fault warning accuracy is low, with frequent false alarms and missed detections, severely impacting the safe operation of the power grid and the efficiency of emergency response. Summary of the Invention

[0004] The present application provides a substation management system and method based on Internet of Things technology to solve the problems of low inspection efficiency, high risk of false detection, and poor transmission stability in the existing technology.

[0005] The first embodiment of the present application provides a substation management system based on Internet of Things technology, including: a ubiquitous Internet of Things perception matrix, an electric power intelligent brain evolution center, a time-space fusion twin module, a nonlinear optimization decision module, and a multi-level vibration risk control model; wherein, the ubiquitous Internet of Things perception matrix is ​​used to build a global perception Internet of Things network, and collect substation equipment operating status data, environmental parameters and power grid operation information in real time; the electric power intelligent brain evolution center is used for equipment health status assessment, life prediction and intelligent identification and positioning of abnormal events; the time-space fusion twin module is used to build a substation digital twin, integrating the spatial position, operating sequence and historical data of the equipment, and performing operation and maintenance process simulation, operation rehearsal and fault scenario reproduction; the nonlinear optimization decision module is used to generate response control strategies for nonlinear and uncertainty problems in power grid operation; the multi-level vibration risk control model is used to establish a multi-level risk prevention and control system, to evaluate equipment failure risks, power grid safety risks and environmental impact risks in real time, and to dynamically adjust prevention and control strategies.

[0006] Preferably, the ubiquitous Internet of Things perception matrix includes a heterogeneous sensor fusion network and a dynamic panoramic visualization module, wherein the heterogeneous sensor fusion network is used to deploy infrared thermal imaging, ultrasonic partial discharge detectors, and micro-electromechanical system vibration sensors, and form a three-dimensional monitoring matrix covering the "temperature-electrical-mechanical" status of the equipment through the Internet of Things transmission network; the dynamic panoramic visualization module uses WebGL to generate an interactive three-dimensional monitoring interface, displays equipment status parameters in a matrix form, and compares and analyzes real-time data with historical trends.

[0007] Preferably, the power intelligent brain evolution center includes an equipment health assessment unit, a life prediction module and an anomaly detection engine, wherein the equipment health assessment unit analyzes the equipment operation data and uses a physical model algorithm to evaluate the health status of the equipment and identify potential fault hazards; the life prediction module is used to analyze the equipment's operation history, aging characteristics, and environmental factor data to predict the remaining service life of the equipment; the anomaly detection engine is used to monitor the equipment's operating status in real time, quickly identify abnormal events, and accurately locate them.

[0008] Preferably, the space-time fusion twin module includes a three-dimensional space modeling unit, an operation and maintenance simulation system, and a fault scenario deduction module, wherein the three-dimensional space modeling unit is used to construct a three-dimensional digital model of the substation to reflect the spatial position, layout and structural relationship of the equipment; the operation and maintenance simulation system is used to simulate various operation and maintenance operation processes and evaluate the feasibility and safety of the operation; the fault scenario deduction module simulates the occurrence and development process of various fault scenarios based on historical fault data and real-time operating status.

[0009] Preferably, the nonlinear optimization decision module includes a nonlinear optimization solver, a multi-objective decision model and an adaptive control strategy generator, wherein the nonlinear optimization solver is used to process nonlinear optimization problems in power grid operation and find the optimal control strategy; the multi-objective decision model is used to generate the optimal control scheme based on multiple target data such as the safety, reliability and economy of the power grid; and the adaptive control strategy generator is used to adaptively adjust the control strategy according to the real-time operating status of the power grid and changes in uncertainty factors.

[0010] Preferably, the multi-level vibration risk management model includes a multi-level risk identification unit, a risk dynamic early warning module and an emergency response linkage mechanism, wherein the multi-level risk identification unit identifies potential risks from multiple levels of equipment, system and network; the risk dynamic early warning module is used to monitor changes in risk indicators, analyze risk development trends, and provide real-time early warnings; the emergency response linkage mechanism is used to link the emergency response system of the substation and quickly initiate emergency plans when major risk events occur.

[0011] The second embodiment of the present application provides a substation management method based on Internet of Things technology, including: obtaining substation equipment operating status data, environmental parameters and power grid operating information; analyzing and processing the substation equipment operating status data, environmental parameters and power grid operating information based on the Internet of Things platform layer to generate a panoramic data set of equipment status; constructing an XGBoost gradient boosting tree model based on the data set, evaluating the health status and remaining service life of the equipment based on the XGBoost gradient boosting tree model, intelligently identifying and locating abnormal events, and obtaining evaluation results and abnormal location data; constructing a digital twin of the substation based on the evaluation results, integrating equipment The spatial location, operation sequence and historical data of the equipment are used to simulate the operation and maintenance process, rehearse the operation and reproduce the fault scenario, and generate an operation risk assessment report; based on the operation risk assessment report, for the power grid flow optimization and strong nonlinear problems of reactive power compensation, the IPOPT interior point method solver is used to construct a multi-objective optimization model with constraints, and the control parameters are dynamically adjusted in combination with Pareto frontier analysis to generate a target control strategy; according to the control strategy, the risk index of equipment failure, power grid safety and environmental impact is calculated in combination with the fuzzy comprehensive evaluation method, and a multi-level risk prevention and control system is established to evaluate the risks of equipment failure, power grid safety and environmental impact in real time, and dynamically adjust the prevention and control strategy.

[0012] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and runnable on the processor. The processor executes the program to implement a substation management method based on Internet of Things technology as described in the above embodiment.

[0013] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement a substation management method based on Internet of Things technology as described in the above embodiment.

[0014] The fifth embodiment of the present application provides a computer program product, including a computer program or instructions, for implementing a substation management method based on Internet of Things technology as described in the above embodiment.

[0015] Therefore, this application has the following beneficial effects: The embodiment of the present application builds a comprehensive, all-round IoT perception network through a ubiquitous IoT perception matrix, which collects real-time data covering equipment operating parameters, environmental indicators and power grid dynamics, processes massive amounts of information, and monitors the operating status of substations in real time. The power intelligent brain evolution center continuously learns equipment operating patterns and historical fault data to accurately assess equipment health status and predict remaining lifespan. Based on a dynamically updated abnormal feature database, it issues early warnings for potential faults, reducing the probability of sudden accidents. The spatiotemporal fusion twin module deeply integrates equipment spatial layout, operating sequence and historical data to conduct virtual drills of operation and maintenance operations and immersive reproduction of fault scenarios, reducing human operational errors and accelerating the inheritance of operation and maintenance experience. The nonlinear optimization decision module solves complex nonlinear problems such as large-scale grid connection and drastic fluctuations in power grid currents, generates control strategies that take into account economy, reliability and low carbon, and enhances the resilience of the power grid to uncertainty. The multi-level vibration risk management model generates three-dimensional risk maps of equipment, power grid and environment in real time. Through intelligent hierarchical warning and dynamic optimization of prevention and control strategies, it reduces systemic risks, improves substation operation and maintenance efficiency, shortens the average fault handling time, and reduces operation and maintenance costs and safety hazards. This solves the problems of low inspection efficiency, high risk of false detection, and poor transmission stability in the prior art.

[0016] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 This is a structural diagram of a substation management system based on Internet of Things technology provided according to an embodiment of the present application; Figure 2 A schematic diagram of a ubiquitous Internet of Things sensing matrix provided according to one embodiment of the present application; Figure 3 A schematic diagram of a power intelligent brain evolution center provided according to one embodiment of the present application; Figure 4 This is a schematic diagram of an insulation condition assessment system for a 110 kV main transformer in a substation according to one embodiment of the present application; Figure 5 This is a schematic diagram of a spatiotemporal fusion twin module provided according to one embodiment of the present application; Figure 6 A schematic diagram of an annual maintenance scenario of a 220kV substation provided according to one embodiment of the present application; Figure 7 A schematic diagram of a nonlinear optimization decision module provided according to one embodiment of the present application; Figure 8 A schematic diagram of a multi-level vibration risk management model provided according to one embodiment of the present application; Figure 9 This is a schematic diagram of a 500kV hub substation early warning system provided according to one embodiment of the present application; Figure 10 A schematic diagram of a substation management system based on Internet of Things technology provided according to an embodiment of the present application; Figure 11 This is a flowchart of a substation management method based on Internet of Things technology according to one embodiment of the present application; Figure 12 This is a schematic diagram of a 220kV hub substation prediction system provided according to one embodiment of the present application; Figure 13 A schematic diagram of a substation management method based on Internet of Things technology provided according to one embodiment of the present application; Figure 14 A schematic diagram of the layout of settlement observation points provided according to one embodiment of the present application; Figure 15 A schematic diagram of the dimensions of a basic plan view provided according to one embodiment of the present application; Figure 16 A schematic diagram of a steel bar arrangement diagram provided according to one embodiment of the present application; Figure 17 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] The following describes a substation management system based on the Internet of Things technology in an embodiment of the present application with reference to the accompanying drawings. In response to the high risk of false detection mentioned in the above background technology, the present application provides a substation management system based on the Internet of Things technology. In this system, an all-round, no-dead-angle Internet of Things perception network is constructed through a ubiquitous Internet of Things perception matrix to collect real-time data covering equipment operating parameters, environmental indicators and power grid dynamics, process massive amounts of information, and monitor the substation operating status in real time; the power intelligent brain evolution center continuously learns the equipment operating rules and historical fault data, accurately evaluates the equipment health status, predicts the remaining life, and issues early warnings for potential faults based on a dynamically updated abnormal feature database to reduce the probability of sudden accidents; the time-space fusion twin module Deeply integrating equipment spatial layout, operating sequence, and historical data, the system conducts virtual O&M drills and immersive fault scenario replays, reducing human operational errors and accelerating the transfer of O&M experience. A nonlinear optimization decision-making module addresses complex nonlinear issues such as large-scale grid connection and drastic fluctuations in grid currents, generating control strategies that balance economy, reliability, and low carbon, enhancing the grid's resilience to uncertainty. A multi-level vibration risk management model generates real-time three-dimensional risk maps for equipment, grids, and the environment. Through intelligent, hierarchical early warning and dynamic optimization of prevention and control strategies, it reduces systemic risks, improves substation O&M efficiency, shortens the average fault handling time, and reduces O&M costs and safety hazards. This addresses existing issues such as low inspection efficiency, high risk of false detection, and poor transmission stability.

[0020] Figure 1 A schematic diagram of the structure of a substation management system based on Internet of Things technology provided in an embodiment of the present application.

[0021] The present application embodiment provides a substation management system based on Internet of Things technology, the system 10 including: Ubiquitous IoT perception matrix 100, power intelligent brain evolution center 200, time-space fusion twin module 300, nonlinear optimization decision module 400, multi-level vibration risk management model 500.

[0022] Among them, the ubiquitous IoT perception matrix 100 is used to build a full-domain perception IoT network to collect substation equipment operating status data, environmental parameters and power grid operation information in real time; the power intelligent brain evolution center 200 is used to evaluate equipment health status, predict life and intelligently identify and locate abnormal events; the space-time fusion twin module 300 is used to build a substation digital twin, integrating the spatial position, operating sequence and historical data of the equipment to simulate the operation and maintenance process, rehearse operations and reproduce fault scenarios; the nonlinear optimization decision module 400 is used to generate response control strategies for nonlinear and uncertain problems in power grid operation; the multi-level vibration risk management model 500 is used to establish a multi-level risk prevention and control system to evaluate equipment failure risks, power grid safety risks and environmental impact risks in real time, and dynamically adjust prevention and control strategies.

[0023] It can be understood that in the embodiment of the present application, a comprehensive and blind-angle-free IoT perception network is constructed through the ubiquitous IoT perception matrix, which collects equipment operating parameters, environmental indicators and power grid dynamic data in real time, processes massive information, and monitors the operating status of the substation in real time; the power intelligent brain evolution center continuously learns the equipment operating rules and historical fault data, accurately assesses the health status of the equipment, predicts the remaining life, and issues early warnings for potential faults based on the dynamically updated abnormal feature database, thereby reducing the probability of sudden accidents; the time-space fusion twin module deeply integrates the equipment spatial layout, operating sequence and historical data to conduct virtual drills of operation and maintenance operations and immersive reproduction of fault scenarios, reducing human operational errors and accelerating the inheritance of operation and maintenance experience; the nonlinear optimization decision module solves complex nonlinear problems such as large-scale grid connection and drastic fluctuations in power grid currents, generates a control strategy that takes into account economy, reliability and low carbon, and enhances the resilience of the power grid to deal with uncertainty; the multi-level vibration risk management model generates a three-dimensional risk map of equipment, power grid and environment in real time, and dynamically optimizes the intelligent hierarchical warning and prevention and control strategies to reduce systemic risks, improve substation operation and maintenance efficiency, shorten the average fault processing time, and reduce operation and maintenance costs and safety hazards. This solves the problems of low inspection efficiency, high risk of false detection, and poor transmission stability in the prior art.

[0024] In the embodiment of the present application, the ubiquitous IoT sensing matrix 100 further includes: Figure 2 As shown, heterogeneous sensor fusion network and dynamic panoramic visualization module.

[0025] Among them, the heterogeneous sensor fusion network is used to deploy infrared thermal imaging, ultrasonic partial discharge detectors, and micro-electromechanical system vibration sensors, and through the Internet of Things transmission network, a three-dimensional monitoring matrix covering the "temperature-electrical-mechanical" status of the equipment is formed; the dynamic panoramic visualization module uses WebGL to generate an interactive three-dimensional monitoring interface, displaying equipment status parameters in matrix form, and comparing and analyzing real-time data with historical trends.

[0026] It can be understood that the embodiment of the present application builds a "temperature-electrical-mechanical" multi-dimensional stereoscopic monitoring matrix by deploying infrared thermal imaging, ultrasonic partial discharge detectors, and micro-electromechanical system vibration sensors. It accurately captures hot spots on the surface of the equipment, weak partial discharge signals and mechanical vibration anomalies, improves the accuracy of fault identification, and avoids missed detection problems caused by a single monitoring dimension; at the same time, with the help of the Internet of Things transmission network, data is interacted in real time, data transmission delays are shortened, and abnormal equipment conditions are responded to quickly; the dynamic panoramic visualization module generates a highly interactive three-dimensional monitoring interface based on WebGL, and intuitively displays key equipment status parameters in the form of a matrix, allowing managers to view equipment details in all directions through operations such as zooming and rotating; through intelligent comparative analysis of real-time data and historical trends, the changing patterns of equipment operating status are clearly presented, helping operation and maintenance personnel to quickly locate the root cause of the anomaly and improve fault location efficiency.

[0027] It should be noted that the formula of the multi-dimensional stereo monitoring matrix is: .

[0028] in, It is a multi-dimensional three-dimensional monitoring matrix; is the corresponding temperature dimension data; is the corresponding electrical dimension data; is the corresponding mechanical dimension data; is the field of real numbers; is the spatial dimension of the temperature field data; is the total number of features in the electrical + mechanical dimensions.

[0029] It should be noted that WebGL is a browser-based graphics rendering tool that can perform high-performance graphics rendering in the browser without plug-ins. It converts the spatial structure of the device and sensor position data into a three-dimensional geometric model, renders and generates a virtual scene, binds click and zoom interaction events, obtains real-time monitoring parameters and maps them to the corresponding positions of the three-dimensional model, overlays historical trend curves, and forms a freely operable immersive monitoring interface, allowing users to perform interactive operations such as zooming and rotating, view device details from any angle, and present the originally abstract and complex monitoring data intuitively in matrix form.

[0030] For example, in the intelligent operation and maintenance scenario of 110kV high-voltage switchgear in a substation, the dynamic panoramic visualization module uses WebGL to accurately construct a 1:1 3D virtual switchgear cluster. In the interactive interface, each switchgear panel is mapped to a 12×8 matrix of equipment status parameters (covering key areas such as the three-phase contacts, cable compartment, and circuit breaker compartment). Real-time core data such as temperature (accuracy ±0.5°C), ultrasonic partial discharge amplitude (resolution 1pC), and MEMS vibration acceleration (sampling rate 2kHz) are collected and populated in the matrix using dynamic color blocks and digital dual dimensions. When the temperature matrix value of the contact area of ​​phase A in switchgear #5 reached 78°C (the historical average for healthy operating conditions during the same period was 52°C, and the maximum warning threshold in summer was 65°C), the module automatically retrieved the historical trend matrix for the past 30 days for temporal and spatial comparison. This revealed that the temperature data had been rising at an average daily rate of 1.2°C since the 25th day. In the associated partial discharge matrix, the UHF signal amplitude jumped from 20pC to 85pC, and the energy proportion of the 120Hz characteristic frequency in the vibration matrix increased from 15% to 42%. Through matrix linkage analysis within the 3D interface, maintenance personnel quickly identified the potential fault of abnormally increased contact resistance. Combined with the temperature rise development model reproduced by the digital twin, they predicted that overheating protection would be triggered within 48 hours if no intervention was taken. This provided data support for precise maintenance decisions, increased fault diagnosis efficiency by 60%, and reduced the false positive rate to less than 3%, establishing a full-time, multi-dimensional intelligent monitoring system for equipment status.

[0031] In the embodiment of the present application, the power intelligent brain evolution center 200 includes: Figure 3 As shown, the equipment health assessment unit, life prediction module and anomaly detection engine.

[0032] Among them, the equipment health assessment unit analyzes the equipment operation data and uses physical model algorithms to evaluate the health status of the equipment and identify potential fault hazards; the life prediction module is used to analyze the equipment's operation history, aging characteristics, and environmental factor data to predict the equipment's remaining service life; the anomaly detection engine is used to monitor the equipment's operating status in real time, quickly identify abnormal events, and accurately locate them.

[0033] It can be understood that the equipment health assessment unit of the embodiment of the present application analyzes the key parameters of the internal loss and temperature field distribution of the equipment from a microscopic level based on the physical model algorithm, based on the thermodynamic principles of the equipment, and combined with real-time operation data, accurately quantifies the health status of the equipment, and improves the accuracy of identifying potential fault hazards; the life prediction module integrates the operation history and aging law data of the equipment throughout its life cycle, combined with environmental temperature and humidity, and load change factors, to construct a dynamic life prediction model to predict the remaining service life of the equipment, help operation and maintenance personnel plan equipment replacement and upgrade plans in advance, reduce downtime losses caused by sudden failures, and reduce the full life cycle cost of the equipment; the anomaly detection engine scans the equipment operation status in real time, and through multi-dimensional data cross-comparison and dynamic threshold analysis, quickly locks the fault type and location at the moment the abnormal event occurs, thereby improving fault response efficiency.

[0034] It should be noted that the physical model algorithm formula is: in, is temperature; is the thermal diffusivity; is the internal heat source power; is the density; is the specific heat capacity; is the partial differential.

[0035] It should be noted that the dynamic life prediction model formula is: .

[0036] in, is the ambient temperature; is the ambient humidity; For load; , , The coefficients fitted for the equipment operation data; is the remaining life; It is the initial life reference value.

[0037] For example, Figure 4As shown, the insulation condition of the substation's 110kV main transformer was assessed. The equipment health assessment unit constructed a multi-dimensional diagnostic system using a physical model algorithm. Based on the Fourier heat conduction equation and real-time load data (e.g., current 1200A, ambient temperature 32°C), the system calculated the winding hotspot temperature to be 98°C. Simultaneously, the dissolved gas concentration in the oil (hydrogen 25μL / L, acetylene 0.5μL / L) was monitored, and the gas generation rate equation was used to determine the presence of an internal low-temperature overheating fault. Furthermore, using an insulation paper aging kinetic model, the system predicted an annual decrease in the degree of polymerization of 3.2%, corresponding to a remaining service life of approximately 15 years. When the model detected a sudden increase in hotspot temperature by 5°C and a daily increase in methane concentration of 1μL / L, the system immediately triggered an alert, indicating a potential risk of poor winding contact. Based on this information, maintenance personnel conducted a DC resistance test on the winding, finding a deviation of 1.8% for phase B (standard ≤ 2%). Prompt action was taken to avoid a sudden short circuit. This process uses physical models to achieve intelligent analysis from parameter monitoring to fault tracing, compressing the traditional manual diagnosis cycle from 24 hours to 30 minutes, and increasing the fault prediction accuracy to 96%, significantly enhancing the foresight and accuracy of equipment operation and maintenance.

[0038] In the embodiment of the present application, the space-time fusion twin module 300 includes: Figure 5 As shown, there are three-dimensional space modeling unit, operation and maintenance simulation system, and fault scenario deduction module.

[0039] Among them, the three-dimensional spatial modeling unit is used to construct a three-dimensional digital model of the substation to reflect the spatial position, layout and structural relationship of the equipment; the operation and maintenance simulation system is used to simulate various operation and maintenance operation processes and evaluate the feasibility and safety of the operation; the fault scenario deduction module simulates the occurrence and development process of various fault scenarios based on historical fault data and real-time operating status.

[0040] It can be understood that the embodiment of the present application collects the geometric dimensions, spatial coordinates, and material texture data of the equipment in the substation through a three-dimensional spatial modeling unit, constructs a three-dimensional digital model, and presents the spatial layout and structural relationship of facilities such as the main transformer, GIS equipment, and transmission lines, providing an immersive visualization experience for operation and maintenance personnel and improving the efficiency of cognition of the overall architecture of the substation; the operation and maintenance simulation system builds a highly realistic virtual operation and maintenance environment based on the three-dimensional digital model, and has built-in standardized operating procedures covering equipment maintenance, switching operations, and test and debugging. During simulated circuit breaker maintenance, the system monitors personnel's operating steps in real time. If a component is disassembled without releasing spring energy according to specifications, a safety warning is immediately triggered, and the correct operating sequence is visually demonstrated through 3D animation. During simulated switching operations, the system automatically verifies the compliance of the operation ticket and checks the compatibility of equipment status with the operating logic, identifying and correcting potential operational risks in advance. This shortens the training cycle for maintenance personnel, improves the assessment pass rate, and reduces the risk of operational errors during on-site maintenance operations. The fault scenario simulation module deeply integrates historical fault databases, real-time monitoring data, and equipment operating parameters to dynamically simulate various fault scenarios, including transformer winding overheating, switchgear partial discharge, and transmission line ice fracture. If an abnormally high oil temperature and excessive acetylene content in a main transformer are detected, historical data for similar faults is quickly retrieved. Combined with factors such as the current load factor and ambient temperature, the module simulates the complete evolution of the transformer's internal local overheating, which can lead to insulation aging, increased oil decomposition and gas production, and ultimately a winding short circuit. 3D animation and data curves are used to visually display the fault propagation path and impact range, shortening fault response time, reducing power outage losses caused by the fault, and providing early warning of potential risks.

[0041] It should be noted that the three-dimensional digital model formula is: in, It is a three-dimensional digital model; is the rotation matrix; is the vertex coordinate in the local coordinate system; is the translation vector; is the vertex attribute mapping function; is the vertex association parameter; It is a triangular mesh description; is the kth triangle; is a set of vertices; A collection of triangle faces.

[0042] For example, Figure 6As shown in the figure, during the annual maintenance of a 220kV substation, maintenance personnel used an O&M simulation system to rehearse a main transformer bushing replacement operation. Based on a 3D digital model, the system accurately recreated the operating environment. It simulated an operator wearing insulating gear approaching live equipment, triggering a real-time alarm indicating insufficient safety distance (less than the standard 2.5 meters). An animation demonstrated the correct insulation shielding procedure. The system also simulated the bushing installation process using lifting equipment. Based on the equipment weight (1.2 tons) and boom angle (45°), the system calculated the wire rope stress and predicted the potential overload risk for a certain wire rope type, prompting the replacement of a higher-specification lifting equipment. Through simulation optimization, the actual operation time was reduced from the original plan of 8 hours to 6 hours, and the error rate in the operation steps was reduced from 12% to 2%. This significantly improved operation safety and efficiency, preventing equipment damage and electric shock risks caused by improper operation.

[0043] In the embodiment of the present application, the nonlinear optimization decision module 400 includes: Figure 7 As shown, nonlinear optimization solver, multi-objective decision model and adaptive control strategy generator.

[0044] Among them, the nonlinear optimization solver is used to deal with nonlinear optimization problems in power grid operation and find the optimal control strategy; the multi-objective decision-making model is used to generate the optimal control plan based on multiple target data such as safety, reliability, and economy of the power grid; the adaptive control strategy generator is used to adaptively adjust the control strategy according to the real-time operating status of the power grid and changes in uncertainty factors.

[0045] It is understood that the embodiments of the present application use a nonlinear optimization solver to construct a constrained optimization model for nonlinear problems such as power flow calculation and voltage stability control. This model can quickly complete the optimal power flow calculation of multi-node distribution networks and improve the accuracy of voltage over-limit risk prediction. The multi-objective decision-making model integrates multiple objective data on power grid safety, reliability, and economy to build a multi-dimensional collaborative optimization system. Utilizing a dynamic weight allocation mechanism, it intelligently balances objective priorities in different scenarios (e.g., prioritizing economy during normal operation and safety during fault conditions), quantifies solutions to conflicting objectives, improves the scientific nature of decision-making, and enhances the efficiency of multi-objective coordination. This provides the grid with a globally optimal control strategy in complex scenarios such as high penetration of renewable energy and load fluctuations. The adaptive control strategy generator integrates real-time measurement data (PMU sampling rate 100Hz) with uncertainty predictions (e.g., wind power fluctuation range) to dynamically update the control strategy, reduce the amplitude of frequency fluctuations, and improve absorption capacity.

[0046] It should be noted that when it detects that the distributed generation (DG) penetration rate exceeds 30% and the wind speed changes suddenly, the module triggers adaptive adjustment: automatically adjusting the energy storage charging and discharging power (error <2%), optimizing the on-load transformer tap position (adjustment time is shortened by 40%), and synchronously updating the safety constraint boundary to control the voltage deviation within ±2%.

[0047] It should be noted that the optimization model formula with constraints is: in, is the total active power loss of the power grid; is the system state variable; For transmission line collection; is the line conductance; is the node voltage amplitude; is the node voltage phase angle; is the phase angle difference; is the cosine of the phase angle difference.

[0048] For example, during smart grid operations in a coastal region, an adaptive control strategy generator detected in real time that a typhoon caused regional wind power generation to plummet from 80% to 15% of rated capacity within an hour, with some lines experiencing sag alarms due to strong winds. The system swiftly initiated an adaptive response: first, based on historical typhoon disaster data and real-time weather forecasts (wind speeds exceeding 35 m / s), combined with the grid's real-time topology and load distribution, it predicted within 0.5 seconds five potential voltage collapse risk points within the next two hours. It then automatically adjusted the discharge power of adjacent energy storage power stations to full capacity (10 MW) and triggered a demand-side response mechanism, sending flexible load control commands to industrial and commercial users via smart meters, mitigating 3 MW of interruptible load within 15 minutes. Furthermore, when the system detected that the main transformer oil temperature at a 220 kV substation was approaching a critical value due to overload, it immediately optimized the regional thermal power dispatch, shifting some load to backup units, reducing the main transformer load factor from 98% to 85%. During the entire process, the adaptive control strategy generator dynamically adjusted the control parameters 23 times, and modified the strategy in real time to match the changes in the power grid, ultimately successfully resisting the impact of extreme weather. Compared with traditional manual control, the failure risk was reduced by 70% and the power supply reliability was increased to 99.99%.

[0049] In the embodiment of the present application, the multi-level vibration risk management model 500 includes: Figure 8 As shown, there are multi-level risk identification units, risk dynamic early warning modules and emergency response linkage mechanisms.

[0050] Among them, the multi-level risk identification unit identifies potential risks from multiple levels of equipment, systems and networks; the risk dynamic early warning module is used to monitor changes in risk indicators, analyze risk development trends, and provide real-time early warnings; the emergency response linkage mechanism is used to link the substation's emergency response system and quickly activate emergency plans when major risk events occur.

[0051] It can be understood that the multi-level risk identification unit of the embodiment of the present application adopts a hierarchical diagnosis mode. At the equipment level, the high-frequency vibration (2000-5000Hz) caused by the cracks of the pot-type insulator of the GIS equipment is captured through an acceleration sensor (sampling frequency 10kHz), and the characteristic frequency of the bearing wear is extracted using the wavelet packet decomposition algorithm; at the system level, combined with the wide-area measurement system data, the grid power oscillation (such as the interval oscillation frequency 0.2-2Hz) and vibration coupling risks are identified through modal analysis; at the network level, the packet loss rate and delay jitter of vibration data transmission in the industrial Ethernet are monitored to prevent monitoring failures caused by communication interruptions and improve the risk coverage dimension; the risk dynamic warning module tracks the fluctuations of risk indicators in real time, promptly detects subtle fluctuations in risks, predicts risk trends through big data analysis, and issues alarms in advance so that operation and maintenance personnel can grasp the situation; when a major risk event occurs, the emergency response linkage mechanism quickly integrates resources from all parties, efficiently activates emergency plans, and improves emergency response efficiency.

[0052] It should be noted that the wavelet packet decomposition algorithm formula is: in, is the number of decomposition layers; is the subband index; is the new subband position index; is the original signal position index; is the low-pass filter coefficient; is the high-pass filter coefficient; is the wavelet coefficient of scale j and subband k; is the low-frequency sub-band coefficient of the next layer; is the high frequency sub-band coefficient of the next layer.

[0053] It should be noted that the risk dynamic warning module tracks the fluctuations of risk indicators in real time, detects subtle fluctuations in risks in a timely manner, predicts risk trends through big data analysis, and issues alarms in advance so that operation and maintenance personnel can grasp the situation. Among them, risk indicators at the equipment level cover vibration characteristics (such as acceleration, main frequency energy), temperature characteristics (surface temperature, temperature gradient), electrical characteristics (partial discharge, dielectric loss factor) and oil / gas characteristics (SF6 decomposition products, transformer oil dissolved gas), which are used to monitor hardware failures; the system level includes operating status indicators (voltage deviation, frequency deviation), power load indicators (active power, load rate), protection control indicators (number of protection actions, command response delay) and network topology risk indicators, which are used to maintain the stable operation of the power system.

[0054] It should be noted that when a major risk event occurs, the emergency response linkage mechanism will quickly integrate resources from all parties, efficiently launch emergency plans, and improve emergency response efficiency. The integration of resources from all parties includes hardware resources (spare equipment, repair tools, etc.), human resources (operation and maintenance teams, experts and external rescue forces), information resources (real-time monitoring data, plan documents), communication resources (emergency communication networks and contact channels), energy resources (backup power, etc.), and external collaborative resources (dispatch centers, suppliers, government departments, etc.), to improve emergency response efficiency and reduce accident losses.

[0055] For example, Figure 9 As shown in the image, in a 500kV hub substation, the main transformer experienced sudden and severe vibration due to long-term high-load operation. The vibration acceleration instantly exceeded the 25g threshold, triggering the highest-level alert of the multi-level vibration risk management model. The emergency response linkage mechanism activated in milliseconds: the relay protection system tripped the main transformer circuit breaker within 0.1 seconds, isolating the faulty equipment. The fire protection system simultaneously activated the HFC-227ea automatic fire extinguishing device to prevent fires caused by internal insulation damage caused by vibration. Simultaneously, the intelligent dispatching system immediately adjusted the grid operation mode, quickly transferring the load to the backup main transformer to maintain regional power supply stability. AR smart terminals worn by maintenance personnel received real-time visual work orders containing the 3D location of the fault point, a list of maintenance tools, and operational procedures. The system also automatically retrieved historical examples of similar vibration fault handling to assist in decision-making. Throughout the entire process, the emergency response linkage mechanism coordinated closely with eight major systems within the station, and the time from fault detection to isolation was only 30 seconds, an efficiency improvement of over 20 times compared to traditional manual handling, successfully averting a major incident that could have paralyzed the regional power grid.

[0056] The embodiment of the present application proposes a substation management system based on the Internet of Things technology. It builds an all-round and blind-angle-free Internet of Things perception network through the ubiquitous Internet of Things perception matrix, collects equipment operating parameters, environmental indicators and power grid dynamic data in real time, processes massive amounts of information, and monitors the substation operation status in real time; the power intelligent brain evolution center continuously learns the equipment operation rules and historical fault data, accurately evaluates the equipment health status and predicts the remaining life, and issues early warnings for potential faults based on the dynamically updated abnormal feature database, thereby reducing the probability of sudden accidents; the time-space fusion twin module integrates the equipment spatial layout and operation sequence The system deeply integrates historical data to conduct virtual operation and maintenance drills and immersive reproduction of fault scenarios, reducing human operational errors and accelerating the inheritance of operation and maintenance experience. The nonlinear optimization decision-making module solves complex nonlinear problems such as large-scale grid connection and drastic fluctuations in grid currents, generating a control strategy that takes into account economy, reliability, and low carbon, and enhancing the resilience of the grid to uncertainty. The multi-level vibration risk management model generates a three-dimensional risk map of equipment, grid, and environment in real time. Through intelligent hierarchical early warning and dynamic optimization of prevention and control strategies, it reduces systemic risks, improves substation operation and maintenance efficiency, shortens the average fault handling time, and reduces operation and maintenance costs and safety hazards. This solves the problems of low inspection efficiency, high risk of false detection, and poor transmission stability in existing technologies.

[0057] The following will describe a substation management system based on Internet of Things technology through a specific embodiment. Figure 10 Shown, including: A global awareness IoT network has been built across key areas and equipment in the substation. At the main transformer, high-precision vibration sensors (sampling frequency 1000 times / second, capable of capturing vibration changes as small as 0.001mm / s²), oil chromatography sensors (capable of detecting 14 dissolved gases, with a hydrogen detection limit of 0.1ppm and an acetylene detection accuracy of 0.01ppm), and infrared temperature sensors (scanning every three minutes, with a temperature range of -20°C to 200°C and an accuracy of ±0.3°C) are deployed to collect real-time equipment operating status data. Within the high-voltage switchgear, partial discharge sensors (detection frequency band 300MHz-1500MHz, sensitivity 1pC) and humidity sensors (measuring range 0-100%RH, with a one-second warning if the RH threshold exceeds 60%) continuously monitor internal insulation and environmental conditions. Furthermore, at key locations such as substation entrances and exits and equipment areas, 4K high-definition cameras (equipped with AI image recognition, identifying anomalies within 0.5 seconds) and pulse-type electronic fences (with a pulse voltage of 5,000V-10,000V and a 0.2-second response to intrusions) collect real-time environmental parameters and human activity information. Simultaneously, grid metering devices and smart meters simultaneously acquire real-time information on grid voltage, current, and power, forming a comprehensive data collection network covering equipment, the environment, and the power grid.

[0058] The Power Intelligent Brain Evolution Center, serving as the system's "intelligent core," receives massive amounts of data transmitted by the ubiquitous IoT sensing matrix. Leveraging deep learning and machine learning algorithms, it manages equipment health and handles abnormal events. Using an LSTM neural network combined with a gray prediction model for main transformer oil chromatogram data, validated through historical data training, it can predict gas content trends 30 days in advance, achieving a fault prediction accuracy of 92%. A convolutional neural network (CNN) performs pattern recognition on equipment vibration data, achieving 98% accuracy on the training and 95% accuracy on the test sets. It can accurately identify 12 abnormal vibration patterns, such as bearing wear and gear failures. Based on the equipment's full lifecycle operating data and combined with a particle filter algorithm based on degradation trajectories, it can dynamically predict the equipment's remaining useful life with an error margin of ±5%. When the main transformer's oil temperature exceeds the set threshold of 85°C, the system automatically initiates a multi-source data analysis process, integrating vibration, oil chromatogram, and load data. Within two minutes, it accurately locates the fault cause (such as cooling system abnormality or internal overload) and generates an analysis report containing the fault level and recommended actions, providing a scientific basis for operational and maintenance decisions.

[0059] Using collected equipment spatial coordinates, real-time operating parameters, and historical data, the spatiotemporal fusion twin module constructs a 1:1, high-precision digital twin of the substation. This 3D visualization not only fully reproduces the spatial layout of the substation buildings and equipment but also, driven by real-time data, dynamically displays equipment operating status, such as changes in transformer oil temperature and switch opening and closing movements. In a maintenance simulation scenario, for the annual main transformer maintenance task, the system simulates the maintenance personnel's movement paths, tool usage sequence, and equipment assembly and disassembly procedures. This helps identify potential risks (such as collisions in confined spaces) and optimize maintenance plans, improving maintenance efficiency by 30%. For complex tasks like switching operations, the digital twin is used for rehearsal. By combining grid topology and equipment status, the system predicts the impact of the operation on grid current and voltage, preventing cascading failures caused by incorrect operations. In the event of a fault, the system recreates the fault's evolution based on pre- and post-fault operational data. For example, it simulates the temperature, vibration, and current curves when a main transformer winding short-circuits, helping technicians quickly locate the root cause and develop targeted improvement measures.

[0060] To address the nonlinearity and uncertainty inherent in power grid operation, the three components of the nonlinear optimization decision-making module work in tandem. The nonlinear optimization solver utilizes interior point methods and particle swarm optimization algorithms to solve power flow calculations and voltage stability control models for complex power grids with distributed generation (DGs). It completes optimization calculations involving over 3,000 variables within 100 milliseconds, enabling precise control of power output and load distribution, while maintaining grid voltage deviation within ±5%. The multi-objective decision-making model utilizes the NSGA-III multi-objective evolutionary algorithm and fuzzy comprehensive evaluation technology. During peak load periods, it dynamically adjusts transformer tap adjustment and capacitor bank switching strategies, taking into account grid safety (short-circuit current limiting), reliability (power outage risk), and economic efficiency (power purchase cost). This has been proven to reduce line losses by 12% while keeping the main transformer load factor within the safety threshold of 90%. The adaptive control strategy generator monitors in real time scenarios such as fluctuations in renewable energy power generation (e.g., wind power fluctuations exceeding 30% of the rated value within 10 minutes) and sudden load changes. Based on prediction models and historical experience, it adjusts the control strategy within 0.5 seconds, such as quickly starting the energy storage system for power compensation to maintain the grid frequency stable within the range of 50±0.2Hz.

[0061] The multi-level vibration risk management model constructs a risk prevention and control system from three dimensions: equipment, system, and network. At the equipment level, vibration signal spectrum analysis and feature extraction are used to identify over 10 potential faults, including loose main transformer cores and abnormal wear of high-voltage switch contacts. At the system level, modal analysis combines grid power oscillations (0.1-2Hz) with equipment vibration data to predict the risk of system disturbances triggering equipment resonance. At the network level, the vibration data transmission link latency (threshold > 50ms) and packet loss rate (threshold > 3%) are monitored in real time to prevent monitoring blind spots caused by communication interruptions. The risk dynamic warning module uses time series analysis and LSTM prediction algorithms to monitor 15 key indicators, including vibration amplitude and frequency, in real time. When the main transformer vibration acceleration exceeds the 25m / s² threshold, a red alert is issued and the fault development trend is predicted within the next two hours. After receiving a major risk signal, the emergency response linkage mechanism initiates multiple responses within 0.1 seconds: the linkage relay protection system quickly isolates the faulty equipment and triggers the fire protection system to activate the fire extinguishing device; it simultaneously sends suggestions for adjusting the grid operation mode to the dispatch center and calls on the backup power supply to maintain power supply; and it pushes visual work orders containing fault location and emergency repair steps to operation and maintenance personnel through AR smart terminals to guide on-site handling, reducing the scope of fault impact and recovery time by 70% and 50% respectively.

[0062] In summary, the embodiment of the present application uses the ubiquitous IoT sensing matrix to collect data on equipment, environment, and power grids in real time across the entire domain, providing a data foundation for precise management; the power intelligent brain evolution center relies on deep learning algorithms to increase the accuracy of equipment fault prediction to 92%, and the remaining life prediction error is controlled within ±5%, enabling operation and maintenance to shift from passive maintenance to active prevention. The time-space fusion twin module uses digital twin simulation to increase the efficiency of main transformer maintenance by 30%, and significantly reduce the risk of switching operations; the nonlinear optimization decision module completes complex power grid optimization calculations within 100ms, reduces the line loss rate by 12%, ensures that the grid voltage deviation is within ±5%, and significantly improves operational economy and stability. The multi-level vibration risk management model constructs a three-dimensional protection system, which shortens the fault warning response time to 0.1 seconds, reduces the fault impact range by 70%, and shortens the recovery time by 50%. Overall, the system has comprehensively improved the intelligence level of the substation, effectively reduced operation and maintenance costs, and enhanced the grid's ability to resist risks.

[0063] Next, a substation management method based on Internet of Things technology proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0064] like Figure 11 As shown, the substation management method based on the Internet of Things technology includes the following steps: In step S101, substation equipment operating status data, environmental parameters and power grid operating information are obtained.

[0065] It can be understood that the embodiments of the present application provide key data for building a data-aware network by real-time collection of key data such as equipment temperature anomalies, mechanical vibration failures, grid power fluctuations, as well as environmental parameters such as ambient temperature and humidity, and human intrusion, thereby reducing operation and maintenance costs and enhancing the grid's ability to resist risks.

[0066] In step S102, based on the IoT platform layer, the substation equipment operating status data, environmental parameters and power grid operation information are analyzed and processed to generate a panoramic equipment status data set.

[0067] Among them, the equipment status panoramic data set is formed by comprehensively collecting multi-dimensional data such as substation equipment operating parameters, mechanical status, electrical characteristics, environmental impact, etc. through multiple types of sensors and intelligent monitoring equipment. After cleaning, integration and labeling, it is used to support equipment health assessment, fault prediction, and operation and maintenance decision-making.

[0068] It can be understood that the embodiments of the present application form a comprehensive and integrated data set through data cleaning, integration and labeling, provide quantitative data for equipment health assessment, accurately predict potential faults, enable operation and maintenance personnel to make scientific decisions based on data-driven, conduct refined management of substation equipment, reduce operation and maintenance costs, and improve the reliability and safety of power grid operation.

[0069] In step S103, an XGBoost gradient boosting tree model is constructed based on the data set, and the health status and remaining service life of the equipment are evaluated based on the XGBoost gradient boosting tree model, and abnormal events are intelligently identified and located to obtain evaluation results and abnormal location data.

[0070] Among them, the XGBoost gradient boosting tree model is an efficient machine learning algorithm based on the gradient boosting framework.

[0071] It can be understood that the embodiment of the present application fully mines the potential information in the panoramic data set of substation equipment status by using the XGBoost gradient boosting tree model, quickly completes in-depth analysis of the data, accurately judges the health status of the equipment, estimates the remaining service life, and accurately locates the location of abnormal events, reducing the subjectivity and limitations of manual analysis, enabling the operation and maintenance team to quickly grasp the equipment operation status, deploy targeted maintenance measures in advance, avoid sudden failures, and reduce operation and maintenance costs.

[0072] It should be noted that the XGBoost gradient boosting tree model formula is: in, For the function Find the value that makes the expression in the following curly braces reach the minimum value ; The number of samples in the substation equipment status panoramic dataset that participate in model training; is the index of the sample; is the first-order derivative of the loss function with respect to the model prediction value in the t-1th round; is the second-order derivative of the loss function with respect to the model prediction value in the t-1th round; In the tth round of iteration, the tree model For the i-th sample The predicted output of is the characteristic data of the i-th sample; is the penalty coefficient for the number of leaf nodes; For the current tree model The total number of leaf nodes; is the L2 penalty coefficient of the leaf weight; is the index of the leaf node; For tree model The predicted value of the j-th leaf node in; is the optimal prediction value of the jth leaf node; is the sample set contained in the j-th leaf node.

[0073] For example, Figure 12As shown in the figure, at a 220kV hub substation, multi-source data such as equipment vibration, infrared temperature measurement, and oil chromatography are collected based on the Internet of Things platform to form a TB-level panoramic data set. After standardization and outlier cleaning, the training, validation, and test sets are divided into training, validation, and test sets in a ratio of 7:2:1. The XGBoost model is used, and parameters such as the maximum depth of 8 and the learning rate of 0.08 are carefully debugged. Column sampling and row sampling are used to prevent overfitting, and a softmax activation function is set for multi-classification fault diagnosis. The final model has a comprehensive prediction accuracy of 94.2% for 7 types of equipment failures on the test set, with an F1 value of 0.93. It successfully warns of main transformer winding failures 4 days in advance, avoids regional power outages, reduces the risk of unplanned outages by 85%, and reduces potential economic losses by more than 5 million yuan.

[0074] In step S104, based on the assessment results, a digital twin of the substation is constructed, integrating the spatial location, operating sequence and historical data of the equipment, performing operation and maintenance process simulation, operation rehearsal and fault scenario reproduction, and generating an operation risk assessment report.

[0075] Among them, the digital twin of the substation is a 1:1 high-precision virtual mirror constructed through technologies such as laser point cloud scanning and BIM modeling, combined with equipment operating parameters, spatial location, environmental information and historical data collected in real time by the Internet of Things.

[0076] It can be understood that the embodiments of the present application use digital twins to plan maintenance routes in advance, optimize resource allocation, and improve the maintenance efficiency of main transformers; the operation rehearsal function simulates complex tasks such as switching operations, uses collision detection algorithms to predict risks, and reduces the operational error rate; fault scenario reproduction is based on historical fault data and real-time operating status, dynamically displays the fault development process, assists technical personnel in shortening fault location time, generates operation risk assessment reports, and enhances the safety and efficiency of substation operation and maintenance.

[0077] For example, during the annual maintenance of the main transformer of a coastal 220kV hub substation, the operation and maintenance team relied on a digital twin that integrated real-time operating data and high-precision three-dimensional models. Through collision detection algorithms, they simulated the maintenance process with an accuracy of 0.01 meters, identified three hidden dangers of insufficient safety distance and channel occupancy problems in advance, and optimized personnel actions, tool use, and equipment placement plans. During the simulation, they correlated equipment status in real time to predict the impact of operations. During actual maintenance, they used AR smart glasses to interact and obtain virtual guidance, and simultaneously monitored operating parameters. Ultimately, the maintenance time was shortened by 3 hours, efficiency was increased by 40%, and costs were reduced by 25%, effectively ensuring operational safety and power supply stability.

[0078] In step S105, based on the operational risk assessment report, the IPOPT interior point method solver is used to construct a multi-objective optimization model with constraints for the power grid flow optimization and the strong nonlinear problems of reactive power compensation. The control parameters are dynamically adjusted in combination with Pareto front analysis to generate a target regulation strategy.

[0079] Among them, the IPOPT interior point solver is a numerical calculation tool based on the interior point method principle, used to solve large-scale nonlinear programming problems (including equality constraints, inequality constraints, etc.). It can efficiently search for optimal solutions when dealing with complex optimization scenarios (such as power system equipment optimization scheduling, engineering design parameter optimization, etc.).

[0080] It is understood that the embodiments of this application, by adapting to large-scale nonlinear programming and handling equality and inequality constraints, construct a constrained optimization model to efficiently search for optimal solutions. By dynamically adjusting control parameters based on the Pareto front, the system accurately explores the balance between multiple objectives and generates a target control strategy that meets actual operational needs. This improves the optimization efficiency of complex power grid scenarios and enhances the accuracy of power flow optimization and reactive power compensation.

[0081] It should be noted that the IPOPT interior point method solver formula is: in, is the Lagrangian function Hessian; is the current iteration point; is the equality constraint multiplier; is the inequality constraint multiplier; is the gradient of the Lagrangian function; is the Lagrangian function; is the equality constraint function value; is the inequality constraint function value; is the Jacobian matrix of the equality constraint; is the first-order derivative of the equality constraint function h(x) with respect to the decision variable x; is the first-order derivative of the inequality constraint function g(x) with respect to the decision variable x; is the Lagrange multiplier for the inequality constraint and the corresponding inequality constraint function value The ratio of , which is a diagonal matrix with diagonal elements; is a diagonal matrix with diagonal elements; is the inequality constraint function value; is the barrier parameter of the interior point method; is the iteration step length of the decision variable x; is the equality constraint Lagrange multiplier The iteration step size; is the Lagrange multiplier for the inequality constraint The iteration step size.

[0082] It should be noted that the Pareto front refers to the mapping set of all Pareto optimal solutions in the target space. The Pareto optimal solution is the solution where "improving one target will inevitably harm other targets". These solutions constitute the frontier, which is usually a curve when there are two targets and a hypersurface when there are multiple targets. It can reflect the non-dominance of the solution and the trade-off between targets, enabling decision makers to find the best trade-off point between conflicting targets.

[0083] The Pareto front can clearly present the optimal trade-off relationship between multiple objectives (such as network loss, voltage stability, equipment cost, etc.). By exploring the set of non-dominated solutions and corresponding boundaries where "improving one objective must come at the expense of other objectives", it provides diversified options for grid control. On the one hand, it dynamically adjusts control parameters, balances conflicts between different objectives, and adapts to grid operation needs after operational risk assessment. On the other hand, it enables operation and maintenance personnel to intuitively see the boundaries between trade-offs between objectives, accurately screen the optimal control strategy based on actual operation priorities (such as focusing on economy or safety), and improve the comprehensive benefits of grid operation while meeting constraints.

[0084] For example, in a large-scale urban power grid upgrade covering 500 square kilometers, serving over 2 million users, and encompassing 3,000 kilometers of 110 kV and above transmission lines and 50 substations, the team addressed the challenges of annual network losses of 50 million yuan and a 5% increase in defective product rates for industrial users due to voltage fluctuations. A multi-objective optimization model was constructed to reduce network losses, improve voltage stability, and control equipment costs within 10 million yuan. This model included equality constraints based on Kirchhoff's laws and inequality constraints such as transformer capacity. Using the IPOPT interior point solver, the model addressed inequality constraints using a logarithmic barrier function. The KKT system equations were iteratively solved based on the Newton method, adjusting decision variables such as generator reactive output, capacitor bank switching, and transformer tap position. After 100 iterations, 50 Pareto-front non-dominated solutions were generated. A strategy was selected after weighing the objectives, ultimately reducing network losses by 18% to 41 million yuan per year, stabilizing the voltage deviation rate at ±1.5%, and reducing equipment investment by 9.5 million yuan, significantly improving grid operational efficiency.

[0085] In step S106, based on the control strategy, the risk index of equipment failure, power grid safety and environmental impact is calculated in combination with the fuzzy comprehensive evaluation method, and a multi-level risk prevention and control system is established to evaluate the risks of equipment failure, power grid safety and environmental impact in real time and dynamically adjust the control strategy.

[0086] Among them, the fuzzy comprehensive evaluation method is a multi-factor decision-making method based on fuzzy mathematics theory. It constructs factor sets and judgment sets, determines weight vectors, and uses fuzzy transformation principles to comprehensively consider the weights of various factors in a fuzzy environment for objects affected by multiple factors, thereby converting qualitative evaluation into quantitative analysis, thereby obtaining relatively objective and comprehensive evaluation results.

[0087] It can be understood that the embodiment of the present application constructs a factor set, a judgment set and determines a weight vector, uses the fuzzy transformation principle to convert qualitative descriptions into quantitative risk indexes, comprehensively considers the complex relationships and weight differences between various factors, objectively reflects the overall situation of potential risks in power grid operation, carefully distinguishes the degree of influence of different risk factors, establishes a multi-level risk prevention and control system, conducts real-time dynamic assessments of various risks, accurately adjusts prevention and control strategies, and improves the safety of power grid operation.

[0088] It should be noted that the formula of fuzzy comprehensive evaluation method is: Where n is the total number of factors; m is the number of evaluation levels; is the weight of the i-th risk factor; is the membership degree of the i-th factor to the j-th evaluation level; is the quantitative value of the jth evaluation level; is the grid risk index.

[0089] It should be noted that when constructing the factor set, we focus on the grid operation risks and sort out the risk sources from the dimensions of equipment (such as transformer and circuit breaker failures), grid (such as current exceeding the limit, voltage anomaly, etc.), and environment (such as extreme weather, external force damage, etc.). We screen the key influencing factors through historical fault data analysis and expert experience, and refine the sub-factors as needed. When constructing the evaluation set, we combine the grid safety standards and the severity of risk consequences to divide the risk levels into high, relatively high, relatively low, and low. We clarify the qualitative description and quantitative thresholds of each level (such as the amount of loss, the scope of power outage), and assign quantitative scores. At the same time, we support dynamic updates and expert verification, adapt to the actual risk prevention and control needs of the grid, and provide basic data for fuzzy comprehensive evaluation.

[0090] It should be noted that the risk levels are divided into high, relatively high, relatively low and low. Through historical accident data, industry standards and expert judgment, each level is judged from aspects such as direct economic losses, scale and duration of user power outages, and degree of equipment damage. Losses exceeding 50 million yuan and power outages for more than 24 hours for one million users are classified as high risk; economic losses of 10-50 million yuan and power outages for 6-24 hours for 500,000-1 million users are classified as relatively high risk; losses of 1 million-10 million yuan and power outages for 100,000-500,000 users for 1-6 hours are classified as relatively low risk; losses of less than 1 million yuan, with few affected users and a short power outage, are classified as low risk.

[0091] According to a substation management method based on Internet of Things technology proposed in the embodiment of the present application, an all-round and blind-angle-free Internet of Things perception network is constructed through a ubiquitous Internet of Things perception matrix, which collects equipment operating parameters, environmental indicators and power grid dynamic data in real time, processes massive amounts of information, and monitors the substation operating status in real time; the power intelligent brain evolution center continuously learns the equipment operating rules and historical fault data, accurately evaluates the equipment health status and predicts the remaining life, and issues early warnings for potential faults based on a dynamically updated abnormal feature database to reduce the probability of sudden accidents; the time-space fusion twin module integrates the equipment spatial layout and operation The system deeply integrates sequential and historical data to conduct virtual operation and maintenance drills and immersive reproduction of fault scenarios, reducing human operational errors and accelerating the inheritance of operation and maintenance experience. The nonlinear optimization decision-making module solves complex nonlinear problems such as large-scale grid connection and drastic fluctuations in grid currents, generating control strategies that balance economy, reliability, and low carbon, and enhancing the grid's resilience to uncertainty. The multi-level vibration risk management model generates a three-dimensional risk map of equipment, grid, and environment in real time. Through intelligent hierarchical early warning and dynamic optimization of prevention and control strategies, it reduces systemic risks, improves substation operation and maintenance efficiency, shortens the average fault handling time, and reduces operation and maintenance costs and safety hazards. This solves the problems of low inspection efficiency, high risk of false detection, and poor transmission stability in existing technologies.

[0092] The following will describe a substation management method based on Internet of Things technology through a specific embodiment. Figure 13 Shown, including: Deploy IoT sensors on the substation equipment foundation and surrounding environment to collect multi-dimensional data and monitor the structural status: Figure 14 Regarding settlement observation points, laser ranging sensors are installed at the four corners and center of the top surface of the foundation, including the transformer base, to monitor settlement with an accuracy of ≤3mm. Vibrating wire strain gauges are embedded in the foundation concrete to monitor the stress state of HRB400E steel bars. Accelerometers are deployed at the connection between the equipment and the foundation, with a vibration frequency threshold set to ≤200Hz. Environmental and operational monitoring: Temperature and humidity sensors are embedded within the foundation. Based on the required thickness of the anti-corrosion layer, an early warning of corrosion status is issued when the humidity exceeds 70%. Corrosion potential sensors are placed on the steel bar surfaces to monitor electrochemical corrosion. Water immersion sensors are installed in conjunction with drainage pumps to collect equipment operating data (such as transformer oil temperature) and power grid parameters at a frequency of ≥1 per minute.

[0093] Multi-source data is cleaned, verified, and structured. Data cleaning and fusion: Structural data (settlement, strain, vibration), environmental data (temperature, humidity, and water infiltration), and equipment operation data are integrated. Outliers with settlement deviations greater than 5mm are eliminated. Missing data, such as sensor failures, is filled using a time-series interpolation algorithm. Continuous data such as temperature, humidity, and stress are normalized to a range of 0-1, referring to the quantification standard for backfill soil dry bulk density. Categorized storage: Following the bill of quantities classification logic, data is categorized and stored in a distributed database by equipment type (e.g., transformer foundation), time dimension (hours / days / months), and data category (structure / environment / operation), forming a "foundation status panoramic dataset" covering the entire foundation lifecycle.

[0094] A model was built based on a panoramic data set to assess equipment status. Model training used input features such as concrete strength, reinforcement ratio, settlement rate, strain, temperature and humidity to output a health score (0-1, ≥0.8 normal, 0.6-0.8 warning, <0.6 fault) and a remaining life prediction. Model parameters were optimized through cross-validation (tree depth ≤ 6, learning rate 0.1) to achieve a test set accuracy of ≥95% (referring to wind turbine equipment prediction accuracy). Anomaly handling: Anomaly identification is triggered when the health score is <0.6. The abnormal area is located using the three-dimensional coordinates of the settlement observation points based on the anchor bolt coordinate system, with an accuracy of ≤0.5m (analogous to the anchor bolt concentricity deviation standard of ≤5mm).

[0095] Rely on the drawing data to build digital twins and simulate operation and maintenance scenarios. Model construction: Based on Figure 15 Basic plan dimensions and Figure 16 A 1:1 digital twin model of the reinforcement layout was generated using 3dsMax, synchronizing settlement data (green <3mm, yellow 3-5mm, red >5mm) with reinforcement stress contours (referenced to design values) in real time. Scenario simulation: The twin model recreates an accident in which uneven foundation settlement causes equipment tilt, analyzes stress concentration points at the anchor-concrete interface, and predicts crack propagation paths. The impact of additional equipment loads is simulated, and overturning stability is calculated using the IPOPT interior point method to generate load safety thresholds. Based on the anchor tensioning risk control process, an assessment report is generated, including risk points, levels (I-III), and countermeasures (such as phased construction).

[0096] An optimization model was constructed based on the drawing parameters, and tiered risk management was implemented. For power flow optimization, a multi-objective model was constructed to address scenarios where foundation settlement affects power flow. This model incorporated constraints such as Kirchhoff's law, settlement ≤ 5 mm (analogous to anchor concentricity deviation), and reinforcement stress ≤ 360 N / m². Pareto front analysis was used to generate control strategies (e.g., monitoring settlement rate when adjusting transformer taps). Risk control and prevention: A fuzzy comprehensive evaluation method was used to construct a factor set {foundation risk (weight 0.5), grid security risk (0.3), and environmental impact (0.2)} and a judgment set {high risk > 0.8, medium risk 0.5-0.8, low risk < 0.5}. When the health score is < 0.6 and the grid loss is > 5%, the risk is determined to be high. Based on the anchor bolt anomaly handling logic, level 1 control (operation suspension and reinforcement) is initiated. For medium-risk scenarios, monitoring is increased (once per hour). For low-risk scenarios, routine operation and maintenance is maintained.

[0097] In summary, this embodiment of the application deploys IoT sensors on substation equipment foundations and their surroundings to achieve real-time, accurate monitoring of foundation structure conditions (settlement, strain, vibration) and environmental parameters (temperature, humidity, water accumulation, and corrosion) (settlement accuracy ≤ 3mm, vibration threshold ≤ 200Hz). This data is combined with material parameters such as rebar and concrete (e.g., HRB400E rebar strength 360N / m², C20 concrete) and construction standards (e.g., anti-corrosion layer thickness ≥ 8mm) as shown in the drawings) to ensure comprehensive and accurate data collection. Platform-level data processing removes outliers with settlement deviations > 5mm and normalizes continuous data to form a "panoramic foundation status dataset" covering the entire lifecycle, providing reliable support for equipment health assessment. Health assessment (accuracy ≥ 95%) and remaining life prediction based on the XGBoost model, combined with the coordinate system in the drawings (e.g., anchor bolt installation location diagrams), accurately locates abnormal areas (accuracy ≤ 0.5m), providing early warning of foundation risks (triggered when health < 0.6). The digital twin uses a 1:1 model (referencing the foundation plan's 3800mm x 3300mm dimensions and reinforcement layout) to map monitoring data in real time. It dynamically simulates fault scenarios (such as equipment tilting due to settlement) and operational rehearsals (such as calculating anti-overturning loads). It generates assessment reports that include risk levels and countermeasures, enhancing the scientific nature of operation and maintenance decisions. A multi-objective model for power flow optimization (incorporating constraints such as settlement ≤ 5mm and reinforcement stress ≤ 360N / m²) dynamically adjusts control strategies using Pareto front analysis. This reduces network losses and improves voltage stability while also addressing basic operation and maintenance costs (referencing cost parameters such as excavation volume of 2500m³). A multi-level risk prevention and control system based on fuzzy comprehensive evaluation achieves dynamic responses from high-risk (shutdown and reinforcement) to low-risk (routine operation and maintenance), effectively integrating construction process standards in the drawings (such as the anchor bolt tensioning risk control process) with grid operation requirements. This enhances the safety, reliability, and intelligence of substation operations, reduces operation and maintenance costs, and ensures stable and efficient grid operation.

[0098] Figure 17 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: A memory 1701 , a processor 1702 , and a computer program stored in the memory 1701 and executable on the processor 1702 .

[0099] When the processor 1702 executes the program, the substation management method based on the Internet of Things technology provided in the above embodiment is implemented.

[0100] Furthermore, the electronic device further includes: The communication interface 1703 is used for communication between the memory 1701 and the processor 1702 .

[0101] The memory 1701 is used to store computer programs that can be run on the processor 1702 .

[0102] The memory 1701 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0103] If the memory 1701, processor 1702, and communication interface 1703 are implemented independently, the communication interface 1703, memory 1701, and processor 1702 can be connected to each other via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 17 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0104] Optionally, in a specific implementation, if the memory 1701, the processor 1702 and the communication interface 1703 are integrated on a chip, the memory 1701, the processor 1702 and the communication interface 1703 can communicate with each other through an internal interface.

[0105] The processor 1702 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0106] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned substation management method based on Internet of Things technology.

[0107] In addition, an embodiment of the present application also provides a computer program product, including a computer program or instructions, which, when executed, implements the above-mentioned substation management method based on Internet of Things technology.

[0108] In the description of this specification, reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0109] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0111] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0112] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above-mentioned embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0113] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A substation management system based on Internet of Things technology, characterized in that: include: Ubiquitous IoT perception matrix, power intelligent brain evolution center, time-space fusion twin module, nonlinear optimization decision module, multi-level vibration risk control model; among them, The ubiquitous IoT sensing matrix is ​​used to build a global sensing IoT network to collect substation equipment operating status data, environmental parameters and power grid operation information in real time; The Power Intelligent Brain Evolution Center is used for equipment health status assessment, life prediction, and intelligent identification and location of abnormal events; The spatiotemporal fusion twin module is used to build a digital twin of the substation, integrating the spatial location, operating sequence and historical data of the equipment to simulate the operation and maintenance process, conduct operation rehearsals and reproduce fault scenarios; The nonlinear optimization decision module is used to generate response control strategies for nonlinear and uncertain problems in power grid operation; The multi-level vibration risk management and control model is used to establish a multi-level risk prevention and control system, to assess equipment failure risks, power grid safety risks and environmental impact risks in real time, and to dynamically adjust prevention and control strategies.

2. The substation management system based on Internet of Things technology according to claim 1 is characterized in that: The ubiquitous IoT perception matrix includes a heterogeneous sensor fusion network and a dynamic panoramic visualization module. The heterogeneous sensor fusion network is used to deploy infrared thermal imaging, ultrasonic partial discharge detectors, and micro-electromechanical system vibration sensors, forming a three-dimensional monitoring matrix covering the "temperature-electrical-mechanical" status of the equipment through the IoT transmission network. The dynamic panoramic visualization module uses WebGL to generate an interactive three-dimensional monitoring interface, displaying equipment status parameters in matrix form, and comparing and analyzing real-time data with historical trends.

3. The substation management system based on Internet of Things technology according to claim 1 is characterized in that: The power intelligent brain evolution center includes an equipment health assessment unit, a life prediction module and an anomaly detection engine. The equipment health assessment unit analyzes the equipment operation data and uses physical model algorithms to evaluate the health status of the equipment and identify potential fault hazards; the life prediction module is used to analyze the equipment's operation history, aging characteristics, and environmental factor data to predict the equipment's remaining service life; the anomaly detection engine is used to monitor the equipment's operating status in real time, quickly identify abnormal events, and accurately locate them.

4. The substation management system based on Internet of Things technology according to claim 1 is characterized in that: The space-time fusion twin module includes a three-dimensional space modeling unit, an operation and maintenance simulation system, and a fault scenario deduction module. The three-dimensional space modeling unit is used to construct a three-dimensional digital model of the substation to reflect the spatial position, layout and structural relationship of the equipment; the operation and maintenance simulation system is used to simulate various operation and maintenance operation processes and evaluate the feasibility and safety of the operations; the fault scenario deduction module simulates the occurrence and development process of various fault scenarios based on historical fault data and real-time operating status.

5. The substation management system based on Internet of Things technology according to claim 1 is characterized in that: The nonlinear optimization decision module includes a nonlinear optimization solver, a multi-objective decision model and an adaptive control strategy generator, wherein the nonlinear optimization solver is used to process nonlinear optimization problems in power grid operation and find the optimal control strategy; the multi-objective decision model is used to generate the optimal control plan based on multiple target data such as the safety, reliability and economy of the power grid; and the adaptive control strategy generator is used to adaptively adjust the control strategy according to the real-time operating status of the power grid and changes in uncertainty factors.

6. The substation management system based on Internet of Things technology according to claim 1 is characterized in that: The multi-level vibration risk management model includes a multi-level risk identification unit, a risk dynamic early warning module and an emergency response linkage mechanism. The multi-level risk identification unit identifies potential risks from multiple levels of equipment, systems and networks; the risk dynamic early warning module is used to monitor changes in risk indicators, analyze risk development trends, and provide real-time early warnings; the emergency response linkage mechanism is used to link the substation's emergency response system and quickly initiate emergency plans when major risk events occur.

7. A substation management method based on Internet of Things technology, characterized in that: include: Obtain substation equipment operating status data, environmental parameters and power grid operation information; Based on the IoT platform layer, the substation equipment operating status data, environmental parameters and grid operation information are analyzed and processed to generate a panoramic equipment status data set; Based on the data set, an XGBoost gradient boosting tree model is constructed, and the health status and remaining service life of the equipment are evaluated based on the XGBoost gradient boosting tree model, abnormal events are intelligently identified and located, and evaluation results and abnormal location data are obtained; Based on the assessment results, a digital twin of the substation is constructed, integrating the spatial location, operating sequence, and historical data of the equipment to simulate the operation and maintenance process, conduct operation rehearsals, and reproduce fault scenarios, and generate an operational risk assessment report; Based on the operational risk assessment report, the IPOPT interior point solver is used to construct a multi-objective optimization model with constraints for the power grid flow optimization and strong nonlinear problems of reactive power compensation. The control parameters are dynamically adjusted in combination with Pareto frontier analysis to generate a target control strategy. According to the control strategy, the risk index of equipment failure, power grid safety and environmental impact is calculated in combination with the fuzzy comprehensive evaluation method, and a multi-level risk prevention and control system is established to evaluate the risks of equipment failure, power grid safety and environmental impact in real time and dynamically adjust the prevention and control strategy.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a substation management method based on Internet of Things technology as described in claim 7.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed, the substation management method based on Internet of Things technology described in claim 7 is implemented.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the substation management method based on Internet of Things technology described in claim 7 is implemented.

Images