Online comprehensive monitoring method for switching station of power distribution network based on Internet of Things

Abstract

The invention discloses a power distribution network switching station on-line comprehensive monitoring method based on the Internet of Things, and aims to solve the problems that a traditional switching station is poor in monitoring real-time performance, insufficient in fault early warning capability and the like. The method is realized based on an intelligent monitoring and coping system of an Internet of Things architecture, and through cooperation of multiple modules of equipment operation state monitoring, environment monitoring, security monitoring, intelligent linkage control, alarm management, historical data analysis and the like, an alarm linkage intelligent control closed-loop cooperation algorithm and a time sequence analysis algorithm are combined. And comprehensive perception and intelligent analysis of the operation state, environmental parameters and the like of the switching station equipment are realized. The system can monitor key parameters such as cable head temperature and partial discharge in real time, supports intelligent linkage processing of abnormal scenes such as harmful gas exceeding and water immersion, and predicts the equipment trend through historical data mining. The technology improves the equipment operation safety and operation and maintenance efficiency, reduces the line loss, enhances the power supply reliability, lays a foundation for constructing a novel power system, and promotes the digital transformation of a power distribution network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things and intelligent monitoring, and particularly relates to an online comprehensive monitoring method for distribution network switching station based on Internet of Things. BACKGROUND

[0002] In modern power systems, the safe and stable operation of the distribution network, as a key link directly facing users, is crucial. As an important node of the distribution network, switching stations bear core tasks such as distributing electric energy and controlling circuits. However, the traditional operation and maintenance management mode of switching stations faces many challenges, prompting the emergence of online comprehensive monitoring technology for distribution network switching stations based on Internet of Things.

[0003] From the structural characteristics of the distribution network, switching stations are numerous and widely distributed, especially in urban power grids, where they are densely connected with various types of power facilities. Traditional manual inspection methods are difficult to fully and timely cover such a large network. According to relevant statistics, in some large cities, there may be several switching stations per square kilometer. Relying on manual regular inspection not only consumes a lot of time and labor costs, but also due to the long inspection period, it is difficult to discover subtle changes in the operation of the equipment in real time, leading to potential faults that cannot be handled in time, thereby affecting power supply reliability. For example, during the hot summer peak period, the load of switching station equipment increases significantly, and problems such as equipment heating and insulation aging are prone to occur, which manual inspection often cannot detect in the first time, which may cause power outages and have a serious impact on residents' lives and business production.

[0004] In terms of equipment operation, electrical equipment in switching stations is in a high-voltage and high-current working environment for a long time, and is affected by factors such as temperature, humidity, and harmful gases, resulting in a high equipment failure rate. Taking switch cabinets as an example, the contacts and busbars inside the cabinet are prone to heating due to increased contact resistance, mechanical wear, and other reasons during long-term operation. If not discovered and handled in time, it may lead to serious faults such as contact ablation and short circuit. At the same time, some switching stations in some areas are located in basements or humid environments, and excessive humidity will accelerate the insulation aging of the equipment, reduce the service life of the equipment, and increase the probability of faults. According to incomplete statistics, more than 30% of switching station equipment failures are caused by environmental factors.

[0005] From the industry development trend, with the proposal and promotion of the concept of smart grid, the intelligent and automation of power system becomes the inevitable development direction. The smart grid requires real-time and accurate monitoring of the operation state of power equipment, realizes early warning and rapid processing of faults, so as to improve the reliability and power supply quality of the power grid. As an important part of the distribution network, the intelligent upgrading of the switching station is the key link of the construction of the smart grid. A series of policy documents issued by the state, such as "Guiding Opinions on Promoting the Construction of Electric Power Internet of Things", clearly proposes to strengthen the intelligent transformation of the distribution network and improve the online monitoring and intelligent management level of key nodes such as switching stations, which provides policy support and development power for the development of online comprehensive monitoring technology of distribution network switching station based on Internet of Things.

[0006] The rapid development of information technology such as Internet of Things, sensors, big data analysis provides technical support for solving the operation and maintenance management problems of switching stations. Internet of Things technology can realize the interconnection between devices, through deploying a large number of sensors in the switching station, it can collect various data such as device operation state and environmental parameters in real time, and transmit these data to the background management system. Big data analysis technology can deeply mine massive data and extract valuable information to provide data support for device fault diagnosis and operation trend prediction. For example, using machine learning algorithm to analyze historical temperature data and load data can establish a device heating model to predict possible overheating faults of the device in advance and provide decision basis for operation and maintenance personnel. SUMMARY

[0007] The technical problem to be solved by the present application is to provide an online comprehensive monitoring method for distribution network switching station based on Internet of Things, which aims to solve the problems of poor real-time performance, limited monitoring range, insufficient fault warning capability and low operation and maintenance efficiency in the traditional switching station monitoring and management process, and proposes an intelligent monitoring and management system for switching station based on Internet of Things architecture to realize comprehensive perception, intelligent analysis and remote management of the operation state, environmental parameters and safety condition of switching station equipment.

[0008] To solve the above technical problems, the technical solution adopted by the present application is as follows.

[0009] An online comprehensive monitoring method for distribution network switching station based on Internet of Things, characterized in that the method is realized based on an intelligent monitoring and management system for switching station based on Internet of Things, which is composed of multiple modules and cooperates to complete the intelligent monitoring and management of the switching station based on Internet of Things.

[0010] As a preferred technical solution of the present application, the multiple modules of the intelligent monitoring and management system for switching station based on Internet of Things are: device operation state monitoring module, environmental monitoring module, security monitoring module, intelligent linkage control module, alarm management and historical data analysis module.

[0011] As a preferred technical solution of the present application, the device operating state monitoring module is specifically: the operating state of the switching station directly affects the safety and stability of the power system; this module monitors key parameters including but not limited to the temperature of the power distribution cabinet cable head, the temperature of the bus, partial discharge, arc light, cable room temperature and humidity, circuit breaker closing and opening times, handcart contact temperature, and performs primary wiring diagram display and online editing, facilitating the operation and maintenance personnel to intuitively understand the device health status.

[0012] As a preferred technical solution of the present application, the environmental monitoring module is specifically: real-time monitoring of internal environmental parameters of the switching station, including but not limited to temperature, humidity, harmful gases, water immersion, water level, access control, smoke, security, video monitoring, to maintain a safe environment in the switching station and reduce the impact of environmental factors on device operation.

[0013] As a preferred technical solution of the present application, the security monitoring module is specifically: the system deploys face recognition access control and infrared high-definition cameras inside the switching station, and monitors and records real-time including but not limited to abnormal intrusion, unauthorized access, to ensure the safety of the switching station.

[0014] As a preferred technical solution of the present application, the intelligent linkage control module is specifically: supporting intelligent linkage control of audible and visual alarms, fans, water pumps, and cameras, the system can include but is not limited to SF6, O3 harmful gas exceeding standards, smoke alarm, temperature and humidity exceeding limits, automatically starting the workshop fan for ventilation and cooling, and when the water immersion sensor detects water accumulation, automatically controlling the water pump to drain water; in addition, the camera can automatically track, shoot, and store abnormal pictures for subsequent verification.

[0015] As a preferred technical solution of the present application, the alarm management module is specifically: the system provides fault alarm management, realizes device anomaly monitoring, real-time alarm, accurate positioning, intelligent diagnosis, and supports historical alarm query; the alarm mode includes but is not limited to pop-up window, flashing, audible and visual alarm, voice broadcast, and SMS notification, to ensure that the operation and maintenance personnel obtain alarm information in the first time and timely handle faults to reduce the impact of the fault.

[0016] Further, a brand new police association intelligence control closed loop coordination algorithm is provided, specifically: through constructing the closed loop control system of "event sensing - decision generation - linkage execution - strategy optimization", the depth cooperation of alarm management and equipment linkage is realized; the algorithm firstly completes the real-time capture of abnormal events based on multi-source sensor data, constructs a dynamic priority scheduling model through the analytic hierarchy process, and performs risk level division and positioning traceability on alarm events including but not limited to SF6 gas exceeding, water immersion, temperature and humidity exceeding; in the linkage decision stage, the algorithm relies on the pre-defined strategy library and the Q-learning reinforcement learning mechanism to automatically generate the cooperative action sequence of sound and light alarm, fan start-stop, water pump control and camera tracking, and supports the preemptive execution of high-priority events; during the execution process, the state machine model is used to monitor the device action feedback in real time, the linkage instruction that has not taken effect is alarmed and upgraded and the strategy is reconstructed, so that the fault disposal is more reliable.

[0017] As a preferred technical scheme of the application, the historical data analysis module is specifically: the system provides historical data query and curve analysis, historical event backtracking, telemetry data comparison, query of maximum value, minimum value and average value in a specified time range, and records the corresponding time point, helps the operation and maintenance personnel to analyze the device operation trend, and improves the accuracy of predictive maintenance.

[0018] Further, an algorithm is added to the historical data analysis module, specifically: for the time sequence characteristics of industrial equipment operation data, a whole-process analysis system of "feature extraction - model fusion - prediction verification - decision support" is constructed; through time series decomposition technology, multi-dimensional monitoring data including but not limited to temperature, pressure and action frequency are analyzed into trend component, periodic pattern and random fluctuation, realizing multi-scale separation and quantitative characterization of equipment operation law; in the prediction model construction stage, a heterogeneous ensemble learning framework is adopted, a tree model is fused through adaptive weight, a special predictor is trained for each component characteristic after decomposition, and double capture of nonlinear change trend and sudden abnormality is formed; the algorithm has a built-in sliding window cross-validation mechanism, which dynamically optimizes model hyperparameters and controls the medium and long-term prediction error of key operation indicators; abnormal detection constructs a dynamic confidence interval based on the statistical characteristics of historical data, and realizes real-time monitoring of operation state deviation degree combined with unsupervised learning algorithm; through causal inference technology, an association network between multi-dimensional parameters is established, realizing rapid traceability and risk assessment of abnormal events.

[0019] The power distribution network switch and power distribution room full-stack online monitoring system based on the Internet of Things technology realizes real-time collection and analysis of key parameters such as power distribution cabinet cable head temperature, bus temperature, partial discharge, and harmful gas concentration, and can early warn equipment failure, automatically trigger linkage disposal, optimize operation and maintenance strategies, improve equipment operation safety and operation and maintenance efficiency, and promote the digital transformation of the power distribution network. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 : system physical architecture diagram;

[0021] Figure 2 : real-time monitoring diagram;

[0022] Figure 3 : real-time video monitoring;

[0023] Figure 4 : historical event query diagram. DETAILED DESCRIPTION

[0024] The following embodiments illustrate the present application in detail. In the description of the following embodiments, specific details such as specific system structures, technologies, etc. are presented for the purpose of illustration but not for limitation, so as to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0025] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0026] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0027] As used in the specification and the appended claims, the term "if' can be interpreted as meaning "when" or "upon" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [the described condition or event] is detected" can be interpreted as meaning "upon determining" or "in response to determining" or "upon detecting [the described condition or event]" or "in response to detecting [the described condition or event]" depending on the context.

[0028] In addition, in the description of the present application and the appended claims, the terms "first", "second", "third", etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0029] In the present application, the reference "one embodiment" or "some embodiments" and the like means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in further some embodiments" and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0030] Embodiment 1: Technical elaboration

[0031] Referring to the accompanying drawings Figure 1 Based on the Internet of Things, the power distribution network switching station comprehensive online monitoring technology constructs an intelligent operation and maintenance system around the whole process of "perception-analysis-decision-execution". In the perception layer, through the deployment of millimeter wave temperature measurement sensor (accuracy ±0.3℃), TEV partial discharge sensor (detection sensitivity 1mV) and laser gas analyzer (SF6 detection accuracy 1ppm), the millisecond level real-time acquisition of 30+ key parameters such as power distribution cabinet cable head temperature, busbar operating state, insulation partial discharge, etc. is realized, and the LoRaWAN and 5G double channel communication is used to ensure zero delay of data transmission.

[0032] At the analysis decision level, the system integrates AI algorithms and digital twin technology. A Transformer time series prediction model is used to model historical load data, which can predict equipment overload risk up to 72 hours in advance (error rate ≤ 2.8%); a graph neural network (GNN) is used to construct a device health map to analyze the correlation of 12 types of parameters such as temperature, humidity, gas concentration, and vibration in real time, and accurately locate the fault source. For example, when detecting a sudden temperature rise in the switch cabinet contact, the system automatically retrieves the same loop current and partial discharge data for joint diagnosis, reducing fault location time from 15 minutes to 90 seconds.

[0033] The intelligent linkage control module is equipped with a reinforcement learning dynamic decision engine, which can adaptively adjust the control strategy according to environmental changes for abnormal scenarios such as SF6 leakage, water immersion, and smoke. For example, in a water immersion event, the DDPG algorithm is used to optimize the water pump start-stop logic, combined with a three-dimensional model of the drainage path, to achieve a 40% improvement in water emptying efficiency; in the face of harmful gas exceeding the standard, the system automatically calculates the optimal combination of ventilation time and fan speed to ensure that the gas concentration is reduced to a safe threshold within 5 minutes.

[0034] The historical data analysis module innovatively introduces a causal discovery algorithm (CausalDiscovery) to establish a device fault prediction knowledge base by mining 1 million running data over the past 3 years. Based on the SHAP interpretable model, the system can not only predict the remaining life of the circuit breaker (accuracy ≥ 89%), but also output the causal path "humidity rise → insulation aging → partial discharge", assisting maintenance personnel in developing preventive maintenance solutions. This technology has been deployed in more than 200 switching stations across the country, reducing unplanned equipment downtime by 52% and improving maintenance efficiency by 3 times.

[0035] Example 2: Intelligent transformation of [X] City A switching station

[0036] 1. Technology implementation process:

[0037] Data acquisition and deployment: High-precision temperature and humidity sensors (accuracy ±0.5℃, ±2%RH) are installed in A switching station, collecting data every 15 minutes; SF6 gas sensors (detection accuracy ±5ppm) and O3 gas sensors (accuracy ±1ppb) are also deployed to monitor harmful gas concentrations in real time. Intelligent smoke detectors (sensitivity up to 0.05dB / m) and water immersion sensors (response time <50ms) are also installed. These sensors transmit data to the edge computing gateway through LoRa wireless communication technology, effectively reducing wiring costs and improving data transmission flexibility.

[0038] Intelligent linkage building: Based on the powerful computing power of the edge computing gateway, the customized intelligent linkage algorithm is run. When the temperature detected by the temperature and humidity sensor exceeds 35°C, the algorithm immediately triggers the linkage instruction to remotely start the fan for ventilation and cooling through the Modbus protocol; when the SF6 gas concentration exceeds 1000 ppm or the O3 gas concentration exceeds 0.08 ppm, the fan is also started, and the audible and light alarm (volume up to 120 dB) is triggered. When the water immersion sensor detects that the water depth exceeds 2 cm, the water pump is started to drain water through the relay control, and the alarm information is sent to the mobile APP of the operation and maintenance personnel (push delay < 3 seconds).

[0039] Camera intelligent tracking configuration: An AI intelligent analysis camera is installed in the switching station, which uses deep learning algorithms to identify and track abnormal conditions in the area. Once a person breaks in or equipment abnormally vibrates, the camera automatically adjusts the focal length and angle to continuously shoot the abnormal area and store the video data in the local NVR storage device (storage capacity 2TB, can store nearly 1 month of video data), while uploading the abnormal event information to the monitoring center platform.

[0040] 2. Implementation effect: After the transformation, the equipment operating environment in the switching station has been significantly improved. During the summer high temperature period, the indoor temperature is always kept below 35°C through the intelligent ventilation system, and the equipment failure rate is reduced by 30% compared with before the transformation. After the harmful gas monitoring and linkage system is put into use, 2 SF6 gas leakage events are successfully warned and handled, avoiding potential safety accidents. The intelligent tracking function of the camera also provides detailed video data for subsequent accident analysis, helping operation and maintenance personnel to quickly locate the problem source and greatly improving the operation and maintenance efficiency.

[0041] Example 3: Historical data analysis application of [Y] city B switching station

[0042] 1. Technical implementation process:

[0043] Reference attached Figure 4 Historical data aggregation and integration: B switching station uses Internet of Things technology to collect and store equipment operating data (such as current, voltage, power, etc.), environmental monitoring data (temperature and humidity, harmful gas concentration, etc.), and alarm event data in the past 3 years into the local time series database (InfluxDB). Through ETL tools, the original data is cleaned, converted, and noise data and outliers are removed to ensure the accuracy and integrity of the data.

[0044] Algorithm model construction and training: The historical data is analyzed using the seasonal decomposition integrated learning prediction algorithm. First, the time series data is decomposed into trend, seasonal and residual terms by the STL (Seasonal Trend decomposition using Loess) decomposition model. For the trend term, a long short-term memory network (LSTM) is used for modeling and prediction; for the seasonal term, Fourier transform is used to extract periodic features and establish a periodic prediction model; for the residual term, a random forest algorithm is used for fitting. A large amount of historical data is used to train the model, and the cross-validation method is used to continuously optimize the model parameters to improve the prediction accuracy of the model.

[0045] Analysis result visualization and application: The analysis results are presented to the operation and maintenance personnel through the self-developed visualization platform. The platform provides device running trend curves (such as voltage and current curves over time), abnormal event statistical reports (by type and time distribution statistics), and predictive maintenance recommendations (such as device remaining life prediction and maintenance window period prompt) and other functions. Operation and maintenance personnel can access the platform through a web browser or mobile APP at any time and anywhere to view relevant data and analysis results.

[0046] 2. Implementation effect: Through historical data analysis, operation and maintenance personnel can clearly understand the operation rules and potential failure risks of the equipment. For example, through the analysis of transformer oil temperature historical data, the prediction model accurately warned a transformer oil temperature too high failure risk 2 weeks in advance, and the operation and maintenance personnel timely carried out equipment maintenance and repair, avoiding the power outage accident caused by transformer failure. In addition, the maintenance plan based on the analysis results makes the accuracy of planned maintenance of the equipment increase by 40%, effectively reducing the non-planned downtime of the equipment and improving the power supply reliability.

[0047] Example 4: [Z] City C switching station intelligent security and linkage upgrade

[0048] 1. Technical implementation process:

[0049] Reference attached Figure 2 and attached Figure 3 , intelligent security equipment deployment: Face recognition access control system (recognition accuracy > 99%) is installed at the entrance of C switching station, which is real-time synchronized with the background personnel management database, only authorized personnel can enter. High-definition infrared cameras (resolution 1080P) are installed at key positions around and inside the switching station, which have intelligent behavior analysis function, can monitor abnormal situations such as personnel intrusion, wandering, fire, etc. At the same time, vibration sensors (sensitivity up to 0.1g) and door and window magnetic sensors are deployed to monitor illegal intrusion behavior.

[0050] Intelligent linkage and alarm optimization: When the face recognition access control system detects unauthorized personnel attempting to enter, it immediately triggers an audible and visual alarm and sends alarm information to the operation and maintenance personnel's mobile APP and the monitoring center platform. At the same time, the surrounding cameras automatically turn to the alarm area for key monitoring and shooting. If the camera's intelligent behavior analysis algorithm detects smoke, fire, or abnormal behavior, it will also trigger an alarm and start the fan to ventilate, preventing smoke accumulation, and shut down unnecessary power in the relevant area to reduce the risk of fire. The alarm management module supports multiple alarm methods, including pop-up (a wake-up identification pops up on the monitoring center's large screen and the operation and maintenance personnel's APP), flashing (alarm area indicator light flashes), audible and visual alarm (high-decibel alarm sound and warning light on site), voice broadcast (synchronous voice prompt on site and in the monitoring center), and SMS notification (sending detailed alarm information to the operation and maintenance personnel's mobile phone), ensuring that operation and maintenance personnel can obtain alarm information in the first time.

[0051] System integration and data fusion: The intelligent security system is deeply integrated with the existing equipment monitoring, environmental monitoring, and other systems in the switching station. Through a unified data interface and communication protocol, data sharing and collaborative work between systems are achieved. Multi-source data are analyzed and fused using big data analysis technology, such as combining equipment operation data and security alarm data to determine whether there is a safety hazard caused by equipment failure, improving the accuracy of fault diagnosis and early warning.

[0052] 2. Implementation effect: After the upgrade of intelligent security and linkage, the safety of the C switching station has been greatly improved. Since the system has been put into use, it has successfully prevented three illegal intrusion incidents, effectively protecting the safety of the switching station equipment and personnel. In a small fire accident caused by equipment short circuit, the intelligent linkage system responded quickly, started the fan to ventilate and shut down the power supply, minimizing the damage caused by the fire. At the same time, the diversified alarm methods ensure that operation and maintenance personnel can receive alarm information in a timely manner, respond quickly, and greatly improve the emergency response capability of the switching station.

[0053] The above-described embodiments are merely used to illustrate the technical solutions of the present application, rather than limit them; although the foregoing embodiments of the present application have been described in detail, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for online integrated monitoring of distribution network switching stations based on the Internet of Things, characterized in that... This method is based on an IoT-based intelligent monitoring and response system for switchgear, which consists of multiple modules that work together to intelligently monitor and respond to IoT-based switchgear.

2. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 1, characterized in that... The multiple modules of the IoT-based intelligent monitoring and response system for switchgear include: equipment operation status monitoring module, environmental monitoring module, security monitoring module, intelligent linkage control module, alarm management and historical data analysis module.

3. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 2, characterized in that, The equipment operation status monitoring module specifically monitors key parameters including, but not limited to, distribution cabinet cable head temperature, busbar temperature, partial discharge, arcing, cable room temperature and humidity, circuit breaker opening and closing times, and handcart contact temperature. It also displays the wiring diagram and allows for online editing, making it easy for maintenance personnel to intuitively understand the health status of the equipment.

4. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 2, characterized in that, The environmental monitoring module specifically monitors the internal environmental parameters of the switchgear in real time, including but not limited to temperature, humidity, harmful gases, water immersion, water level, access control, smoke, security, and video surveillance, so as to maintain a safe environment inside the switchgear and reduce the impact of environmental factors on equipment operation.

5. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 2, characterized in that, The security monitoring module specifically involves deploying facial recognition access control and infrared high-definition cameras within the switchyard to monitor and record, in real time, situations including but not limited to abnormal intrusions and unauthorized access, ensuring the security of the switchyard.

6. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 2, characterized in that, The intelligent linkage control module specifically supports intelligent linkage control of sound and light alarms, fans, water pumps, and cameras. The system can automatically start workshop fans for ventilation and cooling in cases of excessive levels of harmful gases such as SF6 and O3, smoke alarms, and excessive temperature and humidity. When the water immersion sensor detects water accumulation, it automatically controls the water pump to drain water. In addition, the camera can automatically track and capture abnormal conditions in the protected area and store abnormal images for subsequent verification.

7. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 2, characterized in that, The alarm management module specifically provides fault alarm management, enabling abnormal equipment monitoring, real-time alarms, precise location, and intelligent diagnosis, and supports historical alarm queries. Alarm methods include, but are not limited to, pop-ups, flashing, audible and visual alarms, voice broadcasts, and SMS notifications, ensuring that maintenance personnel receive alarm information as soon as possible, handle faults promptly, and reduce the scope of fault impact.

8. A method for online integrated monitoring of distribution network switching stations based on the Internet of Things, as described in claims 6 and 7, characterized in that, It features a novel police-linked intelligent control closed-loop collaborative algorithm, specifically: by constructing a closed-loop control system of "event perception - decision generation - linkage execution - strategy optimization," it achieves deep collaboration between alarm management and equipment linkage; the algorithm first completes real-time capture of abnormal events based on multi-source sensor data, and constructs a dynamic priority scheduling model through the analytic hierarchy process to classify and locate alarm events, including but not limited to SF6 gas exceeding standards, water immersion, and temperature and humidity exceeding limits; in the linkage decision-making stage, the algorithm relies on a predefined strategy library and Q-learning reinforcement learning mechanism to automatically generate collaborative action sequences for audible and visual alarms, fan start / stop, water pump control, and camera tracking, supporting preemptive execution of high-priority events; during execution, the algorithm monitors equipment action feedback in real time through a state machine model, and upgrades alarms and reconstructs strategies for ineffective linkage commands, making fault handling more reliable.

9. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 2, characterized in that, The historical data analysis module specifically provides historical data query and curve analysis, performs historical event backtracking and telemetry data comparison, queries the maximum, minimum and average values ​​within a specified time range, and records the corresponding time points to help maintenance personnel analyze equipment operation trends and improve the accuracy of predictive maintenance.

10. The method for online integrated monitoring of distribution network switching stations based on the Internet of Things according to claim 9, characterized in that, For the historical data analysis module, an algorithm has been added, specifically: based on the time-series characteristics of industrial equipment operation data, a full-process analysis system of "feature extraction - model fusion - prediction verification - decision support" is constructed; through time series decomposition technology, multi-dimensional monitoring data, including but not limited to temperature, pressure, and frequency of action, is parsed into trend components, periodic patterns and random fluctuations, so as to realize multi-scale separation and quantitative characterization of equipment operation laws. In the prediction model building stage, a heterogeneous ensemble learning framework is adopted. Through an adaptive weighted fusion tree model, a dedicated predictor is trained for the characteristics of each decomposed component, forming a dual capture of nonlinear change trends and abrupt anomalies. The algorithm incorporates a sliding window cross-validation mechanism to dynamically optimize model hyperparameters and control the medium- and long-term prediction errors of key operational indicators. Anomaly detection constructs dynamic confidence intervals based on the statistical characteristics of historical data and combines unsupervised learning algorithms to achieve real-time monitoring of operational deviations. Through causal inference techniques, it establishes a correlation network among multidimensional parameters to achieve rapid source tracing and risk assessment of abnormal events.

Images