10kV switch cabinet intelligent automatic operation monitoring and early warning method, system and medium

Abstract

The invention relates to a 10kV switch cabinet intelligent automatic operation monitoring and early warning method and system and a medium, and the method specifically comprises the following steps: 1, collecting the partial discharge data information of each key part, including a sound wave signal, an instantaneous pulse current signal and a high-frequency electromagnetic wave signal; 2, carrying out data processing, and obtaining a partial discharge abnormal point data value of each key part; 3, realizing partial discharge early warning of the switch cabinet by adopting a fault early warning method based on current and sound wave abnormal point data of the switch cabinet; 4, collecting the temperature of each key part and the environment temperature; 5, carrying out data processing, and obtaining a change relation function of the temperature rise of each key part along with the current; step 6, establishing a switch cabinet dynamic early warning model to realize dynamic temperature rise early warning; the method has the advantages that the operation and maintenance cost is reduced, the equipment operation efficiency is improved, potential safety hazards are found in time, and remote monitoring and early warning are achieved.

Description

Technical Field

[0001] This invention belongs to the field of switchgear monitoring technology, specifically relating to a method, system and medium for intelligent automated operation monitoring and early warning of 10kV switchgear. Background Technology

[0002] 10kV indoor AC metal-enclosed switchgear (hereinafter referred to as switchgear) is the most widely used switchgear in substations of 110kV and above voltage levels. Its reliability is directly related to the safe and stable operation of the main transformer and even the entire substation. In actual operation, switchgear has a large operating current, many operation frequency, involves complex types of loads, and is frequently affected by external line and equipment failures. Moreover, the safe distance between switchgear and substation operation, inspection, testing, and maintenance personnel is minimal. Therefore, the defect rate of 10kV switchgear has been high for a long time, and incidents of complete equipment burnout leading to tripping or even damage to the main transformer on all three sides occur frequently. More seriously, some switchgear that does not meet the IAC protection level requirements directly... The safety of personnel at substations is endangered, resulting in significant economic losses and social impact. Operation and maintenance personnel need to conduct long-term monitoring and maintenance of switchgear equipment. Traditional early warning methods rely on regular manual inspections to identify potential safety hazards, which is labor-intensive, resource-intensive, inefficient, prone to missed or false detections, has limited monitoring capabilities, restricted communication methods, long passive early warning response times, high energy consumption, and is difficult to integrate and expand with other systems, failing to meet intelligent requirements. Therefore, it is essential to provide a 10kV switchgear intelligent automated operation monitoring and early warning method, system, and medium that reduces operation and maintenance costs, improves equipment operating efficiency, promptly identifies potential safety hazards, and enables remote monitoring and early warning. Summary of the Invention

[0003] (I) Technical Solution

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, system and medium for intelligent automated operation monitoring and early warning of 10kV switchgear, which reduces operation and maintenance costs, improves equipment operating efficiency, timely detects potential safety hazards, and realizes remote monitoring and early warning.

[0005] The objective of this invention is achieved as follows: Firstly, a method for intelligent automated operation monitoring and early warning of a 10kV switchgear, the specific steps of which are as follows:

[0006] Step 1: Collect partial discharge data from key components, including acoustic signals, instantaneous pulse current signals, and high-frequency electromagnetic wave signals;

[0007] Step 2: Perform data processing to obtain the data values ​​of partial discharge anomaly points in various key areas;

[0008] Step 3: Employ a fault early warning method based on switchgear current and acoustic anomaly data to achieve partial discharge early warning for switchgear;

[0009] Step 4: Collect the temperature of each key component and the ambient temperature;

[0010] Step 5: Perform data processing to obtain the relationship function between temperature rise and current for each key component;

[0011] Step 6: Establish a dynamic early warning model for the switchgear to achieve dynamic temperature rise early warning;

[0012] Step 7: When the number of abnormal points occurring in each key part within a period reaches or exceeds the threshold, a multi-point red warning is triggered; or if the number of abnormal points occurring in each key part within a period does not reach the threshold, but the abnormal value points and the first occurrence of abnormal value points in at least one key part during a non-high frequency occurrence period both reach or exceed the corresponding threshold, a single-point orange warning signal is triggered.

[0013] A yellow warning signal is triggered when the temperature rise of any critical component or at least one critical component reaches or exceeds the corresponding threshold.

[0014] Furthermore, the fault early warning method based on switch cabinet current and acoustic anomaly data in step 3 includes the following steps:

[0015] Step 3.1: Outlier value acquisition and update: This includes outlier value acquisition, outlier classification, and outlier update;

[0016] Step 3.2: Fault warning based on anomalies: Based on the analysis results of the spatiotemporal patch map, the anomaly values ​​are comprehensively utilized. According to the spatiotemporal patch map of anomaly values, single-point warnings are made for anomaly values ​​in non-high frequency occurrence periods and for the first occurrence of anomaly values. By combining the frequency and the first occurrence of anomalies, timely warnings can be given for sudden situations.

[0017] Step 3.3: Update the fault knowledge base: For early warnings and alarms caused by anomalies and faults that trigger maintenance and troubleshooting, record them in a timely manner and upload and update the fault warning rule pool to achieve dynamic operation and maintenance management of equipment; dynamically adjust the rules of the warning pool according to the characteristics of the fault occurrence and the fault data content uploaded manually, and combine the rules into feature values ​​of the fault feature library; when the warning content meets the matching content of the fault feature library, push the existing solutions in the fault knowledge base to the operation and maintenance personnel.

[0018] Furthermore, the acquisition of outlier values ​​in step 3.1 is as follows:

[0019] Plot a standard curve for the independent switchgear current, and construct the current value F from the standard curve. t,n , will F t,nConstruct the latest standard curve by performing a connection;

[0020] Calculate the real-time data of coarse abnormal phase currents corresponding to the standard curve at each time point;

[0021] By comparing historical data with real-time abnormal data, we can obtain information on the frequency and time periods of abnormal data occurrence.

[0022] Furthermore, the anomaly classification in step 3.1 is as follows: The anomalies in the current / acoustic waves of each station's switchgear are classified, and the anomaly situation within one cycle is described: S = {S1, S2, ..., S...} 14 In the formula, S represents the number of outliers occurring within one period; S1, S2, ..., S 14 This represents the number of outliers occurring on each day within a 14-day period.

[0023] The first occurrence of an outlier is expressed as: S>0&{S1,S2,...,S 13} = 0, and the other anomalies are: S > 0; the first anomaly can reflect the suddenness of the abnormal data, which is likely to be accidental and may cause significant damage to the equipment.

[0024] Furthermore, the switchgear dynamic early warning model in step 6 is specifically as follows: based on the temperature rise data of the healthy switchgear, a functional relationship is established between the temperature of the monitoring point and the main circuit current and energizing time; when an early warning is issued, the system uses the current and energizing time obtained from online monitoring, combined with the functional relationship, to calculate the temperature rise alarm threshold, and automatically judges whether there is a thermal defect fault at the monitoring point through the dynamically changing threshold.

[0025] Secondly, a 10kV switchgear intelligent automated operation monitoring and early warning system is provided. The system includes an electrical data acquisition module, a data processing module, a data early warning platform, a temperature data acquisition module, a data transmission DTU module, an indicator monitoring and early warning module, and data reporting and visualization components. The system is used to execute the 10kV switchgear intelligent automated operation monitoring and early warning method described above.

[0026] The electrical data acquisition module is used to collect partial discharge data information from various key parts, including acoustic signals, instantaneous pulse current signals, and high-frequency electromagnetic wave signals.

[0027] The data processing module is used to process data and obtain the data values ​​of partial discharge anomaly points in various key parts.

[0028] The data early warning platform is used to implement partial discharge early warning of switchgear by adopting a fault early warning method based on switchgear current and acoustic abnormality point data;

[0029] The temperature data acquisition module is used to collect the temperature of various key components and the ambient temperature.

[0030] The data transmission DTU module is used to process data and obtain the temperature rise of each key component as a function of current.

[0031] The indicator monitoring and early warning module is used to establish a dynamic early warning model for the switchgear and realize dynamic temperature rise early warning.

[0032] The data report and visualization components are used to trigger a multi-point red warning when the number of abnormal points occurring in each key part within a period reaches or exceeds the threshold; or to trigger a single-point orange warning signal when the number of abnormal points occurring in each key part within a period does not reach the threshold, but the abnormal value points and the first occurrence of abnormal value points in at least one key part during a non-high frequency occurrence period both reach or exceed the corresponding threshold.

[0033] It is also used to trigger a yellow warning signal when the temperature rise of each critical part or at least one critical part reaches or exceeds the corresponding threshold.

[0034] In this invention, the data processing module is a computing module that can process and analyze data. It can operate as a standalone device or as part of a larger system and can be used for various applications, including data analysis, data management, and data storage. The data processing module typically includes computing resources such as processors and memory for processing and storing data.

[0035] Data Transmission Unit (DTU) Module: Edge computing and data transmission. The device has a built-in edge computing module that preprocesses the raw data (such as filtering and feature extraction) to reduce the amount of data transmitted. It supports multiple communication methods such as 4G / 5G, LoRa, and fiber optic to ensure that data is uploaded to the cloud platform or dispatch center in real time.

[0036] Data Early Warning Platform: Data Acquisition and Storage: The data early warning platform acquires data from various data sources through multi-source streaming data acquisition technology and uses data storage modules to store and manage the data; Data Analysis and Mining: The platform uses data mining and machine learning algorithms to perform in-depth analysis of the data, revealing potential patterns and trends in the data and discovering anomalies.

[0037] Indicator monitoring and early warning module: Set early warning thresholds for key indicators. Once an indicator exceeds or reaches the early warning threshold, the system will promptly send an alert notification. The early warning platform supports one-stop real-time data processing and rule-based early warning. Through a real-time computing engine, it performs pattern matching between data and rules, generates early warning messages, and pushes them to the message middleware and database.

[0038] Data Reporting and Visualization Components: The platform visualizes data through charts, tables, and reports, facilitating real-time data monitoring and analysis for users. Simultaneously, the platform can automatically generate intelligent reports, providing users with in-depth data analysis and decision-making suggestions.

[0039] Furthermore, the electrical data acquisition module includes an ultrasonic detection system and an ultra-high frequency detection system. The ultrasonic detection system includes an ultrasonic sensor, and the ultra-high frequency detection system includes an ultra-high frequency sensor. Both the ultrasonic detection system and the ultra-high frequency detection system include a data acquisition unit, a data processing unit, a display unit, a control unit, and a charging unit.

[0040] In this invention, the electrical data acquisition module is a core component of the power monitoring and automation system. It is responsible for acquiring the operating parameters of electrical equipment (such as voltage and current) in real time, providing basic data support for subsequent analysis, control and early warning.

[0041] Furthermore, the temperature data acquisition module includes an environmental parameter acquisition module, a thermal imaging acquisition module, and a wireless temperature monitoring terminal; the wireless temperature monitoring terminal includes a temperature sensor, an MCU, a ZigBee module, and a power supply module.

[0042] In this invention, the environmental parameter acquisition module uses high-precision sensors to monitor environmental parameters such as temperature and humidity inside the switchgear in real time. The acquired data is sent to a processor for processing, which converts the acquired temperature and humidity data into binary electrical signals for further processing. The thermal imaging acquisition module employs thermal imaging technology, using a thermal imaging camera to monitor the temperature distribution inside the switchgear in real time, paying particular attention to high-temperature areas to identify potential safety hazards.

[0043] Multiple wireless temperature monitoring terminals interconnect with each other using ZigBee modules and send the data to a remote monitoring and diagnostic host computer. A temperature prediction model based on a BP neural network is established, forming a wireless temperature and humidity monitoring and thermal fault diagnosis system based on ZigBee and BP neural network, which can realize accurate early warning of thermal faults. The wireless temperature and humidity monitoring and thermal fault diagnosis system consists of at least one wireless temperature monitoring terminal, at least one router, at least one coordinator, and a remote monitoring and diagnostic host computer.

[0044] In this invention, the 10kV switchgear intelligent automated operation monitoring and early warning system further includes a battery and a wireless charging module. The battery is a high-capacity battery that supports long-term operation of the early warning device. The wireless charging module uses wireless charging technology, eliminating the need for wires or other physical connections. This reduces wire clutter and simplifies the charging process, allowing users to charge the device without disassembling it. It utilizes electromagnetic fields to transfer energy between the charging station and the equipment, thereby charging the device.

[0045] Thirdly, an electronic device includes a processor, a memory, a user interface, and a network interface. The memory stores computer programs / instructions, and the user interface and network interface are both used for communication with other devices. When the computer programs / instructions are executed by the processor, the electronic device performs the 10kV switchgear intelligent automated operation monitoring and early warning method as described above.

[0046] Fourthly, a computer-readable storage medium stores a computer program / instruction, which, when executed by a processor, implements the 10kV switchgear intelligent automated operation monitoring and early warning method as described above.

[0047] (II) Beneficial Effects

[0048] 1. This invention integrates temperature, humidity, thermal imaging, and electrical quantities (voltage, current, etc.) into one, and performs multi-parameter fusion monitoring, overcoming the shortcomings of traditional devices that have single functions and one-sided monitoring, and providing a more comprehensive and accurate picture of the operating status;

[0049] 2. The present invention provides a fault early warning method and a switchgear dynamic early warning model based on switchgear current and acoustic anomaly data, which realizes dynamic temperature rise early warning, transforms passive alarm into active prediction, significantly improves the timeliness and accuracy of early warning, and effectively reduces the accident rate. Attached Figure Description

[0050] Figure 1 This is a flowchart for judging the early warning of current and sound wave anomalies in the present invention.

[0051] Figure 2 This is a flowchart of the updated fault knowledge base of the present invention.

[0052] Figure 3 This is a block diagram of the system composition structure of the present invention.

[0053] Figure 4 This is a block diagram of the ultrasonic / ultra-high frequency detection system of the present invention.

[0054] Figure 5 This is a block diagram of the wireless temperature monitoring terminal of the present invention.

[0055] Figure 6 This is a schematic diagram of the terminal power module of the present invention.

[0056] Figure 7 This is a schematic diagram of the wireless temperature monitoring system of the present invention.

[0057] Figure 8 This is a schematic diagram of the switchgear thermal fault diagnosis and early warning structure of the present invention.

[0058] Figure 9 This is a basic circuit diagram of the CC2530 wireless radio frequency module of the present invention.

[0059] Figure 10 This is a flowchart of the ZigBee communication process of the present invention.

[0060] Figure 11 The image shows the prediction results of the BP neural network model of this invention. Detailed Implementation

[0061] The present invention will be further described below with reference to the embodiments and / or accompanying drawings.

[0062] Example 1

[0063] like Figure 1-11 As shown, a method for intelligent automated operation monitoring and early warning of 10kV switchgear is described, and the specific steps of the method are as follows:

[0064] Step 1: Collect partial discharge data from key components, including acoustic signals, instantaneous pulse current signals, and high-frequency electromagnetic wave signals;

[0065] Step 2: Perform data processing to obtain the data values ​​of partial discharge anomaly points in various key areas;

[0066] Step 3: Employ a fault early warning method based on switchgear current and acoustic anomaly data to achieve partial discharge early warning for switchgear;

[0067] In this embodiment, the specific steps are: 1. Acquisition and updating of current / acoustic wave anomaly point values.

[0068] ① Obtaining abnormal values: The standard curve of switchgear current / sound wave has a period of 14 days. The curve is smoothed by the moving average method. Abnormal current / sound wave can be found by using the mean-variance method. The time and current / sound wave value construction method of the switchgear current / sound wave standard curve are shown in Table 1 (taking current value I as an example).

[0069] Table 1. Method for constructing the standard current curve for switchgear.

[0070]

[0071] After processing the data at the same time on different dates within the period, a standard curve is obtained to express the changing trend of switchgear current in different time periods.

[0072] Based on the standard curve determined within the period, a standard curve can be plotted for each independent station, and the values ​​of superelevation anomalies can be obtained based on the standard curve. A spatiotemporal patch map can then be constructed for the anomaly values. This process involves three steps:

[0073] 1) Plot a standard curve for the independent switchgear current, and construct the current value F from the standard curve. t,n The formula for calculating F is: t,n =w1I t,1 +w2I t,2 +...+w n I t,n In the formula, w n The daily weight within the period; I t,n is the actual current value at that point in time; t is the number of days (t = 1, 2, ..., 14); n is the number of times the current value is measured within 1 day (n = 0, 1, ..., 287); F t,n Perform a connection to construct the latest standard curve.

[0074] 2) Calculate the real-time data of gross abnormal phase currents corresponding to the standard curve at each time point; according to the 3σ criterion, data whose actual phase current data exceeds the range of (μ±3σ) (where μ is the mean and σ is the standard deviation) are defined as gross abnormal phase current data of noteworthy value; for the data within the aforementioned standard curve period, μ and σ can be calculated: μ t,n =F t,n ,

[0075] 3) Comparative analysis was conducted between historical data and real-time abnormal data to obtain information such as the frequency and time period of abnormal data occurrence (see Table 2).

[0076] Table 2 Statistics of abnormal current data in switchgear

[0077]

[0078] Based on statistical analysis, large anomaly data obtained through the 3σ criterion are used to assess the equipment status using big data analytics.

[0079] ② Anomaly Classification: The current / acoustic anomalies of each site's switchgear are classified, describing the anomalies within one cycle: S={S1,S2,...,S...} 14 In the formula, S represents the number of outliers occurring within one period; S1, S2, ..., S 14 This represents the number of outliers occurring on each day within a 14-day period.

[0080] The first occurrence of an outlier is expressed as: S>0&{S1,S2,...,S 13} = 0, and the other anomalies are: S > 0; the first anomaly can reflect the suddenness of the abnormal data, and is likely to be accidental, which may cause significant damage to the equipment. In the method of this invention, it is given greater weight.

[0081] ③ Anomaly Update: Continuous data processing adopts an iterative approach. Taking the switchgear current / acoustic standard curves for 3 consecutive days from 20xx-xx-25, 20xx-xx-26, to 20xx-xx-27 as an example, the date intersection for the standard curve calculation is 20xx-xx-13-20xx-xx-24. Although there is a date intersection, the standard curve is redrawn daily, and the most recent date is given greater weight. As the date changes, the standard curve iterates, and the anomaly values ​​are regenerated, completing the data update. In some cases, a point value that was an anomaly in the previous period T1 may become a non-anomaly in the new period T3. During the anomaly value update process, the first appearance of an anomaly data may indicate that the equipment is operating in an unhealthy state, which is of greater value for equipment status assessment and maintenance strategy formulation.

[0082] II. Fault Warning

[0083] ① Anomaly-based fault early warning method: Early warning based on anomaly data involves comprehensively utilizing the analysis results of spatiotemporal patterns to identify and address anomaly values. Based on the spatiotemporal pattern of anomaly values, single-point early warnings can be issued for anomalies occurring in infrequent periods and for newly appearing anomalies. By considering both frequency and the initial occurrence of anomalies, timely warnings can be issued for sudden situations, facilitating focused attention by maintenance personnel. Through refined processing of anomaly values ​​and setting warning levels, the severity of alarm information in terms of business operations can be reflected at the data level. The early warning and alarm judgment process for switchgear current / acoustic wave abnormalities is as follows: Figure 1 As shown.

[0084] Figure 1 In this system, the early warning and alarm judgment process can be set according to specific needs regarding the occurrence of abnormal points within a cycle, such as setting a threshold for the number of abnormal points within a cycle and a threshold-triggered alarm for each abnormal point. Early warning alarms are triggered based on the warning process content, reminding maintenance personnel to take timely action. The content of the abnormal value warnings includes not only current / sound distortion, but also three-phase current imbalance / sound wave abrupt changes, and even line short circuits. By monitoring current / sound wave anomalies, it is possible to promptly understand emergencies and take corresponding actions to protect power supply equipment.

[0085] The abnormal points at each site trigger corresponding rules to issue early warnings, allowing maintenance personnel to formulate timely and efficient maintenance plans for the equipment based on the anomaly priority.

[0086] ② Update the Fault Knowledge Base: The fault knowledge base can provide timely solutions based on fault characteristics, bringing convenience to maintenance personnel. In equipment procurement, switchgear models are usually quite consistent, so common processing can be applied to the same models. Warnings and alarms caused by anomalies, as well as faults triggering maintenance investigations, need to be recorded promptly, and the fault warning rule pool needs to be uploaded and updated to ensure that maintenance personnel can more accurately manage equipment and achieve dynamic equipment maintenance management. The fault knowledge base establishment flowchart is as follows: Figure 2 As shown.

[0087] The rules of the early warning pool are dynamically adjusted based on the characteristics of the fault occurrence and the fault data uploaded manually, and the rules are combined into feature values ​​of the fault feature library. When the early warning content meets the matching content of the fault feature library, the existing solutions in the fault knowledge base are pushed to the operation and maintenance personnel.

[0088] In summary, this invention, based on the daily regularity of switchgear current / acoustic waves, utilizes machine learning to generate standard curves, employs the 3σ criterion to screen out outlier values ​​with gross errors, and classifies and utilizes these outliers according to their periodicity. Through historical data analysis (combining long-period data with spatiotemporal pattern analysis), it finally proposes an outlier-based fault early warning method and a fault knowledge base update strategy. This improves the accuracy of equipment condition assessment, enabling condition-based maintenance and increasing maintenance efficiency. It allows for timely monitoring of key equipment or emergencies based on proactively set priorities, and derives maintenance plans from the fault knowledge base based on content matching the fault feature database. This invention effectively achieves macro-level control of equipment by detecting extremely high anomalies, and the outlier-based early warning method provides excellent pre-emptive feedback control.

[0089] Step 4: Collect the temperature of each key component and the ambient temperature;

[0090] Step 5: Perform data processing to obtain the relationship function between temperature rise and current for each key component;

[0091] Step 6: Establish a dynamic early warning model for the switchgear to achieve dynamic temperature rise early warning;

[0092] In this embodiment, the switchgear dynamic early warning model is specifically as follows:

[0093] The switchgear dynamic early warning model is based on the temperature rise data of healthy switchgear and establishes a functional relationship between the temperature of the monitoring point and the main circuit current and energizing time. When an early warning is issued, the system uses the current and energizing time obtained from online monitoring and combines them with the functional relationship to calculate the temperature rise alarm threshold. Through the dynamically changing threshold, it automatically determines whether there is a thermal defect fault at the monitoring point.

[0094] The model first requires obtaining the relationship between the temperature rise of the switchgear and the current. The formula for calculating the temperature rise of the switchgear is: In the formula, I is the real-time maximum phase current; I ref T represents the rated current of the switchgear. ref The stable temperature rise under rated current; T stable This is the stable temperature rise of the maximum phase current in real time; the exponent a is adjustable, and can be taken as 1.6 to 2.0 here.

[0095] Substituting the real-time maximum phase current into the above formula, the normal temperature rise of the switchgear at that current value can be calculated; the only known parameter in the above formula is I. ref The stable temperature rise T under rated current ref It needs to be obtained through testing; in reality, in the operating environment of the switchgear, T ref Due to manufacturing errors and environmental factors, T is not a fixed value but fluctuates within a range; in this case, it is difficult to use a precise mathematical formula to calculate it. ref Therefore, probability and statistics methods are needed to obtain it. According to the central limit theorem, some phenomena in industrial production are affected by many independent random factors. When the influence of each factor is very small, the total influence can be regarded as following a normal distribution. The actual temperature rise test data of switchgear basically conforms to this conclusion. Therefore, the normal distribution can be used to statistically determine T. ref ; Statistical analysis of the probability distribution of the rated temperature rise of the switchgear revealed that the normal distribution model of X ~ (73.2,3) was extended to T ref It can just cover its range of changes.

[0096] Therefore, in its normal distribution curve, take a point from left to right, connect the vertical coordinates of the intersection point with the normal distribution curve to form the first dashed line, and the area to the left of this dashed line accounts for 80% of the total area of ​​the normal distribution. The temperature within this range can cover most normal temperature rise conditions. The temperature at this dashed line is taken as T. ref Substituting into the above formula, the calculated T stable It can already be used as a value when the temperature rise exceeds T. stableAt this point, it can be considered that the monitoring point is likely faulty. Then, take another point from left to right, connect the vertical coordinates of this point to the intersection with the normal distribution curve, forming a second dashed line, with the left side of this dashed line occupying 95% of the total area of ​​the normal distribution. Select another T at this dashed point. ref Calculations can yield another value that fully covers normal temperature rise conditions; values ​​exceeding this threshold indicate a malfunction at the monitoring point.

[0097] The above equation only introduces current as a variable, while the temperature change is also related to the time of current flow. Generally, when the current is constant, the temperature increases exponentially with time. Therefore, considering the time variable, we also need to introduce the formula for the thermal time constant: θ stable =T stable +θ ambient

[0098] In the formula, θ m For real-time temperature; θ m-1 The real-time temperature at the previous time point; θ stable Equal to steady temperature rise T stable Add ambient temperature θ ambient ; t is the time length between two time points; τ is the thermal time constant.

[0099] The above formula was originally used to represent the transient process of temperature change in a thermometer, describing the temperature θ of the thermometer. stable When a certain object is viewed, after time t, the reading changes from θ. m-1 Become θ m The process; obviously, when t = τ, the above formula equals e-1, and τ is the thermal time constant of the thermometer; here, the above formula can also be used to calculate the thermal time constant of the switchgear; take two different temperature points and the rated stable temperature rise from the test temperature rise data of the switchgear under rated current and substitute them into the above formula to calculate the thermal time constant τ of the switchgear; it should be noted that the structure of the circuit breaker and the operating environment will affect the magnitude of τ, and it will also be different for different monitoring points, so it needs to be calculated separately for each monitoring point; finally, the above formula is transformed into: By substituting θ stable The temperature alarm threshold θ, which varies with current and time, can be calculated using the thermal time constant τ. m .

[0100] As a concrete implementation example, a dynamic temperature rise early warning model is established based on the temperature curve of a certain manufacturer's switchgear. The temperature alarm threshold can dynamically change with the current value. Compared with the weekly fixed alarm threshold method, this model can remind the operators when the current is 2500A and the temperature is less than 80℃, which effectively improves the practicality of the early warning system.

[0101] Step 7: When the number of abnormal points occurring in each key part within a period reaches or exceeds the threshold, a multi-point red warning is triggered; or if the number of abnormal points occurring in each key part within a period does not reach the threshold, but the abnormal value points and the first occurrence of abnormal value points in at least one key part during a non-high frequency occurrence period both reach or exceed the corresponding threshold, a single-point orange warning signal is triggered.

[0102] A yellow warning signal is triggered when the temperature rise of any critical component or at least one critical component reaches or exceeds the corresponding threshold.

[0103] This invention relates to an intelligent automated operation monitoring and early warning method for 10kV switchgear. In use, this invention integrates temperature, humidity, thermal imaging, and electrical quantities (voltage, current, etc.) into a single system, achieving multi-parameter fusion monitoring. This overcomes the shortcomings of traditional devices, which have limited functionality and only provide a more comprehensive and accurate picture of the operating status. The intelligent early warning system utilizes a fault early warning method based on switchgear current and acoustic anomaly data, along with a dynamic early warning model for the switchgear. This enables dynamic temperature rise early warning, transforming passive alarms into proactive predictions, significantly improving the timeliness and accuracy of early warnings, and effectively reducing the accident rate. This invention effectively reduces the frequency of manual inspections, avoids major equipment damage, shortens power outage time, and optimizes equipment operating efficiency. Furthermore, this invention offers advantages such as reduced maintenance costs, improved equipment operating efficiency, timely detection of potential safety hazards, and remote monitoring and early warning capabilities.

[0104] Example 2

[0105] like Figure 1-11 As shown, a 10kV switchgear intelligent automated operation monitoring and early warning system is provided. The system includes an electrical data acquisition module, a data processing module, a data early warning platform, a temperature data acquisition module, a data transmission DTU module, an indicator monitoring and early warning module, and data reporting and visualization components. The system is used to execute the 10kV switchgear intelligent automated operation monitoring and early warning method described above.

[0106] The electrical data acquisition module is used to collect partial discharge data information from various key parts, including acoustic signals, instantaneous pulse current signals, and high-frequency electromagnetic wave signals.

[0107] The data processing module is used to process data and obtain the data values ​​of partial discharge anomaly points in various key parts.

[0108] The data early warning platform is used to implement partial discharge early warning of switchgear by adopting a fault early warning method based on switchgear current and acoustic abnormality point data;

[0109] The temperature data acquisition module is used to collect the temperature of various key components and the ambient temperature.

[0110] The data transmission DTU module is used to process data and obtain the temperature rise of each key component as a function of current.

[0111] The indicator monitoring and early warning module is used to establish a dynamic early warning model for the switchgear and realize dynamic temperature rise early warning.

[0112] The data report and visualization components are used to trigger a multi-point red warning when the number of abnormal points occurring in each key part within a period reaches or exceeds the threshold; or to trigger a single-point orange warning signal when the number of abnormal points occurring in each key part within a period does not reach the threshold, but the abnormal value points and the first occurrence of abnormal value points in at least one key part during a non-high frequency occurrence period both reach or exceed the corresponding threshold.

[0113] It is also used to trigger a yellow warning signal when the temperature rise of each critical part or at least one critical part reaches or exceeds the corresponding threshold.

[0114] The electrical data acquisition module includes an ultrasonic detection system and an ultra-high frequency (UHF) detection system. The ultrasonic detection system includes an ultrasonic sensor, and the UHF detection system includes an UHF sensor. Both the ultrasonic detection system and the UHF detection system include a data acquisition unit, a data processing unit, a display unit, a control unit, and a charging unit.

[0115] In this embodiment, ① an ultrasonic detection system: When partial discharge occurs inside the switchgear, it is often accompanied by physical phenomena such as vibration and luminescence. Vibration generates sound waves with frequencies ranging from a few hertz to several megahertz. The ultrasonic sensor converts the received ultrasonic signals into electrical signals. By analyzing the electrical signals, it can be determined whether partial discharge has occurred inside the switchgear. If partial discharge has occurred, the electrical signals are further analyzed to ultimately determine the type and extent of the partial discharge. The ultrasonic sensor converts sound signals into electrical signals, which is beneficial for the acquisition and analysis of sound signals. The ultrasonic detection system consists of an ultrasonic sensor, a data acquisition unit, a data processing unit, and a data display section, etc. Figure 4 As shown, the ultrasonic sensor is connected to the data acquisition unit, the data acquisition unit is connected to the data processing unit, the data processing unit is connected to the display unit, and the control unit and the charging unit are connected to the data processing unit respectively.

[0116] ② UHF Detection System: When partial discharge occurs inside the GIS (Gas Insulator System) of the switchgear, a steep instantaneous pulse current will appear, simultaneously emitting a high-frequency electromagnetic wave of 300MHz to 3GHz. These electromagnetic waves propagate along the waveguide direction and are emitted outward at the insulator gate of the switchgear, where they are received by the UHF sensor, thereby realizing the detection and location of the partial discharge. The UHF partial discharge detection method detects the characteristics of the UHF signal inside the GIS cavity of the switchgear using the UHF sensor, thereby reflecting the type of partial discharge and determining whether there is a discharge phenomenon inside the GIS and the approximate location of the partial discharge. The switchgear GIS UHF partial discharge measurement system consists of an UHF sensor, a data acquisition unit, a data processing unit, and a data display section, etc. The system block diagram is as follows: Figure 4 As shown, the ultrasonic sensor is connected to the data acquisition unit, the data acquisition unit is connected to the data processing unit, the data processing unit is connected to the display unit, and the control unit and the charging unit are connected to the data processing unit respectively.

[0117] The process of detecting partial discharge faults in switchgear using ultra-high frequency (UHF) technology involves receiving UHF signals emitted by the faulty switchgear from a UHF sensor installed on the switchgear enclosure. These signals are then sent to a data acquisition unit, including a detector, filter, and amplifier, for amplification and filtering before being sent to a dedicated data processing unit. The data processing unit further filters and amplifies the signal, transforming the waveform into various forms such as spectral waveforms, pulse sequence phase waveforms, and phase decomposition waveforms, depending on the requirements. Finally, the data processing unit transmits the signal to a display unit, where a clear waveform is displayed. By observing and analyzing the waveform on the display and comparing it with typical partial discharge fault spectrum diagrams of switchgear, the type of partial discharge occurring in the faulty switchgear can be determined.

[0118] Fault location in switchgear is achieved by simultaneously detecting different UHF signals using two or more UHF sensors. The processing of these signals includes comparing the time difference between received signals, the amplitude of the signals, and the degree of phase attenuation. This process allows the location of the fault to be determined.

[0119] The temperature data acquisition module includes an environmental parameter acquisition module, a thermal imaging acquisition module, and a wireless temperature monitoring terminal; the wireless temperature monitoring terminal includes a temperature sensor, an MCU, a ZigBee module, and a power supply module.

[0120] In this embodiment, the wireless temperature monitoring terminal obtains power from the measurement point using a current transformer (CT), communicates with the host computer via ZigBee, and uses a DS18B20 digital temperature sensor to monitor the temperature. The power module of the wireless temperature monitoring terminal obtains power from the main circuit using a CT. The principle of the power module is as follows: Figure 6As shown, the CT current flows in through ports AC1 and AC2, passes through a voltage limiting circuit composed of D2, D3, R1, R2, and Q1, and is then connected to a rectifier bridge and energy storage capacitor C1. Finally, it is connected to the linear regulator chip AMS1117, which outputs a 3.3V DC power supply to power each module. This invention uses a PIC16F18446 microcontroller as the microcontroller unit (MCU). Its operating temperature range is -40℃ to 125℃, and it has 11 input / output (I / O) interfaces, as well as a 12-bit analog-to-digital converter (ADC) interface and a sufficient number of peripheral interfaces available for use.

[0121] The ZigBee module consists of an RF transceiver chip CC2530 and an onboard antenna. It also transmits data with the MCU via a serial peripheral interface (SPI).

[0122] Figure 9 This is the hardware circuit schematic of the CC2530 chip. Figure 9 The 32MHz crystal oscillator circuit is the main crystal oscillator used in normal operation; the 32.768kHz crystal oscillator circuit is used in sleep mode, thus reducing system power consumption. To improve transmission power and extend the ZigBee wireless communication distance, the system of this invention uses the RFX2401C chip as the front-end power amplifier. This chip is a highly integrated CMOS single-chip RF front-end amplifier. Considering the complex operating environment of the switch cabinet, anti-interference design is required. The analog circuit and digital circuit are separated, the system ground line is wrapped, the ground line width is increased, and the chip power supply decoupling capacitor is added to improve the stability of chip operation.

[0123] Multiple wireless temperature monitoring terminals interconnect with each other using ZigBee modules and send the data to a remote monitoring and diagnostic host computer. A temperature prediction model based on a BP neural network is established, forming a wireless temperature and humidity monitoring and thermal fault diagnosis system based on ZigBee and BP neural network, which can realize accurate early warning of thermal faults. The wireless temperature and humidity monitoring and thermal fault diagnosis system consists of at least one wireless temperature monitoring terminal, at least one router, at least one coordinator, and a remote monitoring and diagnostic host computer.

[0124] In this embodiment, the wireless temperature monitoring terminal of the present invention is used for switchgear temperature monitoring and fault diagnosis. It adopts ZigBee wireless communication technology to realize wireless measurement of temperature parameters, uses BP neural network to establish switchgear temperature prediction model, and collects parameters such as normal ambient temperature and load current as training samples for training. Then, it uses measured data to predict temperature and diagnose and warn of thermal faults.

[0125] The block diagram of the passive wireless temperature monitoring and thermal fault diagnosis system for switchgear based on ZigBee wireless communication technology is as follows: Figure 7As shown, it mainly consists of four parts: a remote monitoring and diagnostic computer, a ZigBee temperature acquisition terminal, a ZigBee router, and a coordinator.

[0126] ①The ZigBee coordinator, as the gateway of the entire ZigBee network, is responsible for the establishment and maintenance of the wireless network. It collects the temperature data detected by the field acquisition terminals and then transmits it to the remote monitoring computer via serial port for further analysis and processing.

[0127] ② ZigBee routers serve as network relay devices to enhance the stability of wireless networks. ZigBee acquisition terminals can join the wireless network through ZigBee routers for network expansion.

[0128] ③ The ZigBee data acquisition terminal (wireless temperature monitoring terminal) serves as the terminal measurement node of the wireless network, responsible for acquiring underlying temperature data. Temperature acquisition uses a PT100 temperature sensor, and current acquisition uses a Hall effect current sensor. The temperature sensor is placed in the switch cabinet where temperature needs to be acquired to enable network node addition and data transmission.

[0129] ④ The remote monitoring computer summarizes and processes the collected data, inputting the collected temperature T0, the real-time temperature T1 of the equipment monitoring point, and the load current I into the trained BP neural network to calculate the predicted temperature value of the switchgear. The predicted value is then compared with the real-time temperature to determine the operating status of the equipment. The switchgear thermal fault diagnosis and early warning structure diagram is shown below. Figure 8 As shown.

[0130] ZigBee Communication: After the coordinator is powered on, it establishes a ZigBee communication network according to the preset parameters. The terminal nodes first join the network created by the coordinator, and then start to collect temperature data at regular intervals. The data packets are sent to the coordinator using the CC2530 wireless radio frequency module.

[0131] The coordinator receives temperature data from different terminal nodes and uploads it via serial port to a remote monitoring computer for processing and display. The program flowchart of the coordinator node is as follows: Figure 10 As shown in (a), the terminal node program flowchart is as follows: Figure 10 As shown in (b).

[0132] As a feasible implementation method, the switchgear thermal fault early warning algorithm based on BP neural network addresses the issue that there is no linear relationship between the load current and ambient temperature of the switchgear and the switchgear temperature value, making it difficult to establish an accurate mathematical model. A neural network can be viewed as a nonlinear function, with the network's input and predicted values ​​being the independent and dependent variables, respectively. When the number of input nodes is n and the number of output nodes is m, the neural network can express the functional mapping relationship from n independent variables to m dependent variables. This invention utilizes the ability of neural networks to solve complex nonlinear problems to establish a normal switchgear temperature prediction model. A BP neural network is selected to construct the normal switchgear temperature function mapping relationship, and the data normalization method uses the minimax method. Its functional form is: In the formula, x max x min These are the maximum and minimum values ​​of the data sequence, respectively.

[0133] The BP network is selected as a three-layer structure. The inputs are ambient temperature, real-time temperature of the equipment monitoring point and load current, respectively. The output is the predicted temperature. The number of nodes in the hidden layer is selected as 5 based on experience. The node transfer function is the tansig function: y = 2 / [1+exp(-2x)]-1.

[0134] This invention uses 100 sets of data collected on-site as samples to construct the network. From these, 90 sets of data are randomly selected as training data to train the network, and 10 sets of data are used as test data to test the accuracy of the final network. The comparison between the predicted values ​​and actual detection values ​​of the BP neural network is shown in the figure below. Figure 11 As shown, the results indicate that the BP neural network can predict the temperature of the switchgear, meeting the requirements for thermal fault early warning.

[0135] In summary, the switchgear temperature monitoring and thermal fault early warning system based on ZigBee and BP neural network technology of the present invention can monitor multiple areas of multiple switchgears simultaneously, provide early warning of potential joint thermal faults, predict potential faults, and prevent safety faults caused by abnormal temperature rise.

[0136] This invention relates to an intelligent automated operation monitoring and early warning system for 10kV switchgear. In use, this invention integrates temperature, humidity, thermal imaging, and electrical quantities (voltage, current, etc.) into a single system, achieving multi-parameter fusion monitoring. This overcomes the shortcomings of traditional devices, which often have limited functionality and only partial monitoring capabilities, providing a more comprehensive and accurate picture of the operating status. By monitoring environmental parameters such as temperature and humidity inside the switchgear in real time, this invention can promptly detect potential safety hazards, such as high temperature, high humidity, and smoke, preventing accidents such as fires and equipment damage. It also avoids production delays and economic losses caused by equipment failures, as well as maintenance costs incurred due to backup failures. This invention enables remote monitoring and early warning, effectively reducing the frequency of manual inspections, preventing major equipment damage, shortening power outage time, and optimizing equipment operating efficiency. Through real-time monitoring of the switchgear's internal environment, equipment operating parameters can be adjusted according to environmental changes, improving equipment operating efficiency and energy utilization. This invention offers the advantages of reducing maintenance costs, improving equipment operating efficiency, timely detection of potential safety hazards, and enabling remote monitoring and early warning.

[0137] Example 3

[0138] An electronic device includes a processor, a memory, a user interface, and a network interface. The memory stores computer programs / instructions, and the user interface and network interface are used for communication with other devices. When the computer programs / instructions are executed by the processor, the electronic device performs the 10kV switchgear intelligent automated operation monitoring and early warning method as described above.

[0139] As one possible implementation, the user interface may include a display screen and a camera. Optional user interfaces may also include standard wired interfaces and wireless interfaces. Network interfaces may optionally include standard wired interfaces and wireless interfaces (such as Wi-Fi interfaces).

[0140] As one possible implementation, a bus may also be included, which is used to connect the components.

[0141] The memory stores computer-executable programs / instructions; the processor executes the computer-executable programs / instructions stored in the memory.

[0142] The memory and processor are electrically connected directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines, such as bus connections. The memory stores computer-executable programs / instructions that implement data access control methods, including at least one software functional module that can be stored in the memory in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory.

[0143] The memory can be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), etc.; wherein, the memory is used to store programs, and the processor executes the programs / instructions after receiving them; furthermore, the software programs and modules in the aforementioned memory may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and can communicate with various hardware or software components to provide an operating environment for other software components.

[0144] The processor can be an integrated circuit chip with signal processing capabilities; the processor mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can implement or execute the methods disclosed in the embodiments of this invention; the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0145] As a specific implementation method, the processor can be implemented using at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor can integrate one or a combination of several of the following: central processing unit (CPU), graphics processing unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem can also be implemented as a separate chip without being integrated into the processor.

[0146] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0147] Example 4

[0148] A computer-readable storage medium stores a computer program / instruction, which, when executed by a processor, implements the 10kV switchgear intelligent automated operation monitoring and early warning method as described above.

[0149] The computer-readable storage medium is any available medium that a computing device can store, or a data storage device such as a server or data center that integrates one or more available media.

[0150] The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives).

[0151] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware related to program instructions. The aforementioned program / instructions can be stored in a computer-readable storage medium. When executed, the program / instructions perform the steps of the above method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for intelligent automated operation monitoring and early warning of 10kV switchgear, characterized in that: The specific steps of the method are as follows: Step 1: Collect partial discharge data from key components, including acoustic signals, instantaneous pulse current signals, and high-frequency electromagnetic wave signals; Step 2: Perform data processing to obtain the data values ​​of partial discharge anomaly points in various key areas; Step 3: Employ a fault early warning method based on switchgear current and acoustic anomaly data to achieve partial discharge early warning for switchgear; Step 4: Collect the temperature of each key component and the ambient temperature; Step 5: Perform data processing to obtain the relationship function between temperature rise and current for each key component; Step 6: Establish a dynamic early warning model for the switchgear to achieve dynamic temperature rise early warning; Step 7: When the number of abnormal points occurring in each key part within a period reaches or exceeds the threshold, a multi-point red warning is triggered; or if the number of abnormal points occurring in each key part within a period does not reach the threshold, but the abnormal value points and the first occurrence of abnormal value points in at least one key part during a non-high frequency occurrence period both reach or exceed the corresponding threshold, a single-point orange warning signal is triggered. A yellow warning signal is triggered when the temperature rise of any critical component or at least one critical component reaches or exceeds the corresponding threshold.

2. The intelligent automated operation monitoring and early warning method for 10kV switchgear as described in claim 1, characterized in that: The fault early warning method based on switch cabinet current and acoustic anomaly data in step 3 includes the following steps: Step 3.1: Outlier value acquisition and update: This includes outlier value acquisition, outlier classification, and outlier update; Step 3.2: Fault warning based on anomalies: Based on the analysis results of the spatiotemporal patch map, the anomaly values ​​are comprehensively utilized. According to the spatiotemporal patch map of anomaly values, single-point warnings are made for anomaly values ​​in non-high frequency occurrence periods and for the first occurrence of anomaly values. By combining the frequency and the first occurrence of anomalies, timely warnings can be given for sudden situations. Step 3.3: Update the fault knowledge base: For early warnings and alarms caused by anomalies and faults that trigger maintenance and troubleshooting, record them in a timely manner and upload and update the fault warning rule pool to achieve dynamic operation and maintenance management of equipment; dynamically adjust the rules of the warning pool according to the characteristics of the fault occurrence and the fault data content uploaded manually, and combine the rules into feature values ​​of the fault feature library; when the warning content meets the matching content of the fault feature library, push the existing solutions in the fault knowledge base to the operation and maintenance personnel.

3. The intelligent automated operation monitoring and early warning method for 10kV switchgear as described in claim 2, characterized in that: The acquisition of outlier values ​​in step 3.1 is as follows: Plot a standard curve for the independent switchgear current, and construct the current value F from the standard curve. t,n , will F t,n Construct the latest standard curve by performing a connection; Calculate the real-time data of coarse abnormal phase currents corresponding to the standard curve at each time point; By comparing historical data with real-time abnormal data, we can obtain information on the frequency and time periods of abnormal data occurrence.

4. The intelligent automated operation monitoring and early warning method for 10kV switchgear as described in claim 3, characterized in that: The anomaly classification in step 3.1 is as follows: The current / acoustic anomalies of each station's switchgear are classified, and the anomaly situation within one cycle is described: S = {S1, S2, ..., S...} 14 In the formula, S represents the number of outliers occurring within one period; S1, S2, ..., S 14 This represents the number of outliers occurring on each day within a 14-day period. The first occurrence of an outlier is expressed as: S>0&{S1,S2,...,S 13 } = 0, and the other anomalies are: S > 0; the first anomaly can reflect the suddenness of the abnormal data, which is likely to be accidental and may cause significant damage to the equipment.

5. The intelligent automated operation monitoring and early warning method for 10kV switchgear as described in claim 4, characterized in that: The switchgear dynamic early warning model in step 6 is as follows: based on the temperature rise data of the healthy switchgear, a functional relationship is established between the temperature of the monitoring point and the main circuit current and energizing time; when an early warning is issued, the system uses the current and energizing time obtained from online monitoring, combined with the functional relationship, to calculate the temperature rise alarm threshold, and automatically judges whether there is a thermal defect fault at the monitoring point through the dynamically changing threshold.

6. The 10kV switchgear intelligent automated operation monitoring and early warning system as described in claim 1, characterized in that: The system includes an electrical data acquisition module, a data processing module, a data early warning platform, a temperature data acquisition module, a data transmission DTU module, an indicator monitoring and early warning module, and data reporting and visualization components; the system is used to execute the 10kV switchgear intelligent automated operation monitoring and early warning method as described in any one of claims 1-5; The electrical data acquisition module is used to collect partial discharge data information from various key parts, including acoustic signals, instantaneous pulse current signals, and high-frequency electromagnetic wave signals. The data processing module is used to process data and obtain the data values ​​of partial discharge anomaly points in various key parts. The data early warning platform is used to implement partial discharge early warning of switchgear by adopting a fault early warning method based on switchgear current and acoustic abnormality point data; The temperature data acquisition module is used to collect the temperature of various key components and the ambient temperature. The data transmission DTU module is used to process data and obtain the temperature rise of each key component as a function of current. The indicator monitoring and early warning module is used to establish a dynamic early warning model for the switchgear and realize dynamic temperature rise early warning. The data report and visualization components are used to trigger a multi-point red warning when the number of abnormal points occurring in each key part within a period reaches or exceeds the threshold; or to trigger a single-point orange warning signal when the number of abnormal points occurring in each key part within a period does not reach the threshold, but the abnormal value points and the first occurrence of abnormal value points in at least one key part during a non-high frequency occurrence period both reach or exceed the corresponding threshold. It is also used to trigger a yellow warning signal when the temperature rise of each critical part or at least one critical part reaches or exceeds the corresponding threshold.

7. The 10kV switchgear intelligent automated operation monitoring and early warning system as described in claim 6, characterized in that: The electrical data acquisition module includes an ultrasonic detection system and an ultra-high frequency (UHF) detection system. The ultrasonic detection system includes an ultrasonic sensor, and the UHF detection system includes an UHF sensor. Both the ultrasonic detection system and the UHF detection system include a data acquisition unit, a data processing unit, a display unit, a control unit, and a charging unit.

8. The 10kV switchgear intelligent automated operation monitoring and early warning system as described in claim 6, characterized in that: The temperature data acquisition module includes an environmental parameter acquisition module, a thermal imaging acquisition module, and a wireless temperature monitoring terminal; the wireless temperature monitoring terminal includes a temperature sensor, an MCU, a ZigBee module, and a power supply module.

9. The 10kV switchgear intelligent automated operation monitoring and early warning system as described in claim 8, characterized in that: Multiple wireless temperature monitoring terminals interconnect with each other using ZigBee modules and send the data to a remote monitoring and diagnostic host computer. A temperature prediction model based on a BP neural network is established, forming a wireless temperature and humidity monitoring and thermal fault diagnosis system based on ZigBee and BP neural network, which enables accurate early warning of thermal faults. The wireless temperature and humidity monitoring and thermal fault diagnosis system consists of at least one wireless temperature monitoring terminal, at least one router, at least one coordinator, and a remote monitoring and diagnosis host computer.

10. A computer-readable storage medium storing a computer program / instructions, characterized in that: When the computer program / instruction is executed by the processor, it implements the 10kV switchgear intelligent automated operation monitoring and early warning method as described in any one of claims 1-5.

Images