Switch cabinet maintenance auxiliary system and method and switch cabinet

Abstract

The invention relates to the field of power equipment maintenance, and discloses a switch cabinet maintenance auxiliary system and method and a switch cabinet, the switch cabinet maintenance auxiliary system comprises a sensor network module used for collecting operation data in the switch cabinet in real time, the operation data comprises environment parameters and electrical parameters, and the invention also discloses a switch cabinet maintenance auxiliary method. Comprising the following steps that S1, a sensor network module collects operation data in a switch cabinet in real time and transmits the operation data to an intelligent analysis module; the invention also discloses a switch cabinet which comprises the switch cabinet maintenance auxiliary system. Through real-time monitoring of the sensor network module and deep diagnosis capability of the intelligent analysis module, early detection of potential faults is realized, a deep neural network technology and a self-learning mechanism are combined, complex faults are accurately diagnosed, the system adapts to variable operation environments, and meanwhile, through a standardized pre-arranged plan library of the remote monitoring and emergency response module, the real-time monitoring and emergency response of the system are realized. And fault alarm, isolation and load adjustment are automatically completed.

Description

Technical Field

[0001] The present invention relates to the field of power equipment maintenance, and in particular to a switch cabinet maintenance auxiliary system, method and switch cabinet. Background Art

[0002] As core power distribution and protection equipment in power systems, switchgear's operating status directly impacts the overall safety and reliability of the power grid. However, traditional switchgear designs lack effective intelligent diagnostic capabilities and maintenance methods, exposing numerous problems in the increasingly complex modern power system. During switchgear operation, various factors, such as environmental conditions, load fluctuations, and aging electrical components, can directly impact the equipment's status and even cause faults such as overheating, insulation degradation, or partial discharge. If these faults are not detected and addressed promptly, they could escalate into major equipment failures, threatening the normal operation of the power grid.

[0003] Currently, switchgear maintenance and repairs mostly rely on manual inspections or periodic equipment testing. This traditional model has significant limitations. Manual inspections rely heavily on the experience of operators, resulting in low efficiency and subjectivity. For example, latent faults (such as gradual deterioration of insulation performance) often have no obvious external manifestations in the early stages, making it difficult to detect potential risks through manual inspections. Furthermore, while periodic inspections can alleviate this problem to some extent through regular checks, the intervals between inspections are often long, and unpredictable, sudden faults may occur during these intervals. This passive maintenance approach can easily lead to the accumulation of hidden problems.

[0004] Furthermore, traditional manual inspection models exhibit significant shortcomings when faced with complex operating conditions. For example, when equipment operates in complex environments and loads fluctuate frequently, maintenance personnel may be unable to promptly analyze subtle anomalies in operating parameters, missing the optimal opportunity for early intervention. Furthermore, manual inspections are often limited in scope and depth, making it difficult to quickly and accurately identify critical issues such as dynamic changes in partial discharge signals or abnormal temperature rises using the naked eye or simple tools. This model cannot meet the high reliability and rapid response requirements of modern power grids for switchgear.

[0005] Overall, current switchgear maintenance and fault detection methods have the following main problems: First, detection methods lag behind and rely too much on manual judgment, making it difficult to detect potential hidden dangers in a timely manner; second, the periodic detection mode cannot continuously and in real time monitor the equipment status, which easily leads to delayed response to sudden failures; finally, the traditional manual detection mode lacks systematic analysis capabilities for operating conditions in complex environments, resulting in incomplete hidden danger detection and even missed detections. Against this backdrop, there is an urgent need for an intelligent switchgear maintenance assistance system that can compensate for the shortcomings of the traditional model through real-time monitoring, intelligent analysis, and rapid response functions, thereby improving equipment operation reliability and maintenance efficiency. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides a switch cabinet maintenance auxiliary system, method and switch cabinet, which solves the problems that traditional switch cabinets rely on manual inspections and periodic inspections, resulting in difficulty in timely detection of hidden faults, low maintenance efficiency and inability to adapt to complex operating environments.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a switch cabinet maintenance auxiliary system, comprising: a sensor network module, which is used to collect operating data in the switch cabinet in real time, the operating data including environmental parameters and electrical parameters, wherein the environmental parameters include temperature and humidity, and the electrical parameters include current, voltage, and partial discharge signals; An intelligent analysis module, which is in communication with the sensor network module and is used to receive and process the operating data, and perform pre-processing, fault detection, risk assessment and diagnosis on the data; Remote monitoring and emergency response module, which is connected to the intelligent analysis module and is used to display the operating status of the switchgear, receive alarm signals and trigger emergency response operations; Among them, the intelligent analysis module identifies potential faults based on the received operating data through anomaly detection methods, and generates alarm signals and fault risk levels according to the risk assessment results. The remote monitoring and emergency response module performs isolation, load adjustment and rapid recovery operations according to the risk level.

[0008] Preferably, the sensor network module includes: Temperature and humidity sensor, which is used to collect environmental temperature and humidity parameters; Current transformer, which is used to monitor the current signals of each circuit of the switch cabinet; A partial discharge sensor, which is used to collect partial discharge signals; Infrared thermal imaging equipment is used to obtain the temperature distribution of key components.

[0009] Preferably, the intelligent analysis module includes: A data preprocessing unit, which is used to denoise and normalize the collected data; A fault detection unit, which is used to extract multi-dimensional features from environmental data and electrical parameters and identify the fault type through a diagnostic model; The risk assessment unit is used to perform a comprehensive risk score on the detected faults according to the feature weights to generate a fault risk level.

[0010] Preferably, the remote monitoring and emergency response module includes: Visual display unit, which is used to display operating status, fault location and alarm signals; An emergency plan execution unit, which is used to automatically perform isolation operations, load adjustment or enable backup power supply according to the fault risk level; a communication interface, which is used to complete instruction transmission and execution.

[0011] The auxiliary method for switch cabinet maintenance includes the following steps: S1. The sensor network module collects the operating data in the switch cabinet in real time and transmits the operating data to the intelligent analysis module; S2, the intelligent analysis module pre-processes the received data, including data denoising and normalization; S3, the intelligent analysis module performs fault detection on the pre-processed data, identifies abnormal conditions and determines whether there are potential faults; S4. The intelligent analysis module performs risk assessment on the fault, generates a risk level, and sends an alarm signal to the remote monitoring and emergency response module; S5, the remote monitoring and emergency response module executes emergency plans based on risk levels, including power outage isolation, load adjustment, and rapid recovery operations; S6. Generate and store fault reports for operation and maintenance analysis Preferably, the fault detection step in step S3 includes: Monitor temperature increments and compare them with preset thresholds to determine if there is overheating. Calculate the effective value of current and voltage, and judge electrical parameter abnormalities based on power factor changes; Analyze the amplitude and frequency of partial discharge signals to identify partial discharge anomalies.

[0012] Preferably, the step of executing the emergency plan in step S5 includes: Select and activate pre-set emergency plans based on risk levels; Automatically cut off power and isolate the fault point; Adjust load distribution to ensure continuity of grid power supply; Generate a detailed fault handling report and transmit it to the remote operation and maintenance terminal.

[0013] A switch cabinet, comprising: The switch cabinet maintenance auxiliary system, wherein: The temperature and humidity sensors in the sensor network module are installed on the inner wall of the cabinet, the current transformer and voltage transformer are installed at the loop respectively, the partial discharge sensor is arranged at the busbar joint and cable terminal, the infrared thermal imaging device is embedded in the inner side of the cabinet door panel, and the remote monitoring and emergency response module is connected to the switch cabinet control unit through a communication interface to trigger power-off isolation, load adjustment and rapid recovery operations.

[0014] The present invention provides a switch cabinet maintenance auxiliary system, method and switch cabinet, which have the following beneficial effects: 1. The present invention uses a sensor network module to monitor the environmental and electrical parameters inside the switch cabinet in real time, and combines it with the deep diagnostic capabilities of the intelligent analysis module to achieve the technical effect of early detection of potential faults. Compared with the existing methods that rely on manual inspections and fixed-cycle detection, the present invention effectively solves the problems of low detection efficiency and high misjudgment rate of traditional methods, greatly improves the accuracy of fault prediction, and reduces unplanned downtime caused by hidden faults.

[0015] 2. The present invention introduces deep neural network technology to extract multi-dimensional data features and classify faults, and combines it with a self-learning mechanism to dynamically optimize the diagnostic model, thereby achieving the technical effect of accurately diagnosing complex fault modes and adapting to changes in the operating environment. Compared with the static threshold judgment method in the existing technology, the present invention solves the shortcomings of traditional solutions that are difficult to deal with new faults and complex operating conditions, and ensures the stable operation and efficient diagnostic capabilities of the system in changing scenarios.

[0016] 3. The present invention builds a standardized emergency plan library through remote monitoring and emergency response modules, realizes an automated processing flow from fault alarm to rapid isolation and load adjustment, and achieves the technical effect of shortening fault response time and improving power grid operation reliability. Compared with the emergency handling method that relies on manual decision-making and operation in the existing technology, the present invention solves the problems of long response time and high operational inconsistency, and significantly improves the safety of switchgear in high-risk environments and the operation and maintenance efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a system framework diagram of the present invention; Figure 2 This is a sensor network module framework diagram of the present invention; Figure 3 This is a framework diagram of the intelligent analysis module of the present invention; Figure 4 This is a framework diagram of the remote monitoring and emergency response module of the present invention; Figure 5 is a flow chart of the method of the present invention; Figure 6 It is a front view of the cabinet of the present invention; Figure 7 It is a side perspective view of the cabinet of the present invention.

[0018] Among them, 1. Cabinet. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Example 1: Please see the attached Figure 1 , an embodiment of the present invention provides a switch cabinet maintenance auxiliary system, comprising: A sensor network module is used to collect real-time operating data within the switchgear. The operating data includes environmental parameters such as temperature and humidity, and electrical parameters such as current, voltage, and partial discharge signals. Please see the attached Figure 2 In this embodiment, the sensor network module includes the following parts: Temperature and humidity sensors are used to collect the ambient temperature and humidity parameters of the switch cabinet in real time.

[0021] Specifically, the temperature and humidity sensor is installed on the inner wall of the switch cabinet to ensure that it can accurately reflect the real-time changes in the environmental conditions inside the switch cabinet. In some embodiments, the temperature and humidity sensor is connected to the intelligent analysis module via wireless communication. In general, temperature and humidity data can be used to identify the potential impact of environmental changes on equipment operation. For example, under high humidity conditions, insulation performance may be reduced, causing problems such as partial discharge. As an option, the sampling frequency of temperature and humidity can be set to 1Hz to meet the needs of real-time monitoring. The collected data will be transmitted to the intelligent analysis module after preliminary filtering for further processing.

[0022] Current transformers and voltage transformers are used to monitor the current and voltage signals of each circuit in the switchgear in real time.

[0023] Specifically, these transformers are installed on the circuits of the switchgear and can capture instantaneous current and voltage fluctuations in each circuit. In some embodiments, the output signals of the current transformer and voltage transformer are used by the intelligent analysis module to calculate the effective value and power factor to determine whether the changes in electrical parameters exceed the safety threshold. For example, the formula for calculating the effective value of current is as follows: Among them, I rms Indicates the effective value of the current, N indicates the number of sampling points, l i Represents the current value at the i-th sampling point. Similarly, the calculation formula for the effective value of voltage is: In one possible implementation, the power factor cosφ can be calculated by combining the current and voltage rms values: Among them, P is active power, which means the actual electric power consumed by the load, V rms ,I rms are the effective values of voltage and current respectively, cosφ is the power factor, which indicates the proportion of actual active power in the total power. It has no unit and ranges from [0,1].

[0024] Changes in power factor can reflect changes in load characteristics and operating conditions. If it deviates from the preset range, there may be a risk of failure. As an option, the transformer supports a high-frequency sampling mode to capture short-term fluctuations.

[0025] Partial discharge sensors are used to collect partial discharge signals from key components within switchgear. Generally, collecting partial discharge signals is important for identifying the insulation status of electrical equipment. Partial discharge sensors are installed at busbar joints and cable terminals, which are high-risk areas for discharge. In some embodiments, partial discharge signals are captured in the form of pulses, specifically including the discharge amplitude Q. pd and frequency f pd In one possible implementation, the amplitude of the partial discharge signal can be calculated using the following formula: Among them, Q pd represents the amplitude of partial discharge, i(t) represents the partial discharge current signal, t1 and t2 are the time points when the discharge starts and ends, respectively.

[0026] The calculation formula for discharge frequency is: Among them, N pd Indicates the number of discharges per unit time, T indicates the monitoring time interval, f pd is the partial discharge frequency, which indicates the number of discharges per unit time, in Hertz.

[0027] Optionally, the discharge data is analyzed and compared with historical data to determine discharge trends and their severity.

[0028] Infrared thermal imaging equipment is used to obtain the temperature distribution of key components of the switchgear in real time.

[0029] Typically, infrared thermal imaging devices are embedded inside switchgear door panels and can monitor the temperature of conductor connectors, insulation components, and other components within the switchgear. In some embodiments, the thermal imaging device captures the temperature distribution within the switchgear in a timed manner and transmits the image data to an intelligent analysis module via a wireless communication module. Specifically, thermal imaging devices are primarily used to identify localized temperature rise anomalies, such as overheated connectors or aging insulation materials. Optionally, multiple temperature alarm thresholds can be set for the thermal imaging device to distinguish between normal operation, warning levels, and severe fault levels.

[0030] In one possible implementation, all sensors in the sensor network module connect to the intelligent analysis module via a unified communication protocol, such as ZigBee or LoRa. This network architecture generally ensures real-time and reliable data transmission while avoiding physical interference caused by excessive wiring.

[0031] Through the design of this sensor network module, the environmental and electrical conditions within the switchgear can be comprehensively and real-time monitored, providing high-quality basic data support for subsequent fault diagnosis and risk assessment. In another expansion implementation, the sensor network module can also be adapted to other types of sensors, such as vibration sensors, to monitor the mechanical status of operating equipment, further enhancing the functionality of the system.

[0032] An intelligent analysis module, which is in communication with the sensor network module and is used to receive and process operating data, perform data pre-processing, fault detection, risk assessment and diagnosis; Please see the attached Figure 3 , the intelligent analysis module includes: A data preprocessing unit, which is used to denoise and normalize the collected data; A fault detection unit, which is used to extract multi-dimensional features from environmental data and electrical parameters and identify the fault type through a diagnostic model; The risk assessment unit is used to perform a comprehensive risk score on the detected faults according to the feature weights to generate a fault risk level.

[0033] Specifically, in this embodiment, the data preprocessing unit is used to receive real-time data from the sensor network module and perform denoising and normalization processing on the data to ensure the accuracy and stability of subsequent analysis.

[0034] The goal of denoising is to eliminate high-frequency noise interference in sensor signals, which is achieved using a sliding mean filter algorithm. Specifically, the formula for calculating the filtered data is as follows: Where: x filtered (t) is the signal value at time t after filtering; x(ti) is the original signal value at the sampling time; N is the size of the sliding window.

[0035] Alternatively, in some embodiments, the window size N can be dynamically adjusted based on the noise characteristics of the collected data. For example, when the noise amplitude is high, the window size can be increased to improve the filtering effect; while for data with sudden and rapid changes (such as current and voltage), a smaller window size can be selected to avoid signal delays.

[0036] The purpose of normalization is to unify the dimensions of different data dimensions so that different types of sensor data can be processed comprehensively in the same model. In general, the normalization method uses the following formula: Where: x norm is the normalized data value; x is the original data; x min 、x max are the minimum and maximum values of the data respectively.

[0037] In one possible implementation, the minimum and maximum values for normalization can be dynamically adjusted based on historical operating data. For example, for current data, if historical data indicates that the current range of a circuit is typically 0 to 500A, this range can be used as the upper and lower limits for normalization to prevent extreme values from affecting the normalization results.

[0038] In this embodiment, the fault detection unit analyzes environmental data and electrical parameters through multi-dimensional feature extraction and a fault diagnosis model to identify potential fault types and fault locations.

[0039] Specifically, multidimensional feature extraction includes the following: For temperature data, calculate the temperature increment of key components: ΔT=T current -T baseline Where: T current is the current temperature; T baseline The historical benchmark temperature.

[0040] For current and voltage data, calculate their real-time effective values using the following formula: Where: I rms 、V rms is the effective value of current and voltage; l i 、V i is the instantaneous value of the sample; N is the number of sampling points.

[0041] For partial discharge signals, extract the discharge amplitude and frequency characteristics. The calculation formula for the partial discharge amplitude is: Where: Q pd represents the amplitude of the partial discharge, i(t) represents the partial discharge current signal, and t1 and t2 are the time points of the start and end of the discharge respectively.

[0042] Through the above feature extraction, the fault detection unit inputs the key features into a pre-trained diagnostic model to determine the fault type. Generally, the diagnostic model is implemented using a deep neural network, and its core formula is: Where: y is the fault type output by the model; x i is the i-th input feature value; w i is the corresponding feature weight; b is the bias term; f is the activation function.

[0043] In a possible implementation, the output of the diagnostic model includes fault types such as overheating abnormality, electrical parameter abnormality, and partial discharge abnormality.

[0044] In this embodiment, the risk assessment unit calculates the comprehensive risk score and generates a risk level based on the detected fault features and their weights.

[0045] The risk score is calculated using a weighted method, and its formula is: Where: R f is the comprehensive risk score; w i is the weight value of the i-th fault feature; F i is the normalized value of the i-th fault feature; n is the total number of fault features.

[0046] Generally, the feature weight w i is preset according to the importance of the feature by expert experience or a machine learning model. For example, if temperature abnormality contributes more to the system risk in a specific scenario, a higher weight can be assigned.

[0047] As an option, the risk assessment unit divides the risk score into different levels, for example: When R f < T1, it is a low risk; When T1 ≤ R f < T2, it is a medium risk; When R f ≥ T2, it is a high risk.

[0048] In one possible implementation, the risk assessment unit outputs a risk level and corresponding action recommendations. For example, for high-risk events, the system might recommend an immediate power outage and manual inspection; for low-risk events, continuous monitoring might be implemented.

[0049] Remote monitoring and emergency response module, which is connected to the intelligent analysis module and is used to display the operating status of the switchgear, receive alarm signals and trigger emergency response operations; Please see the attached Figure 4 , the remote monitoring and emergency response module includes: Visual display unit, which is used to display operating status, fault location and alarm signals; An emergency plan execution unit, which is used to automatically perform isolation operations, load adjustment or enable backup power supply according to the fault risk level; a communication interface, which is used to complete instruction transmission and execution.

[0050] Specifically, the remote monitoring and emergency response module is the terminal module of this invention. It primarily communicates with the intelligent analysis module, receives analysis results, displays the operating status of the switchgear, and executes automated emergency response operations based on the fault risk level. This module intuitively presents the output of the intelligent analysis module to operation and maintenance personnel, and combines it with the system's built-in emergency handling functions to achieve rapid response and precise handling.

[0051] Typically, the remote monitoring and emergency response module receives real-time operational data, fault diagnosis results, and risk assessment levels from the intelligent analysis module via a communication interface, and parses, displays, and processes this information. To ensure efficient and stable system operation, this module integrates a visual display unit, an emergency plan execution unit, and a communication interface to achieve comprehensive integration of monitoring, decision-making, and operations.

[0052] In this embodiment, the visual display unit is used to intuitively display the switchgear's operating status, fault diagnosis information, and alarm signals on the operation and maintenance terminal. Generally, the interface design of the visual display unit includes the following main contents: Operating status monitoring: Displaying key operating parameters within the switchgear, including dynamic data such as temperature, current, voltage, and humidity.

[0053] Fault location indication: When the intelligent analysis module detects a fault, the location of the faulty component, such as busbar connectors, cable terminals or switch contacts, is visually marked through the interface.

[0054] Alarm signal display: When a fault is identified or the risk level reaches the warning threshold, the interface will display the alarm information in real time, including the alarm level, fault type, fault occurrence time and recommended treatment measures.

[0055] Specifically, in some embodiments, the visual display unit presents operational status data using dynamic charts or heat maps. For example, if the busbar joint temperature rises abnormally, the interface will highlight the relevant area in red and issue an alarm. Furthermore, the alarm signal can be communicated to maintenance personnel via audio, text message, or app notification, ensuring timely information delivery.

[0056] In this embodiment, the emergency plan execution unit automatically matches the preset emergency treatment plan according to the fault risk level and the diagnosis result, and sends instructions to the execution agency through the communication interface to complete the isolation operation, load adjustment or backup power activation.

[0057] Specifically, the functions of the emergency plan execution unit include: Isolation Operation: When a high-risk fault is detected, the emergency plan execution unit sends a power-off command to the circuit breaker control system through the communication interface to isolate the fault area and prevent the accident from expanding.

[0058] For example, when the temperature of a phase cable joint exceeds the threshold and is assessed as high risk, the system will immediately trigger an isolation operation to prevent the temperature rise from causing fire or equipment damage.

[0059] Load Regulation: If the fault does not affect the main power supply circuit, but there is an overload risk, the emergency plan execution unit will ensure the safe operation of the power supply system by adjusting the load distribution.

[0060] The specific calculation formula is: P new =P total -P fault Where: P new is the load power after adjustment; P total is the original power supply; P fault is the power in the fault area.

[0061] Backup power enabled: When a fault or power outage in the main power supply circuit is detected and the risk level is high, the system will automatically enable the backup power supply to ensure power supply continuity for critical equipment.

[0062] The activation process includes switching the backup power switch, adjusting the load distribution, and monitoring the operating status of the backup power supply in real time.

[0063] In one possible implementation, the emergency plan execution unit optimizes plan selection based on historical operating data. For example, for certain faults (such as local overload), the system will prioritize load adjustment rather than directly triggering power outages and isolation, thereby minimizing impacts on the entire power supply system.

[0064] In this embodiment, the communication interface is used to achieve efficient transmission and execution of instructions. Generally, the communication interface establishes a connection with the intelligent analysis module and the actuator through a wireless communication protocol (such as ZigBee, LoRa, 5G) to complete data reception and instruction transmission.

[0065] Specifically, the functions of the communication interface include: Data reception: Receive real-time operating data, fault diagnosis results and risk assessment levels sent by the intelligent analysis module.

[0066] Data transmission has the characteristics of low latency and high reliability, ensuring that the system can still operate stably under high load conditions.

[0067] Command sending: Send operating instructions to the actuator, including circuit breaker de-energization, load adjustment and backup power switching.

[0068] Through the built-in feedback mechanism, the command execution results can be confirmed and recorded in real time.

[0069] Remote Control: The communication interface allows remote operators to monitor and control the switchgear via mobile devices. For example, operators can manually trigger emergency response plans or modify risk assessment parameters remotely via a mobile app.

[0070] In some embodiments, the communication interface can also connect to a cloud platform, allowing operations personnel to view historical data and analyze reports. Furthermore, the communication interface supports collaborative communication between multiple devices. For example, in large-scale industrial scenarios, the operating status of multiple switchgear can be monitored simultaneously and centrally managed.

[0071] The remote monitoring and emergency response module is closely connected with the intelligent analysis module through the communication interface. Its working logic is as follows: First, after the intelligent analysis module completes data analysis and fault diagnosis, it sends the operating status data, alarm signals and risk assessment levels to the remote monitoring and emergency response module.

[0072] The visual display unit receives data and presents it in real time, including operating parameters, fault locations and alarm information.

[0073] When the risk level reaches warning or high risk, the emergency plan execution unit automatically calls the matching emergency response plan and sends operation instructions to the relevant execution agency through the communication interface.

[0074] The connection with other modules also includes the following aspects: The output of the intelligent analysis module is the risk assessment level and treatment suggestions, which provide a decision-making basis for triggering the emergency plan.

[0075] The executive agency completes specific operations according to the instructions sent by the emergency plan execution unit, and feeds back the execution results to the system through the communication interface.

[0076] Through the above design, the remote monitoring and emergency response module not only realizes comprehensive monitoring of fault status, but also significantly shortens fault response time through automated plan execution, effectively improving the safety and reliability of switchgear operation.

[0077] Among them, the intelligent analysis module identifies potential faults based on the received operating data through anomaly detection methods, and generates alarm signals and fault risk levels according to the risk assessment results. The remote monitoring and emergency response module performs isolation, load adjustment and rapid recovery operations according to the risk level.

[0078] Please see the attached Figure 5 , the switch cabinet maintenance auxiliary method includes the following steps: S1, the sensor network module collects the operating data in the switch cabinet in real time and transmits the operating data to the intelligent analysis module; S2, the intelligent analysis module pre-processes the received data, including data denoising and normalization; S3, the intelligent analysis module performs fault detection on the pre-processed data, identifies abnormal conditions and determines whether there are potential faults; S4. The intelligent analysis module performs risk assessment on the fault, generates a risk level, and sends an alarm signal to the remote monitoring and emergency response module; S5, the remote monitoring and emergency response module executes emergency plans based on risk levels, including power outage isolation, load adjustment, and rapid recovery operations; S6. Generate and store fault reports for operation and maintenance analysis.

[0079] The fault detection steps in step S3 include: Monitor temperature increments and compare them with preset thresholds to determine if there is overheating. Calculate the effective value of current and voltage, and judge electrical parameter abnormalities based on power factor changes; Analyze the amplitude and frequency of partial discharge signals to identify partial discharge anomalies.

[0080] The steps for executing the emergency plan in step S5 include: Select and activate pre-set emergency plans based on risk levels; Automatically cut off power and isolate the fault point; Adjust load distribution to ensure continuity of grid power supply; Generate a detailed fault handling report and transmit it to the remote operation and maintenance terminal.

[0081] Example 2: In this embodiment, the intelligent analysis module combines deep neural network technology to optimize fault detection. Generally, fault detection involves three stages: data feature extraction, classification model invocation, and fault assessment. Through these stages, the system can extract high-value features from raw data, identify complex fault patterns, and assess fault severity.

[0082] In one possible implementation, a deep neural network is designed as a multi-layered structure, with each layer extracting features tailored to specific data characteristics. Input data includes pre-processed temperature, humidity, current, voltage, and partial discharge signal amplitude and frequency. The model automatically identifies correlations between the data and, through nonlinear mapping, extracts the features that best reflect the fault state.

[0083] The specific process of feature extraction is as follows: Where: h i is the extracted eigenvalue; x t-j is the data point of the sensor at time tj; W ij is the convolution kernel weight; b i is the bias value; f is the activation function (such as ReLU).

[0084] In this embodiment, the feature values are mapped to the probability distribution of fault categories through the fully connected layer. Specifically, the Softmax function is used to output the probability of each fault category: Where: P(y=c|X) is the predicted probability of category c; z c is the score output of the model for category c; C is the total number of fault types.

[0085] In some embodiments, the fault categories may include overheating anomalies, short circuit faults, partial discharge faults, etc. In addition, the model can evaluate the severity of the detection results to provide data support for subsequent risk assessment.

[0086] The self-learning mechanism further optimizes detection accuracy. Specifically, after each fault is handled, the system automatically stores the input data and actual results of the new fault and adds them to the model's training data set. Through incremental learning, the system dynamically adjusts the model weights according to the following formula: Where: w t is the current model parameter; η is the learning rate; L is the loss function, which represents the difference between the predicted result and the actual result.

[0087] In this embodiment, the remote monitoring and emergency response module improves the speed and reliability of emergency response by introducing an automated emergency plan library. Generally, the system selects a matching emergency plan based on the risk level, covering the entire process from alarm triggering to power restoration.

[0088] The emergency plan library has built-in standardized processing procedures for different types and risk levels of failures. Specifically: For low-risk faults, the system only records fault information and continuously monitors it.

[0089] For medium-risk faults, load adjustment is prioritized to balance the power supply pressure.

[0090] For high-risk faults, the system directly triggers power-off isolation operations and simultaneously starts the backup power supply to maintain the operation of critical equipment.

[0091] In one possible implementation, when the intelligent analysis module generates a risk level R f After that, the system first retrieves the corresponding processing flow from the plan library. Then, the remote monitoring module automatically issues an execution instruction, triggering the circuit breaker or backup power switch through the communication interface.

[0092] Fast fault isolation is implemented as follows: The system sends instructions to the circuit breaker through the communication interface to cut off the power supply to the fault circuit.

[0093] The system then redistributes the load, calculated as: P new =P total -P fault Where: P new is the total load after adjustment; P total is the original power supply; P fault is the power in the fault area.

[0094] When the backup power supply is activated, the system prioritizes ensuring the continuity of power supply to important circuits. As an option, the switching conditions for the backup power supply include triggering a main power failure signal and insufficient power to the critical load.

[0095] The emergency plan library features dynamic updates. For example, if the same type of fault occurs multiple times, the system will optimize the plan's processing steps and priorities to improve the efficiency of subsequent fault handling.

[0096] In this embodiment, the system supports coordinated response to address scenarios where multiple switchgear cabinets experience simultaneous failures. Generally, the system prioritizes faults by level, prioritizing high-risk failures. Furthermore, the system dynamically adjusts power distribution based on network load to prevent local failures from impacting global power supply.

[0097] For example, when two switchgears simultaneously detect a high-risk fault, the system prioritizes isolating the fault point with the highest current, then redistributes the load and gradually restores lower-priority fault areas.

[0098] By introducing deep neural network technology, the accuracy and comprehensiveness of fault detection have been significantly improved. The model automatically performs multi-dimensional feature extraction, fault classification, and severity assessment, seamlessly integrating with the existing intelligent analysis module. Furthermore, a built-in self-learning mechanism ensures that the model can dynamically adapt to changes in the operating environment.

[0099] The automated emergency plan library expands the functionality of the remote monitoring module, enabling it to quickly match the processing flow after the detection results are generated. By standardizing the plan management, the system effectively shortens the response time and reduces the need for human intervention.

[0100] This optimized method further improves the intelligence and reliability of the system while maintaining the clear logic of the original steps, providing a strong guarantee for the safe operation of the switchgear.

[0101] The switch cabinet described below and the switch cabinet maintenance auxiliary system described above can be referred to in correspondence with each other.

[0102] Please see the attached Figure 6 -Attached Figure 7 , a switch cabinet, comprising: Switchgear maintenance auxiliary system, including: The temperature and humidity sensors in the sensor network module are installed on the inner wall of cabinet 1, the current transformer and voltage transformer are installed at the loop respectively, the partial discharge sensor is arranged at the busbar joint and cable terminal, and the infrared thermal imaging device is embedded in the inner side of the door panel of cabinet 1. The remote monitoring and emergency response module is connected to the switch cabinet control unit through the communication interface to trigger power-off isolation, load adjustment and rapid recovery operations.

[0103] The switch cabinet device of this embodiment can be used to execute the above-mentioned method embodiment and system embodiment. Its principles and technical effects are similar and will not be described in detail here.

[0104] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The switch cabinet maintenance auxiliary system is characterized by: include: A sensor network module for collecting real-time operating data within the switch cabinet, the operating data including environmental parameters such as temperature and humidity and electrical parameters such as current, voltage, and partial discharge signals; An intelligent analysis module, which is in communication with the sensor network module and is used to receive and process the operating data, and perform pre-processing, fault detection, risk assessment and diagnosis on the data; Remote monitoring and emergency response module, which is connected to the intelligent analysis module and is used to display the operating status of the switchgear, receive alarm signals and trigger emergency response operations; Among them, the intelligent analysis module identifies potential faults based on the received operating data through anomaly detection methods, and generates alarm signals and fault risk levels according to the risk assessment results. The remote monitoring and emergency response module performs isolation, load adjustment and rapid recovery operations according to the risk level.

2. The switch cabinet maintenance auxiliary system according to claim 1, characterized in that: The sensor network module includes: Temperature and humidity sensor, which is used to collect environmental temperature and humidity parameters; Current transformer, which is used to monitor the current signals of each circuit of the switch cabinet; Voltage transformer, which is used to monitor the voltage signals of each circuit of the switchgear; A partial discharge sensor, which is used to collect partial discharge signals; Infrared thermal imaging equipment is used to obtain the temperature distribution of key components.

3. The switch cabinet maintenance auxiliary system according to claim 1, characterized in that: The intelligent analysis module includes: A data preprocessing unit, which is used to denoise and normalize the collected data; A fault detection unit, which is used to extract multi-dimensional features from environmental data and electrical parameters and identify the fault type through a diagnostic model; The risk assessment unit is used to perform a comprehensive risk score on the detected faults according to the feature weights to generate a fault risk level.

4. The switch cabinet maintenance auxiliary system according to claim 1, characterized in that: The remote monitoring and emergency response module includes: Visual display unit, which is used to display operating status, fault location and alarm signals; An emergency plan execution unit, which is used to automatically perform isolation operations, load adjustment, or enable backup power supply according to the fault risk level; Communication interface, which is used to complete instruction transmission and execution.

5. A switch cabinet maintenance auxiliary method, characterized in that: The following steps are involved: S1. The sensor network module collects the operating data in the switch cabinet in real time and transmits the operating data to the intelligent analysis module; S2, the intelligent analysis module pre-processes the received data, including data denoising and normalization; S3, the intelligent analysis module performs fault detection on the pre-processed data, identifies abnormal conditions and determines whether there are potential faults; S4. The intelligent analysis module performs risk assessment on the fault, generates a risk level, and sends an alarm signal to the remote monitoring and emergency response module; S5, the remote monitoring and emergency response module executes emergency plans based on risk levels, including power outage isolation, load adjustment, and rapid recovery operations; S6. Generate and store fault reports for operation and maintenance analysis.

6. The switch cabinet maintenance auxiliary method according to claim 5, characterized in that: The fault detection step in step S3 includes: Monitor temperature increments and compare them with preset thresholds to determine if there is overheating. Calculate the effective value of current and voltage, and judge electrical parameter abnormalities based on power factor changes; Analyze the amplitude and frequency of partial discharge signals to identify partial discharge anomalies.

7. The switch cabinet maintenance auxiliary method according to claim 5, characterized in that: The steps of executing the emergency plan in step S5 include: Select and activate pre-set emergency plans based on risk levels; Automatically cut off power and isolate the fault point; Adjust load distribution to ensure continuity of grid power supply; Generate a detailed fault handling report and transmit it to the remote operation and maintenance terminal.

8. A switch cabinet, characterized in that: include: The switch cabinet maintenance auxiliary system, wherein: The temperature and humidity sensors in the sensor network module are installed on the inner wall of the cabinet (1), the current transformer and the voltage transformer are respectively installed at the loop, the partial discharge sensor is arranged at the busbar joint and the cable terminal, the infrared thermal imaging device is embedded in the inner side of the cabinet (1) door panel, and the remote monitoring and emergency response module is connected to the switch cabinet control unit through a communication interface to trigger power-off isolation, load adjustment and rapid recovery operations.

Images