Power cabinet comprehensive monitoring method and system based on multiple sensors, and power distribution cabinet

Abstract

The invention discloses an electric power cabinet comprehensive monitoring method and system based on multiple sensors and a power distribution cabinet, and relates to the technical field of sensor monitoring. During operation of the system, various sensor data are collected from an electric power cabinet and the surrounding environment of the electric power cabinet, and electromagnetic environments, equipment states and environmental parameters inside and outside the electric power cabinet are monitored in real time; the method comprises the following steps: preprocessing original sensor data through a signal filtering algorithm, extracting feature information related to electromagnetic interference (EMI) from the processed data, calculating and obtaining an EMIindex through a machine learning algorithm, performing state evaluation and fault prediction on equipment in the power cabinet, providing early warning of fault types and giving maintenance suggestions, when the electromagnetic interference intensity exceeds the standard or an equipment fault occurs, a real-time alarm signal is automatically triggered through an intelligent judgment mechanism, a system self-adaptive control mechanism is started, an electromagnetic environment index and an equipment state report are generated, and remote monitoring is carried out on the electric power cabinet.

Description

Technical Field

[0001] The present invention relates to the field of sensor monitoring technology, and in particular to a multi-sensor based comprehensive monitoring method and system for a power cabinet and a distribution cabinet. Background Art

[0002] With the continuous development of the power system, power cabinets, as important power distribution equipment, play a key role in controlling and protecting various types of equipment in the power system. The normal operation of the power cabinet is directly related to the stability and safety of the power system. Therefore, real-time monitoring of the power cabinet, especially the continuous monitoring of the environment and equipment status inside and outside the power cabinet, has become an urgent need in the power industry. Traditional power cabinet monitoring methods mainly focus on monitoring basic parameters such as electrical parameters (such as current, voltage, etc.) and temperature. However, these methods cannot fully reflect the various interference factors that the power cabinet may be subject to in a complex environment, especially electromagnetic interference (EMI). Electromagnetic interference, as a potential threat to the normal operation of power cabinet equipment, may cause equipment failure, communication interference and even system crash. Therefore, how to efficiently and accurately monitor and evaluate the electromagnetic environment has become an important issue to improve the safety of power cabinets.

[0003] Electromagnetic interference (EMI) is a common potential hazard in power systems, especially in key facilities such as distribution cabinets. The interference source comes not only from the external environment, but also from the operation of equipment inside the system. Traditional power cabinet monitoring systems are limited to monitoring electrical parameters and environmental changes, and it is difficult to effectively identify the impact of electromagnetic interference on system stability. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a comprehensive monitoring method and system for a power cabinet and a distribution cabinet based on multiple sensors, which solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a comprehensive monitoring system for a power cabinet based on multiple sensors, including a data acquisition module, a preprocessing module, an EMI feature extraction module, a fault diagnosis and prediction module, a real-time alarm control module, a data analysis module and a remote monitoring module;

[0006] The data acquisition module is used to collect various sensor data from the power cabinet and its surrounding environment, monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time, and transmit the data to the data preprocessing module through a wireless or wired network;

[0007] The preprocessing module is used to perform denoising on the raw sensor data through a signal filtering algorithm, remove interference noise, and use smoothing and interpolation methods to complete and correct the data;

[0008] The EMI feature extraction module is used to extract feature information related to electromagnetic interference EMI from the processed data, including electric field strength, magnetic field strength, spectrum distribution and interference fluctuation parameters, and form a feature vector of the electromagnetic environment, and obtain the electromagnetic environment index EMI through machine learning algorithm calculation index ;

[0009] The fault diagnosis and prediction module is used to perform status assessment and fault prediction on the equipment in the power cabinet based on machine learning, combined with real-time collected electromagnetic interference data, electrical parameters and environmental data, to provide early warning of fault types and give maintenance suggestions;

[0010] The real-time alarm control module is used to automatically trigger a real-time alarm signal and start the system adaptive control mechanism through an intelligent judgment mechanism when the electromagnetic interference intensity exceeds the standard or equipment failure occurs;

[0011] The data analysis module is used to combine the electromagnetic environment data inside and outside the power cabinet, generate the electromagnetic environment index and equipment status report through data mining and trend analysis technology, and put forward optimization suggestions for the power cabinet, including equipment configuration and layout adjustment;

[0012] The remote monitoring module is used to remotely monitor the electromagnetic environment, equipment status and alarm information of the power cabinet through a cloud platform or a remote management system, and supports remote fault diagnosis, equipment maintenance and optimization adjustment.

[0013] Preferably, the data acquisition module includes an electromagnetic interference data acquisition unit, a device status data acquisition unit and an environmental parameter data acquisition unit;

[0014] The electromagnetic interference data acquisition unit is used to deploy electromagnetic field sensors including electric field and magnetic field sensors to monitor the electromagnetic interference situation in real time inside and outside the power cabinet, collect electromagnetic wave intensity, spectrum and electric field intensity parameters, and obtain the electric field intensity value E f , magnetic field strength value H f And the interference power value P emi ,The sensor collects data regularly according to the preset range, and transmits the collected results to the data preprocessing module in the form of digital signals;

[0015] The device status data acquisition unit is used to collect the operating status data of the equipment inside the power cabinet through current, voltage and temperature sensors, monitor electrical parameters, including current, voltage fluctuations and equipment temperature, and obtain the current fluctuation amplitude value I v , voltage fluctuation amplitude value U v and the device temperature change rate T dev , and transmit the data to the pre-processing module for processing;

[0016] The environmental parameter data acquisition unit is used to monitor the impact of external environmental factors of the power cabinet on electromagnetic interference through environmental sensors, including temperature and humidity sensors, air pressure sensors and distance sensors, and obtain the environmental temperature value T env , Ambient humidity value H env and interference distance value P dist .

[0017] Preferably, the preprocessing module includes a data preprocessing unit;

[0018] The data preprocessing unit is used to filter the raw data using a low-pass filter and a Kalman filter algorithm, remove high-frequency noise and interference in the sensor signal, smooth the signal using a smoothing algorithm, a moving average method, and an exponentially weighted average method, eliminate signal fluctuations caused by equipment errors or collection gaps, and use a linear interpolation algorithm to complete missing or incomplete sensor data.

[0019] Preferably, the EMI feature extraction module includes an electromagnetic fluctuation amplitude extraction unit and an electromagnetic environment index calculation unit;

[0020] The electromagnetic fluctuation amplitude extraction unit is used to convert the time domain signal into the frequency domain signal by using the spectrum analysis method of fast Fourier transform FFT, extract the distribution of electric field and magnetic field strength in different frequency bands, analyze the spectrum characteristics of electromagnetic interference, extract the fluctuation amplitude and change rate parameters of electromagnetic waves from the data collected by the electromagnetic field sensor, and reflect the intensity and dynamic change trend of electromagnetic interference around the power cabinet;

[0021] The electromagnetic environment index calculation unit is used to combine the extracted electromagnetic interference features, and to perform modeling through machine learning algorithms, including support vector machines and random forests, to calculate the electromagnetic interference intensity coefficient K emi , Electrical parameter stability coefficient K elec 、Environmental interference influence coefficient K env And electromagnetic environment index EMI index .

[0022] The electromagnetic interference intensity coefficient K emi Calculate using the following formula

[0023]

[0024] In the formula, E f,i represents the electric field strength at the ith collection point, H f,i represents the magnetic field strength at the i-th acquisition point, P emi,i represents the interference power of the ith collection point, and n represents the total number of electromagnetic interference collection points;

[0025] The electrical parameter stability coefficient Kelec Calculate using the following formula

[0026]

[0027] In the formula, I v,j represents the current fluctuation amplitude at the jth time point, U v,j represents the voltage fluctuation amplitude at the jth time point, T dev,j represents the device temperature change rate at the jth time point, and m represents the total number of acquisition time points;

[0028] The environmental interference influence coefficient K env Calculate using the following formula

[0029]

[0030] Where, T env,k represents the ambient temperature at the kth position, H env,k represents the ambient humidity at the kth position, P dist,k represents the distance from the interference source at the kth position to the power cabinet, and p represents the total number of environmental collection locations;

[0031] The electromagnetic environment index EMI index Calculate using the following formula

[0032] EMI index =K emi ×K elec ×K env ;

[0033] In the formula, K emi Indicates the electromagnetic interference intensity coefficient, K elec Indicates the electrical parameter stability coefficient, K env Represents the environmental interference influence coefficient.

[0034] Preferably, the fault diagnosis prediction module includes a fault data analysis unit, a machine learning diagnosis unit and a maintenance suggestion generation unit;

[0035] The fault data analysis unit is used to identify potential fault signs in the operation of the power cabinet by analyzing the relationship between the electromagnetic interference inside and outside the power cabinet, the electrical parameters of the equipment and the environmental data, and to perform preliminary data analysis so as to make a preliminary assessment of the equipment status;

[0036] The machine learning diagnosis unit is used to train and predict the failure mode of the power cabinet by using machine learning models including decision trees, neural networks and support vector machines, combining historical data and real-time monitoring data, and using the electromagnetic environment index EMI indexCompare with the preset first qualified threshold T and the preset second qualified threshold B, evaluate the status of the equipment, and predict the occurrence of potential failures;

[0037] The maintenance suggestion generating unit is used to automatically generate maintenance suggestions based on the fault diagnosis and prediction results, combined with the maintenance history and operating status of the equipment, and the suggestions include equipment maintenance, repair or replacement measures to help operators perform troubleshooting and maintenance work;

[0038] The electromagnetic environment index EMI index Compare with the preset first qualified threshold T and the preset second qualified threshold B to obtain a status assessment plan;

[0039] When EMI index When ≤T, the electromagnetic environment is within the safe and qualified range, indicating that the electromagnetic interference intensity inside and outside the power cabinet has no impact on the operation of the equipment;

[0040] When T <EMI index When ≤B, the electromagnetic interference intensity has exceeded the standard by 30%, affecting the stability of equipment operation but not causing obvious faults;

[0041] When EMI index >B, it indicates that the electromagnetic interference intensity has exceeded the standard by more than 30%, resulting in equipment failure or unstable system operation, and emergency measures must be taken immediately.

[0042] Preferably, the real-time alarm control module includes a real-time alarm generation unit and an intelligent judgment control unit;

[0043] The real-time alarm generation unit is used to monitor the status of the power cabinet in real time based on the electromagnetic interference intensity and equipment failure, and trigger an alarm signal, which notifies the operator through visual, sound or other forms to reflect abnormal conditions in a timely manner;

[0044] The intelligent judgment control unit is used to intelligently judge and trigger corresponding control operations, including switching power supplies and enabling backup equipment, based on monitored abnormal conditions, including excessive electromagnetic interference intensity and equipment failure. According to the system's intelligent judgment results, emergency response operations are automatically performed, including adjusting loads, switching circuits, and enabling backup power supplies.

[0045] Preferably, the data analysis module includes a trend analysis unit;

[0046] The trend analysis unit is used to use data mining technology to conduct in-depth analysis of historical data, identify potential regularities and trends in the operation of the power cabinet, help predict future changes in the electromagnetic environment and equipment operating conditions, perform time series analysis based on historical monitoring data, and discover long-term change trends in the electromagnetic environment and equipment status inside and outside the power cabinet. Through a comprehensive evaluation of data mining and trend analysis results, power cabinet optimization suggestions are generated, including equipment configuration, environmental adjustment, and layout optimization.

[0047] Preferably, the remote monitoring module includes a remote data monitoring unit and a remote fault diagnosis unit;

[0048] The remote data monitoring unit is used to receive data through a cloud platform or a remote management system, including electromagnetic environment data and equipment operation status inside and outside the power cabinet, receive alarm information in real time, and transmit these data to the remote management platform through the network for real-time monitoring. It supports displaying the real-time status of the power cabinet through a visual interface, and generates real-time electromagnetic environment diagrams and equipment operation diagrams according to different data parameters, which is convenient for remote operators to observe and diagnose;

[0049] The remote fault diagnosis unit is used to provide fault diagnosis, equipment maintenance and optimization adjustment functions based on the remote platform. When the electromagnetic interference in the power cabinet exceeds the standard or the equipment fails, the remote platform automatically analyzes the status inside the power cabinet through an algorithm, identifies potential faults, and provides a fault diagnosis report. The remote operator makes remote adjustments through the system based on the diagnosis results, including modifying the power cabinet configuration, adjusting the equipment working mode, or starting the adaptive control mechanism. It supports the execution of equipment maintenance operations through remote commands. If an unresolvable fault occurs, a maintenance team dispatch signal is triggered.

[0050] The comprehensive monitoring method of the power cabinet based on multiple sensors includes the following steps:

[0051] Step 1: Collect various sensor data from the power cabinet and its surrounding environment, monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time, and transmit the data to the data preprocessing module through wireless or wired network;

[0052] Step 2: De-noise the raw sensor data through the signal filtering algorithm to remove the interference noise, and use the smoothing and interpolation methods to complete and correct the data;

[0053] Step 3: Extract characteristic information related to electromagnetic interference (EMI) from the processed data, including electric field strength, magnetic field strength, spectrum distribution, and interference fluctuation parameters, and form a characteristic vector of the electromagnetic environment. Obtain the electromagnetic environment index (EMI) through machine learning algorithm calculation. index ;

[0054] Step 4: Based on machine learning, combined with real-time collected electromagnetic interference data, electrical parameters and environmental data, the equipment in the power cabinet is evaluated and faults are predicted, and early warnings of fault types are provided and maintenance recommendations are given;

[0055] Step 5: When the electromagnetic interference intensity exceeds the standard or equipment failure occurs, the intelligent judgment mechanism automatically triggers a real-time alarm signal and starts the system adaptive control mechanism;

[0056] Step 6: Combine the electromagnetic environment data inside and outside the power cabinet, generate the electromagnetic environment index and equipment status report through data mining and trend analysis technology, and put forward optimization suggestions for the power cabinet, including equipment configuration and layout adjustment;

[0057] Step 7: Remotely monitor the electromagnetic environment, equipment status and alarm information of the power cabinet through the cloud platform or remote management system to support remote fault diagnosis, equipment maintenance and optimization adjustment.

[0058] A power distribution cabinet, comprising the following contents:

[0059] Electromagnetic interference sensor: installed at key positions inside and outside the power distribution cabinet body, used to detect the electromagnetic interference EMI in the power cabinet and its surrounding environment in real time. When the electromagnetic interference intensity exceeds the preset threshold, an alarm signal is triggered. The sensor collects electromagnetic environment data through precise electric field strength, magnetic field strength and interference power sensors and transmits the data to the data preprocessing module through wireless or wired networks;

[0060] Equipment status monitor: installed inside the power distribution cabinet body, monitors the operating status of the equipment in the power cabinet in real time, including key electrical parameters such as current, voltage, temperature and humidity. When abnormal equipment operation is detected, including current fluctuation and temperature exceeding the standard, the corresponding fault alarm signal is triggered and provided to the fault diagnosis module for analysis;

[0061] Environmental parameter sensor: installed outside the power distribution cabinet body, used to detect changes in the environment where the power distribution cabinet is located, including temperature, humidity and air pressure environmental data;

[0062] The present invention provides a comprehensive monitoring method, system and distribution cabinet for a power cabinet based on multiple sensors, which have the following beneficial effects:

[0063] (1) When the system is running, various sensor data are collected from the power cabinet and its surrounding environment to monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time. The original sensor data is pre-processed through the signal filtering algorithm, and the characteristic information related to electromagnetic interference (EMI) is extracted from the processed data. The electromagnetic environment index (EMI) is calculated through the machine learning algorithm. index, evaluate the status and predict faults of the equipment in the power cabinet, provide early warning of fault types and give maintenance suggestions. When the electromagnetic interference intensity exceeds the standard or equipment failure occurs, the intelligent judgment mechanism will automatically trigger a real-time alarm signal, start the system adaptive control mechanism, generate an electromagnetic environment index and equipment status report, and remotely monitor the power cabinet.

[0064] (2) The multi-sensor-based integrated monitoring system for power cabinets achieves comprehensive monitoring of the inside and outside of the power cabinet by integrating seven modules, including data acquisition, preprocessing, feature extraction, fault diagnosis, real-time alarm, data analysis, and remote monitoring. The greatest advantage of this system is that through the collaborative work of multiple sensors, it can simultaneously obtain multi-dimensional information such as electrical parameters, electromagnetic environment, and equipment status, thereby improving the comprehensive perception of the operating status of the power cabinet. By collecting data on electromagnetic interference, electrical faults, and environmental changes in real time, the system can predict and warn of potential faults before problems occur, providing more reliable protection for the safe operation of the power cabinet.

[0065] (3) Compared with the existing traditional power cabinet monitoring system, the integrated monitoring system based on multiple sensors has significantly improved the intelligence level of the system. Traditional systems mostly rely on a single sensor or only rely on the monitoring of electrical parameters, making it difficult to fully understand the actual operation of the power cabinet. However, through electromagnetic interference monitoring and real-time collection of equipment status, the system can not only detect electrical equipment failures in a timely manner, but also monitor external electromagnetic interference and reduce equipment failures caused by the deterioration of the electromagnetic environment. The system monitors the electromagnetic environment index EMI index The comprehensive assessment of the equipment status can send out early warning signals before a fault occurs, preventing equipment from being damaged by external factors such as electromagnetic interference, thereby improving the stability and safety of the power cabinet.

[0066] (4) This system combines data analysis with remote monitoring modules to achieve remote fault diagnosis, equipment maintenance and optimization adjustments, greatly improving the maintenance efficiency of the power cabinet. Through the cloud platform or remote management system, operators can obtain the operating data and alarm information of the power cabinet in real time, and perform fault troubleshooting and remote optimization adjustments at any time. This remote monitoring capability not only improves the response speed, but also reduces the frequency and cost of on-site inspections. Compared with current traditional methods, it provides a more efficient and convenient maintenance method. Overall, the multi-sensor based comprehensive monitoring system for power cabinets has brought significant technological breakthroughs in fault prediction, environmental monitoring and remote management of power cabinets, effectively improving the safety, reliability and intelligence level of power cabinets. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 The block diagram of the comprehensive monitoring system of the power cabinet based on multiple sensors of the present invention;

[0068] Figure 2 The figure is a schematic diagram of the steps of the comprehensive monitoring method of a power cabinet based on multiple sensors of the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0070] Example 1

[0071] The present invention provides a comprehensive monitoring system for power cabinets based on multiple sensors. Figure 1 , including data acquisition module, preprocessing module, EMI feature extraction module, fault diagnosis and prediction module, real-time alarm control module, data analysis module and remote monitoring module;

[0072] The data acquisition module is used to collect various sensor data from the power cabinet and its surrounding environment, monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time, and transmit the data to the data preprocessing module through a wireless or wired network;

[0073] The preprocessing module is used to perform denoising on the raw sensor data through a signal filtering algorithm, remove interference noise, and use smoothing and interpolation methods to complete and correct the data;

[0074] The EMI feature extraction module is used to extract feature information related to electromagnetic interference EMI from the processed data, including electric field strength, magnetic field strength, spectrum distribution and interference fluctuation parameters, and form a feature vector of the electromagnetic environment, and obtain the electromagnetic environment index EMI through machine learning algorithm calculation index ;

[0075] The fault diagnosis and prediction module is used to perform status assessment and fault prediction on the equipment in the power cabinet based on machine learning, combined with real-time collected electromagnetic interference data, electrical parameters and environmental data, to provide early warning of fault types and give maintenance suggestions;

[0076] The real-time alarm control module is used to automatically trigger a real-time alarm signal and start the system adaptive control mechanism through an intelligent judgment mechanism when the electromagnetic interference intensity exceeds the standard or equipment failure occurs;

[0077] The data analysis module is used to combine the electromagnetic environment data inside and outside the power cabinet, generate the electromagnetic environment index and equipment status report through data mining and trend analysis technology, and put forward optimization suggestions for the power cabinet, including equipment configuration and layout adjustment;

[0078] The remote monitoring module is used to remotely monitor the electromagnetic environment, equipment status and alarm information of the power cabinet through a cloud platform or a remote management system, and supports remote fault diagnosis, equipment maintenance and optimization adjustment.

[0079] In this embodiment, various sensor data are collected from the power cabinet and its surrounding environment to monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time. The original sensor data is preprocessed by a signal filtering algorithm, and characteristic information related to electromagnetic interference EMI is extracted from the processed data to form a characteristic vector of the electromagnetic environment. The electromagnetic environment index EMI is calculated by a machine learning algorithm. index , evaluate the status and predict faults of the equipment in the power cabinet, provide early warning of fault types and give maintenance suggestions. When the electromagnetic interference intensity exceeds the standard or equipment failure occurs, the intelligent judgment mechanism automatically triggers the real-time alarm signal and starts the system adaptive control mechanism. Combined with the electromagnetic environment data inside and outside the power cabinet, the electromagnetic environment index and equipment status report are generated through data mining and trend analysis technology, and suggestions for power cabinet optimization are put forward, including equipment configuration and layout adjustment. The electromagnetic environment, equipment status and alarm information of the power cabinet are remotely monitored through the cloud platform or remote management system, supporting remote fault diagnosis, equipment maintenance and optimization adjustment.

[0080] Example 2

[0081] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes an electromagnetic interference data acquisition unit, a device status data acquisition unit and an environmental parameter data acquisition unit;

[0082] The electromagnetic interference data acquisition unit is used to deploy electromagnetic field sensors including electric field and magnetic field sensors to monitor the electromagnetic interference situation in real time inside and outside the power cabinet, collect electromagnetic wave intensity, spectrum and electric field intensity parameters, and obtain the electric field intensity value E f , magnetic field strength value H f And the interference power value P emi ,The sensor collects data regularly according to the preset range, and transmits the collected results to the data preprocessing module in the form of digital signals;

[0083] The device status data acquisition unit is used to collect the operating status data of the equipment inside the power cabinet through current, voltage and temperature sensors, monitor electrical parameters, including current, voltage fluctuations and equipment temperature, and obtain the current fluctuation amplitude value I v , voltage fluctuation amplitude value U v and the device temperature change rate T dev , and transmit the data to the pre-processing module for processing;

[0084] The environmental parameter data acquisition unit is used to monitor the impact of external environmental factors of the power cabinet on electromagnetic interference through environmental sensors, including temperature and humidity sensors, air pressure sensors and distance sensors, and obtain the environmental temperature value T env , Ambient humidity value H env and interference distance value P dist .

[0085] The preprocessing module includes a data preprocessing unit;

[0086] The data preprocessing unit is used to filter the raw data using a low-pass filter and a Kalman filter algorithm, remove high-frequency noise and interference in the sensor signal, smooth the signal using a smoothing algorithm, a moving average method, and an exponentially weighted average method, eliminate signal fluctuations caused by equipment errors or collection gaps, and use a linear interpolation algorithm to complete missing or incomplete sensor data.

[0087] The EMI feature extraction module includes an electromagnetic fluctuation amplitude extraction unit and an electromagnetic environment index calculation unit;

[0088] The electromagnetic fluctuation amplitude extraction unit is used to convert the time domain signal into the frequency domain signal by using the spectrum analysis method of fast Fourier transform FFT, extract the distribution of electric field and magnetic field strength in different frequency bands, analyze the spectrum characteristics of electromagnetic interference, extract the fluctuation amplitude and change rate parameters of electromagnetic waves from the data collected by the electromagnetic field sensor, and reflect the intensity and dynamic change trend of electromagnetic interference around the power cabinet;

[0089] The electromagnetic environment index calculation unit is used to combine the extracted electromagnetic interference features, and to perform modeling through machine learning algorithms, including support vector machines and random forests, to calculate the electromagnetic interference intensity coefficient K emi , Electrical parameter stability coefficient K elec 、Environmental interference influence coefficient K env And electromagnetic environment index EMI index .

[0090] The electromagnetic interference intensity coefficient K emi Calculate using the following formula

[0091]

[0092] In the formula, E f,i represents the electric field strength at the ith collection point, H f,i represents the magnetic field strength at the i-th acquisition point, P emi,i represents the interference power of the ith collection point, and n represents the total number of electromagnetic interference collection points;

[0093] The electrical parameter stability coefficient Kelec Calculate using the following formula

[0094]

[0095] In the formula, I v,j represents the current fluctuation amplitude at the jth time point, U v,j represents the voltage fluctuation amplitude at the jth time point, T dev,j represents the device temperature change rate at the jth time point, and m represents the total number of acquisition time points;

[0096] The environmental interference influence coefficient K env Calculate using the following formula

[0097]

[0098] Where, T env,k represents the ambient temperature at the kth position, H env,k represents the ambient humidity at the kth position, P dist,k represents the distance from the interference source at the kth position to the power cabinet, and p represents the total number of environmental collection locations;

[0099] The electromagnetic environment index EMI index Calculate using the following formula

[0100] EMI index =K emi ×K elec ×K env ;

[0101] In the formula, K emi Indicates the electromagnetic interference intensity coefficient, K elec Indicates the electrical parameter stability coefficient, K env Represents the environmental interference influence coefficient.

[0102] In this embodiment, comprehensive monitoring of the electromagnetic environment, electrical status and external environment inside and outside the power cabinet can be achieved. The integration of the electromagnetic interference data acquisition unit, the equipment status data acquisition unit and the environmental parameter data acquisition unit enables the system to accurately identify and evaluate potential problems of the power cabinet and its environment while acquiring multi-dimensional data. The signal filtering and completion processing of the data preprocessing module ensures the quality and integrity of the data, further improving the accuracy of subsequent analysis. The EMI feature extraction module generates an electromagnetic environment index by accurately analyzing the electromagnetic fluctuation amplitude and spectrum, providing a scientific basis for system fault diagnosis and optimization design, and significantly improving the safety and reliability of the power cabinet.

[0103] Example 3

[0104] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the fault diagnosis prediction module includes a fault data analysis unit, a machine learning diagnosis unit and a maintenance suggestion generation unit;

[0105] The fault data analysis unit is used to identify potential fault signs in the operation of the power cabinet by analyzing the relationship between the electromagnetic interference inside and outside the power cabinet, the electrical parameters of the equipment and the environmental data, and to perform preliminary data analysis so as to make a preliminary assessment of the equipment status;

[0106] The machine learning diagnosis unit is used to train and predict the failure mode of the power cabinet by using machine learning models including decision trees, neural networks and support vector machines, combining historical data and real-time monitoring data, and using the electromagnetic environment index EMI index Compare with the preset first qualified threshold T and the preset second qualified threshold B, evaluate the status of the equipment, and predict the occurrence of potential failures;

[0107] The maintenance suggestion generating unit is used to automatically generate maintenance suggestions based on the fault diagnosis and prediction results, combined with the maintenance history and operating status of the equipment, and the suggestions include equipment maintenance, repair or replacement measures to help operators perform troubleshooting and maintenance work;

[0108] The electromagnetic environment index EMI index Compare with the preset first qualified threshold T and the preset second qualified threshold B to obtain a state assessment scheme, including:

[0109] When EMI index When ≤T, the electromagnetic environment is within the safe and qualified range, indicating that the electromagnetic interference intensity inside and outside the power cabinet has no impact on the operation of the equipment. The data acquisition module collects and records the electromagnetic environment data every 10 minutes to ensure the stability of the monitoring data. The real-time alarm control module displays the "normal operation of the electromagnetic environment" status information, and the remote monitoring module can send monitoring reports to operators;

[0110] When T <EMI index When ≤B, the electromagnetic interference intensity has exceeded the standard by 30%, affecting the stability of equipment operation, but not causing obvious faults. The data acquisition module shortens the sampling interval from 10 minutes to 2 minutes, increases the data acquisition frequency, tracks the dynamic changes of electromagnetic interference in real time, starts the forced heat dissipation device (such as cooling fan or ventilation system), reduces the temperature inside the power cabinet, and adjusts the humidity around the power cabinet to a reasonable range (40% to 60%) to reduce the electromagnetic interference coupling phenomenon caused by humidity;

[0111] When EMI index>B, it indicates that the electromagnetic interference intensity has exceeded the standard by more than 30%, causing equipment failure or unstable system operation. Emergency measures must be taken immediately. Through the fault diagnosis and prediction module, the main source of electromagnetic interference (such as poor cable contact, current shock source or external electromagnetic interference source) is identified, and the switch is automatically triggered to cut off the specific interference source circuit, or the key equipment is switched to the backup power line to avoid further damage. The electromagnetic shielding device is started, and a metal shielding layer or conductive coating is added inside the power cabinet to reduce the electromagnetic radiation coupling intensity. Physical isolation measures are taken for high-interference equipment outside the power cabinet, and the distance between devices is increased to a minimum of 2 meters, and shielding devices are added near the interference source. Forced to start high-power heat dissipation equipment to quickly reduce the internal temperature of the power cabinet to below 25°C. The emergency status alarm is triggered through the real-time alarm control module to notify the operation and maintenance personnel, and the real-time data and fault diagnosis report are pushed to the cloud platform through the remote monitoring module.

[0112] The real-time alarm control module includes a real-time alarm generation unit and an intelligent judgment control unit;

[0113] The real-time alarm generation unit is used to monitor the status of the power cabinet in real time based on the electromagnetic interference intensity and equipment failure, and trigger an alarm signal, which notifies the operator through visual, sound or other forms to reflect abnormal conditions in a timely manner;

[0114] The intelligent judgment control unit is used to intelligently judge and trigger corresponding control operations, including switching power supplies and enabling backup equipment, based on monitored abnormal conditions, including excessive electromagnetic interference intensity and equipment failure. According to the system's intelligent judgment results, emergency response operations are automatically performed, including adjusting loads, switching circuits, and enabling backup power supplies.

[0115] The data analysis module includes a trend analysis unit;

[0116] The trend analysis unit is used to use data mining technology to conduct in-depth analysis of historical data, identify potential regularities and trends in the operation of the power cabinet, help predict future changes in the electromagnetic environment and equipment operating conditions, perform time series analysis based on historical monitoring data, and discover long-term change trends in the electromagnetic environment and equipment status inside and outside the power cabinet. Through a comprehensive evaluation of data mining and trend analysis results, power cabinet optimization suggestions are generated, including equipment configuration, environmental adjustment, and layout optimization.

[0117] In this embodiment, by analyzing the relationship between electromagnetic interference inside and outside the power cabinet, equipment electrical parameters and environmental data, the unit can identify potential fault signs in the operation of the power cabinet. Through preliminary data analysis, it provides a basis for subsequent equipment status evaluation, using a variety of machine learning algorithms, including decision trees, neural networks and support vector machines (SVM), based on historical data and real-time data training models, combined with the electromagnetic environment index EMIindex Compare with the preset qualified thresholds (T and B), predict the possible fault type and occurrence time of the equipment, provide accurate equipment status assessment, and generate personalized maintenance suggestions, including equipment maintenance, repair or replacement measures. By combining the maintenance history and current operating status of the equipment, it helps operators quickly identify problems and take appropriate maintenance measures.

[0118] Example 4

[0119] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the remote monitoring module includes a remote data monitoring unit and a remote fault diagnosis unit;

[0120] The remote data monitoring unit is used to receive data through a cloud platform or a remote management system, including electromagnetic environment data and equipment operation status inside and outside the power cabinet, receive alarm information in real time, and transmit these data to the remote management platform through the network for real-time monitoring. It supports displaying the real-time status of the power cabinet through a visual interface, and generates real-time electromagnetic environment diagrams and equipment operation diagrams according to different data parameters, which is convenient for remote operators to observe and diagnose;

[0121] The remote fault diagnosis unit is used to provide fault diagnosis, equipment maintenance and optimization adjustment functions based on the remote platform. When the electromagnetic interference in the power cabinet exceeds the standard or the equipment fails, the remote platform automatically analyzes the status inside the power cabinet through an algorithm, identifies potential faults, and provides a fault diagnosis report. The remote operator makes remote adjustments through the system based on the diagnosis results, including modifying the power cabinet configuration, adjusting the equipment working mode, or starting the adaptive control mechanism. It supports the execution of equipment maintenance operations through remote commands. If an unresolvable fault occurs, a maintenance team dispatch signal is triggered.

[0122] In this embodiment, electromagnetic environment data and equipment operation status information inside and outside the power cabinet are received in real time through a cloud platform or a remote management system, and the alarm information is transmitted to the remote platform to support real-time monitoring. Through the visual interface, remote operators can clearly view the real-time status of the power cabinet, generate electromagnetic environment maps and equipment operation maps, so that monitoring personnel can grasp the health status of the equipment and changes in the surrounding environment without going to the site in person. Through the display of data charts, operators can intuitively find potential problems and quickly take corresponding measures to reduce delays in on-site fault judgment and improve work efficiency. The status inside the power cabinet is analyzed by an automated algorithm, potential faults are identified, and a fault diagnosis report is generated. This function not only saves time for manual detection, but also can quickly respond to excessive electromagnetic interference or other abnormal conditions that occur during equipment operation, and provide accurate fault diagnosis. Remote operators can make real-time adjustments based on the diagnosis results, including modifying equipment configuration, adjusting working mode, or enabling adaptive control mechanisms. This remote control capability greatly improves the flexibility of equipment management, enables problems to be solved in the shortest time, and reduces the frequency and cost of on-site maintenance. By supporting remote commands to perform equipment maintenance operations, especially when problems cannot be solved through system adaptive control, it can trigger the maintenance team to dispatch signals and arrange on-site repairs in a timely manner. This not only shortens the fault response time, but also ensures that the fault handling process is efficient and orderly, avoiding excessive equipment downtime. In addition, remote maintenance also supports optimizing equipment working modes, adjusting equipment settings in advance, and avoiding potential faults, thereby improving the overall stability and reliability of the power cabinet and improving the operational efficiency and safety of the system.

[0123] Example 5

[0124] For a comprehensive monitoring method of power cabinets based on multiple sensors, please refer to Figure 2 , specifically: including the following steps:

[0125] Step 1: Collect various sensor data from the power cabinet and its surrounding environment, monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time, and transmit the data to the data preprocessing module through wireless or wired network;

[0126] Step 2: De-noise the raw sensor data through the signal filtering algorithm to remove the interference noise, and use the smoothing and interpolation methods to complete and correct the data;

[0127] Step 3: Extract characteristic information related to electromagnetic interference (EMI) from the processed data, including electric field strength, magnetic field strength, spectrum distribution, and interference fluctuation parameters, and form a characteristic vector of the electromagnetic environment. Obtain the electromagnetic environment index (EMI) through machine learning algorithm calculation. index ;

[0128] Step 4: Based on machine learning, combined with real-time collected electromagnetic interference data, electrical parameters and environmental data, the equipment in the power cabinet is evaluated and faults are predicted, and early warnings of fault types are provided and maintenance recommendations are given;

[0129] Step 5: When the electromagnetic interference intensity exceeds the standard or equipment failure occurs, the intelligent judgment mechanism automatically triggers a real-time alarm signal and starts the system adaptive control mechanism;

[0130] Step 6: Combine the electromagnetic environment data inside and outside the power cabinet, generate the electromagnetic environment index and equipment status report through data mining and trend analysis technology, and put forward optimization suggestions for the power cabinet, including equipment configuration and layout adjustment;

[0131] Step 7: Remotely monitor the electromagnetic environment, equipment status and alarm information of the power cabinet through the cloud platform or remote management system to support remote fault diagnosis, equipment maintenance and optimization adjustment.

[0132] In this embodiment, through the sensor data collection process in step one, the system can monitor the electromagnetic environment, equipment status, and environmental parameters inside and outside the power cabinet in real time, ensuring comprehensive monitoring of the power cabinet operation status from multiple angles. And the data is quickly transmitted to the data preprocessing module through a wireless or wired network, which effectively reduces the frequency of on-site inspections and improves monitoring efficiency. Step two uses signal filtering algorithms and data completion methods to ensure that the original sensor data can provide high-quality input data after noise removal, smoothing, and interpolation completion. Through the electromagnetic interference feature extraction in step three, the system can accurately calculate the electromagnetic environment index EMI index , providing an accurate basis for the status assessment and fault prediction of the power cabinet, reducing false alarms caused by environmental factors, equipment failure or interference, etc. The machine learning diagnosis and intelligent judgment mechanism of steps 4 and 5 realizes the real-time status assessment and fault warning of the power cabinet equipment. When the electromagnetic interference intensity exceeds the standard or equipment failure occurs, the system can automatically trigger the alarm signal and start the adaptive control mechanism to quickly take countermeasures, reducing the reliance on human intervention, improving the fault response speed, and providing early warning before the equipment fails. Step 6 uses data mining and trend analysis technology to combine the electromagnetic environment data inside and outside the power cabinet to generate an electromagnetic environment index and equipment status report, and put forward optimization suggestions for equipment configuration and layout adjustment. This data-based optimization capability has continuously improved the operating efficiency and stability of the power cabinet. Finally, through the remote monitoring and fault diagnosis of step 7, remote management personnel can conduct comprehensive monitoring, fault diagnosis, equipment maintenance and optimization adjustments of the power cabinet through the cloud platform or remote management system, avoiding delays in on-site maintenance and improving the operating efficiency and maintenance response speed of the equipment.

[0133] Example 6

[0134] A power distribution cabinet, comprising the following contents:

[0135] Electromagnetic interference sensor: installed at key positions inside and outside the power distribution cabinet body, used to detect the electromagnetic interference EMI in the power cabinet and its surrounding environment in real time. When the electromagnetic interference intensity exceeds the preset threshold, an alarm signal is triggered. The sensor collects electromagnetic environment data through precise electric field strength, magnetic field strength and interference power sensors and transmits the data to the data preprocessing module through wireless or wired networks;

[0136] Equipment status monitor: installed inside the power distribution cabinet body, monitors the operating status of the equipment in the power cabinet in real time, including key electrical parameters such as current, voltage, temperature and humidity. When abnormal equipment operation is detected, including current fluctuation and temperature exceeding the standard, the corresponding fault alarm signal is triggered and provided to the fault diagnosis module for analysis;

[0137] Environmental parameter sensor: installed outside the power distribution cabinet body, used to detect changes in the environment where the power distribution cabinet is located, including temperature, humidity and air pressure environmental data;

[0138] Shell design: The body of the power distribution cabinet should be made of durable steel or aluminum alloy, with a protection level of IP54 or above;

[0139] Size and modularity: The distribution cabinet has enough space to accommodate various sensors, electrical equipment and monitoring system modules;

[0140] Heat dissipation design: The power distribution cabinet has ventilation and heat dissipation design, and is equipped with fans or air conditioning modules to maintain a suitable operating temperature and prevent equipment from overheating.

[0141] Although 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 the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A comprehensive monitoring system for power cabinets based on multiple sensors, characterized in that: It includes data acquisition module, preprocessing module, EMI feature extraction module, fault diagnosis and prediction module, real-time alarm control module, data analysis module and remote monitoring module; The data acquisition module is used to collect various sensor data from the power cabinet and its surrounding environment, monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time, and transmit the data to the data preprocessing module through a wireless or wired network; The preprocessing module is used to perform denoising on the raw sensor data through a signal filtering algorithm, remove interference noise, and use smoothing and interpolation methods to complete and correct the data; The EMI feature extraction module is used to extract feature information related to electromagnetic interference EMI from the processed data, including electric field strength, magnetic field strength, spectrum distribution and interference fluctuation parameters, and form a feature vector of the electromagnetic environment, and obtain the electromagnetic environment index through machine learning algorithm calculation; The fault diagnosis and prediction module is used to perform status assessment and fault prediction on the equipment in the power cabinet based on machine learning, combined with real-time collected electromagnetic interference data, electrical parameters and environmental data, to provide early warning of fault types and give maintenance suggestions; The real-time alarm control module is used to automatically trigger a real-time alarm signal and start the system adaptive control mechanism through an intelligent judgment mechanism when the electromagnetic interference intensity exceeds the standard or equipment failure occurs; The data analysis module is used to combine the electromagnetic environment data inside and outside the power cabinet, generate the electromagnetic environment index and equipment status report through data mining and trend analysis technology, and put forward optimization suggestions for the power cabinet, including equipment configuration and layout adjustment; The remote monitoring module is used to remotely monitor the electromagnetic environment, equipment status and alarm information of the power cabinet through a cloud platform or a remote management system, and supports remote fault diagnosis, equipment maintenance and optimization adjustment.

2. The multi-sensor based integrated monitoring system for power cabinets according to claim 1 is characterized in that: The data acquisition module includes an electromagnetic interference data acquisition unit, an equipment status data acquisition unit and an environmental parameter data acquisition unit; The electromagnetic interference data acquisition unit is used to monitor the electromagnetic interference situation in real time inside and outside the power cabinet by deploying electromagnetic field sensors including electric field and magnetic field sensors, collect electromagnetic wave intensity, spectrum and electric field intensity parameters, obtain electric field intensity value, magnetic field intensity value and interference power value, and the sensor collects data regularly according to a preset range and transmits the collection results to the data preprocessing module in the form of digital signals; The device status data acquisition unit is used to collect the operating status data of the equipment inside the power cabinet through current, voltage and temperature sensors, monitor electrical parameters, including current, voltage fluctuations and device temperature, obtain the current fluctuation amplitude value, voltage fluctuation amplitude value and device temperature change rate, and transmit the data to the preprocessing module for processing; The environmental parameter data acquisition unit is used to monitor the impact of external environmental factors of the power cabinet on electromagnetic interference through environmental sensors, including temperature and humidity sensors, air pressure sensors and distance sensors, and obtain environmental temperature values, environmental humidity values ​​and interference distance values.

3. The multi-sensor based integrated monitoring system for power cabinets according to claim 1 is characterized in that: The preprocessing module includes a data preprocessing unit; The data preprocessing unit is used to filter the raw data using a low-pass filter and a Kalman filter algorithm, remove high-frequency noise and interference in the sensor signal, smooth the signal using a smoothing algorithm, a moving average method, and an exponentially weighted average method, eliminate signal fluctuations caused by equipment errors or collection gaps, and use a linear interpolation algorithm to complete missing or incomplete sensor data.

4. The multi-sensor based integrated monitoring system for power cabinets according to claim 1 is characterized in that: The EMI feature extraction module includes an electromagnetic fluctuation amplitude extraction unit and an electromagnetic environment index calculation unit; The electromagnetic fluctuation amplitude extraction unit is used to convert the time domain signal into the frequency domain signal by using the spectrum analysis method of fast Fourier transform FFT, extract the distribution of electric field and magnetic field strength in different frequency bands, analyze the spectrum characteristics of electromagnetic interference, extract the fluctuation amplitude and change rate parameters of electromagnetic waves from the data collected by the electromagnetic field sensor, and reflect the intensity and dynamic change trend of electromagnetic interference around the power cabinet; The electromagnetic environment index calculation unit is used to combine the extracted electromagnetic interference features, and to perform modeling through machine learning algorithms, including support vector machines and random forests, to calculate: electromagnetic interference intensity coefficient, electrical parameter stability coefficient, environmental interference influence coefficient and electromagnetic environment index.

5. The multi-sensor based integrated monitoring system for power cabinets according to claim 1 is characterized in that: The fault diagnosis prediction module includes a fault data analysis unit, a machine learning diagnosis unit and a maintenance suggestion generation unit; The fault data analysis unit is used to identify potential fault signs in the operation of the power cabinet by analyzing the relationship between the electromagnetic interference inside and outside the power cabinet, the electrical parameters of the equipment and the environmental data, and to perform preliminary data analysis so as to make a preliminary assessment of the equipment status; The machine learning diagnosis unit is used to use machine learning models including decision trees, neural networks and support vector machines to train and predict the failure mode of the power cabinet, combine historical data and real-time monitoring data, compare the electromagnetic environment index with a preset first qualified threshold and a preset second qualified threshold, evaluate the status of the equipment, and predict the occurrence of potential failures; The maintenance suggestion generating unit is used to automatically generate maintenance suggestions based on the fault diagnosis and prediction results, combined with the maintenance history and operating status of the equipment, and the suggestions include equipment maintenance, repair or replacement measures to help operators perform troubleshooting and maintenance work; The electromagnetic environment index EMI index Compare with the preset first qualified threshold T and the preset second qualified threshold B to obtain a state assessment scheme, including: When EMI index When ≤T, the electromagnetic environment is within the safe and qualified range, indicating that the electromagnetic interference intensity inside and outside the power cabinet has no impact on the operation of the equipment; When T <EMI index When ≤B, the electromagnetic interference intensity has exceeded the standard by 30%, affecting the stability of equipment operation but not causing obvious faults; When EMI index >B, it indicates that the electromagnetic interference intensity has exceeded the standard by more than 30%, resulting in equipment failure or unstable system operation, and emergency measures must be taken immediately.

6. The multi-sensor based integrated monitoring system for power cabinets according to claim 1 is characterized in that: The real-time alarm control module includes a real-time alarm generation unit and an intelligent judgment control unit; The real-time alarm generation unit is used to monitor the status of the power cabinet in real time based on the electromagnetic interference intensity and equipment failure, and trigger an alarm signal, which notifies the operator through visual, sound or other forms to reflect abnormal conditions in a timely manner; The intelligent judgment control unit is used to intelligently judge and trigger corresponding control operations, including switching power supplies and enabling backup equipment, based on monitored abnormal conditions, including excessive electromagnetic interference intensity and equipment failure. According to the system's intelligent judgment results, emergency response operations are automatically performed, including adjusting loads, switching circuits, and enabling backup power supplies.

7. The multi-sensor based integrated monitoring system for power cabinets according to claim 1 is characterized in that: The data analysis module includes a trend analysis unit; The trend analysis unit is used to use data mining technology to conduct in-depth analysis of historical data, identify potential regularities and trends in the operation of the power cabinet, help predict future changes in the electromagnetic environment and equipment operating conditions, perform time series analysis based on historical monitoring data, and discover long-term change trends in the electromagnetic environment and equipment status inside and outside the power cabinet. Through a comprehensive evaluation of data mining and trend analysis results, power cabinet optimization suggestions are generated, including equipment configuration, environmental adjustment, and layout optimization.

8. The multi-sensor based integrated monitoring system for power cabinets according to claim 1 is characterized in that: The remote monitoring module includes a remote data monitoring unit and a remote fault diagnosis unit; The remote data monitoring unit is used to receive data through a cloud platform or a remote management system, including electromagnetic environment data and equipment operation status inside and outside the power cabinet, receive alarm information in real time, and transmit these data to the remote management platform through the network for real-time monitoring. It supports displaying the real-time status of the power cabinet through a visual interface, and generates real-time electromagnetic environment diagrams and equipment operation diagrams according to different data parameters, which is convenient for remote operators to observe and diagnose; The remote fault diagnosis unit is used to provide fault diagnosis, equipment maintenance and optimization adjustment functions based on the remote platform. When the electromagnetic interference in the power cabinet exceeds the standard or the equipment fails, the remote platform automatically analyzes the status inside the power cabinet through an algorithm, identifies potential faults, and provides a fault diagnosis report. The remote operator makes remote adjustments through the system based on the diagnosis results, including modifying the power cabinet configuration, adjusting the equipment working mode, or starting the adaptive control mechanism. It supports the execution of equipment maintenance operations through remote commands. If an unresolvable fault occurs, a maintenance team dispatch signal is triggered.

9. A multi-sensor based integrated monitoring system for a power cabinet and a distribution cabinet, applied to the multi-sensor based integrated monitoring system for a power cabinet as claimed in any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Collect various sensor data from the power cabinet and its surrounding environment, monitor the electromagnetic environment, equipment status and environmental parameters inside and outside the power cabinet in real time, and transmit the data to the data preprocessing module through wireless or wired network; Step 2: De-noise the raw sensor data through the signal filtering algorithm to remove the interference noise, and use the smoothing and interpolation methods to complete and correct the data; Step 3: Extract characteristic information related to electromagnetic interference (EMI) from the processed data, including electric field strength, magnetic field strength, spectrum distribution, and interference fluctuation parameters, and form a characteristic vector of the electromagnetic environment. Obtain the electromagnetic environment index (EMI) through machine learning algorithm calculation. index ; Step 4: Based on machine learning, combined with real-time collected electromagnetic interference data, electrical parameters and environmental data, the equipment in the power cabinet is evaluated and faults are predicted, and early warnings of fault types are provided and maintenance recommendations are given; Step 5: When the electromagnetic interference intensity exceeds the standard or equipment failure occurs, the intelligent judgment mechanism automatically triggers a real-time alarm signal and starts the system adaptive control mechanism; Step 6: Combine the electromagnetic environment data inside and outside the power cabinet, generate the electromagnetic environment index and equipment status report through data mining and trend analysis technology, and put forward optimization suggestions for the power cabinet, including equipment configuration and layout adjustment; Step 7: Remotely monitor the electromagnetic environment, equipment status and alarm information of the power cabinet through the cloud platform or remote management system to support remote fault diagnosis, equipment maintenance and optimization adjustment.

10. A power distribution cabinet, characterized in that: include: Electromagnetic interference sensors are installed at key positions inside and outside the power distribution cabinet body to detect the electromagnetic interference EMI in the power cabinet and its surrounding environment in real time. When the electromagnetic interference intensity exceeds the preset threshold, an alarm signal is triggered. The sensor collects electromagnetic environment data through precise electric field strength, magnetic field strength and interference power sensors and transmits the data to the data preprocessing module through wireless or wired networks; The equipment status monitor is installed inside the power distribution cabinet body to monitor the operating status of the equipment in the power cabinet in real time, including key electrical parameters such as current, voltage, temperature and humidity. When abnormal equipment operation is detected, including current fluctuation and temperature exceeding the standard, the corresponding fault alarm signal is triggered and provided to the fault diagnosis module for analysis; The environmental parameter sensor is installed outside the power distribution cabinet body and is used to detect changes in the environment where the power distribution cabinet is located, including temperature, humidity and air pressure environmental data.

Images