A comprehensive quality assessment system and method for switchgear based on Internet of Things technology

Abstract

The present invention discloses a comprehensive quality evaluation system and method for switchgear based on Internet of Things technology, specifically relating to the technical field of switchgear: by installing electromagnetic interference detection equipment, the electromagnetic field intensity around the switchgear and the operating state of the equipment are monitored in real time, electromagnetic field data and state data in different time periods are obtained, weighted calculation is performed on them to generate an overall electromagnetic interference index; using fuzzy logic to comprehensively analyze the electromagnetic interference index and the real-time state data of the switchgear to generate a health evaluation report, accurately showing the health status of the equipment, effectively improving the operation monitoring and maintenance optimization capabilities of the switchgear, and being able to predict potential faults and reduce misjudgments.

Description

Technical Field

[0001] The present invention relates to the technical field of switchgear, and particularly to a comprehensive quality evaluation system and method for switchgear based on Internet of Things technology. Background Art

[0002] The comprehensive quality evaluation of switchgear based on Internet of Things technology refers to the use of Internet of Things technology to monitor, collect and analyze the status and performance of switchgear in the power system in real time, so as to comprehensively evaluate and manage its operation quality. This method uses technical means such as sensors, data transmission, cloud computing and intelligent algorithms to collect and process the operating parameters of switchgear, such as temperature, humidity, vibration, current, voltage, etc., and then judges the health status of switchgear, predicts possible faults, and conducts maintenance optimization by analyzing these data. When the Internet of Things platform conducts remote monitoring and control, it relies on wireless signal transmission and sensor devices. However, if there is strong electromagnetic interference in the environment where the switchgear is located, it may have a serious impact on sensors, communication networks, and even the electronic components of the switchgear itself. Strong electromagnetic fields may cause wireless signal interference, resulting in data transmission interruption or error, making the data received by the monitoring platform distorted and leading to incorrect status judgment. At the same time, the data transmission interruption caused by electromagnetic interference will prevent the Internet of Things platform from obtaining the real-time status data of the switchgear. If real-time data is lacking, the system may rely on outdated or incorrect data for judgment, and then make an incorrect evaluation. For example, the system may rely on previous normal data and think that the device is still in a healthy state, while in fact the device may have failed or been overloaded. Summary of the Invention

[0003] The purpose of the present invention is to provide a comprehensive quality evaluation system and method for switchgear based on Internet of Things technology to solve the deficiencies in the background art.

[0004] To achieve the above purpose, the present invention provides the following technical solution: A comprehensive quality evaluation method for switchgear based on Internet of Things technology, including the following steps:

[0005] S1: Install electromagnetic interference detection devices around the switchgear and at several communication nodes, and conduct real-time monitoring of electromagnetic interference through the Internet of Things platform to obtain electromagnetic field intensity data at different time periods and real-time status data of the switchgear;

[0006] S2: Determine the weight coefficients of electromagnetic field intensity data at different time periods, and calculate the overall electromagnetic interference index of the switchgear after weighted averaging of the weight coefficients of electromagnetic field intensity data at different time periods;

[0007] S3: After comprehensively analyzing the calculated overall electromagnetic interference index of the switchgear and the real-time status data of the switchgear using fuzzy logic, a comprehensive evaluation report is generated to display the health status of the switchgear.

[0008] Preferably, in S1, electromagnetic field intensity data and real-time status data of the switchgear are obtained within different time periods, where the different time periods include: high-load periods, medium-load periods, and low-load periods.

[0009] Preferably, in S2, the weight coefficients of the electromagnetic field intensity data within different time periods are determined, where the electromagnetic field intensity data includes an electromagnetic interference frequency anomaly index and a geomagnetic polarization swing index; the method for obtaining the electromagnetic interference frequency anomaly index is as follows:

[0010] Collect the time-domain signal of the electromagnetic signal within the Q time period and label it as x[n], whose length is N, and set the sampling frequency , and use the FFT algorithm to convert the discrete signal x[n] in the time domain into a frequency-domain signal X[k], and the expression is: ; where X[k] is the k-th frequency component of the frequency-domain signal, k is the frequency index, N is the total number of sampling points, x[n] is the n-th sampling point in the time domain, j represents the imaginary unit, and X[k] obtained by FFT is a complex number. The amplitude of the spectrum is expressed as: ; Re(X[k]) and Im(X[k]) are the real part and the imaginary part of X[k] respectively; the frequency corresponding to each k The calculation expression is: ; where is the sampling frequency, the normal operating frequency of the switchgear system is fnormal, and the frequency tolerance range is set as , and the allowable normal operating frequency range is ; in the spectrum, the frequency components outside [fnormal - Δf, fnormal + Δf] are marked as abnormal frequencies, and the total energy of all frequency components is calculated, and the expression is: ; calculate the total energy sum of all abnormal frequencies , and the expression is: ; calculate the electromagnetic interference frequency anomaly index, and the expression is: ; where is the electromagnetic interference frequency anomaly index.

[0011] Preferably, the method for obtaining the geomagnetic polarization swing index is as follows:

[0012] The time series signal of the collected geomagnetic polarization data is marked as x(t). The geomagnetic field signal x(t) is decomposed into several intrinsic mode functions (IMFs) by EMD. The IMFs represent signal components at different time scales. By gradually extracting the local maxima and minima in the signal, the original signal x(t) is decomposed into several IMFs, expressed as: ; where is the i-th intrinsic mode function, is the remaining residue, n is the total number of signals. Find the local maxima and minima in x(t), and respectively construct the upper envelope and lower envelope through the interpolation method, calculate the average value of the upper envelope and lower envelope to generate the local trend curve of the signal, gradually remove this trend curve from the original signal, extract the first IMF, and decompose the signal into several IMFs; perform Hilbert transform on each to obtain the instantaneous frequency and instantaneous amplitude. Through the Hilbert transform, the signal is transformed into a complex analytic signal , defined as: ; where is the instantaneous amplitude, is the instantaneous phase, j is the imaginary unit, and the instantaneous frequency is calculated through the derivative of the phase, and the expression is: ; Calculate the geomagnetic polarization swing index, and the expression is: ; In the formula, and are the start and end points of the time interval, is the geomagnetic polarization swing index.

[0013] Preferably, convert the electromagnetic interference frequency anomaly index and the geomagnetic polarization swing index into the first eigenvector, and use the first eigenvector as the input of the machine learning model. The machine learning model takes predicting the weight coefficient value label of the electromagnetic field strength data in different time periods as the prediction target, and takes minimizing the sum of the prediction errors of the weight coefficient value labels of the electromagnetic field strength data in all different time periods as the training target, and trains the machine learning model until the sum of the prediction errors reaches convergence and then stops the model training. Determine the weight coefficient values of the electromagnetic field strength data in different time periods according to the model output results. Among them, the machine learning model is a polynomial regression model, and the overall electromagnetic interference index of the switch cabinet is calculated after weighted averaging the weight coefficients of the electromagnetic field strength data in different time periods.

[0014] Preferably, in S3, after comprehensively analyzing the calculated overall electromagnetic interference index of the switchgear and the real-time status data of the switchgear using fuzzy logic, a comprehensive evaluation report is generated;

[0015] Among them, the real-time status data of the switchgear includes the load balance fluctuation index of the switchgear. The method for obtaining the load balance fluctuation index is as follows: Collect the three-phase current of the switchgear and label them respectively as , representing the current values of the three-phase system. Set the sampling frequency f to monitor the changes of the three-phase load in real time, calculate the average value of the three-phase current, and the calculation expression is: ; In the formula, is the average value of the three-phase current; Calculate the deviation of each group of current from the average value, and the expression is: ; Quantify the fluctuation of the load balance and calculate its deviation from the average value. The expressions are respectively: ; Combine the deviation values of each group through root mean square calculation to obtain the load balance fluctuation index, and the expression is: ; In the formula, LB is the load balance fluctuation index.

[0016] Preferably, take the calculated load balance fluctuation index LB and the overall electromagnetic interference index MY as the input items of fuzzy logic, and take the health degree QE of the switchgear as the output item of fuzzy logic; Define fuzzy sets for each input item and output item, and use membership functions to map the input values to fuzzy values; Define the fuzzy set combinations of the input items according to the fuzzy rule base to obtain the fuzzy set of the output item; Use the fuzzy inference mechanism to map the input items to the output item; Calculate the membership degree of the input items for each rule; Combine the results of all rules through the fuzzy inference mechanism; Use the defuzzification method to convert the fuzzy set into a specific numerical result, and generate a health assessment report for the switchgear according to the fuzzy logic output result.

[0017] The present invention also provides a comprehensive quality assessment system for switchgear based on Internet of Things technology, including a data acquisition module, an overall electromagnetic interference assessment module, and a comprehensive assessment module;

[0018] Data acquisition module: Install electromagnetic interference detection devices around the switchgear and at several communication nodes, and perform real-time monitoring of electromagnetic interference through the Internet of Things platform to obtain the electromagnetic field intensity data in different time periods and the real-time status data of the switchgear;

[0019] Overall electromagnetic interference assessment module: Determine the weight coefficients of the electromagnetic field intensity data in different time periods, and calculate the overall electromagnetic interference index of the switchgear after weighted averaging of the weight coefficients of the electromagnetic field intensity data in different time periods;

[0020] Comprehensive evaluation module: After comprehensively analyzing the calculated overall electromagnetic interference index of the switchgear and the real-time status data of the switchgear using fuzzy logic, a comprehensive evaluation report is generated to display the health status of the switchgear.

[0021] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0022] 1. The present invention effectively evaluates the operation quality of the switchgear by real-time monitoring the electromagnetic field intensity around the switchgear and the status data of the equipment, especially in the presence of electromagnetic interference. By installing electromagnetic interference detection equipment, algorithms such as FFT and EMD are used to analyze the abnormal index of electromagnetic interference frequency and the polarization swing index of the geomagnetic field, and a machine learning model is used to optimize the weight coefficients in different time periods. Finally, the overall electromagnetic interference index of the switchgear is calculated. Combining with the real-time status data of the switchgear, such as the load balance fluctuation index, fuzzy logic is used for comprehensive analysis to generate a health assessment report to help predict possible faults of the equipment and optimize the maintenance strategy.

[0023] 2. The present invention can not only accurately obtain the real-time status of the switchgear in a strong electromagnetic interference environment to ensure the accuracy of data transmission and evaluation, but also introduce fuzzy logic and machine learning models to enable the system to more intelligently process complex data analysis and generate a comprehensive health assessment report. At the same time, the monitoring accuracy of the operation status of the switchgear is improved, which can help operation and maintenance personnel predict potential problems, optimize maintenance decisions, and thus improve the reliability and safety of the equipment. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0025] Figure 1 It is the method flow chart of the present invention.

[0026] Figure 2 It is the system module diagram of the present invention. Detailed Embodiments

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] Example 1, please refer to Figure 1 As shown, a comprehensive quality assessment method for switchgear based on Internet of Things technology in this embodiment includes the following steps:

[0029] S1: Install electromagnetic interference detection devices around the switchgear and at several communication nodes, and conduct real-time monitoring of electromagnetic interference through the Internet of Things platform to obtain electromagnetic field intensity data and real-time status data of the switchgear at different time periods;

[0030] S2: Determine the weight coefficients of the electromagnetic field intensity data at different time periods, and calculate the overall electromagnetic interference index of the switchgear after weighted averaging the weight coefficients of the electromagnetic field intensity data at different time periods;

[0031] S3: After comprehensively analyzing the calculated overall electromagnetic interference index of the switchgear and the real-time status data of the switchgear by using fuzzy logic, generate a comprehensive assessment report to display the health status of the switchgear.

[0032] Among them, in S1, installing electromagnetic interference detection devices around the switchgear and at several communication nodes, and conducting real-time monitoring of electromagnetic interference through the Internet of Things platform to obtain electromagnetic field intensity data and real-time status data of the switchgear at different time periods, specifically:

[0033] The step of installing electromagnetic interference (EMI) detection devices around the switchgear and at several communication nodes needs to be reasonably planned to ensure comprehensive interference detection, reliable data, and help identify the sources and impacts of electromagnetic interference.

[0034] According to the frequency range of electromagnetic interference and the characteristics of interference sources, select appropriate electromagnetic interference detection devices. The detection devices should support a wide frequency range (such as from 50 Hz in the low frequency to several GHz of high-frequency wireless signals), and be able to accurately capture the interference intensity and patterns. Select portable devices for mobile measurement, and at the same time select fixed sensors for continuous monitoring. The fixed devices should have remote monitoring and data transmission functions to facilitate integration with the Internet of Things platform. Ensure that the detection devices have high sensitivity and can detect weak electromagnetic interference, especially in the signal transmission areas of communication lines and switchgear.

[0035] Top and bottom detection: Install an electromagnetic interference detection device at the top and bottom of the switchgear respectively to monitor possible electromagnetic radiation from above and below, especially the interference near high-voltage cables and substation equipment. Install a device on the front and back of the switchgear to capture the spatial radiation around the device, especially the instantaneous electromagnetic interference caused by switch operations or the indirect radiation of other devices. Install an electromagnetic interference sensor at the communication interface of the switchgear to detect the interference when the device communication module is connected to the external network and prevent electromagnetic interference from being introduced by external transmission lines. At several typical nodes (such as signal amplifiers, distributors or interfaces) on the key signal transmission lines between the switchgear and other devices, install electromagnetic interference detection devices to ensure that the signals at these nodes are not affected by interference. Install detection devices near sensors and wireless communication modules (such as Wi-Fi, RFID modules, etc.) to monitor the electromagnetic interference at close range and prevent signal distortion of wireless communication caused by interference.

[0036] Use a metal bracket or a support frame made of insulating material to fix the electromagnetic interference detection device at the designated position. Ensure that the device maintains an appropriate distance from the area to be measured, avoid direct contact, and reduce the interference of the device itself. Configure a dedicated signal line or power line for each electromagnetic interference detection device to ensure that the wiring is reasonable and avoids high-voltage lines or other signal cables to prevent the introduction of additional electromagnetic interference. Wireless communication node layout: If the device supports wireless communication, ensure that the wireless signal does not conflict with the signals of nearby devices. According to the coverage of the wireless network, reasonably configure the position of the communication antenna.

[0037] Ensure that the electromagnetic interference detection device supports a communication protocol compatible with the Internet of Things platform (such as TCP / IP, Modbus, ZigBee, etc.). Connect through Wi-Fi, Ethernet or 4G / 5G network to upload the data of the detection device to the Internet of Things monitoring platform in real time. After the device is installed, conduct a data transmission test to confirm that the device can stably send interference data to the platform. Check the stability of data transmission and the signal strength to ensure that there is no data packet loss or transmission interruption.

[0038] Real-time monitoring of electromagnetic interference is carried out through the Internet of Things (IoT) platform to obtain the electromagnetic field intensity data and the real-time status data of the switchgear in different time periods. Sensors and IoT technologies are required to achieve data collection, transmission, storage, and analysis. The main components of the system include: Electromagnetic interference sensors, which are used to detect the electromagnetic field intensity in the environment. The sensors can capture electromagnetic waves in different frequency ranges in real time (such as low-frequency interference, high-frequency wireless interference, etc.). Switchgear status sensors, which are used to monitor the key parameters of the switchgear, such as current, voltage, temperature, etc., to understand its operating status in real time. Gateway devices, which are responsible for transmitting the collected sensor data to the IoT platform via wired or wireless means (such as Wi-Fi, LoRa, 4G / 5G networks). The IoT platform, which is used to receive and store sensor data and supports data visualization, analysis, and alarm functions.

[0039] The load change of the equipment has a great impact on electromagnetic interference. Therefore, key time periods can be divided according to the working load of the switchgear:

[0040] High-load period: This is the period when the switchgear operates at full load or near full load. Usually, the current and voltage loads are high, and the electromagnetic interference is relatively strong. Typical time periods are: peak industrial production periods (such as daytime production periods), when high-energy-consuming equipment is running (such as when motors and power generation equipment start);

[0041] Medium-load period: The switchgear operates at a medium load level, and the electromagnetic interference is relatively lower than that in the high-load period. It is common in periods when some equipment is turned on but the load is small, such as: some periods when equipment stops working at noon, some operating periods at night;

[0042] Low-load period: The switchgear operates at a low load or near no-load state, and the electromagnetic interference is weak at this time. For example: at night or when the equipment has not been fully started, during shutdown maintenance or non-working periods.

[0043] The electromagnetic interference sensors installed around the switchgear collect the intensity and spectrum information of the electromagnetic field in real time. These data include the electromagnetic field intensity in different frequency bands (unit: μT or nT), interference waveforms, timestamps, etc. Set the sampling frequency of the sensors (such as collecting data once per second) to ensure that the dynamic electromagnetic interference in the environment can be captured. High-frequency sampling can help detect instantaneous interference waves. Through temperature sensors, current sensors, voltage sensors, etc. installed inside the switchgear, the real-time operating status data of the switchgear are collected. These data include the temperature inside the equipment, switch status, load current, input voltage, etc. Similarly, the data collection frequency can be set to facilitate comparative analysis of the status changes of the switchgear when electromagnetic interference occurs.

[0044] All the collected data is transmitted to the Internet of Things platform through the gateway. The transmission methods that can be adopted are as follows: Wi-Fi / LoRa: suitable for local monitoring environments, such as places with good local network coverage like factories or substations. 4G / 5G networks: used for long-distance transmission to ensure stable data upload during remote monitoring. Wired network: If the environmental interference intensity is extremely high, wired transmission may be used to avoid wireless signal interference.

[0045] S2: Determine the weight coefficients of the electromagnetic field intensity data in different time periods, and calculate the overall electromagnetic interference index of the switchgear by performing weighted averaging on the weight coefficients of the electromagnetic field intensity data in different time periods.

[0046] Determine the weight coefficients of the electromagnetic field intensity data in different time periods, where the electromagnetic field intensity data includes the electromagnetic interference frequency anomaly index and the geomagnetic field polarization swing index; the electromagnetic interference frequency anomaly index refers to the degree of deviation of the electromagnetic interference signal from the normal operating frequency, and is used to evaluate whether abnormal high-frequency or low-frequency interference occurs within the operating frequency band of the equipment. This index is usually used to detect whether external interference sources (such as wireless communication devices or industrial equipment) have an impact on the system within the frequency range where they should not exist, resulting in a shift in the operating frequency of the equipment or signal distortion.

[0047] The geomagnetic field polarization swing index describes the change amplitude and frequency of the polarization direction of the geomagnetic field in a short period of time, reflecting the stability of the geomagnetic environment. When the polarization swing of the geomagnetic field is intense, it may interfere with the electronic components and sensors of the equipment, especially for equipment that relies on precise magnetic field measurement or stable operation. This index can help evaluate the potential impact of external natural magnetic field changes on equipment operation.

[0048] Then the method for obtaining the electromagnetic interference frequency anomaly index is as follows:

[0049] Collect the time-domain signal of the electromagnetic signal in the Q time period and mark it as x[n], and its length is N (the number of sampling points). Set the sampling frequency (unit: Hz), which determines the number of samples collected per second. Use the FFT algorithm to convert the discrete signal x[n] in the time domain into the frequency-domain signal X[k], and the expression is: ; where X[k] is the kth frequency component of the frequency-domain signal, k is the frequency index, N is the total number of sampling points, x[n] is the nth sampling point in the time domain, j represents the imaginary unit, and X[k] obtained through FFT is a complex number. The amplitude of the spectrum is expressed as: ; Re(X[k]) and Im(X[k]) are the real and imaginary parts of X[k] respectively; the frequency corresponding to each k is calculated by the expression: ; where, is the sampling frequency. The normal operating frequency of the switchgear system is fnormal, which can be the power supply frequency of the device (such as 50 Hz or 60 Hz) or other signal frequencies. The set frequency tolerance range is , and the allowed normal operating frequency range is ; in the spectrum, frequency components outside [fnormal−Δf,fnormal+Δf] are marked as abnormal frequencies, and the total energy of all frequency components is calculated , and the expression is: ; calculate the sum of the energies of all abnormal frequencies , and the expression is: ; calculate the electromagnetic interference frequency anomaly index, and the expression is: ; where FAI is the electromagnetic interference frequency anomaly index.

[0050] The larger the electromagnetic interference frequency anomaly index, the more serious the electromagnetic interference intensity around the switchgear, and the more interference components with frequencies deviating from the normal operating frequency. This means that outside the normal frequency range, there are a large number of high-frequency or low-frequency abnormal signal interferences, which may have a significant impact on the electronic components, communication modules or control systems of the switchgear. A larger frequency anomaly index indicates that these abnormal signals not only increase the noise of equipment operation, but may also cause misoperations, data loss or equipment failures, thus threatening the stability and safety of the switchgear.

[0051] Among them, the method for obtaining the geomagnetic polarization swing index is:

[0052] The time series signal of the polarization data of the geomagnetic field collected is marked as x(t), which represents the component of the geomagnetic polarization direction changing with time. The geomagnetic field signal x(t) is decomposed into several intrinsic mode functions (IMFs) with physical meanings through EMD. The IMFs represent signal components at different time scales, usually arranged from high frequency to low frequency. By gradually extracting the local maximum and minimum values in the signal, the original signal x(t) is decomposed into several IMFs, which is expressed as: ; where is the i-th intrinsic mode function, is the remaining residue, usually the trend component, n is the total number of signals, find the local maximum and minimum values in x(t), and respectively construct the upper envelope and the lower envelope through the interpolation method, calculate the average value of the upper envelope and the lower envelope, generate the local trend curve of the signal, gradually remove this trend curve from the original signal, extract the first IMF, and decompose the signal into several IMFs; perform Hilbert transform on each , obtain the instantaneous frequency and instantaneous amplitude, and through the Hilbert transform, the signal Convert to a complex analytic signal , defined as: ; where is the instantaneous amplitude, is the instantaneous phase, j is the imaginary unit, and the instantaneous frequency is calculated through the derivative of the phase, and the expression is: ; Calculate the geomagnetic polarization swing index, and the expression is: ; In the formula, and are the start and end points of the time interval, and GM is the geomagnetic polarization swing index.

[0053] The larger the geomagnetic polarization swing index, the more intense the geomagnetic polarization swing, the greater the changes in the instantaneous amplitude and frequency, indicating that the fluctuation amplitude of the geomagnetic polarization direction is large and the frequency changes rapidly, which may have a greater impact on sensitive devices. A smaller geomagnetic polarization swing index indicates that the geomagnetic polarization swing is relatively stable, with a small swing amplitude and a stable frequency, meaning that the geomagnetic environment is relatively stable.

[0054] Convert the electromagnetic interference frequency anomaly index and the geomagnetic polarization swing index into the first eigenvector, use the first eigenvector as the input of the machine learning model, use the machine learning model to predict the weight coefficient value label of the electromagnetic field strength data in different time periods as the prediction target, and use minimizing the sum of the prediction errors of the weight coefficient value labels of the electromagnetic field strength data in all different time periods as the training target to train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the weight coefficient value of the electromagnetic field strength data in different time periods according to the model output result. Among them, the machine learning model is a polynomial regression model, and the overall electromagnetic interference index of the switchgear is calculated after weighted averaging the weight coefficients of the electromagnetic field strength data in different time periods.

[0055] The method for obtaining the weight coefficient value of the electromagnetic field strength data in different time periods is: obtain the corresponding function expression from the first eigenvector training data of the trained machine learning model: ; In the formula, F is the output function of the model, FAI is the electromagnetic interference frequency anomaly index, GM is the geomagnetic polarization swing index, and CW is the weight coefficient value of the electromagnetic field strength data in different time periods.

[0056] S3: After comprehensively analyzing the calculated overall electromagnetic interference index of the switchgear and the real-time status data of the switchgear using fuzzy logic, generate a comprehensive evaluation report to display the health status of the switchgear.

[0057] Among them, the real-time status data of the switchgear includes the load balance fluctuation index of the switchgear. The method for obtaining the load balance fluctuation index is as follows: collect the three-phase current of the switchgear, and label them respectively as , representing the current values of the three-phase system. Set the sampling frequency f to monitor the changes of the three-phase load in real time, calculate the average value of the three-phase current, and the calculation expression is: ; In the formula, is the average value of the three-phase current; calculate the deviation between each group of current and the average value, and the expression is: ; In order to quantify the fluctuation of the load balance and calculate its deviation from the average value, the expressions are respectively: ; Combine the deviation values of each group through root mean square calculation to obtain the load balance fluctuation index, and the expression is: ; In the formula, LB is the load balance fluctuation index.

[0058] Take the calculated load balance fluctuation index LB and the overall electromagnetic interference index MY as the input items of fuzzy logic, and take the health degree QE of the switchgear as the output item of fuzzy logic;

[0059] Define fuzzy sets for each input item and output item, and use membership functions to map the input values to fuzzy values.

[0060] Load balance fluctuation index (LB): It can be divided into three fuzzy sets: small, medium, and large. The health degree (QE): It is defined as healthy, sub-healthy, and unhealthy, and is represented by triangular membership functions or trapezoidal membership functions. For example: Small (Low): The load balance fluctuation is small. Medium: The load balance fluctuation is moderate. High: The load balance fluctuation is large. Example of membership function definition (assuming the value range of LB is 0 to 1): ;

[0061] Overall electromagnetic interference index (MY): It is also divided into three fuzzy sets: low, medium, and high, and is represented by similar membership functions. Low: The electromagnetic interference is low. Medium: The electromagnetic interference is moderate. High: The electromagnetic interference is strong. Example of membership function definition (assuming the value range of MY is 0 to 1): ;

[0062] Health level (QE): Defined as healthy, sub-healthy, and unhealthy, and the membership function is used to represent the output items. Healthy: The device is in normal condition and does not require immediate maintenance. Sub-healthy: The device is in a slightly abnormal condition and may require monitoring. Unhealthy: The device is in a poor condition, may face failures, and requires maintenance. The membership function of the health level can be defined according to the expected value of the device state.

[0063] The fuzzy rule base defines how to obtain the fuzzy set of the output item according to the combination of the fuzzy sets of the input items. Fuzzy rules usually take the form of "if... then...". Example fuzzy rules: Rule 1: If LB is small and MY is low, then QE is healthy. Rule 2: If LB is large and MY is high, then QE is unhealthy. Rule 3: If LB is medium and MY is medium, then QE is sub-healthy. Rule 4: If LB is small and MY is medium, then QE is healthy. Rule 5: If LB is large and MY is low, then QE is sub-healthy. The combination method of these rules is determined by expert experience or historical data and can be comprehensively evaluated through multiple rules.

[0064] Use a fuzzy inference mechanism (such as the Mamdani model) to map the input items to the output items.

[0065] For each rule, calculate the membership degree of the input items. Combine the "if... then..." rule and determine the membership degree of the output item according to the membership degree of the input items.

[0066] Use the "min" operation to determine the applicability of the rule, that is, the output fuzzy value of the rule is the minimum value of the input membership degrees.

[0067] Combine the results of all rules through the fuzzy inference mechanism. A common method is to use the "max" operation to merge the fuzzy sets output by all rules into the final fuzzy output.

[0068] Use a defuzzification method to convert the fuzzy set into a specific numerical result. Common defuzzification methods include the centroid method, the maximum membership degree method, etc. Calculate the centroid position of the fuzzy result and output the corresponding health level value.

[0069] Generate a health assessment report for the switchgear according to the fuzzy logic output result: Summarize the calculation results of the load balance fluctuation index (LB), the overall electromagnetic interference index (MY), and the health level (QE). Generate a health status report for the switchgear according to the health level (QE) output by the fuzzy logic, showing the current state of the device and the recommended maintenance measures.

[0070] For example, the report may include: the current load balancing fluctuation index (LB) and the overall electromagnetic interference index (MY) values. The numerical value of the comprehensive health index (QE) and the corresponding status description (such as "healthy" or "sub-healthy"). Maintenance suggestions: If the health level is low, it is recommended to arrange preventive maintenance or inspections.

[0071] By using fuzzy logic, the load balancing fluctuation index (LB) and the overall electromagnetic interference index (MY) of the switchgear are used as input items, and the health level (QE) is generated as the output item. Through the fuzzy rule base, fuzzy inference, and defuzzification, the health assessment result of the switchgear is finally obtained, and a comprehensive assessment report is generated to display the health status of the equipment and provide maintenance suggestions.

[0072] In this embodiment, during the electromagnetic interference monitoring and health assessment of the switchgear, first, electromagnetic interference detection devices are installed around the switchgear and at communication nodes, and real-time monitoring is carried out using the Internet of Things platform to obtain the electromagnetic field intensity data and the real-time status data of the switchgear at different time periods. Then, weight coefficients are assigned to the electromagnetic field intensity data at different time periods, and the overall electromagnetic interference index of the switchgear is calculated through weighted average. Finally, the overall electromagnetic interference index and the real-time status data of the switchgear are comprehensively analyzed using fuzzy logic to generate a comprehensive assessment report to display the health status of the switchgear, help predict the operating status of the equipment, and provide maintenance suggestions.

[0073] Example 2, please refer to Figure 2 As shown, the comprehensive quality assessment system for switchgear based on Internet of Things technology in this embodiment includes a data acquisition module, an overall electromagnetic interference assessment module, and a comprehensive assessment module;

[0074] Data acquisition module: Install electromagnetic interference detection devices around the switchgear and at several communication nodes, and conduct real-time monitoring of electromagnetic interference through the Internet of Things platform to obtain the electromagnetic field intensity data and the real-time status data of the switchgear at different time periods;

[0075] Overall electromagnetic interference assessment module: Determine the weight coefficients of the electromagnetic field intensity data at different time periods, and calculate the overall electromagnetic interference index of the switchgear after weighted averaging of the weight coefficients of the electromagnetic field intensity data at different time periods;

[0076] Comprehensive assessment module: After comprehensively analyzing the calculated overall electromagnetic interference index of the switchgear and the real-time status data of the switchgear using fuzzy logic, generate a comprehensive assessment report to display the health status of the switchgear.

[0077] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulations to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0078] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0079] It should be understood that the term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0080] In this application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following (items)" or similar expressions refer to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0081] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Claims

1. A comprehensive evaluation method for switch cabinet quality based on Internet of Things technology, characterized by: The following steps are involved: S1: Install electromagnetic interference detection equipment around the switch cabinet and at several communication nodes, and use the Internet of Things platform to monitor electromagnetic interference in real time, obtain electromagnetic field strength data in different time periods and real-time status data of the switch cabinet; S2: Determine the weight coefficient of the electromagnetic field strength data in different time periods, and calculate the overall electromagnetic interference index of the switch cabinet after weighted averaging the weight coefficients of the electromagnetic field strength data in different time periods; The electromagnetic field strength data includes the electromagnetic interference frequency anomaly index. The electromagnetic interference frequency anomaly index is obtained by collecting the time domain signal of the electromagnetic signal in the Q time period and marking it as x[n], whose length is N, and setting the sampling frequency , use the FFT algorithm to convert the discrete signal x[n] in the time domain into the frequency domain signal X[k], the expression is: ; In the formula, X[k] is the kth frequency component of the frequency domain signal, k is the frequency index, N is the total number of sampling points, x[n] is the nth sampling point in the time domain, j represents the imaginary unit, X[k] obtained by FFT is a complex number, and the amplitude of the spectrum is expressed as: ; Re(X[k]) and Im(X[k]) are the real and imaginary parts of X[k] respectively; the frequency corresponding to each k is The calculation expression is: ;in, is the sampling frequency, the normal operating frequency of the switch cabinet system is fnormal, and the frequency tolerance range is set to , the allowed normal operating frequency range is ; In the spectrum, the frequency components outside [fnormal−Δf, fnormal+Δf] are marked as abnormal frequencies, and the total energy of all frequency components is calculated , the expression is: ; Calculate the sum of the energy of all abnormal frequencies , the expression is: ; Calculate the electromagnetic interference frequency anomaly index, the expression is: ; In the formula, is the electromagnetic interference frequency anomaly index; S3: After comprehensively analyzing the calculated overall electromagnetic interference index of the switch cabinet and the real-time status data of the switch cabinet using fuzzy logic, a comprehensive evaluation report is generated to display the health status of the switch cabinet.

2. According to claim 1, a comprehensive switch cabinet quality assessment method based on Internet of Things technology is characterized by: In S1, electromagnetic field strength data and real-time status data of the switch cabinet in different time periods are obtained, wherein the different time periods include: a high load period, a medium load period and a low load period.

3. According to claim 1, a comprehensive switch cabinet quality assessment method based on Internet of Things technology is characterized by: in, The method for obtaining the geomagnetic field polarization oscillation index is: The time series signal of the polarization data of the geomagnetic field is marked as x(t). The geomagnetic field signal x(t) is decomposed into several intrinsic mode functions IMFs through EMD. IMFs represent the signal components on different time scales. By gradually extracting the local maximum and minimum values ​​in the signal, the original signal x(t) is decomposed into several IMFs, which are expressed as: ;in, is the ith eigenmode function, is the remaining residual, z is the total number of signals, find the local maximum and minimum in x(t), and construct the upper envelope and lower envelope respectively by interpolation, calculate the average value of the upper envelope and the lower envelope, generate the local trend curve of the signal, gradually remove the trend curve from the original signal, extract the first IMF, and decompose the signal into several IMFs; for each Perform Hilbert transform to obtain instantaneous frequency and instantaneous amplitude. Convert to complex analytic signal , defined as: ;in, is the instantaneous amplitude, is the instantaneous phase, j is the imaginary unit, and the instantaneous frequency It is calculated by the derivative of the phase, and the expression is: ; Calculate the geomagnetic field polarization swing index, the expression is: ; In the formula, and is the starting point and end point of the time interval. is the index of the Earth's magnetic field polarization swing.

4. The switch cabinet quality comprehensive evaluation method based on Internet of Things technology according to claim 3 is characterized by: The electromagnetic interference frequency anomaly index and the geomagnetic field polarization swing index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the weight coefficient value label of the electromagnetic field strength data in different time periods as the prediction target, and takes minimizing the sum of the prediction errors of the weight coefficient value labels of the electromagnetic field strength data in all different time periods as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weight coefficient value of the electromagnetic field strength data in different time periods is determined according to the model output results, wherein the machine learning model is a polynomial regression model, and the overall electromagnetic interference index of the switchgear is calculated by weighted averaging the weight coefficients of the electromagnetic field strength data in different time periods.

5. The switch cabinet quality comprehensive evaluation method based on Internet of Things technology according to claim 4 is characterized in that: In S3, after comprehensively analyzing the calculated overall electromagnetic interference index of the switch cabinet and the real-time status data of the switch cabinet using fuzzy logic, a comprehensive evaluation report is generated; The real-time status data of the switch cabinet includes the load balance fluctuation index of the switch cabinet. The load balance fluctuation index is obtained by collecting the three-phase current of the switch cabinet and marking them as , represents the current value of the three-phase system, sets the sampling frequency f to monitor the changes of the three-phase load in real time, and calculates the average value of the three-phase current. The calculation expression is: ; In the formula, is the average value of the three-phase current; calculate the deviation of each group of currents from the average value, the expression is: ; Quantify the fluctuation of load balance and calculate its deviation from the average value, the expressions are: ; Combine the deviation values ​​of each group through RMS calculation to get the load balance fluctuation index, which is expressed as: ; In the formula, is the load balancing fluctuation index.

6. The switch cabinet quality comprehensive evaluation method based on Internet of Things technology according to claim 5 is characterized by: The calculated load balance fluctuation index LB and overall electromagnetic interference index MY are used as input items of fuzzy logic, and the health level QE of the switch cabinet is used as the output item of fuzzy logic; fuzzy sets are defined for each input item and output item, and membership functions are used to map input values ​​to fuzzy values; The fuzzy set combination of input items is defined according to the fuzzy rule base to obtain the fuzzy set of output items; Use fuzzy reasoning mechanism to map input items to output items; for each rule, calculate the membership of the input items; combine the results of all rules through fuzzy reasoning mechanism; use defuzzification method to convert fuzzy sets into specific numerical results, and generate a health assessment report for the switch cabinet based on the fuzzy logic output results.

7. A switch cabinet quality comprehensive evaluation system based on the Internet of Things technology, used to implement the switch cabinet quality comprehensive evaluation method based on the Internet of Things technology according to any one of claims 1 to 6, characterized in that: It includes data acquisition module, overall electromagnetic interference assessment module and comprehensive assessment module; Data acquisition module: Install electromagnetic interference detection equipment around the switch cabinet and at several communication nodes, and monitor electromagnetic interference in real time through the Internet of Things platform to obtain electromagnetic field strength data in different time periods and real-time status data of the switch cabinet; Overall electromagnetic interference evaluation module: determine the weight coefficient of the electromagnetic field strength data in different time periods, and calculate the overall electromagnetic interference index of the switch cabinet after weighted averaging the weight coefficients of the electromagnetic field strength data in different time periods; Comprehensive evaluation module: After comprehensively analyzing the calculated overall electromagnetic interference index of the switch cabinet and the real-time status data of the switch cabinet using fuzzy logic, a comprehensive evaluation report is generated to display the health status of the switch cabinet.

Images