Power grid equipment fault monitoring method based on non-contact high-voltage mutual inductor

Abstract

The invention discloses a power grid equipment fault monitoring method based on a non-contact high-voltage mutual inductor, and relates to the technical field of non-contact high-voltage mutual inductors, and the method comprises the following steps: obtaining mutual inductor nodes in a to-be-detected region, marking the mutual inductor nodes, and obtaining the power grid fault data of the to-be-detected nodes through a mutual inductor; analyzing the influence of the electrical noise source on the mutual inductor based on linear regression, and correcting power grid fault data; constructing a power grid fault coefficient model based on a machine learning algorithm according to the power grid fault data; dividing the to-be-detected region into a plurality of sub-regions, and calculating an average power grid fault coefficient of each sub-region based on a power grid fault coefficient model; performing coefficient correction on the to-be-detected sub-region through the sub-region connected with the to-be-detected sub-region to obtain a corrected power grid fault coefficient; according to the method, the power grid fault coefficient model is constructed, so that the problem that the equipment fault type and reason cannot be comprehensively and accurately identified is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of non-contact high-voltage mutual inductors, and more specifically, to a method for monitoring faults of power grid equipment based on non-contact high-voltage mutual inductors. Background Art

[0002] Non-contact high-voltage transformers are widely used in power systems for current and voltage measurement and monitoring. Their core function is to convert high-voltage current or voltage signals into low-voltage signals for subsequent control, monitoring and protection equipment use. As the scale of power systems continues to expand, the operating environment of power grid equipment has become increasingly complex, and the monitoring and diagnosis of equipment failures have become a key issue in ensuring the safe and stable operation of the power grid.

[0003] In recent years, the application of non-contact technology has gradually emerged, especially in the field of power equipment monitoring and grid stability optimization. As an innovative sensor, non-contact high-voltage transformers have the characteristics of non-destructive measurement, high precision and high reliability. Non-contact high-voltage transformers obtain voltage and current information in the power system through the principle of electromagnetic induction, which can not only effectively reduce the maintenance cost of traditional contact transformers, but also improve the safety and real-time operation of the power grid. Its working principle is mainly based on the changes in induced current and induced voltage. It accurately measures the electrical parameters of the transmission lines in the power grid in a non-contact manner and provides data support for the dispatching, control and optimization of the power grid.

[0004] The above disclosed technical solutions have at least the following technical problems: Traditional fault diagnosis mainly relies on human experience and lacks intelligent and automated analysis methods, resulting in poor accuracy and timeliness of fault diagnosis, and easy to miss potential fault hazards. In addition, the existing monitoring system has limited ability to analyze the cross-impact of multiple power parameters in a complex power grid environment, resulting in the inability to comprehensively and accurately identify the type and cause of equipment failures. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a power grid equipment fault monitoring method based on a non-contact high-voltage transformer, which solves the problem of being unable to comprehensively and accurately identify the type and cause of equipment faults by constructing a power grid fault coefficient model.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for monitoring power grid equipment faults based on a non-contact high-voltage transformer, comprising: obtaining transformer nodes in a test area, labeling the transformer nodes, and obtaining power grid fault data of the nodes to be tested through the transformer; analyzing the influence of electrical noise sources on the transformers based on linear regression, and correcting the power grid fault data; constructing a power grid fault coefficient model based on a machine learning algorithm according to the power grid fault data; dividing the test area into a plurality of sub-areas, and calculating the average power grid fault coefficient of each sub-area based on the power grid fault coefficient model; correcting the coefficient of the sub-area to be tested through the sub-areas connected to the sub-area to be tested, and obtaining a corrected power grid fault coefficient; sorting the corrected power grid fault coefficient in descending order in a sorting table, and performing maintenance according to the sorting table and a preset power grid equipment fault database.

[0007] In a preferred embodiment, the power grid fault data includes a voltage fluctuation coefficient, and the specific steps for obtaining the voltage fluctuation coefficient are as follows: obtain the electrical signal data of the transformer node to be tested, and amplify the collected electrical signal through an amplifier; transmit the signal amplified by the amplifier to a signal processing unit, and the signal processing unit includes a filter, a signal conditioning circuit and a digital converter; process the signal data through the filter in the signal processing unit to remove noise and interference and retain the effective signal; convert the processed signal data into voltage fluctuation data through the digital converter in the signal processing unit, add and average the voltage fluctuation data to obtain the average voltage; calculate based on the standard deviation formula according to the voltage fluctuation data and the average voltage to obtain the standard deviation of the voltage fluctuation; calculate based on the preset voltage fluctuation formula according to the standard deviation of the voltage fluctuation and the average voltage to obtain the voltage fluctuation coefficient.

[0008] In a preferred embodiment, the power grid fault data includes harmonic intensity, and the specific steps for obtaining the harmonic intensity are as follows: obtain the current signal of the transformer node to be tested, and transmit the current signal to a signal processing unit, process the signal through the signal processing unit to remove noise and interference; upload the processed current signal to an FFT analysis tool, perform Fourier transform on the current signal through the FFT analysis tool, convert the time domain signal into a frequency signal, and extract the frequency and amplitude from the frequency signal; according to the frequency, find the frequency point with the maximum amplitude in the frequency, and use the frequency point with the maximum amplitude as the fundamental frequency; perform FFT conversion on the time domain signal to obtain a set of amplitude and phase data, calculate the amplitude of the amplitude and phase data output based on a preset amplitude spectrum formula, and obtain the amplitude spectrum; analyze the frequency points near the fundamental frequency in the amplitude spectrum, obtain the harmonic frequency based on the principle that the harmonic frequency is an integer multiple of the fundamental frequency, and obtain the harmonic amplitude and fundamental amplitude based on the harmonic frequency and the fundamental frequency; calculate the harmonic intensity based on the harmonic amplitude and the fundamental amplitude based on the preset harmonic intensity formula.

[0009] In a preferred embodiment, the power grid fault data includes electromagnetic compatibility, and the specific steps for obtaining the electromagnetic compatibility are as follows: obtain the device voltage data monitored by the transformer node to be tested, and add and average the peak values ​​and valley values ​​of the voltage data respectively to obtain the voltage peak average value and the voltage valley average value; according to the voltage peak average value and the voltage valley average value, delete the voltage data higher than the voltage peak average value and lower than the voltage valley average value, and add and average the voltage data retained after deletion to obtain the voltage average value; obtain the distance from the electric field source to the receiving point of the transformer node to be tested, and calculate the electric field strength based on the electric field strength formula according to the voltage average value and the distance from the electric field source to the receiving point; obtain the device current data monitored by the transformer node to be tested, The peak values ​​and valley values ​​of the current data are respectively averaged to obtain the current peak value average value and the current valley value average value; according to the current peak value average value and the current valley value average value, the values ​​higher than the current peak value average value and lower than the current valley value average value are deleted, and the current data retained after deletion are averaged to obtain the current average value; the magnetic field strength is calculated based on the magnetic field strength formula according to the current average value and the distance from the electric field source to the receiving point; the power supply impedance and circuit impedance of the device to be tested are obtained, and the electromagnetic radiation power is calculated based on the preset electromagnetic radiation power formula according to the current average value, the power supply impedance and the circuit impedance; the electromagnetic compatibility is calculated based on the preset electromagnetic compatibility formula according to the electromagnetic radiation power, the magnetic field strength and the electric field strength.

[0010] In a preferred embodiment, the influence of the electrical noise source on the transformer is analyzed based on linear regression, and the power grid fault data is corrected. The specific steps are as follows: obtain the transformer node to be tested, use high-efficiency electromagnetic shielding materials to isolate the noise source, and record the signal power and noise power when not affected by the noise source; calculate based on the signal-to-noise ratio formula according to the signal power and noise power to obtain the signal-to-noise ratio when not affected by the noise source; turn on the noise source radiation device, and adjust the power of the equipment, record the signal power and noise power at different powers, calculate based on the signal-to-noise ratio formula, and obtain multiple groups of signal-to-noise ratios under different noise sources; obtain the electrical noise source accuracy influence coefficient based on the signal-to-noise ratio under different noise sources and the signal-to-noise ratio not affected by the noise source based on linear regression analysis, and correct the voltage fluctuation coefficient, harmonic intensity and electromagnetic compatibility parameters according to the electrical noise source accuracy influence coefficient.

[0011] In a preferred embodiment, the area to be tested is divided into multiple sub-areas, and the average grid failure coefficient of each sub-area is calculated based on the grid failure coefficient model, as follows: the coverage area range of the transformer node to be tested is obtained, and it is divided into N sub-areas of equal size according to the coverage area range of the transformer node to be tested; the grid failure coefficients of all transformer nodes in the sub-area are obtained, and the grid failure coefficients of all transformer nodes in the sub-area are added and averaged to obtain the grid failure coefficient of the sub-area.

[0012] In a preferred embodiment, the corrected grid fault coefficient is sorted in descending order in a sorting form, and maintenance is performed according to the sorting form and a preset grid equipment fault database, specifically as follows: the corrected grid fault coefficient of the sub-area is obtained, and sorted in descending order according to the size of the corrected grid fault coefficient. If the grid fault coefficient exceeds a threshold, an alarm will be issued to remind the administrator to perform maintenance; the administrator maintains the grid equipment according to the sorting form and the grid equipment fault database, compares the waveform and the cause of the fault in the grid equipment fault database during the maintenance of each node, and corrects the waveform and the cause of the fault in the grid equipment fault database; if the equipment is still in a faulty state after N repairs, the transformers around the equipment will be checked. If the transformer is not faulty, the equipment will be scrapped and replaced with a new one.

[0013] In a preferred embodiment, the power grid equipment fault database is specifically as follows: obtaining a transformer node to be tested, collecting voltage signals and current signals of the equipment to be tested in real time through the transformer, and converting the collected voltage signals and current signals into low-voltage processable signals; filtering the collected voltage data and current data, reconstructing the voltage data and current data into complete voltage waveforms and current waveforms through DSP technology, and correcting the voltage waveform and current waveform through the accuracy influence coefficient of the electrical noise source; obtaining the voltage waveform and current waveform under normal working conditions as the standard waveform; finding the places where the voltage and current waveforms are offset and unstable by comparing the standard waveform with the real-time voltage and current waveforms, analyzing the causes of the voltage and current waveforms offset and unstable places, and entering the waveforms and causes of the voltage and current waveforms offset and unstable places into the database.

[0014] The technical effects and advantages of the present invention's method for monitoring power grid equipment faults based on non-contact high-voltage mutual inductor are as follows: 1. The present invention collects grid fault data in real time through non-contact high-voltage mutual inductors, including voltage fluctuation coefficient, harmonic intensity and electromagnetic compatibility parameters, and accurately analyzes these data, which can more comprehensively reflect the operating status of grid equipment and provide higher fault detection accuracy than traditional methods. By real-time monitoring and comparison of the voltage waveform and current waveform of the equipment, it is possible to timely discover the abnormal operation of the equipment, identify the equipment failure mode, and enter these fault data into the database for long-term tracking and analysis, thereby realizing the health management and precise maintenance of grid equipment.

[0015] 2. Based on the corrected power grid fault coefficient and power grid fault coefficient, the method can automatically generate a descending sorting form to guide the operation and maintenance personnel to prioritize the areas with greater fault risks. By combining the power grid equipment fault database, a data-driven decision support system is formed, which can more accurately locate the fault source and carry out maintenance in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a schematic structural diagram of a method for monitoring faults of power grid equipment based on a non-contact high-voltage mutual inductor. DETAILED DESCRIPTION

[0017] 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.

[0018] Embodiment 1, Figure 1 The present invention provides a method for monitoring faults of power grid equipment based on a non-contact high-voltage transformer, comprising: S1, obtaining transformer nodes in the area to be tested, labeling the transformer nodes, and obtaining power grid fault data of the nodes to be tested through the transformers, wherein the power grid fault data includes voltage fluctuation coefficient, harmonic intensity and electromagnetic compatibility.

[0019] In this embodiment, the transformer nodes in the test area are obtained, the transformer nodes are labeled, and the power grid fault data of the nodes to be tested are obtained through the transformers. The power grid fault data includes voltage fluctuation coefficient, harmonics and electromagnetic compatibility, which are specifically as follows: Voltage fluctuation coefficient, voltage fluctuation coefficient is an indicator used to measure voltage fluctuation or voltage change, which indicates the degree of voltage change relative to its average value. Usually, it is used to evaluate the stability of voltage in power systems, especially when the load fluctuates greatly.

[0020] The power grid fault data includes a voltage fluctuation coefficient, and the specific steps for obtaining the voltage fluctuation coefficient are as follows: Acquire the electrical signal data of the transformer node to be tested, and amplify the collected electrical signal through an amplifier; Transmitting the signal amplified by the amplifier to a signal processing unit, wherein the signal processing unit includes a filter, a signal conditioning circuit and a digital converter; The signal data is processed by the filter in the signal processing unit to remove noise and interference and retain the effective signal; The processed signal data is converted into voltage fluctuation data by a digital converter in the signal processing unit, and the voltage fluctuation data is added and averaged to obtain an average voltage value; Calculate the standard deviation of the voltage fluctuation based on the voltage fluctuation data and the average value of the voltage based on the standard deviation formula to obtain the standard deviation of the voltage fluctuation; The voltage fluctuation coefficient is obtained by calculating according to the standard deviation of the voltage fluctuation and the average value of the voltage based on a preset voltage fluctuation formula.

[0021] The calculation formula of the voltage fluctuation coefficient is as follows:

[0022] The calculation formula of the average value of the voltage is as follows:

[0023] The calculation formula of the standard deviation of the voltage fluctuation is as follows:

[0024] In the formula, is the voltage fluctuation coefficient, is the standard deviation of voltage fluctuation, is the average value of the voltage, is the total number of data points, is the voltage at the i-th time point, i=1, 2, 3·····N.

[0025] It should be noted that the voltage fluctuation coefficient reflects the relative amplitude of voltage change. If the voltage fluctuation coefficient is small, it means that the voltage fluctuation is small and the power system is relatively stable. If the voltage fluctuation coefficient is large, it means that the voltage fluctuation is large and the system may have voltage instability problems.

[0026] Harmonic intensity: Harmonic intensity refers to the frequency components other than the fundamental frequency in a periodic signal. These components are usually integer multiples of the fundamental frequency. Harmonic analysis is often used in power systems, audio processing, and vibration analysis.

[0027] The power grid fault data includes harmonic intensity, and the specific steps for obtaining the harmonic intensity are as follows: Acquire the current signal of the transformer node to be tested, and transmit the current signal to the signal processing unit, and process the signal through the signal processing unit to remove noise and interference; The processed current signal is uploaded to the FFT (Fast Fourier Transform) analysis tool, and the current signal is Fourier transformed by the FFT (Fast Fourier Transform) analysis tool to convert the time domain signal into a frequency signal, and the frequency and amplitude are extracted from the frequency signal; According to the frequency, find the frequency point with the maximum amplitude in the frequency, and take the frequency point with the maximum amplitude as the fundamental frequency; The time domain signal is subjected to FFT (Fast Fourier Transform) conversion to obtain a set of amplitude and phase data, and the amplitude of the amplitude and phase data output is calculated based on a preset amplitude spectrum formula to obtain an amplitude spectrum; Analyze the frequency points near the fundamental frequency in the amplitude spectrum, obtain the harmonic frequency according to the principle that the harmonic frequency is an integer multiple of the fundamental frequency, and obtain the harmonic amplitude and the fundamental amplitude according to the harmonic frequency and the fundamental frequency; The harmonic intensity is calculated based on the harmonic amplitude and the fundamental wave amplitude based on a preset harmonic intensity formula to obtain the harmonic intensity.

[0028] The calculation formula of the harmonic intensity is as follows:

[0029] The calculation formula of the amplitude spectrum is as follows:

[0030] In the formula, is the harmonic intensity, represents the amplitude of the nth harmonic, represents the fundamental amplitude, is the magnitude of the magnitude and phase data output, is the real part of the amplitude and phase data frequency point, is the imaginary part of the amplitude and phase data at the frequency point.

[0031] Electromagnetic compatibility,Electromagnetic compatibility (EMC) is an important part of ensuring the normal operation of power systems, especially smart grids.For electromagnetic interference (EMI) generated by high-voltage current in the power grid, the intensity and impact of the electromagnetic field are detected by non-contact high-voltage mutual inductors to help evaluate and solve electromagnetic compatibility problems.

[0032] The power grid fault data includes electromagnetic compatibility, and the specific steps of obtaining the electromagnetic compatibility are as follows: Obtaining device voltage data monitored by the transformer node to be tested, and averaging the peak values ​​and valley values ​​of the voltage data to obtain a voltage peak value average value and a voltage valley value average value; According to the voltage peak average value and the voltage valley average value, the values ​​higher than the voltage peak average value and lower than the voltage valley average value are deleted, and the voltage data retained after the deletion are added and averaged to obtain the voltage average value; Obtain the distance from the electric field source of the transformer node to be tested to the receiving point, and calculate the electric field strength based on the electric field strength formula according to the voltage average value and the distance from the electric field source to the receiving point; Acquire the device current data monitored by the transformer node to be tested, and add and average the peak value and valley value of the current data to obtain the current peak value average value and the current valley value average value; According to the current peak average value and the current valley average value, the values ​​higher than the current peak average value and lower than the current valley average value are deleted, and the current data retained after the deletion are added and averaged to obtain the current average value; The magnetic field strength is obtained by calculating based on the magnetic field strength formula according to the current average value and the distance from the electric field source to the receiving point; Obtaining the power supply impedance and circuit impedance of the device under test, and calculating the electromagnetic radiation power based on the current average value, the power supply impedance and the circuit impedance based on a preset electromagnetic radiation power formula to obtain the electromagnetic radiation power; The electromagnetic compatibility is obtained by calculating the electromagnetic radiation power, the magnetic field strength and the electric field strength based on a preset electromagnetic compatibility formula.

[0033] The calculation formula of electromagnetic compatibility is as follows:

[0034] The calculation formula of electromagnetic compatibility is as follows:

[0035] In the formula, is electromagnetic compatibility, is the electromagnetic radiation power, is the electromagnetic radiation power under normal conditions, is the electric field strength, is the electric field strength under normal conditions, is the magnetic field strength, is the magnetic field strength under normal conditions, is the free space wave impedance, , , and is an adjustment factor used to weigh the different contributions of electric field, magnetic field and radiated power to electromagnetic compatibility. is the impedance of the circuit, is the impedance of the power supply, It's electric current.

[0036] S2, based on linear regression analysis of the impact of electrical noise sources on the transformer, and correction of power grid fault data.

[0037] In this embodiment, the influence of the electrical noise source on the transformer is analyzed based on linear regression, and the power grid fault data is corrected. The specific steps are as follows: Obtain the transformer node to be tested, use efficient electromagnetic shielding materials to isolate the noise source, and record the signal power and noise power without being affected by the noise source; Calculate the signal-to-noise ratio based on the signal power and the noise power based on the signal-to-noise ratio formula to obtain the signal-to-noise ratio without being affected by the noise source; Turn on the noise source radiation device and adjust the power of the device, record the signal power and noise power at different powers, and calculate based on the signal-to-noise ratio formula to obtain the signal-to-noise ratio under multiple groups of different noise sources; Based on linear regression analysis, the accuracy influence coefficient of the electrical noise source is obtained according to the signal-to-noise ratio under different noise sources and the signal-to-noise ratio without the influence of the noise source. The voltage fluctuation coefficient, harmonic intensity and electromagnetic compatibility parameters are corrected according to the accuracy influence coefficient of the electrical noise source.

[0038] S3, constructing a power grid fault coefficient model based on the power grid fault data and a machine learning algorithm.

[0039] In this embodiment, the power grid fault coefficient model is constructed based on the machine learning algorithm according to the power grid fault data, as follows: The specific calculation formula of the power grid fault coefficient model is as follows:

[0040] In the formula, is the grid failure coefficient, is the voltage fluctuation coefficient, is the harmonic intensity, is electromagnetic compatibility, is the accuracy influence coefficient of the electrical noise source, It is the natural base.

[0041] S4, dividing the area to be tested into multiple sub-areas, and calculating an average power grid failure coefficient of each sub-area based on a power grid failure coefficient model.

[0042] In this embodiment, the area to be tested is divided into multiple sub-areas, and the average power grid failure coefficient of each sub-area is calculated based on the power grid failure coefficient model, as follows: Obtain the coverage area of ​​the transformer node to be tested, and divide it into N sub-areas of the same size according to the coverage area of ​​the transformer node to be tested; The power grid failure coefficients of all transformer nodes in the sub-area are obtained, and the power grid failure coefficients of all transformer nodes in the sub-area are added and averaged to obtain the power grid failure coefficient of the sub-area.

[0043] S5, performing coefficient correction on the sub-region to be measured through the sub-regions connected to the sub-region to be measured, to obtain a corrected power grid fault coefficient.

[0044] In this embodiment, the sub-region connected to the sub-region to be measured performs coefficient correction on the sub-region to be measured to obtain a corrected power grid fault coefficient, which is specifically as follows: The calculation formula of the corrected power grid fault coefficient is as follows:

[0045] In the formula, is the corrected grid fault coefficient, is the grid failure coefficient, is the weight coefficient, is the number of sub-regions connected to the sub-region to be tested, Represents the weight coefficient of the sub-region connected to the i-th sub-region to be tested.

[0046] S6, sorting the corrected power grid fault coefficient in descending order, and performing maintenance according to the sorting table and a preset power grid equipment fault database.

[0047] In this embodiment, the descending sorting table of the corrected power grid fault coefficient is repaired according to the sorting table and the preset power grid equipment fault database, as follows: Obtain the corrected power grid fault coefficient of the sub-area, sort it in descending order according to the corrected power grid fault coefficient, and if the power grid fault coefficient exceeds the threshold, an alarm will be issued to remind the administrator to perform maintenance; The administrator maintains the power grid equipment according to the sorting list and the power grid equipment fault database. During the maintenance of each node, the waveform and fault cause in the power grid equipment fault database are compared and corrected. If the equipment is still in a faulty state after N repairs, the transformers around the equipment will be checked. If the transformers are not faulty, the equipment will be scrapped and replaced with new equipment.

[0048] In this embodiment, the power grid equipment fault database is specifically: Obtain the transformer node to be tested, collect the voltage signal and current signal of the device to be tested in real time through the transformer, and convert the collected voltage signal and current signal into a low-voltage processable signal; The collected voltage and current data are filtered and reconstructed into complete voltage and current waveforms through DSP (digital signal processor) technology, and the voltage and current waveforms are corrected through the electrical noise source accuracy influence coefficient; Obtaining voltage waveform and current waveform under normal working conditions as standard waveforms; By comparing the standard waveform with the real-time voltage and current waveforms, the offset and unstable parts of the voltage and current waveforms are found, the reasons for the offset and instability of the voltage and current waveforms are analyzed, and the waveforms and reasons for the offset and instability of the voltage and current waveforms are entered into the database.

[0049] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0050] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0051] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0052] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0053] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0054] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring power grid equipment faults based on a non-contact high-voltage transformer, characterized in that: include: Obtaining transformer nodes in the area to be tested, labeling the transformer nodes, and obtaining power grid fault data of the nodes to be tested through the transformers; Analyze the impact of electrical noise sources on transformers based on linear regression and correct grid fault data; Constructing a power grid fault coefficient model based on the machine learning algorithm according to the power grid fault data; The area to be tested is divided into multiple sub-areas, and the average power grid failure coefficient of each sub-area is calculated based on the power grid failure coefficient model; Performing coefficient correction on the sub-region to be measured by the sub-region connected to the sub-region to be measured, so as to obtain a corrected power grid fault coefficient; The corrected power grid fault coefficient is sorted in descending order in a sorting table, and maintenance is performed according to the sorting table and a preset power grid equipment fault database.

2. The method for monitoring power grid equipment faults based on non-contact high-voltage mutual inductor according to claim 1, characterized in that: The power grid fault data includes a voltage fluctuation coefficient, and the specific steps for obtaining the voltage fluctuation coefficient are as follows: Acquire the electrical signal data of the transformer node to be tested, and amplify the collected electrical signal through an amplifier; Transmitting the signal amplified by the amplifier to a signal processing unit, wherein the signal processing unit includes a filter, a signal conditioning circuit and a digital converter; Processing the signal data through the filter in the signal processing unit to remove noise and interference and retain the effective signal; The processed signal data is converted into voltage fluctuation data by a digital converter in the signal processing unit, and the voltage fluctuation data is added and averaged to obtain an average voltage value; Calculate the standard deviation of the voltage fluctuation based on the voltage fluctuation data and the average value of the voltage based on the standard deviation formula to obtain the standard deviation of the voltage fluctuation; The voltage fluctuation coefficient is obtained by calculating according to the standard deviation of the voltage fluctuation and the average value of the voltage based on a preset voltage fluctuation formula.

3. The method for monitoring power grid equipment faults based on non-contact high voltage mutual inductor according to claim 2, characterized in that: The power grid fault data includes harmonic intensity, and the specific steps for obtaining the harmonic intensity are as follows: Acquire the current signal of the transformer node to be tested, and transmit the current signal to the signal processing unit, and process the signal through the signal processing unit to remove noise and interference; The processed current signal is uploaded to the FFT analysis tool, and the current signal is subjected to Fourier transform through the FFT analysis tool, so as to convert the time domain signal into a frequency signal, and extract the frequency and amplitude from the frequency signal; According to the frequency, find the frequency point with the maximum amplitude in the frequency, and take the frequency point with the maximum amplitude as the fundamental frequency; Performing FFT conversion on the time domain signal to obtain a set of amplitude and phase data, calculating the amplitude of the amplitude and phase data output based on a preset amplitude spectrum formula to obtain an amplitude spectrum; Analyze the frequency points near the fundamental frequency in the amplitude spectrum, obtain the harmonic frequency according to the principle that the harmonic frequency is an integer multiple of the fundamental frequency, and obtain the harmonic amplitude and the fundamental amplitude according to the harmonic frequency and the fundamental frequency; The harmonic intensity is calculated based on the harmonic amplitude and the fundamental wave amplitude based on a preset harmonic intensity formula to obtain the harmonic intensity.

4. The method for monitoring power grid equipment faults based on non-contact high-voltage transformer according to claim 3 is characterized in that: The power grid fault data includes electromagnetic compatibility, and the specific steps of obtaining the electromagnetic compatibility are as follows: Obtaining device voltage data monitored by the transformer node to be tested, and averaging the peak values ​​and valley values ​​of the voltage data to obtain a voltage peak value average value and a voltage valley value average value; According to the voltage peak average value and the voltage valley average value, the values ​​higher than the voltage peak average value and lower than the voltage valley average value are deleted, and the voltage data retained after the deletion are added and averaged to obtain the voltage average value; Obtain the distance from the electric field source of the transformer node to be tested to the receiving point, and calculate the electric field strength based on the electric field strength formula according to the voltage average value and the distance from the electric field source to the receiving point; Acquire the device current data monitored by the transformer node to be tested, and add and average the peak value and valley value of the current data to obtain the current peak value average value and the current valley value average value; According to the current peak average value and the current valley average value, the values ​​higher than the current peak average value and lower than the current valley average value are deleted, and the current data retained after the deletion are added and averaged to obtain the current average value; The magnetic field strength is obtained by calculating based on the magnetic field strength formula according to the current average value and the distance from the electric field source to the receiving point; Obtaining the power supply impedance and circuit impedance of the device under test, and calculating the electromagnetic radiation power based on the current average value, the power supply impedance and the circuit impedance based on a preset electromagnetic radiation power formula to obtain the electromagnetic radiation power; The electromagnetic compatibility is obtained by calculating the electromagnetic radiation power, the magnetic field strength and the electric field strength based on a preset electromagnetic compatibility formula.

5. The method for monitoring power grid equipment faults based on non-contact high voltage mutual inductor according to claim 4, characterized in that: The influence of the electrical noise source on the transformer is analyzed based on linear regression, and the power grid fault data is corrected. The specific steps are as follows: Obtain the transformer node to be tested, use efficient electromagnetic shielding materials to isolate the noise source, and record the signal power and noise power without being affected by the noise source; Calculate the signal-to-noise ratio based on the signal power and the noise power based on the signal-to-noise ratio formula to obtain the signal-to-noise ratio without being affected by the noise source; Turn on the noise source radiation device and adjust the power of the device, record the signal power and noise power at different powers, and calculate based on the signal-to-noise ratio formula to obtain the signal-to-noise ratio under multiple groups of different noise sources; Based on linear regression analysis, the accuracy influence coefficient of the electrical noise source is obtained according to the signal-to-noise ratio under different noise sources and the signal-to-noise ratio without the influence of the noise source. The voltage fluctuation coefficient, harmonic intensity and electromagnetic compatibility parameters are corrected according to the accuracy influence coefficient of the electrical noise source.

6. The method for monitoring power grid equipment faults based on non-contact high voltage transformer according to claim 5, characterized in that: The area to be tested is divided into multiple sub-areas, and the average power grid failure coefficient of each sub-area is calculated based on the power grid failure coefficient model, as follows: Obtain the coverage area of ​​the transformer node to be tested, and divide it into N sub-areas of the same size according to the coverage area of ​​the transformer node to be tested; The power grid failure coefficients of all transformer nodes in the sub-area are obtained, and the power grid failure coefficients of all transformer nodes in the sub-area are added and averaged to obtain the power grid failure coefficient of the sub-area.

7. The method for monitoring power grid equipment faults based on non-contact high voltage transformer according to claim 6, characterized in that: The descending sorting table of the corrected power grid fault coefficient is repaired according to the sorting table and the preset power grid equipment fault database, as follows: Obtain the corrected power grid fault coefficient of the sub-area, sort it in descending order according to the corrected power grid fault coefficient, and if the power grid fault coefficient exceeds the threshold, an alarm will be issued to remind the administrator to perform maintenance; The administrator maintains the power grid equipment according to the sorting list and the power grid equipment fault database. During the maintenance of each node, the waveform and fault cause in the power grid equipment fault database are compared and corrected. If the equipment is still in a faulty state after N repairs, the transformers around the equipment will be checked. If the transformers are not faulty, the equipment will be scrapped and replaced with new equipment.

8. The method for monitoring power grid equipment faults based on non-contact high-voltage transformer according to claim 7, characterized in that: The power grid equipment fault database is specifically: Obtain the transformer node to be tested, collect the voltage signal and current signal of the device to be tested in real time through the transformer, and convert the collected voltage signal and current signal into a low-voltage processable signal; The collected voltage and current data are filtered and reconstructed into complete voltage and current waveforms through DSP technology. At the same time, the voltage and current waveforms are corrected through the accuracy influence coefficient of the electrical noise source. Obtaining voltage waveform and current waveform under normal working conditions as standard waveforms; By comparing the standard waveform with the real-time voltage and current waveforms, the offset and unstable parts of the voltage and current waveforms are found, the reasons for the offset and instability of the voltage and current waveforms are analyzed, and the waveforms and reasons for the offset and instability of the voltage and current waveforms are entered into the database.

9. The method for monitoring power grid equipment faults based on non-contact high-voltage transformer according to claim 8, characterized in that: The power grid fault coefficient model is constructed based on the machine learning algorithm according to the power grid fault data, specifically as follows: The specific calculation formula of the power grid fault coefficient model is as follows: In the formula, is the grid failure coefficient, is the voltage fluctuation coefficient, is the harmonic intensity, is electromagnetic compatibility, is the accuracy influence coefficient of the electrical noise source, It is the natural base.

10. The method for monitoring power grid equipment faults based on non-contact high voltage mutual inductor according to claim 9, characterized in that: The coefficient of the sub-region to be measured is corrected by the sub-region connected to the sub-region to be measured to obtain the corrected power grid fault coefficient, which is specifically as follows: The calculation formula of the corrected power grid fault coefficient is as follows: In the formula, is the corrected grid fault coefficient, is the grid failure coefficient, is the weight coefficient, is the number of sub-regions connected to the sub-region to be tested, Represents the weight coefficient of the sub-region connected to the i-th sub-region to be tested.

Images