Grounding system safety monitoring method and device

Abstract

The invention discloses a grounding system safety monitoring method and device. The method comprises the following steps: acquiring target frequency domain characteristic data, including target frequency spectrum data and target phase deviation data, of a target grounding system; determining a target similarity between the target frequency domain characteristic data and preset reference frequency domain characteristic data, wherein the reference frequency domain characteristic data comprises reference frequency spectrum data and reference phase deviation data which are acquired under the condition that the grounding impedance is normal; if the target similarity is lower than a preset threshold value, determining that the target grounding system has a fault; analyzing the target frequency domain feature data by using a pre-trained fault classification model to obtain a fault reason and a fault level; and if the fault level exceeds the preset alarm level, generating fault alarm information, and generating a fault processing work order. According to the invention, the technical problem that the safety of the grounding system is difficult to control efficiently in real time due to the complex grounding impedance measurement process in the related scheme is solved.

Description

Technical Field

[0001] The present application relates to the field of power safety technology, and in particular to a grounding system safety monitoring method and device. Background Art

[0002] The grounding system is an indispensable part of the electrical system, especially in communication buildings, data centers, industrial facilities and other places. It provides a stable reference potential to ensure the normal operation of the electrical system. In the communication building, there are various types of electrical equipment and many connecting cables between the equipment. The ground wire layout is complicated. Various factors make the measurement of the grounding system very difficult. The measurement of grounding resistance is an important part of ensuring the safety and stable operation of the electrical system. When measuring the grounding resistance, a zero potential reference point is required, which is often difficult to find in practice. There are also many traditional measurement methods, such as: three-level method, four-level method, single-clamp measurement, double-clamp method, etc., but most of these methods are complicated to operate and are not suitable for all occasions, resulting in the inability to regularly check the grounding situation. In addition, many ground wires are arranged inside the wall, which brings great difficulties to daily inspections.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for monitoring the safety of a grounding system, so as to at least solve the technical problem in related schemes that it is difficult to effectively and efficiently manage the safety of the grounding system in real time due to the complexity of the grounding impedance measurement process.

[0005] According to one aspect of an embodiment of the present application, a grounding system safety monitoring method is provided, including: obtaining target frequency domain feature data of a target grounding system, wherein the target frequency domain feature data includes: target spectrum data and target phase offset data; determining a target similarity between the target frequency domain feature data and preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference spectrum data and reference phase offset data obtained when the grounding impedance of the target grounding system is normal; when the target similarity is less than a preset similarity threshold, determining that a fault exists in the target grounding system, analyzing the target frequency domain feature data using a pre-trained fault classification model, and obtaining a fault cause and fault level of the target grounding system; when the fault level is greater than a preset alarm level, generating fault alarm information, and generating a fault handling work order based on the fault cause.

[0006] Optionally, target frequency domain characteristic data of the target grounding system is obtained, including: using a spectrum analyzer to collect a frequency signal of the target grounding system, performing fast Fourier transform processing on the frequency signal to obtain target spectrum data, and determining target phase offset data based on the phase information of the frequency signal in the target spectrum data.

[0007] Optionally, determining the similarity between the target frequency domain feature data and the preset benchmark frequency domain feature data includes: splicing the target spectrum data and the target phase offset data into a first feature vector; splicing the benchmark spectrum data and the benchmark phase offset data into a second feature vector; and determining the cosine similarity between the first feature vector and the second feature vector as the target similarity.

[0008] Optionally, the process of determining the similarity threshold includes: obtaining multiple sets of historical frequency domain feature data of the target grounding system under various fault scenarios; respectively determining the similarity between each set of historical frequency domain feature data and the benchmark frequency domain feature data; and determining the similarity threshold based on the maximum similarity among the multiple similarities obtained.

[0009] Optionally, the training process of the fault classification model includes: constructing an initial classification model, wherein the type of the initial classification model includes at least one of the following: logistic regression model, neural network, random forest, decision tree, support vector machine; obtaining multiple sets of historical frequency domain feature data of the target grounding system under various fault scenarios as a training sample set, wherein each training sample is a set of historical frequency domain feature data when a grounding fault of a fault level occurs in the target grounding system due to a fault cause, and the sample label of the training sample is the fault cause and the fault level; using the training sample set to iteratively train the initial classification model, and using the cross-validation method to evaluate the model performance during the model training process to adjust the model parameters, and using the trained model as a fault classification model.

[0010] Optionally, the target frequency domain feature data and multiple groups of historical frequency domain feature data within a preset historical time period are displayed in the human-computer interaction interface; when the fault level is greater than the alarm level, a pop-up window is displayed in the human-computer interaction interface to display the fault alarm information, and the fault alarm information is sent to the target object using a preset method, wherein the fault alarm information includes at least the cause of the fault, and the preset method includes at least one of the following: email, text message.

[0011] Optionally, after generating a fault handling work order based on the cause of the fault, the method also includes: obtaining the fault handling result of the target object for the fault handling work order, and determining the actual fault cause and actual fault level of the target grounding system based on the fault handling result; using the target frequency domain feature data as a new training sample, and storing the actual fault cause and actual fault level as sample labels of the new training sample; periodically using the stored new training samples to retrain the fault classification model, and updating the model parameters of the fault classification model.

[0012] According to another aspect of an embodiment of the present application, a grounding system safety monitoring device is also provided, including: an acquisition module, used to acquire target frequency domain feature data of a target grounding system, wherein the target frequency domain feature data includes: target spectrum data and target phase offset data; a comparison module, used to determine the target similarity between the target frequency domain feature data and preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference spectrum data and reference phase offset data acquired when the grounding impedance of the target grounding system is normal; a fault analysis module, used to determine that a fault exists in the target grounding system when the target similarity is less than a preset similarity threshold, and to analyze the target frequency domain feature data using a pre-trained fault classification model to obtain the fault cause and fault level of the target grounding system; a fault handling module, used to generate fault alarm information when the fault level is greater than a preset alarm level, and to generate a fault handling work order based on the fault cause.

[0013] According to another aspect of an embodiment of the present application, a computer program product is further provided, the computer program product comprising: a computer program, wherein when the computer program is executed by a processor, the above-mentioned grounding system safety monitoring method is implemented.

[0014] According to another aspect of an embodiment of the present application, an electronic device is further provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned grounding system safety monitoring method through the computer program.

[0015] In the present application, the target frequency domain characteristic data of the target grounding system is obtained, wherein the target frequency domain characteristic data includes: target spectrum data and target phase offset data; the target similarity between the target frequency domain characteristic data and the preset reference frequency domain characteristic data is determined, wherein the reference frequency domain characteristic data includes: reference spectrum data and reference phase offset data obtained when the grounding impedance of the target grounding system is normal; when the target similarity is less than the preset similarity threshold, it is determined that there is a fault in the target grounding system, and the target frequency domain characteristic data is analyzed using a pre-trained fault classification model to obtain the fault cause and fault level of the target grounding system; when the fault level is greater than the preset alarm level, a fault alarm message is generated, and a fault handling work order is generated based on the fault cause. In this way, by using frequency domain characteristic data and phase offset data, combined with the trained model, instantaneous faults or performance degradations can be captured, thereby achieving faster response and processing, thereby solving the technical problem in the related scheme that the grounding impedance measurement process is complicated and it is difficult to effectively and efficiently control the safety of the grounding system in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a flow chart of an optional grounding system safety monitoring method according to an embodiment of the present application;

[0018] Figure 2 is a schematic structural diagram of an optional grounding system safety monitoring device according to an embodiment of the present application;

[0019] Figure 3 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] Example 1

[0023] According to an embodiment of the present application, a grounding system safety monitoring method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] Figure 1is a flow chart of a grounding system safety monitoring method provided according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0025] Step S102, obtaining target frequency domain characteristic data of a target grounding system, wherein the target frequency domain characteristic data includes: target spectrum data and target phase offset data;

[0026] Step S104, determining a target similarity between the target frequency domain feature data and preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference frequency spectrum data and reference phase offset data acquired when the ground impedance of the target grounding system is normal;

[0027] Step S106, when the target similarity is less than a preset similarity threshold, it is determined that there is a fault in the target grounding system, and the target frequency domain feature data is analyzed using a pre-trained fault classification model to obtain the fault cause and fault level of the target grounding system;

[0028] Step S108, when the fault level is greater than the preset alarm level, a fault alarm message is generated, and a fault handling work order is generated according to the fault cause.

[0029] The following describes the various steps of the grounding system safety monitoring method in conjunction with a specific implementation process.

[0030] The general grounding system can be understood as a composite oscillator system composed of resistance, inductance and capacitance. If the concept of complex numbers in mathematics is introduced, resistance, inductance and capacitance can be expressed in the same form of complex impedance, which are:

[0031] Z R =R

[0032] Z L =jωL

[0033]

[0034] The total impedance is:

[0035]

[0036] Where j is the imaginary unit (j 2 =-1), ω is the angular frequency (ω = 2πf, f is the frequency), where R is the resistance, ωL is the inductive reactance, For capacitive reactance.

[0037] like It is called "inductive load"; if "Capacitive load"; if When the circuit reaches resonance, the impedance of the inductor L and the capacitor C are equal and opposite in phase, the total impedance of the circuit is minimum, and the current reaches the maximum value. At this time, the resonant frequency of the circuit is:

[0038]

[0039] Where f0 represents the resonant frequency, C represents the capacitance, and L represents the inductance.

[0040] When the grounding system changes, its circuit inductance L and capacitance C change, the resonant frequency of the circuit will also change, the circuit's spectrum resonance point (one of them) will also change accordingly, and the spectrum will change.

[0041] The Smith chart is a graphical tool used to analyze transmission lines and matching networks by normalizing impedance (or admittance) and reflection coefficient and mapping these parameters onto a unit circle for easy visualization and calculation.

[0042] Impedance normalization refers to normalizing the actual impedance to the characteristic impedance to facilitate comparison and calculation on the same scale. The normalized impedance is the ratio of the actual impedance to the characteristic impedance, expressed as:

[0043]

[0044] In the formula, It represents normalized impedance, Z represents the actual impedance at a point on the transmission line, and Z0 represents the standard impedance on the transmission line, which is usually a known constant.

[0045] The reflection coefficient describes the ratio of the reflected wave to the incident wave at a certain point on the transmission line. The relationship between the reflection coefficient and the normalized impedance is expressed as:

[0046]

[0047] In the formula, Γ represents the reflection coefficient, and the reflection coefficient can be obtained by inverse calculation:

[0048]

[0049] Electrical length normalization refers to converting the actual length of the transmission line into electrical length to facilitate calculation in the frequency domain. The electrical length is expressed as:

[0050]

[0051] Where Υ represents the electrical length, λ g represents the waveguide wavelength and l represents the actual length.

[0052] The reflection coefficient depends not only on the load impedance but also on the length of the transmission line. The normalized length can reflect the phase change of the reflection coefficient. The period is half the wavelength. The expression of the reflection coefficient at the input end is:

[0053] Γ in =Γ L ·e -j2βl (0≤|Γ|≤1)

[0054] In the formula, Γ in is the input reflection coefficient, Γ L represents the reflection coefficient of the load, and β represents the propagation coefficient, which is defined as l represents the actual length of the transmission line.

[0055] On the Smith chart, each point represents a specific normalized impedance or reflection coefficient.

[0056] Normalized impedance It can be expressed as:

[0057]

[0058] Where r is the normalized resistance and x is the normalized reactance.

[0059] The reflection coefficient Γ can be expressed as:

[0060] Γ=Γ r +jΓ i

[0061] In the formula, Γ r represents the real part of the reflection coefficient, Γ i Represents the imaginary part of the reflection coefficient.

[0062] Fit the impedance and admittance relationship on the |Γ| circle.

[0063] Known:

[0064]

[0065] Substituting into the expression for reflection coefficient:

[0066]

[0067] Separating the real and imaginary parts, we get:

[0068]

[0069] For the resistor r:

[0070]

[0071] Get the resistance circle equation:

[0072]

[0073] The corresponding coordinates of the circle center are: The radius is: The center of the circle is on the real axis, considering Therefore, the resistance circle always coincides with the straight line Γ r =1 tangent.

[0074] On the Smith chart, the real axis represents the pure impedance point, that is, reactance x = 0, which means that the point on the real axis contains only resistance components and no reactance components. The point corresponding to the resistance r can be used to calculate the voltage standing wave ratio ρ through the real part of the reflection coefficient. The specific expression is:

[0075]

[0076] Where ρ represents the voltage standing wave ratio, which describes the ratio of the maximum and minimum voltage on the transmission line.

[0077] Quarter-wavelength impedance transformation is an important concept in transmission theory. When the length of the transmission line is one quarter of the wavelength, there is a special relationship between the input impedance and the load impedance:

[0078]

[0079] In the formula, z in represents input impedance, Z0 represents characteristic impedance, Z l Indicates the load impedance.

[0080] The normalized input impedance can be expressed as:

[0081]

[0082] Further normalization:

[0083]

[0084] In the above formula, represents the normalized load impedance, represents the normalized load admittance.

[0085] From the above physical formula, we can know that external factors such as temperature, humidity, load changes and other external factors will cause changes in component parameters in the circuit, thereby causing changes in impedance. Changes in impedance will cause changes in the reflection coefficient, because the reflection coefficient is directly related to impedance, which in turn leads to changes in the voltage standing wave ratio in the power supply, because the voltage standing wave ratio is a function of the reflection coefficient modulus. Changes in the transmission line length will also cause changes in the phase of the reflection coefficient.

[0086] The grounding system is considered as a complex electromagnetic system that contains different components such as resistance, inductance and capacitance. These components together determine the system's response to current, including impedance and phase shift. When these components in the grounding system are combined, they will exhibit different impedance characteristics at different frequencies. Impedance is the total resistance of the circuit to the current, which includes the combined effects of resistance, inductance and capacitance. Impedance affects not only the magnitude of the current, but also the phase relationship between the current and voltage. In the absence of external interference, the frequency spectrum curve of the grounding system is relatively stable and can be used as a reference for the normal working state of the system. This frequency spectrum curve can reflect the electromagnetic characteristics of the grounding system. When the grounding system changes, such as material aging, corrosion of connection points, or changes in soil conditions, the parameters of the system's resistance, inductance, and capacitance will change, causing changes in the impedance characteristics and phase response of the entire system. From the analysis of the above physical formula, it can be seen that when the impedance changes, the reflection coefficient and standing wave coefficient of the system will also change. In a system with poor impedance matching, the spectrum will show ringing and distortion caused by reflection and standing waves. Therefore, this application proposes to regularly detect and analyze the spectrum curve of the grounding system, and identify small changes in the spectrum curve by comparing historical data and real-time data, so as to determine whether there are potential problems in the grounding system, and combine artificial intelligence algorithms to improve the accuracy and efficiency of fault detection, so as to better maintain the health of the grounding system. The specific implementation method is as follows:

[0087] First, the target frequency domain characteristic data of the target grounding system is obtained, wherein the target frequency domain characteristic data includes: target spectrum data and target phase offset data. The specific steps for obtaining the above data can be performed in the following manner: First, the frequency signal of the target grounding system is collected by a spectrum analyzer, and then the frequency signal is processed by fast Fourier transform to obtain the target spectrum data, and the target phase offset data is determined based on the phase information of the frequency signal in the target spectrum data.

[0088] Among them, the parameters of the spectrum analyzer can be set first, such as the center frequency, frequency bandwidth, resolution bandwidth, etc., to ensure that it can cover the measured frequency range and provide sufficient frequency resolution. The spectrum analyzer will display the power distribution of the grounding system at different frequencies. The frequency signal data collected by the spectrum analyzer will be exported. Usually, these data will exist in the form of time series. The time series data is processed using fast Fourier transform. Fast Fourier transform can convert time domain signals into frequency domain signals to obtain the frequency components and corresponding amplitudes of the signals. After fast Fourier transform processing, a spectrum will be obtained, showing the amplitude (power) information at different frequencies. The corresponding spectrum data is the target spectrum data. From the complex results obtained after fast Fourier transform processing, the phase information of each frequency component is extracted. For multiple measurement points in the target grounding system, their phase information at the same frequency is compared to determine the phase offset and obtain the target phase offset data. The phase offset can reflect the propagation delay or reflection of the signal in the system.

[0089] As an optional implementation, after obtaining the above data, the similarity between the target frequency domain feature data and the preset reference frequency domain feature data is determined, wherein the reference frequency domain feature data includes: reference spectrum data and reference phase offset data obtained when the grounding impedance of the target grounding system is normal, and the specific steps can be performed by the following steps: splicing the target spectrum data and the target phase offset data into a first feature vector; then splicing the reference spectrum data and the reference phase offset data into a second feature vector; and then determining the cosine similarity between the first feature vector and the second feature vector as the target similarity. The above similarity will be used to compare with the preset similarity threshold to determine whether the target grounding system is faulty.

[0090] Among them, the cosine similarity calculation principle can be understood as:

[0091] The cosine formula of the angle between vector A (x1, y1) and vector B (x2, y2) in three-dimensional space is expressed as:

[0092]

[0093] The cosine of the angle between two n-dimensional sample points a(x11, x12, …, x1n) and a(x21, x22, …, x2n) is similar. For two n-dimensional sample points (x11, x12, …, x1n) and a(x21, x22, …, x2n), a concept similar to the cosine of the angle can be used to measure the similarity between them.

[0094]

[0095] Right now:

[0096]

[0097] In the formula, the value range of the angle cosine cosθ is precisely limited to the interval [-1,1]. Its value directly reflects the size relationship of the angle θ between the two vectors: when the angle cosine value approaches 1, it means that the angle between the two vectors approaches 0, that is, their directions are closer to coincidence; conversely, when the angle cosine value approaches -1, it means that the angle between the two vectors is close to 180 degrees, that is, their directions are almost opposite.

[0098] It should be noted that other similarity calculation methods can also be used to determine the similarity between the target frequency domain feature data and the preset reference frequency domain feature data, such as: Euclidean distance, Manhattan distance, Chebyshev distance, Jaccard similarity coefficient, Hamming distance, etc., which can be selected according to the specific application scenario and data characteristics to achieve effective monitoring and evaluation of the target grounding system status.

[0099] As an optional implementation, the process of determining the similarity threshold includes: obtaining multiple groups of historical frequency domain feature data of the target grounding system under various fault scenarios; respectively determining the similarity between each group of historical frequency domain feature data and the benchmark frequency domain feature data; determining the similarity threshold based on the maximum similarity among the multiple similarities obtained, or the similarity threshold may also be slightly greater than the maximum similarity.

[0100] It should be noted that when determining the similarity threshold, an adaptive threshold segmentation technique can also be used. This method can automatically adjust the similarity threshold according to the characteristics of the data to adapt to different data sets and application scenarios. The selection of the threshold can be based on the distribution characteristics of the data. For example, it can be assumed that the data follows a normal distribution or a log-normal distribution, and the threshold can be determined based on the distribution characteristics.

[0101] When comparing the target similarity with the preset similarity threshold, if the target similarity is less than the preset similarity threshold, it is determined that there is a fault in the target grounding system, and then the pre-trained fault classification model is used to analyze the target frequency domain feature data, so as to obtain the fault cause and fault level of the target grounding system.

[0102] Optionally, the training process of the fault classification model includes: constructing an initial classification model, wherein the type of the initial classification model includes at least one of the following: logistic regression model, neural network, random forest, decision tree, support vector machine; obtaining multiple sets of historical frequency domain feature data of the target grounding system under various fault scenarios as a training sample set, wherein each training sample is a set of historical frequency domain feature data when a grounding fault of a fault level occurs in the target grounding system due to a fault cause, and the sample label of the training sample is the fault cause and the fault level; using the training sample set to iteratively train the initial classification model, and using the cross-validation method to evaluate the model performance during the model training process to adjust the model parameters, and using the trained model as a fault classification model.

[0103] The above-mentioned causes of failure include, for example: changes in the power load of the communication machine, maintenance or replacement of communication equipment, maintenance or replacement of communication equipment, increase in communication traffic, aging of the grounding system over time, etc. The fault level can also be divided artificially according to the severity of the fault: serious, relatively serious, minor, etc.

[0104] Acquiring multiple sets of historical frequency domain feature data of the target grounding system under various fault scenarios may include but is not limited to the following situations, for example: increased use of air conditioning in summer leads to changes in power load, which may introduce harmonics into the system's spectrum and affect the spectrum; when communication equipment is maintained or replaced, the transmission and reception characteristics of the signal may be temporarily changed, thereby affecting the spectrum measured by the spectrum analyzer; during peak communication hours, such as holidays or special events, an increase in communication traffic may cause changes in spectrum density; decoration, equipment movement or other activities inside the building where the target grounding system is located may temporarily affect the grounding effect of the grounding system, resulting in spectrum changes; aging of the grounding system over time may lead to an increase in grounding resistance, affecting the stability and spectrum characteristics of the signal, and so on. Data acquired in scenarios that cause spectrum changes are all training samples.

[0105] It should be noted that the training sample information can also be obtained by using traditional measurement methods, such as the three-wire method, the four-wire method, the single-clamp measurement, the double-clamp method, etc. The data measured by these methods can also be used as training sample data.

[0106] As an optional implementation, before training the fault classification model, the training samples can also be preprocessed, including normalization, missing value processing, feature selection, etc. If the amount of data is small, cross-validation is performed by dividing the training set into multiple small subsets, and then using a part of them for testing and the rest for training. This process is repeated many times, and the average value is finally taken to evaluate the model performance. The most common method is k-fold cross-validation, where k is usually 5 or 10. In each iteration, the data set is divided into k equal parts, and each time a part is left as a validation set, and the remaining k-1 parts are used for training. If the amount of data is large enough, the training sample set can also be divided into a training set, a test set, and a validation set.

[0107] After using the pre-trained fault classification model to analyze the target frequency domain feature data to obtain the fault cause and fault level of the target grounding system, when the fault level is greater than the preset alarm level, a fault alarm information is generated, and a fault handling work order is generated based on the fault cause.

[0108] Optionally, the target frequency domain feature data and multiple groups of historical frequency domain feature data within a preset historical time period can be displayed in the human-computer interaction interface; when the fault level is greater than the alarm level, a pop-up window is displayed in the human-computer interaction interface to display the fault alarm information, and the fault alarm information is sent to the target object using a preset method, wherein the fault alarm information includes at least the cause of the fault, and the preset method includes at least one of the following: email, text message.

[0109] As an optional implementation, after generating a fault handling work order based on the fault cause, the fault handling result of the target object for the fault handling work order can also be obtained, and the actual fault cause and actual fault level of the target grounding system can be determined based on the fault handling result; the target frequency domain feature data is used as a new training sample, and the actual fault cause and actual fault level are stored as sample labels of the new training sample; the fault classification model is periodically retrained using the stored new training samples to update the model parameters of the fault classification model.

[0110] It should be noted that this method is aimed at the AC circuit of the grounding system, and can easily determine the changes in the network structure of the grounding system, such as adding lines, disconnecting branches, loose connections, etc. However, for the scenario where the structure has not changed but the DC resistance of the material has changed (such as replacing copper wire with iron wire), this method is invalid. In order to comprehensively monitor the health status of the grounding system, multiple methods such as DC resistance measurement, temperature monitoring, and material monitoring can be combined.

[0111] In an embodiment of the present application, target frequency domain feature data of a target grounding system is obtained, wherein the target frequency domain feature data includes: target spectrum data and target phase offset data; the target similarity between the target frequency domain feature data and preset reference frequency domain feature data is determined, wherein the reference frequency domain feature data includes: reference spectrum data and reference phase offset data obtained when the grounding impedance of the target grounding system is normal; when the target similarity is less than a preset similarity threshold, it is determined that there is a fault in the target grounding system, and the target frequency domain feature data is analyzed using a pre-trained fault classification model to obtain the fault cause and fault level of the target grounding system; when the fault level is greater than the preset alarm level, fault alarm information is generated, and a fault handling work order is generated based on the fault cause. In this way, by using frequency domain feature data and phase offset data, combined with a trained model, instantaneous faults or performance degradations can be captured, thereby achieving faster response and processing, thereby solving the technical problem in related schemes that the grounding impedance measurement process is complex and it is difficult to effectively and efficiently control the safety of the grounding system in real time.

[0112] Example 2

[0113] According to an embodiment of the present application, a grounding system safety monitoring device for implementing the grounding system safety monitoring method in embodiment 1 is also provided. Figure 2 As shown, the grounding system safety monitoring device at least includes: an acquisition module 21, a comparison module 22, a fault analysis module 23 and a fault processing module 24, wherein:

[0114] An acquisition module 21 is used to acquire target frequency domain characteristic data of a target grounding system, wherein the target frequency domain characteristic data includes: target spectrum data and target phase offset data;

[0115] A comparison module 22 is used to determine the target similarity between the target frequency domain feature data and the preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference frequency spectrum data and reference phase offset data obtained when the ground impedance of the target grounding system is normal;

[0116] The fault analysis module 23 is used to determine that there is a fault in the target grounding system when the target similarity is less than a preset similarity threshold, and analyze the target frequency domain feature data using a pre-trained fault classification model to obtain the fault cause and fault level of the target grounding system;

[0117] The fault handling module 24 is used to generate fault alarm information when the fault level is greater than the preset alarm level, and to generate a fault handling work order according to the fault cause.

[0118] The functions of each module of the grounding system safety monitoring device are explained below in conjunction with the specific implementation process.

[0119] This application proposes to regularly detect and analyze the spectrum curve of the grounding system, and identify small changes in the spectrum curve by comparing historical data and real-time data, so as to determine whether there are potential problems in the grounding system, and combine artificial intelligence algorithms to improve the accuracy and efficiency of fault detection, so as to better maintain the health of the grounding system. The specific implementation methods are as follows:

[0120] First, the acquisition module acquires the target frequency domain characteristic data of the target grounding system, wherein the target frequency domain characteristic data includes: target spectrum data and target phase offset data. The specific steps of acquiring the above data can be carried out in the following manner: First, the frequency signal of the target grounding system is collected by a spectrum analyzer, and then the frequency signal is processed by fast Fourier transform to obtain the target spectrum data, and the target phase offset data is determined based on the phase information of the frequency signal in the target spectrum data.

[0121] Among them, you can first set the parameters of the spectrum analyzer, such as the center frequency, frequency bandwidth, resolution bandwidth, etc., to ensure that it can cover the measured frequency range and provide sufficient frequency resolution. The spectrum analyzer will display the power distribution of the grounding system at different frequencies. The frequency signal data collected by the spectrum analyzer will be exported. Usually, these data will exist in the form of time series. Use fast Fourier transform to process the time series data. Fast Fourier transform can convert time domain signals into frequency domain signals to obtain the frequency components and corresponding amplitudes of the signals. After fast Fourier transform processing, a spectrum will be obtained, showing the amplitude (power) information at different frequencies. This spectrum is the target spectrum data. From the complex results obtained after fast Fourier transform processing, extract the phase information of each frequency component. For multiple measurement points in the target grounding system, compare their phase information at the same frequency to determine the phase offset. The phase offset can reflect the propagation delay or reflection of the signal in the system.

[0122] As an optional implementation, after acquiring the above data, the comparison module determines the similarity between the target frequency domain feature data and the preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference spectrum data and reference phase offset data acquired when the grounding impedance of the target grounding system is normal, and the specific steps can be performed by the following steps: splicing the target spectrum data and the target phase offset data into a first feature vector; then splicing the reference spectrum data and the reference phase offset data into a second feature vector; and then determining the cosine similarity between the first feature vector and the second feature vector as the target similarity. The above similarity will be used to compare with the preset similarity threshold to determine whether the target grounding system is faulty.

[0123] It should be noted that other similarity calculation methods can also be used to determine the similarity between the target frequency domain feature data and the preset reference frequency domain feature data, such as: Euclidean distance, Manhattan distance, Chebyshev distance, Jaccard similarity coefficient, Hamming distance, etc., which can be selected according to the specific application scenario and data characteristics to achieve effective monitoring and evaluation of the target grounding system status.

[0124] As an optional implementation, the process of determining the similarity threshold includes: obtaining multiple groups of historical frequency domain feature data of the target grounding system under various fault scenarios; respectively determining the similarity between each group of historical frequency domain feature data and the benchmark frequency domain feature data; determining the similarity threshold based on the maximum similarity among the multiple similarities obtained, or the similarity threshold may also be slightly greater than the maximum similarity.

[0125] It should be noted that when determining the similarity threshold, an adaptive threshold segmentation technique can also be used. This method can automatically adjust the similarity threshold according to the characteristics of the data to adapt to different data sets and application scenarios. The selection of the threshold can be based on the distribution characteristics of the data. For example, it can be assumed that the data follows a normal distribution or a log-normal distribution, and the threshold can be determined based on the distribution characteristics.

[0126] When comparing the target similarity with the preset similarity threshold, if the target similarity is less than the preset similarity threshold, the fault analysis module determines that there is a fault in the target grounding system, and then uses the pre-trained fault classification model to analyze the target frequency domain feature data, so as to obtain the fault cause and fault level of the target grounding system.

[0127] Optionally, the training process of the fault classification model includes: constructing an initial classification model, wherein the type of the initial classification model includes at least one of the following: logistic regression model, neural network, random forest, decision tree, support vector machine; obtaining multiple sets of historical frequency domain feature data of the target grounding system under various fault scenarios as a training sample set, wherein each training sample is a set of historical frequency domain feature data when a grounding fault of a fault level occurs in the target grounding system due to a fault cause, and the sample label of the training sample is the fault cause and the fault level; using the training sample set to iteratively train the initial classification model, and using the cross-validation method to evaluate the model performance during the model training process to adjust the model parameters, and using the trained model as a fault classification model.

[0128] The above-mentioned causes of failure include, for example: changes in the power load of the communication machine, maintenance or replacement of communication equipment, maintenance or replacement of communication equipment, increase in communication traffic, aging of the grounding system over time, etc. The fault level can also be divided artificially according to the severity of the fault: serious, relatively serious, minor, etc.

[0129] Acquiring multiple sets of historical frequency domain feature data of the target grounding system under various fault scenarios may include but is not limited to the following situations, for example: increased use of air conditioning in summer leads to changes in power load, which may introduce harmonics into the system's spectrum and affect the spectrum; when communication equipment is maintained or replaced, the transmission and reception characteristics of the signal may be temporarily changed, thereby affecting the spectrum measured by the spectrum analyzer; during peak communication hours, such as holidays or special events, an increase in communication traffic may cause changes in spectrum density; decoration, equipment movement or other activities inside the building where the target grounding system is located may temporarily affect the grounding effect of the grounding system, resulting in spectrum changes; aging of the grounding system over time may lead to an increase in grounding resistance, affecting the stability and spectrum characteristics of the signal, and so on. Data acquired in scenarios that cause spectrum changes are all training samples.

[0130] It should be noted that the training sample information can also be obtained by using traditional measurement methods, such as the three-wire method, the four-wire method, the single-clamp measurement, the double-clamp method, etc. The data measured by these methods can also be used as training sample data.

[0131] As an optional implementation, before training the fault classification model, the training samples can also be preprocessed, including normalization, missing value processing, feature selection, etc. If the amount of data is small, cross-validation is performed by dividing the training set into multiple small subsets, and then using a part of them for testing and the rest for training. This process is repeated many times, and the average value is finally taken to evaluate the model performance. The most common method is k-fold cross-validation, where k is usually 5 or 10. In each iteration, the data set is divided into k equal parts, and each time a part is left as a validation set, and the remaining k-1 parts are used for training. If the amount of data is large enough, the training sample set can also be divided into a training set, a test set, and a validation set.

[0132] After using the pre-trained fault classification model to analyze the target frequency domain feature data to obtain the fault cause and fault level of the target grounding system, the fault handling module generates fault alarm information when the fault level is greater than the preset alarm level, and generates a fault handling work order based on the fault cause.

[0133] Optionally, the target frequency domain feature data and multiple groups of historical frequency domain feature data within a preset historical time period can be displayed in the human-computer interaction interface; when the fault level is greater than the alarm level, a pop-up window is displayed in the human-computer interaction interface to display the fault alarm information, and the fault alarm information is sent to the target object using a preset method, wherein the fault alarm information includes at least the cause of the fault, and the preset method includes at least one of the following: email, text message.

[0134] As an optional implementation, after generating a fault handling work order based on the fault cause, the fault handling result of the target object for the fault handling work order can also be obtained, and the actual fault cause and actual fault level of the target grounding system can be determined based on the fault handling result; the target frequency domain feature data is used as a new training sample, and the actual fault cause and actual fault level are stored as sample labels of the new training sample; the fault classification model is periodically retrained using the stored new training samples to update the model parameters of the fault classification model.

[0135] It should be noted that each module in the grounding system safety monitoring device in the embodiment of the present application corresponds one by one to each implementation step of the grounding system safety monitoring method in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1 and will not be elaborated here.

[0136] Example 3

[0137] According to an embodiment of the present application, a computer program product is also provided. The computer program product includes a computer program, wherein when the computer program is executed by a processor, the grounding system safety monitoring method in Example 1 is implemented.

[0138] According to an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the grounding system safety monitoring method in Example 1 by running the computer program.

[0139] According to an embodiment of the present application, a processor is also provided, which is used to run a computer program, wherein the grounding system safety monitoring method in Example 1 is executed when the computer program is running.

[0140] According to an embodiment of the present application, an electronic device is also provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the grounding system safety monitoring method in Example 1 through the computer program.

[0141] Specifically, the following steps are executed when the computer program is running: obtaining target frequency domain feature data of the target grounding system, wherein the target frequency domain feature data includes: target spectrum data and target phase offset data; determining the target similarity between the target frequency domain feature data and preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference spectrum data and reference phase offset data obtained when the grounding impedance of the target grounding system is normal; when the target similarity is less than a preset similarity threshold, determining that a fault exists in the target grounding system, analyzing the target frequency domain feature data using a pre-trained fault classification model, and obtaining the fault cause and fault level of the target grounding system; when the fault level is greater than a preset alarm level, generating fault alarm information, and generating a fault handling work order based on the fault cause.

[0142] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 3 FIG. 1 shows a hardware structure block diagram of an electronic device for implementing a grounding system safety monitoring method. Figure 3 As shown, the electronic device 30 may include one or more (302a, 302b, ..., 302n are used to illustrate) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission device 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.

[0143] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the electronic device 30. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0144] The memory 304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the grounding system safety monitoring method in the embodiment of the present application. The processor 302 executes various functional applications and data processing by running the software programs and modules stored in the memory 304, that is, to implement the vulnerability detection method of the above-mentioned application. The memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 304 may further include a memory remotely arranged relative to the processor 302, and these remote memories may be connected to the electronic device 30 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0145] The transmission device 306 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the electronic device 30. In one example, the transmission device 306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 306 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0146] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 30 .

[0147] The serial numbers of the above embodiments are only for description and do not represent the advantages or disadvantages of the embodiments.

[0148] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0149] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0151] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0152] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0153] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A grounding system safety monitoring method, characterized in that: include: Acquire target frequency domain characteristic data of a target grounding system, wherein the target frequency domain characteristic data includes: target spectrum data and target phase offset data; Determining a target similarity between the target frequency domain feature data and preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference frequency spectrum data and reference phase offset data acquired when the grounding impedance of the target grounding system is normal; When the target similarity is less than a preset similarity threshold, it is determined that there is a fault in the target grounding system, and the target frequency domain feature data is analyzed using a pre-trained fault classification model to obtain the fault cause and fault level of the target grounding system; When the fault level is greater than the preset alarm level, fault alarm information is generated, and a fault handling work order is generated according to the fault cause.

2. The method according to claim 1, characterized in that Obtain target frequency domain characteristic data of the target grounding system, including: The frequency signal of the target grounding system is collected by using a spectrum analyzer, and the frequency signal is processed by fast Fourier transform to obtain the target spectrum data, and the target phase offset data is determined according to the phase information of the frequency signal in the target spectrum data.

3. The method according to claim 1, characterized in that Determining the similarity between the target frequency domain feature data and preset reference frequency domain feature data includes: splicing the target spectrum data and the target phase offset data into a first eigenvector; splicing the reference spectrum data and the reference phase offset data into a second eigenvector; The cosine similarity between the first feature vector and the second feature vector is determined as the target similarity.

4. The method according to claim 1, characterized in that: The process of determining the similarity threshold comprises: Acquire multiple groups of historical frequency domain characteristic data of the target grounding system under multiple fault scenarios; respectively determining the similarity between each group of the historical frequency domain feature data and the reference frequency domain feature data; The similarity threshold is determined according to the maximum similarity among the obtained multiple similarities.

5. The method according to claim 1, characterized in that The training process of the fault classification model includes: Constructing an initial classification model, wherein the type of the initial classification model includes at least one of the following: a logistic regression model, a neural network, a random forest, a decision tree, and a support vector machine; Acquire multiple groups of historical frequency domain feature data of the target grounding system under multiple fault scenarios as a training sample set, wherein each training sample is a group of historical frequency domain feature data when a grounding fault of a fault level occurs in the target grounding system due to a fault cause, and the sample label of the training sample is the fault cause and the fault level; The initial classification model is iteratively trained using the training sample set, and during the model training process, the model performance is evaluated using a cross-validation method to adjust model parameters, and the trained model is used as the fault classification model.

6. The method according to claim 1, characterized in that The method further comprises: Displaying the target frequency domain feature data and multiple groups of historical frequency domain feature data within a preset historical time period in a human-computer interaction interface; When the fault level is greater than the warning level, the fault warning information is displayed in a pop-up window in the human-computer interaction interface, and the fault warning information is sent to the target object using a preset method, wherein the fault warning information at least includes the cause of the fault, and the preset method includes at least one of the following: email, text message.

7. The method according to claim 5, characterized in that After generating a fault handling work order according to the fault cause, the method further includes: Obtaining a fault handling result of the target object for the fault handling work order, and determining an actual fault cause and an actual fault level of the target grounding system according to the fault handling result; Taking the target frequency domain feature data as a new training sample, and storing the actual fault cause and the actual fault level as sample labels of the new training sample; The fault classification model is periodically retrained using the stored new training samples to update model parameters of the fault classification model.

8. A grounding system safety monitoring device, characterized in that: include: An acquisition module, used to acquire target frequency domain characteristic data of a target grounding system, wherein the target frequency domain characteristic data includes: target spectrum data and target phase offset data; A comparison module, used to determine the target similarity between the target frequency domain feature data and preset reference frequency domain feature data, wherein the reference frequency domain feature data includes: reference frequency spectrum data and reference phase offset data obtained when the grounding impedance of the target grounding system is normal; A fault analysis module, used to determine that a fault exists in the target grounding system when the target similarity is less than a preset similarity threshold, and to analyze the target frequency domain feature data using a pre-trained fault classification model to obtain a fault cause and a fault level of the target grounding system; The fault handling module is used to generate fault alarm information when the fault level is greater than the preset alarm level, and generate a fault handling work order according to the fault cause.

9. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the grounding system safety monitoring method described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the grounding system safety monitoring method according to any one of claims 1 to 7 through the computer program.

Images