AC fault arc detection method, apparatus and device, and readable storage medium

Abstract

The invention relates to an alternating current fault arc detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a current signal to be detected; performing Hilbert transform on the current signal to be detected to obtain a Hilbert transform result, and determining a current analysis signal according to the Hilbert transform result; mapping the current analysis signal from a time domain to a parameter domain, and determining a peak value of each time window in the parameter domain; the peak value is used for representing an arc energy intensity extreme value of the time-frequency joint space; and determining a fault arc detection result based on the peak value change degree of the adjacent time windows. By adopting the method, the detection accuracy of the alternating-current fault arc can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrical safety detection, and in particular to an alternating current fault arc detection method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] With the continuous improvement of the degree of electrification in modern society, the application of electrical equipment in production and life is becoming more and more widespread, and the electrical fire hazard is also increasingly prominent. Among them, the fault arc is one of the key factors that cause electrical fires, which seriously threatens people's life and property safety. Fault arc is a kind of gas insulation breakdown discharge phenomenon. Arc discharge refers to: under atmospheric pressure, when the power capacity is large enough, after the gas spark discharge, it develops to the opposite electrode immediately, and a very bright continuous arc appears, which is called arc discharge. Arc discharge time is long, and even when the external voltage is lower than the initial voltage, the arc can still be maintained. Arc discharge current is large, and arc temperature is high. Fault arc is often accompanied by open fire and high temperature, which is easy to cause electrical fire.

[0003] The alternating current fault arc detection device in the prior art is easily affected by the nonlinear load in the circuit, resulting in misoperation or refusal to operate, and the detection accuracy of the fault arc is low. SUMMARY

[0004] Therefore, it is necessary to provide an alternating current fault arc detection method, device, computer equipment, computer readable storage medium and computer program product capable of improving the detection accuracy of fault arc in view of the above technical problems.

[0005] In a first aspect, the present application provides an alternating current fault arc detection method, comprising:

[0006] obtaining a to-be-detected current signal;

[0007] performing Hilbert transform on the to-be-detected current signal to obtain a Hilbert transform result, and determining a current analytic signal according to the Hilbert transform result;

[0008] mapping the current analytic signal from time domain to parameter domain to determine a peak value of each time window in the parameter domain; the peak value is used to represent the arc energy intensity extreme value in the time-frequency joint space;

[0009] determining a fault arc detection result based on the peak value change degree of adjacent time windows.

[0010] In one embodiment, the determination of the current analytic signal according to the Hilbert transform result comprises:

[0011] The current analytic signal is mapped from a time domain to a parameter domain, and a peak value of each time window in the parameter domain is determined.

[0012] In one of the embodiments, the mapping of the current analytic signal from the time domain to the parameter domain and the determination of the peak value of each time window in the parameter domain include:

[0013] The current analytic signal is converted from the time domain to a time-frequency domain, and is mapped from the time-frequency domain to the parameter domain, and the peak value of each time window in the parameter domain is determined.

[0014] In one of the embodiments, the conversion of the current analytic signal from the time domain to the time-frequency domain and the mapping from the time-frequency domain to the parameter domain and the determination of the peak value of each time window in the parameter domain include:

[0015] A Wigner quasi-probability distribution of the current analytic signal is calculated, and a Hough transform is performed on the Wigner quasi-probability distribution to obtain a Hough transform result.

[0016] A peak value of each time window in the Hough transform result is determined.

[0017] In one of the embodiments, the determination of the fault arc detection result based on the peak value change degree of the adjacent time windows includes:

[0018] The peak value change degree of each adjacent time window is determined.

[0019] Gradient boosting prediction is performed on the peak value change degree of each of the adjacent time windows to obtain a prediction probability.

[0020] If the prediction probability is greater than or equal to a probability threshold, the fault arc detection result is determined as existing fault arc.

[0021] If the prediction probability is less than the probability threshold, the fault arc detection result is determined as non-existing fault arc.

[0022] In one of the embodiments, the determination of the fault arc detection result based on the peak value change degree of the adjacent time windows includes:

[0023] The peak value change degree of each adjacent time window is determined.

[0024] If the peak value change degree of each of the adjacent time windows is greater than a preset degree threshold, the fault arc detection result is determined as existing fault arc, and a line is instructed to be cut off.

[0025] In a second aspect, the application further provides an alternating current fault arc detection device, which includes:

[0026] acquire a current signal to be detected;

[0027] perform Hilbert transform on the current signal to be detected to obtain a Hilbert transform result, and determine a current analysis signal according to the Hilbert transform result;

[0028] map the current analysis signal from a time domain to a parameter domain, and determine a peak value of each time window in the parameter domain; the peak value is used to represent an arc energy intensity extreme value in a time-frequency joint space;

[0029] determine a fault arc detection result based on a peak value change degree of adjacent time windows.

[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and the processor implements the steps of the AC fault arc detection method provided in the first aspect when executing the computer program.

[0031] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the AC fault arc detection method provided in the first aspect when executed by a processor.

[0032] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and the computer program implements the steps of the AC fault arc detection method provided in the first aspect when executed by a processor.

[0033] The AC fault arc detection method, device, computer device, computer readable storage medium and computer program product can acquire a current signal to be detected, perform Hilbert transform on the current signal to be detected to obtain a Hilbert transform result, determine a current analysis signal according to the Hilbert transform result, map the current analysis signal from a time domain to a parameter domain, determine a peak value of each time window in the parameter domain, and determine a fault arc detection result based on a peak value change degree of adjacent time windows. The AC fault arc detection method, device, computer device, computer readable storage medium and computer program product can realize analysis of the current signal in a time-frequency domain joint manner, highlight the arc signal characteristics, determine the fault arc detection result according to the peak value change degree of the arc signal, avoid the influence of nonlinear loads in a line, and improve the fault arc detection accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application or the related art. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained from these drawings without creative effort.

[0035] Figure 1 An application environment diagram of the alternating current fault arc detection method in one embodiment;

[0036] Figure 2 A flowchart of the alternating current fault arc detection method in one embodiment;

[0037] Figure 3 A schematic diagram of an alternating current series arc fault experimental platform in one embodiment;

[0038] Figure 4 A current signal diagram of a drill load in one embodiment;

[0039] Figure 5 A flowchart of the alternating current fault arc detection method in another embodiment;

[0040] Figure 6 A WHT peak diagram under arc burning of a drill load in one embodiment;

[0041] Figure 7 A structural block diagram of the alternating current fault arc detection device in one embodiment;

[0042] Figure 8 An internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the present application more clear, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0044] It should be noted that the terms "first", "second" and the like used in the present application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "include" and "have" and any variations thereof used in the present application are intended to cover non-exclusive inclusion. The term "multiple" used in the present application refers to two and more than two. The term "and / or" used in the present application refers to one of the solutions, or any combination of multiple solutions.

[0045] With the continuous development of society and the continuous improvement of people's living standards, the power equipment in industrial and residential areas is increasing, the layout of power supply network is becoming more and more complex, and the safety hazards of power lines are also increasing. For most existing buildings, in order to connect the safety and the line to be clear and orderly, the cable is usually placed in the hidden trench. Therefore, in the early stage of fire, it is usually not possible to respond in time because of the hidden location, and when smoke or open fire appears, large-scale fire is inevitable and difficult to rescue in time. Because the line is in overload operation for a long time, the quality of the cable on the market is uneven, and the power line will age, the insulation skin will be damaged, etc. with the increase of service life, which may cause the circuit to produce arc.

[0046] When the series arc fault occurs, due to the voltage drop, the current of the arc fault is usually lower than that in normal operation, and there are a large number of abnormal waveforms in the arc current. The series arc current is also related to the load working in the circuit, and under different load working conditions, the arc current is quite different. In actual application scenarios, even if the same load is in the same state, the arc current will also change randomly. Based on the above arc characteristics, the common circuit protection device cannot effectively identify the fault arc in the circuit, so as to cut off the circuit and achieve the purpose of protecting the normal operation of the power grid. Therefore, the detection of the fault arc on the line is particularly important for the stable operation of the power supply system. Due to the characteristics of the series arc fault, the traditional overload, short circuit and leakage protection device in the low-voltage power distribution system cannot accurately detect the fault arc in the circuit. At the same time, the existing low-voltage alternating current fault arc detection is easily affected by the nonlinear load in the system, resulting in misoperation or refusal to operate.

[0047] In view of the above problem that the fault arc detection is not accurate, the embodiment of the application provides an alternating current fault arc detection method. By performing time-frequency domain joint analysis on the current signal in the line, the arc signal in the current signal can be highlighted. By determining the fault arc detection result according to the peak value change degree corresponding to the arc signal, the influence of the nonlinear load in the line can be avoided, and the fault arc detection accuracy can be improved.

[0048] The alternating current fault arc detection method provided by the embodiment of the application can be applied to, for example Figure 1The application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. After receiving the to-be-detected current signal sent by the terminal 102, the server 104 performs Hilbert transform on the to-be-detected current signal, obtains the Hilbert transform result, and determines the current analytic signal according to the Hilbert transform result, maps the current analytic signal from the time domain to the parameter domain, determines the peak value of each time window in the parameter domain, and determines the fault arc detection result based on the peak value change degree between adjacent time windows. The server 104 can return the determined fault arc detection result to the terminal 102. Among them, the terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, unmanned aerial vehicles, low-altitude aircraft, Internet of Things devices and portable wearable devices, Internet of Things devices can be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. It should be noted that the embodiments of the present application are not limited to the application in the application scenario of the interaction between the terminal and the server, but also applicable to the application scenario of a single terminal or a single server.

[0049] In one exemplary embodiment, as shown in Figure 2 An alternating current fault arc detection method is provided, which is applied to the server in Figure 1 for example, including the following steps 202 to 208. Among them:

[0050] Step 202, obtaining a to-be-detected current signal.

[0051] Among them, the to-be-detected current signal refers to the current signal that needs to be detected for fault arc. The to-be-detected current signal is usually the current signal in the circuit loop, for example, the to-be-detected current signal can be the current signal collected in the circuit loop of the load such as air conditioner, dust collector, electric drill, incandescent lamp, etc. The current signal can be collected once every interval of a preset period, for example, once every interval of 5 seconds, 8 seconds or 10 seconds, etc. The preset period can be set according to the actual application scenario.

[0052] In an actual application scenario, the current sensor can be arranged at any position where a fault arc can exist in the power supply and distribution system, and a current signal is collected by the current sensor as a to-be-processed current signal. The to-be-processed current signal can be analyzed and detected in real time to determine whether a fault arc exists in a loop where the corresponding load is located. Generally, the current signal collected by the current sensor is a time domain signal.

[0053] In step 204, a Hilbert transform is performed on the to-be-detected current signal to obtain a Hilbert transform result, and a current analytic signal is determined according to the Hilbert transform result.

[0054] The Hilbert transform is used to convert a signal to extract information such as instantaneous amplitude, phase, and frequency of the signal. The Hilbert transform can make all frequency components of the original signal delayed by 90 degrees. The Hilbert transform converts the time domain information of the real domain signal into instantaneous characteristics that are easier to analyze by constructing an analytic signal.

[0055] For example, the current analytic signal can be determined according to the to-be-detected current signal and the Hilbert transform result of the to-be-detected current signal.

[0056] In step 206, the current analytic signal is mapped from the time domain to the parameter domain to determine a peak value of each time window in the parameter domain. The peak value is used to represent an arc energy intensity extreme value in a time-frequency joint space.

[0057] The current analytic signal is mapped from the time domain to the parameter domain, and the current analytic signal in the parameter domain is obtained. The current analytic signal in the parameter domain can clearly represent the change of the arc energy intensity at different times, while the current signal is a periodic signal, and the peak value of the arc energy intensity exists in each period. Each time window can be one period or multiple periods. The size of the time window can be selected according to the actual application scenario. After obtaining the arc energy intensity at each time in the parameter domain, the peak value of the arc energy intensity in the time window is easily determined.

[0058] For example, the current analytic signal can be directly mapped from the time domain to the parameter domain. Alternatively, the current analytic signal can be converted from the time domain to the time-frequency domain, and then mapped from the time-frequency domain to the parameter domain. Alternatively, the current analytic signal can be converted from the time domain to the statistical domain, and then mapped from the statistical domain to the parameter domain.

[0059] In step 208, a fault arc detection result is determined based on a peak value change degree between adjacent time windows.

[0060] The peak value change degree between adjacent time windows can be represented by a peak value difference absolute value or a peak value change rate absolute value between adjacent time windows. For example, if the first time window and the second time window are adjacent time windows, the peak value of the first time window is P1, and the peak value of the second time window is P2, the peak value change degree between the first time window and the second time window can be |P1-P2| or |(P2-P1) / P1|.

[0061] Exemplarily, the fault arc detection result can be determined based on the peak value change degree between adjacent time windows and a preset degree threshold. For example, if there is a peak value change degree between adjacent time windows that is greater than the preset degree threshold, the fault arc detection result is determined to be that there is a fault arc; if there is no peak value change degree between adjacent time windows that is greater than the preset degree threshold, the fault arc detection result is determined to be that there is no fault arc. If the fault arc detection result is that there is a fault arc, an alarm signal can be output or the circuit loop can be controlled to be cut off.

[0062] Exemplarily, the peak value change degree between adjacent time windows can be gradient enhanced to obtain a prediction probability, and the fault arc detection result can be determined based on a size relationship between the prediction probability and a probability threshold. For example, if the prediction probability is greater than or equal to the probability threshold, the fault arc detection result is determined to be that there is a fault arc; if the prediction probability is less than the probability threshold, the fault arc detection result is determined to be that there is no fault arc.

[0063] In the above-mentioned alternating current fault arc detection method, by obtaining the to-be-detected information, the Hilbert transform is performed on the to-be-detected current signal to obtain a Hilbert transform result, and the current analytic signal is determined according to the Hilbert transform result, the current analytic signal is mapped from the time domain to the parameter domain, the peak value of each time window in the parameter domain is determined, and the fault arc detection result is determined based on the peak value change degree between adjacent time windows. The current signal can be analyzed by time-frequency domain joint, so that the arc signal characteristics can be more highlighted, and the influence of the nonlinear load in the circuit can be avoided by determining the fault arc detection result according to the peak value change degree corresponding to the arc signal, thereby improving the fault arc detection accuracy.

[0064] In some embodiments, the current analytic signal is determined according to the Hilbert transform result in step 204, including:

[0065] The to-be-detected current signal is taken as a real part, and the Hilbert transform result is taken as an imaginary part, and the current analytic signal is determined according to the real part and the imaginary part.

[0066] After obtaining the Hilbert transform result of the to-be-detected current signal, the to-be-detected current signal can be taken as a real part, and the Hilbert transform result can be taken as an imaginary part, so that the current analytic signal is obtained. For example, the to-be-detected current signal is s(t), and the current analytic signal z(t) = s(t) + jH[s(t)], where j is an imaginary unit, and H[s(t) represents the Hilbert transform result of the to-be-detected current signal s(t).

[0067] In one example, it is assumed that the to-be-detected current signal is x(t), and t represents time. The Hilbert transform is performed on the to-be-detected current signal, and the Hilbert transform result is wherein

[0068] Formula (1)

[0069] Then, the current analytic signal z(t) is as shown in the following formula (2).

[0070] Formula (2)

[0071] Exemplarily, the instantaneous characteristics f(t) such as the amplitude A(t), the phase and the frequency can be extracted from the current analytic signal. The specific extraction manner is as shown in the following formula (3) to formula (5).

[0072] Formula (3)

[0073] Formula (4)

[0074] Formula (5)

[0075] According to the above formula (3) to formula (5), the instantaneous amplitude, the instantaneous phase and the instantaneous frequency at any moment can be extracted from the current analytic signal.

[0076] In this embodiment, the to-be-detected current signal is taken as a real part, and the Hilbert transform result is taken as an imaginary part, so that the current analytic signal is obtained, which can accurately convert the time-domain current information into the instantaneous characteristics that are easier to analyze, and improve the accuracy of the current analytic signal.

[0077] In some embodiments, the current analytic signal is mapped from the time domain to the parameter domain, and the peak value of each time window in the parameter domain is determined, including:

[0078] The current analytic signal is converted from the time domain to the time-frequency domain, and is mapped from the time-frequency domain to the parameter domain, and the peak value of each time window in the parameter domain is determined.

[0079] The current analytic signal is converted from the time domain to the time-frequency domain, which can capture the non-stationarity of the arc. The current analytic signal is converted from the time domain to the time-frequency domain, for example, by a short-time Fourier transform (STFT) or a continuous wavelet transform (CWT). That is, the current analytic signal is subjected to a short-time Fourier transform or a continuous wavelet transform, so that the current analytic signal can be converted from the time domain to the time-frequency domain. Mapping from the time domain to the parameter domain is to convert the time-frequency characteristics into a low-dimensional parameter space, for example, by a Hough transform or principal component analysis (PCA).

[0080] Exemplarily, the current analytic signal is converted from the time domain to the time-frequency domain, and is mapped from the time-frequency domain to the parameter domain, and the energy distribution characteristics of the arc are extracted from the parameter domain, and the peak value of each time window is determined according to the arc energy distribution characteristics.

[0081] In this embodiment, by converting the current analytic signal from the time domain to the time-frequency domain, and mapping from the time-frequency domain to the parameter domain, the peak value of each time window in the parameter domain is determined, which can avoid the loss of the current signal and improve the accuracy of the parameter domain signal.

[0082] In some embodiments, converting the current analytic signal from the time domain to the time-frequency domain, and mapping from the time-frequency domain to the parameter domain, and determining the peak value of each time window in the parameter domain, comprises:

[0083] The Wigner quasi-probability distribution of the current analytic signal is calculated, and a Hough transform is performed on the Wigner quasi-probability distribution to obtain a Hough transform result; and the peak value of each time window in the Hough transform result is determined.

[0084] The Wigner quasi-probability distribution (Wigner-Ville Distribution, WVD) of the current analytic signal can be used to represent the energy density of the current signal in the time-frequency plane. The instantaneous high-frequency component of the arc current will appear as a high-energy ridge line in the WVD. The transformation of the Wigner quasi-probability distribution is essentially a Fourier transform of the instantaneous autocorrelation of the current analytic signal z(t). Exemplarily, the expression of the WVD distribution is shown in the following formula (6).

[0085] Formula (6)

[0086] Wherein, represents the conjugate complex signal of the current analytic signal . f represents the frequency, represents the time delay. The WVD distribution has phase invariance, represents the conjugate of the WVD. In other words, to obtain the WVD distribution at a fixed time, the signal at a past time is multiplied by the signal at a future time, the past time of the signal being equal to the future time.

[0087] Hough transform is a typical geometric shape discrimination method in the field of image recognition. Taking a straight line as an example, the polar coordinate parameter equation is:

[0088] Equation (7)

[0089] The Hough transform can correspond an arbitrary point (x, y) to a sine wave, and the amplitude of the sine wave is the density of the corresponding point on the plane. The specific process of line detection is to traverse the possible values, then calculate the p value, and accumulate the array according to the two values, and count the number of common straight line points. At this time, the corresponding wave peak can be obtained in the plane. Assuming that the current analytical signal is , wherein, is white noise. The Hough transform result obtained after Hough transform is: Equation (8)

[0090] After the Wigner-Hough transform of the current analytical signal, a peak point will appear in each time window, and the peak point vertical coordinate is the corresponding WHT peak value.

[0091] In this embodiment, the Wigner quasi-probability distribution of the current analytical signal is calculated, and the Hough transform result is obtained by performing Hough transform on the Wigner quasi-probability distribution. The peak value of each time window in the Hough transform result can obtain significant fault arc characteristics, and improve the accuracy of fault arc detection.

[0092] In some embodiments, based on the peak value change degree of adjacent time windows, the fault arc detection result is determined, including:

[0093] The peak value change degree between each adjacent time window is determined; the peak value change degree of each adjacent time window is gradient enhancement prediction to obtain a prediction probability; if the prediction probability is greater than or equal to a probability threshold, it is determined that the fault arc detection result is that there is a fault arc; if the prediction probability is less than the probability threshold, it is determined that the fault arc detection result is that there is no fault arc.

[0094] The peak value change degree between each adjacent time window is determined; the peak value change degree of each adjacent time window is gradient enhancement prediction to obtain a prediction probability; if the prediction probability is greater than or equal to a probability threshold, it is determined that the fault arc detection result is that there is a fault arc; if the prediction probability is less than the probability threshold, it is determined that the fault arc detection result is that there is no fault arc.

[0095] ​The current analytical signal of the parameter domain usually corresponds to a plurality of time windows. The degree of change of the peak value of each adjacent time window is determined in sequence, and the degrees of change of the peak values of the adjacent time windows are regarded as a distribution. Gradient boosting prediction is performed on the distribution to obtain a prediction probability. According to the size relationship between the prediction probability and a probability threshold, a fault arc detection result is determined. The prediction probability is used to represent the possibility of the existence of a fault arc. The probability threshold can be set according to the actual application scenario, for example, the probability threshold is 50%, 60%, or 70%, etc. Different loads can correspond to different probability thresholds.

[0096] Exemplarily, the degrees of change of the peak values of the adjacent time windows can be subjected to gradient boosting prediction by using algorithms such as NG-Boost (Natural Gradient Boosting), XGBoost (eXtreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), or CatBoost (Categorical Gradient Boosting) to obtain the prediction probability. In an example, the degrees of change of the peak values of the adjacent time windows are subjected to gradient boosting prediction by using the NG-Boost algorithm to obtain the prediction probability. If the preset probability is greater than or equal to 50%, it is determined that the fault arc detection result is that a fault arc exists, and an alarm or a circuit disconnection indication can be issued. If the preset probability is less than 50%, it is determined that the fault arc detection result is that a fault arc does not exist, and the next detection can be waited for.

[0097] In this embodiment, the degrees of change of the peak values of the adjacent time windows are subjected to gradient boosting prediction, that is, the overall trend of the degrees of change of the peak values of the adjacent time windows is subjected to gradient boosting prediction to obtain the prediction probability. If the prediction probability is greater than or equal to the probability threshold, it is determined that the fault arc detection result is that a fault arc exists. Otherwise, if the prediction probability is less than the probability threshold, it is determined that the fault arc detection result is that a fault arc does not exist. The degrees of change of the peak values of the overall adjacent time windows can be predicted, the fault arc detection under different loads can be adapted, the influence of different loads can be avoided, and the detection accuracy of the fault arc can be improved.

[0098] In some embodiments, the fault arc detection result is determined based on the degrees of change of the peak values of the adjacent time windows, including:

[0099] The degree of change of the peak value of each adjacent time window is determined. If the degrees of change of the peak values of the adjacent time windows are all greater than a preset degree threshold, it is determined that the fault arc detection result is that a fault arc exists, and the line is indicated to be cut off.

[0100] After obtaining the peak variation degree of each adjacent time window, the peak variation degree of each adjacent time window can be compared with a preset degree threshold. If the peak variation degree of each adjacent time window is greater than the preset degree threshold, it is determined that the arc fault detection result is that there is a fault, and an indication to cut off the circuit is issued. If the peak variation degree of one adjacent time window is less than the preset degree threshold, it is determined that the arc fault detection result is that there is no fault. Different loads can correspond to different preset degree thresholds.

[0101] In this embodiment, by the peak variation degree of each adjacent time window being greater than the preset degree threshold, it is determined that the arc fault detection result is that there is a fault arc, and the circuit is instructed to be cut off, which can reduce the false detection rate of the fault arc and improve the detection accuracy of the fault arc.

[0102] In one embodiment, in order to study the comprehensive influence of nonlinear load on alternating current arc fault detection, based on the GB / T31143 standard, an alternating current series arc fault experimental platform can be built, as shown in Figure 3 The platform is composed of various loads, carbonized cables, arc fault detection devices (AFDD), current sensors and alternating current sources. The carbonized cable refers to a section of cable with the insulation layer cut and divided. In turn, the load is replaced by a vacuum cleaner, a switch source, a drill, an incandescent lamp, etc. Under each load condition, an alternating current series arc fault occurs. For any kind of load, the current waveform will be severely distorted when an alternating current series arc fault occurs. Taking the drill load as an example, the current signal schematic diagram is as shown in Figure 4 The current waveform under the fault arc condition is distorted compared with the current waveform under the condition that there is no fault arc, the current amplitude is reduced, and the waveform produces a "flat shoulder" phenomenon at the zero crossing point. The current characteristics of other loads are similar to those under the drill load condition, and will not be described here.

[0103] The commonly used signal feature analysis method can be divided into two categories, frequency domain feature analysis and time domain feature analysis. If only the frequency domain analysis method is used, the signal in the entire frequency space will be divided into several frequency components, and such results lack local information related to time. Based on this, the flowchart of the alternating current arc fault detection method provided in this example is as shown in Figure 5 This example uses a time-frequency domain joint analysis method to analyze the acquired current signal s(t). First, the current signal s(t) is converted from a time domain signal to an analytic signal z(t) through Hilbert transform, that is, z(t)=s(t)+jH[s(t)]. Then the signal is converted into Wigner-Ville distribution as follows:

[0104]

[0105] From the above formula, the Wigner-Ville transform is essentially the Fourier transform of the instantaneous autocorrelation of the signal z(t) To obtain the WVD distribution at a fixed time, the signal at the past time is multiplied by the signal at the future time, and the past time of the signal is equal to the future time.

[0106] The Hough transform is performed on the above Wigner-Ville distribution to obtain the WHT (Wigner-Hough Transformation) as follows:

[0107]

[0108] After the Wigner-Hough transform of the current signal, a peak point will appear in each time window, as shown in Figure 6 Each time window can be a period, and the WHT peak value of each period can be obtained. The relative change degree between adjacent two periods is represented by calculating the change ratio of the WHT peak value , as follows:

[0109]

[0110] Under the condition of stable load operation, the similarity of current signals between adjacent periods is high, and the WHT peak value change ratio is small. When arc fault occurs, the uncertainty of arc impedance and arc energy change leads to the decrease of the similarity of current signals in adjacent periods, and the value of WHT peak value change ratio will rise and show more obvious fluctuations. Considering the contingency and internal interference of the system, 4 peak value change rates corresponding to 5 period signals are taken to form the feature vector for fault detection. Taking 7 resistive and resistive load conditions as an example, the calculation results of WHT peak value change ratio are shown in Table 1.

[0111] Table 1

[0112]

[0113] The results show that the WHT peak value change rate of vacuum cleaner, switch source, electric drill and EMI filter increases significantly after the fault occurs. The arc under these load conditions can be detected by manually setting the threshold value. However, for incandescent lamp, fluorescent lamp and halogen lamp, the WHT peak value change ratio does not increase significantly after the fault occurs, and the threshold comparison method fails. Therefore, it is necessary to consider appropriate artificial intelligence algorithm to mine the relationship between WHT peak value change rates at different time periods, so as to realize fault arc detection under more load conditions.

[0114] NG-Boost utilizes natural gradient learning parameters, making the optimization problem independent of parameterization. The scoring rule is related to the probability distribution and the output value, denoted as S(P, y), the more accurate the probability prediction, the smaller the loss for the correct probability distribution and the expectation of obtaining the best value. In this example, the NG-Boost algorithm is used to predict the distribution of the relative change between each of the two adjacent periods The binary task probability value (i.e., the prediction probability) output by the NG-Boost algorithm is used as the basis for determining the fault and normal state, that is, when the prediction probability is greater than 50%, a fault alarm signal is output.

[0115] In the above embodiment, the current signal is analyzed by the time-frequency domain joint analysis method, which can highlight the arc characteristics. The peak value change ratio based on the arc characteristics is used to detect the alternating current fault arc, which can adapt to various load characteristics and effectively represent the fault arc state under various load states, thereby improving the detection accuracy of the alternating current fault arc.

[0116] It should be understood that although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0117] Based on the same inventive concept, the present application also provides an alternating current fault arc detection device for implementing the above-mentioned alternating current fault arc detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more alternating current fault arc detection device embodiments provided below can refer to the limitations of the alternating current fault arc detection method in the above text, which will not be repeated here.

[0118] In one exemplary embodiment, as Figure 7 shown, an alternating current fault arc detection device 700 is provided, comprising a signal acquisition module 702, a signal analysis module 704, a peak value determination module 706, and a fault determination module 708, wherein:

[0119] The signal acquisition module 702 is configured to acquire a current signal to be detected.

[0120] The signal analysis module 704 is configured to perform Hilbert transform on the current signal to be detected to obtain a Hilbert transform result, and determine a current analysis signal according to the Hilbert transform result.

[0121] The peak value determination module 706 is configured to map the current analysis signal from a time domain to a parameter domain, and determine a peak value of each time window in the parameter domain. The peak value is used to represent an arc energy intensity extreme value in a time-frequency joint space.

[0122] The fault determination module 708 is configured to determine a fault arc detection result based on a peak value variation degree of adjacent time windows.

[0123] In some embodiments, the signal analysis module 704 is further configured to take the current signal to be detected as a real part, take the Hilbert transform result as an imaginary part, and determine the current analysis signal according to the real part and the imaginary part.

[0124] In some embodiments, the peak value determination module 706 is further configured to convert the current analysis signal from the time domain to a time-frequency domain, and map the current analysis signal from the time-frequency domain to the parameter domain to determine the peak value of each time window in the parameter domain.

[0125] In some embodiments, the peak value determination module 706 is further configured to calculate a Wigner quasi-probability distribution of the current analysis signal, perform a Hough transform on the Wigner quasi-probability distribution to obtain a Hough transform result, and determine the peak value of each time window in the Hough transform result.

[0126] In some embodiments, the fault determination module 708 is further configured to determine the peak value variation degree of each adjacent time window, perform gradient boosting prediction on the peak value variation degrees of the adjacent time windows to obtain a prediction probability, determine that the fault arc detection result is that there is a fault arc if the prediction probability is greater than or equal to a probability threshold, and determine that the fault arc detection result is that there is no fault arc if the prediction probability is less than the probability threshold.

[0127] In some embodiments, the fault determination module 708 is further configured to determine the peak value variation degree of each adjacent time window, and determine that the fault arc detection result is that there is a fault arc and cut off the circuit if the peak value variation degrees of the adjacent time windows are all greater than a preset degree threshold.

[0128] The above-described various modules in the alternating current fault arc detection device can be all or partially implemented by software, hardware, and a combination thereof. The above-described various modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in the computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to the above-described various modules.

[0129] In an example embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in FIG. 1. Figure 8 The computer device includes a processor, a memory, an input / output interface, and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store data related to alternating current fault arc detection. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with terminals outside through a network connection. The computer program is executed by the processor to implement an alternating current fault arc detection method.

[0130] Those skilled in the art can understand that Figure 8 The structure shown in FIG. 1 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0131] In an example embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0132] In an embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0133] In an embodiment, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0134] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use, and processing of related data need to comply with relevant regulations.

[0135] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0136] The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0137] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for detecting AC fault arcs, characterized in that, The method includes: Acquire the current signal to be detected; The current signal to be detected is subjected to Hilbert transform to obtain the Hilbert transform result, and the current analytical signal is determined based on the Hilbert transform result; The current analytical signal is mapped from the time domain to the parameter domain to determine the peak value of each time window in the parameter domain; the peak value is used to characterize the extreme value of arc energy intensity in the time-frequency joint space. The fault arc detection result is determined based on the degree of peak value variation in adjacent time windows.

2. The method according to claim 1, characterized in that, The step of determining the current analytical signal based on the Hilbert transform result includes: The current signal to be detected is taken as the real part, and the Hilbert transform result is taken as the imaginary part. The current analytical signal is determined based on the real part and the imaginary part.

3. The method according to claim 1, characterized in that, The step of mapping the current analytical signal from the time domain to the parameter domain and determining the peak value of each time window in the parameter domain includes: The current analysis signal is converted from the time domain to the time-frequency domain, and then mapped from the time-frequency domain to the parameter domain to determine the peak value of each time window in the parameter domain.

4. The method according to claim 3, characterized in that, The step of converting the current analysis signal from the time domain to the time-frequency domain, mapping it from the time-frequency domain to the parameter domain, and determining the peak value of each time window in the parameter domain includes: Calculate the Wigner quasi-probability distribution of the current analytical signal, and perform a Hough transform on the Wigner quasi-probability distribution to obtain the Hough transform result; Determine the peak value of each time window in the Hough transform result.

5. The method according to claim 1, characterized in that, The determination of the fault arc detection result based on the degree of peak value variation in adjacent time windows includes: Determine the degree of peak variation for each adjacent time window; Gradient enhancement prediction is performed on the degree of peak change in each of the adjacent time windows to obtain the prediction probability; If the predicted probability is greater than or equal to the probability threshold, the fault arc detection result is determined to be that a fault arc exists; If the predicted probability is less than the probability threshold, the fault arc detection result is determined to be that there is no fault arc.

6. The method according to claim 1, characterized in that, The determination of the fault arc detection result based on the degree of peak value variation in adjacent time windows includes: Determine the degree of peak variation for each adjacent time window; If the peak value change of each of the adjacent time windows is greater than the preset threshold, the fault arc detection result is determined to be that a fault arc exists, and the line is instructed to be cut off.

7. An AC fault arc detection device, characterized in that, The device includes: The signal acquisition module is used to acquire the current signal to be detected; The signal analysis module is used to perform Hilbert transform on the current signal to be detected, obtain the Hilbert transform result, and determine the current analysis signal based on the Hilbert transform result; The peak value determination module is used to map the current analytical signal from the time domain to the parameter domain and determine the peak value of each time window in the parameter domain; the peak value is used to characterize the extreme value of arc energy intensity in the time-frequency joint space. The fault determination module is used to determine the fault arc detection result based on the degree of peak value change in adjacent time windows.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images