Alternating current arc detection method based on current and harmonic wave fluctuation and related device

Abstract

The invention discloses an alternating current arc detection method based on current and harmonic wave fluctuation and a related device, and the method comprises the steps: collecting first electrical signal data at a preset position in a target power grid, extracting harmonic wave features in the first electrical signal data, collecting second electrical signal data at the preset position, and extracting current waveform features in the second electrical signal data; determining a dichotomy feature data set and a fluctuation feature data set according to the harmonic features and the current waveform features; training a preset model based on the dichotomy feature data set and the fluctuation feature data set to obtain a dichotomy model and a fluctuation model; and performing arc fault detection on the electrical signal of the preset second time period at the preset position through a dichotomy model and a fluctuation model to determine a target arc fault detection result at the preset position. According to the invention, the arc fault detection is carried out through the combination of the binary classification model and the fluctuation model, and the detection accuracy of the fault arc can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric power and electricity, and in particular, to an alternating current arc detection method and related device based on current and harmonic fluctuations. Background Art

[0002] With the rapid improvement of the global electrification level, the social power demand is increasing day by day. However, the proportion of electrical fires is also increasing, and most of the causes of electrical fires are faulty arcs. Therefore, during actual power operation, it is necessary to detect arcs.

[0003] Existing arc detection technologies usually adopt the current threshold detection method, which judges faults by setting a fixed current threshold, but cannot distinguish normal start / stop from arc faults. Or they adopt the low-frequency harmonic detection method, which uses the low-frequency harmonic characteristics generated by arcs, with less information and low distinguishability from the characteristics of many interfering electrical appliances. Or they can also adopt the waveform slope detection method, which judges whether there is an arc fault by analyzing the current change rate, but it is not sensitive enough to low-power loads. Existing arc detection technologies have problems such as high false alarm rates, slow response speeds, and poor anti-interference capabilities. Therefore, how to improve the detection accuracy of faulty arcs has become an urgent problem to be solved. Summary of the Invention

[0004] The embodiments of the present application provide an alternating current arc detection method and related device based on current and harmonic fluctuations, which jointly perform arc fault detection through a binary classification model and a fluctuation model, and achieve an improvement in the detection accuracy of faulty arcs.

[0005] In a first aspect, the embodiments of the present application provide an alternating current arc detection method based on current and harmonic fluctuations, which is applied to a control device of an arc detection system. The arc detection system further includes: a first data acquisition device and a second data acquisition device. The method includes: Collect first electrical signal data at a preset position in a target power grid through the first data acquisition device at a first sampling frequency within a preset first time period, and extract harmonic characteristics in the first electrical signal data. At the same time, collect second electrical signal data at the preset position through the second data acquisition device at a second sampling frequency within the preset first time period, and extract current waveform characteristics in the second electrical signal data. The first sampling frequency is greater than the second sampling frequency; Determine a binary classification feature data set according to the harmonic characteristics and the current waveform characteristics; Determine a fluctuation feature data set according to the harmonic characteristics and the current waveform characteristics; Train a preset model based on the binary classification feature data set and the fluctuation feature data set respectively to obtain a binary classification model and a fluctuation model; Perform arc fault detection on the electrical signals in a preset second time period at a preset position through the binary classification model and the fluctuation model, and obtain a first detection result and a second detection result; Determine the target arc fault detection result at the preset position according to the first detection result and the second detection result.

[0006] In a second aspect, an embodiment of the present application provides an alternating current arc detection device based on current and harmonic fluctuations, which is applied to a control device of an arc detection system. The arc detection system further includes: a first data acquisition device and a second data acquisition device; the alternating current arc detection device based on current and harmonic fluctuations includes: a data acquisition module, a first data set processing module, a second data set processing module, a model training module, an arc fault detection module, and a detection determination module. Among them, The data acquisition module is configured to collect first electrical signal data at a preset position in a target power grid through the first data acquisition device at a first sampling frequency within a preset first time period, extract harmonic features in the first electrical signal data, and at the same time, collect second electrical signal data at the preset position through the second data acquisition device at a second sampling frequency within the preset first time period, and extract current waveform features in the second electrical signal data; the first sampling frequency is greater than the second sampling frequency; The first data set processing module is configured to determine a binary classification feature data set according to the harmonic features and the current waveform features; The second data set processing module is configured to determine a fluctuation feature data set according to the harmonic features and the current waveform features; The model training module is configured to train a preset model based on the binary classification feature data set and the fluctuation feature data set respectively to obtain a binary classification model and a fluctuation model; The arc fault detection module is configured to perform arc fault detection on the electrical signals in a preset second time period at the preset position through the binary classification model and the fluctuation model respectively, and obtain a first detection result and a second detection result; The detection determination module is configured to determine the target arc fault detection result at the preset position according to the first detection result and the second detection result.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory, a communication interface, and one or more programs. Among them, the above one or more programs are stored in the above memory and are configured to be executed by the above processor. The above programs include instructions for executing the steps in the first aspect of the embodiment of the present application.

[0008] Fourthly, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application.

[0009] Fifthly, an embodiment of the present application provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product can be a software installation package.

[0010] It can be seen that adopting the embodiment of the present application has the following beneficial effects: By implementing the embodiment of the present application, in a preset first time period, the first electrical signal data at a preset position in the target power grid is collected by the first data acquisition device at a first sampling frequency, and the harmonic characteristics in the first electrical signal data are extracted. At the same time, in the preset first time period, the second electrical signal data at the preset position is collected by the second data acquisition device at a second sampling frequency, and the current waveform characteristics in the second electrical signal data are extracted; a binary classification feature dataset is determined according to the harmonic characteristics and the current waveform characteristics; a fluctuation feature dataset is determined according to the harmonic characteristics and the current waveform characteristics; the preset model is trained respectively based on the binary classification feature dataset and the fluctuation feature dataset to obtain a binary classification model and a fluctuation model; the electrical signals in a preset second time period at the preset position are subjected to arc fault detection by the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result; a target arc fault detection result at the preset position is determined according to the first detection result and the second detection result. It can be seen that by jointly performing arc fault detection by the binary classification model and the fluctuation model, the detection accuracy of the fault arc is improved. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the following will describe the drawings required to be used in the embodiments of the present application or the background art.

[0012] Figure 1 It is a schematic flowchart of an alternating current arc detection method based on current and harmonic fluctuations provided by an embodiment of the present application; Figure 2 It is a schematic diagram of a harmonic feature dataset belonging to a normal signal provided by an embodiment of the present application; Figure 3 It is a schematic diagram of a harmonic feature dataset belonging to an arc signal provided by an embodiment of the present application; Figure 4 It is a schematic diagram of the fluctuation of the harmonic characteristics belonging to a normal signal provided by an embodiment of the present application; Figure 5 It is a schematic diagram of the fluctuation of the harmonic characteristics belonging to an arc signal provided by an embodiment of the present application; Figure 6 It is a schematic diagram of a dataset of the current fluctuation characteristics belonging to a normal signal provided by an embodiment of the present application; Figure 7 It is a schematic diagram of a dataset of the current fluctuation characteristics belonging to an arc signal provided by an embodiment of the present application; Figure 8 It is a schematic diagram of the fluctuation of the current waveform characteristics belonging to a normal signal provided by an embodiment of the present application; Figure 9 It is a schematic diagram of the fluctuation of the current waveform characteristics belonging to an arc signal provided by an embodiment of the present application; Figure 10 It is an application scenario diagram of an alternating current arc detection method based on current and harmonic fluctuations provided by an embodiment of the present application; Figure 11 It is a schematic structural diagram of an alternating current arc detection device based on current and harmonic fluctuations provided by an embodiment of the present application; Figure 12 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0013] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present application.

[0014] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0015] References to "embodiments" in this specification mean that the particular features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive of other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0016] The relevant content, concepts, meanings, technical problems, technical solutions, beneficial effects, etc. involved in the embodiments of the present application are described below.

[0017] Please refer to Figure 1 , Figure 1 which is a schematic flow chart of an alternating current arc detection method based on current and harmonic fluctuations provided by an embodiment of the present application. This method is applied to the control device of an arc detection system, and the arc detection system further includes: a first data acquisition device and a second data acquisition device. The method includes but is not limited to the following steps: S101. During a preset first time period, use the first data acquisition device to collect first electrical signal data at a preset position in the target power grid at a first sampling frequency, and extract the harmonic characteristics in the first electrical signal data. At the same time, during the preset first time period, use the second data acquisition device to collect second electrical signal data at a second sampling frequency at the preset position, and extract the current waveform characteristics in the second electrical signal data.

[0018] The arc detection system of the embodiments of the present application can be used for arc fault detection in an alternating current power grid. For example, in scenarios such as low-voltage distribution systems and industrial electrical equipment, it realizes high-precision and high-reliability detection of arc faults by analyzing the fluctuation characteristics of current and harmonics.

[0019] In the embodiments of the present application, the arc detection system includes: a first data acquisition device and a second data acquisition device. Both the first data acquisition device and the second data acquisition device can be a combination of a transient coil (such as a Rogowski coil) and a data acquisition card (a high-speed ADC data acquisition card). The data acquisition device can sense the current signal at a preset position in the target power grid in real time through the transient coil, and convert the analog signal into a digital signal through the ADC data acquisition card to form original high-frequency current data, thereby realizing the operation of data sampling.

[0020] Among them, the first data acquisition device can collect high-frequency current signals at a preset position in the target power grid based on the first sampling frequency (such as 10 Msps) for extracting harmonic features. Through this high-frequency sampling mechanism, harmonic mutations in different frequency bands caused by arc faults can be captured, and the spectrum distribution of different frequency point channels can be further analyzed through short-time Fourier transform to obtain harmonic features (such as harmonic components and phase mutations in the 1 kHz - 10 kHz frequency band). The second data acquisition device can collect current signals at the same preset position based on the second sampling frequency (20 ksps). The current signals collected at this sampling frequency can retain the time-domain profile features of the current waveform and are used to extract current waveform features (such as effective value fluctuations, waveform distortion, and zero-crossing point offsets). Through this sampling mechanism, data points aligned with the time dimension of the harmonic features can be collected, avoiding feature misalignment caused by timing deviations, facilitating subsequent feature fusion analysis. At the same time, it can effectively reflect the change trend of the current amplitude and the degree of non-sinusoidal distortion of the waveform.

[0021] In the embodiments of the present application, the preset first time period is a pre-set time period. For example, the past 1 month, etc. By extracting features from the electrical signal data in the preset first time period, it is used to train a binary classification model and a fluctuation model that can identify arcs.

[0022] In the embodiments of the present application, the target power grid can be a low-voltage distribution network or an industrial power network with an AC power frequency of 50 Hz / 60 Hz, which includes single-phase / three-phase power supply systems, specifically including but not limited to low-voltage distribution lines in residential buildings and commercial buildings, as well as industrial power equipment connection lines in factories and workshops. Various types of loads can be connected to this power grid, such as resistive loads, inductive loads, and non-linear loads, and it supports power grid scenarios with different line lengths and different topological structures. Among them, the preset position can be a specific line node or load input end on the target power grid, etc.

[0023] In a specific embodiment, within the preset first time period, the first data acquisition device collects the first electrical signal data at a preset position in the target power grid using the first sampling frequency. Then, the harmonic features in the first electrical signal data can be extracted. At the same time, within the preset first time period, the second data acquisition device collects the second electrical signal data at the preset position using the second sampling frequency. Then, the current waveform features in the second electrical signal data can be extracted.

[0024] Among them, the first sampling frequency is greater than the second sampling frequency. Since the first electrical signal data is used to extract harmonic features, and harmonics, as high-frequency components, have a frequency range significantly higher than the power frequency of 50 Hz. According to the Nyquist sampling theorem, to avoid spectral aliasing and accurately capture high-frequency harmonic components, a higher sampling frequency (such as 10 Msps) is required to ensure that high-frequency details (such as 5 kHz harmonics) in the original signal can be completely sampled. Below this, the current waveform features extracted from the second electrical signal data mainly reflect the overall change trend of the current in the time domain (such as RMS fluctuation, waveform distortion, etc.). Such features usually contain more low-frequency components and do not require retaining high-frequency details. Therefore, the first sampling frequency is greater than the second sampling frequency.

[0025] It should be noted that the first data acquisition device and the second data acquisition device need to use the zero-crossing point of the grid voltage as the synchronous trigger reference to ensure that the collected high-frequency and low-frequency signals are completely aligned in time phase. For example, when detecting a certain industrial motor line, the first data acquisition device captures a sudden increase in 5 kHz harmonics (amplitude change rate > 30%) at the moment of arc fault, and at the same time, the second data acquisition device detects that the RMS fluctuation amplitude of the current exceeds the normal range of ±15%. The synchronous acquisition of these two types of features can ensure subsequent joint discrimination.

[0026] Optionally, the above step: extracting harmonic features from the first electrical signal data may include the following steps: A101. Determine the power frequency period corresponding to the target power grid; A102. Determine the target window according to the power frequency period; A103. Based on a preset short-time fast Fourier transform, extract n frequency point channels from the first electrical signal data in the target window; n is a positive integer; A104. Determine the first classification label corresponding to the first electrical signal data; the first classification label includes one of the following: normal label, arc label; A105. Construct the harmonic features according to the n frequency point channels and the first classification label.

[0027] Among them, the preset short-time fast Fourier transform is an algorithm pre-set for time-frequency analysis of time-domain signals. It can divide non-stationary signals into multiple short-time stationary segments through a sliding window, and then perform a fast Fourier transform on each segment to obtain frequency-domain features. In the embodiments of the present application, the window function of the preset short-time fast Fourier transform can adopt a Hanning window, and the window size can be set to 64 sampling points, and 20 frequency point channels can be extracted.

[0028] In a specific embodiment, first, the power frequency period corresponding to the target power grid is determined, and then the target window is determined according to the power frequency period. For example, the AC power frequency of the target power grid in the embodiment of the present application is 50 Hz, and the aligned power frequency period is 20 ms. Then the target window can be taken as half of the power frequency period, that is, 10 ms, which is the time period from one voltage zero crossing to the next zero crossing. Arc faults may cause waveform distortion in the half cycle, and the target window covers the complete half cycle signal, which is convenient for analyzing the symmetry of the positive and negative half cycles.

[0029] Based on the preset short-time fast Fourier transform, n frequency point channels in the first electrical signal data are extracted with the target window, where n is a positive integer. According to the typical harmonic frequency range of arc faults, 1 kHz to 10 kHz, 20 frequency point channels can be selected. Each channel corresponds to the energy distribution in a specific frequency interval, and each frequency point channel can include 200 sampling points.

[0030] Determine the first classification label corresponding to the first electrical signal data, where the first classification label includes one of the following: normal label, arc label. It should be noted that both the first electrical signal data and the second electrical signal data collected within the preset first time period include normal signals or arc signals. For normal signals, they are collected in an arc-free scenario, such as normal start-stop and steady-state operation of equipment, and the harmonic components in the signal are within the normal range. For arc signals, they are collected in an arc fault scenario, such as artificial arcing through an arc generator or line breakdown, and there are abnormal high-frequency harmonics in the signal. They are generated through manual annotation or physical experiments. For normal signals, they can be set as the normal label (marked as 0), and for arc signals, they can be set as the arc label (marked as 1).

[0031] Finally, construct harmonic features according to the n frequency point channels and the first classification label. Specifically, associate the frequency domain data of the 20 frequency point channels, that is, the [20×200] matrix, with the classification label (0 or 1) to form a labeled harmonic feature sample.

[0032] Please refer to Figure 2 , Figure 2 which is a schematic diagram of a harmonic feature data set belonging to normal signals provided by the embodiment of the present application. As shown in the figure, this figure shows the performance of the harmonic feature data set of normal signals in the time domain. The abscissa is time (in ms), covering a time span from 0 ms to 100 ms, and the ordinate is the time-frequency feature amplitude, which reflects the intensity of the harmonic features. Since the target window is 10 ms, this figure shows the harmonic features of 10 normal signals.

[0033] As shown in the figure, while certain harmonic components exist during normal grid operation, there are no drastic harmonic fluctuations, as would be expected from an abnormal situation such as an arc fault. The fluctuations in the figure represent the combined effects of the harmonics generated by various loads under normal operating conditions. Their amplitudes fluctuate within a certain range, with no significant surges or sudden changes. This indicates relatively stable grid operation, without the abnormal increase in harmonics at specific frequencies characteristic of an arc fault.

[0034] See Figure 3 , Figure 3 This figure shows a harmonic signature dataset for arc signals, as provided in an embodiment of the present application. It illustrates the time domain representation of the harmonic signature dataset for arc signals. The horizontal axis represents time (in milliseconds), spanning the time range from 0 to 100 milliseconds. The vertical axis represents the amplitude of the time-frequency signature, reflecting the strength of the harmonic signature. Because the target window is 10 milliseconds, the figure displays the harmonic signatures of ten arc signals.

[0035] The curve in the figure fluctuates significantly, with multiple large spikes. This is because arc faults generate a large number of high-frequency harmonics, disrupting the relatively stable harmonic distribution during normal grid operation. These spikes correspond to the appearance of abnormal high-frequency harmonics at specific moments, indicating that arc faults cause the harmonic components to fluctuate dramatically at certain moments, with energy concentrated in these high-frequency harmonics. Compared with the harmonic feature dataset of normal signals, the time-frequency characteristics of arc signals are significantly larger in amplitude and fluctuate more dramatically, resulting in significant differences in characteristics.

[0036] See Figure 4 , Figure 4 This is a schematic diagram of the fluctuations of the harmonic characteristics of a normal signal, provided in an embodiment of the present application. As shown in the figure, the fluctuations of the harmonic characteristics of a normal signal are shown. The horizontal axis represents time (in milliseconds), ranging from 0 ms to 100 ms, and the vertical axis represents the amplitude of the time-frequency characteristics, reflecting the strength of the harmonic characteristics. The figure shows the fluctuations of the harmonic characteristics from a normal signal to a normal signal within 100 ms.

[0037] The curve in the figure is labeled "Normal to Normal," indicating that the grid operated normally throughout the entire period. As can be seen, the curve exhibits dense and relatively stable fluctuations, without significant spikes or sudden changes. This fluctuation is the result of the combined effects of harmonics generated by various loads during normal grid operation. The amplitude is controlled within a certain range, and there is no sharp increase in energy at any particular frequency.

[0038] See Figure 5 , Figure 5It is a schematic diagram of the fluctuation of the harmonic characteristics of the arc signal provided by an embodiment of the present application. As shown in the figure, this figure shows the fluctuation performance of the harmonic characteristics of the arc signal. The abscissa is time (unit: ms), and the time range is from 0 ms to 100 ms. The ordinate is the time-frequency characteristic amplitude, which reflects the intensity of the harmonic characteristics. This figure shows the fluctuation performance of the harmonic characteristics from the normal signal to the arc signal within 100 ms.

[0039] In the first half of the time axis (such as from 0 ms to 50 ms), the time-frequency characteristic amplitude is relatively low and the fluctuation is gentle, indicating that the power grid is in normal operation. At this time, the harmonic components are stable and there is no abnormal high-frequency energy concentration phenomenon. In the second half (after 50 ms), the time-frequency characteristic amplitude rises sharply, and a large number of large spikes appear. This is because the arc fault generates rich high-frequency harmonics, resulting in an instantaneous surge of energy at specific frequency points. This significant difference in the front and back characteristics intuitively reflects the impact of the arc fault on the harmonic characteristics of the power grid and shows the state transition of the power grid from normal to faulty.

[0040] Optionally, the above step: extracting the current waveform characteristics from the second electrical signal data may include the following steps: B101. Extract the waveform matrix from the second electrical signal data based on the target window; B102. Determine the second classification label corresponding to the second electrical signal data; the second classification label includes one of the following: normal label, arc label; B103. Determine the current waveform characteristics according to the waveform matrix and the second classification label.

[0041] In a specific embodiment, extracting the waveform matrix from the second electrical signal data based on the target window is consistent with the target window in the harmonic feature extraction to ensure that the current waveform and the harmonic characteristics are strictly aligned in time. The first electrical signal data is the data collected based on the first sampling frequency (10 Msps), and the number of harmonic feature data points extracted under the target window is 20×200. While the second electrical signal data is the data collected based on the second sampling frequency (20 ksps). Under the same target window, 200 sampling points can be collected. Therefore, the obtained waveform matrix is a 1×200 matrix, which represents the instantaneous value of the current at each moment and thus retains the time-domain profile of the current waveform.

[0042] Determine the second classification label corresponding to the second electrical signal data, where the second classification label includes one of the following: normal label, arc label. The current waveform characteristics can be determined according to the waveform matrix and the second classification label.

[0043] Please refer to Figure 6 , Figure 6It is a schematic diagram of the current fluctuation feature dataset belonging to normal signals provided by the embodiments of the present application. As shown in the figure, the abscissa is time (unit: ms), covering a time span from 0 ms to 100 ms, and the ordinate is the amplitude of the current waveform, reflecting the instantaneous value of the current. Since the target window is 10 ms, this figure shows the current fluctuation features of 10 normal signals. The curves presenting regular and smooth fluctuation patterns in the figure indicate that under normal working conditions, the grid current is in a stable state, conforming to the change law of the power frequency current, without sudden mutations or abnormal distortions. This regular fluctuation shows that no abnormal events such as arc faults occur in the grid at this time, and the current waveform is not interfered by faults and maintains normal electrical characteristics.

[0044] Please refer to Figure 7 , Figure 7 It is a schematic diagram of the current fluctuation feature dataset belonging to arc signals provided by the embodiments of the present application. As shown in the figure, the abscissa is time (unit: ms), covering a time span from 0 ms to 100 ms, and the ordinate is the amplitude of the current waveform, reflecting the instantaneous value of the current. Since the target window is 10 ms, this figure shows the current fluctuation features of 10 arc signals. The curves presenting the fluctuation patterns of the power frequency current in the figure, but at the rising or falling edge of each half-cycle, obvious small spikes or mutations are superimposed. This is due to the instability of the arc fault, resulting in additional high-frequency oscillations or instantaneous changes on the basis of the normal power frequency current fluctuation. These distortion features are in sharp contrast to the smooth and regular waveform of the normal signal, indicating that the arc interference makes the current waveform no longer stable.

[0045] Please refer to Figure 8 , Figure 8 It is a schematic diagram of the fluctuation of the current waveform features belonging to normal signals provided by the embodiments of the present application. As shown in the figure, this figure shows the fluctuation performance of the current waveform features of normal signals. The abscissa is time (unit: ms), and the time range is from 0 ms to 100 ms. The ordinate is the amplitude of the current waveform, reflecting the instantaneous value of the current. This figure shows the fluctuation performance of the current waveform features from normal signal to normal signal within 100 ms.

[0046] The curve in the figure is labeled as "normal to normal", indicating that the grid is always in a normal operating state throughout the observation period from 0 to 100 ms. From the waveform shape, the curve presents regular, smooth and periodically repeated fluctuations, similar to a standard sine wave. Within each period, the rising edge and the falling edge of the current waveform are symmetric and smooth, without abnormal phenomena such as mutations, spikes or distortions, reflecting the stability of the current following the power frequency change law under normal working conditions. This regular fluctuation shows that the grid is not interfered by abnormal factors such as arc faults, and the current maintains normal electrical characteristics.

[0047] Please refer to Figure 9 ,Figure 9 It is a schematic diagram of the fluctuation of the current waveform characteristics belonging to the arc signal provided by an embodiment of the present application. As shown in the figure, this figure shows the fluctuation performance of the current waveform characteristics of the arc signal. The abscissa is time (unit: ms), and the time range is from 0 ms to 100 ms. The ordinate is the amplitude of the current waveform, reflecting the instantaneous value of the current. This figure shows the fluctuation performance of the current waveform characteristics from the normal signal to the arc signal within 100 ms.

[0048] In the first half of the time axis (such as from 0 ms to 50 ms), the current waveform is approximately a regular sine wave, and the rising edge and the falling edge are relatively symmetrical, reflecting the current characteristics during the normal operation of the power grid. In the second half (after 50 ms), the waveform shows obvious distortion. On the basis of the original sine wave form, several small mutations or spikes are superimposed. This is because when an arc fault occurs, its instability interferes with the normal flow of the current, breaking the smoothness and symmetry of the waveform and resulting in local instantaneous changes. This change in the waveform characteristics from regular to distorted intuitively shows the transformation of the power grid from the normal state to the arc fault state.

[0049] S102. Determine the binary classification feature dataset according to the harmonic characteristics and the current waveform characteristics.

[0050] In a specific embodiment, the binary classification feature dataset can be determined according to the harmonic characteristics and the current waveform characteristics. Specifically, the harmonic characteristics and the current waveform characteristics can be feature - spliced, and the spliced features can be classified. For example, it can be determined whether the spliced features belong to the normal signal or the arc signal, and then the binary classification features can be obtained, and the binary classification feature dataset can be determined.

[0051] Optionally, the above step: determining the binary classification feature dataset according to the harmonic characteristics and the current waveform characteristics, may include the following steps: A201. Combine the harmonic characteristics and the current waveform characteristics to obtain the target combined features; A202. Normalize the target combined features to obtain the first combined features; A203. Determine the target category corresponding to the first combined features according to the first classification label and the second classification label; the target category includes one of the following: normal category, arc category; A204. Determine the binary classification feature dataset according to the first combined features and the target category.

[0052] In a specific embodiment, the harmonic feature is a 20×200 matrix, which represents 20 frequency point channels, with 200 points in each channel, reflecting the frequency domain energy distribution. The current waveform feature is a 1×200 matrix, which is the instantaneous current value after downsampling, reflecting the time domain waveform profile. Combining the harmonic feature and the current waveform feature can obtain a target combined feature, which is a 21×200 matrix. The target combined feature ensures feature alignment through the same time window (10 ms), while retaining the independence of the frequency domain and time domain features.

[0053] Next, each element in the 21×200 matrix is divided by the effective value of the current within the current 10 ms, that is, the equivalent DC current value of the alternating current within the current 10 ms time interval. The harmonic feature and the current waveform feature have different dimensions. Normalization avoids large-value features, and the current amplitude varies greatly under different loads. After normalization, the features only reflect relative changes, improving the adaptability of the subsequent trained model to different working conditions.

[0054] Determine the target category corresponding to the first combined feature according to the first classification label and the second classification label, where the target category includes one of the following: normal category, arc category. For example, only when an arc is detected in both the harmonic feature and the current waveform feature is it determined as an arc fault. By performing the simultaneous determination operation, false alarms of single features can be filtered. For example, the waveform distortion during motor startup but normal harmonics can improve reliability.

[0055] According to the first combined feature and the target category, a binary classification feature dataset can be determined. The combination of frequency domain and time domain features covers the multi-dimensional manifestations of arc faults, such as high-frequency harmonic surges and time domain waveform distortions, and the simultaneous determination of double labels can reduce misjudgments.

[0056] S103. Determine a fluctuation feature dataset according to the harmonic feature and the current waveform feature.

[0057] In a specific embodiment, a fluctuation feature dataset can be determined according to the harmonic feature and the current waveform feature, and the fluctuation feature dataset is used to characterize the dynamic changes of the features. Specifically, by analyzing the change amounts of the harmonic feature and the current waveform feature composed of multiple consecutive target windows, these change information are integrated. For example, the target window is 10 ms. By integrating 10 harmonic features and current waveform features, a fluctuation feature is constructed, and the fluctuation feature can characterize the feature changes within 100 ms.

[0058] Optionally, the harmonic feature includes multiple harmonic features, and the current waveform feature includes multiple current waveform features; the above step: determining a fluctuation feature dataset according to the harmonic feature and the current waveform feature, may include the following steps: A301. Determine multiple first combined features according to the multiple harmonic features and the multiple current waveform features; A302. Combine the multiple first combined features to form a second combined feature; A303. Determine the category corresponding to the second combined feature according to the number of first combined features belonging to the normal category in the second combined feature; A304. Determine the fluctuation feature dataset according to the second combined feature and the category corresponding to the second combined feature.

[0059] Among them, the harmonic features may include multiple harmonic features, and the current waveform features may include multiple current waveform features. For example, in the construction of the binary classification feature dataset, both the harmonic features and the current waveform features are based on a target window as a standard, while the fluctuation feature dataset is used to characterize the dynamic changes of features and can be constructed based on multiple target windows. At this time, the harmonic features extracted from the first electrical signal data may include multiple harmonic features, and the current waveform features extracted from the second electrical signal data may include multiple current waveform features.

[0060] In a specific embodiment, multiple first combined features can be determined according to multiple harmonic features and multiple current waveform features, and each first combined feature corresponds to a target category, where the target category includes one of the following: normal category, arc category. Stacking the multiple first combined features in chronological order can form a second combined feature, which represents the time-frequency feature changes within multiple time windows.

[0061] Determine the category corresponding to the second combined feature according to the number of first combined features belonging to the normal category in the second combined feature. Specifically, for each first combined feature, according to its target category, count the number of normal categories among the multiple target categories to determine the category corresponding to the second combined feature. For example, if the number of first combined features belonging to the normal category exceeds a preset threshold, the category corresponding to the second combined feature is the normal category, otherwise its corresponding category is the arc category, where the preset threshold is a value set in advance or the system default value, and its value can be 7.

[0062] The fluctuation feature dataset can be determined according to the second combined feature and the category corresponding to the second combined feature. The binary classification feature dataset only focuses on the steady-state characteristics of a single time window, while the fluctuation feature dataset can characterize the change law of features over time. By jointly judging through multiple windows, false alarms caused by non-fault factors such as load start-stop and short-time pulses can be reduced.

[0063] S104. Train the preset model based on the binary classification feature dataset and the fluctuation feature dataset respectively to obtain a binary classification model and a fluctuation model.

[0064] In the embodiments of the present application, the preset model may be a one-dimensional convolutional neural network. The one-dimensional convolutional neural network has advantages in processing sequence data. The harmonic features and current waveform features involved in arc fault detection, whether in the binary classification feature dataset or the fluctuation feature dataset, belong to the category of sequence data. For the binary classification feature dataset, the one-dimensional convolutional neural network can quickly identify the feature differences between the normal and arc states within a single time window. For the fluctuation feature dataset, the one-dimensional convolutional neural network can capture the dynamic change trends of features in multiple consecutive time windows, thereby accurately judging the occurrence process of arc faults.

[0065] In a specific embodiment, the binary classification feature dataset represents the fusion of harmonic features and current waveform features within a single time window. Using the binary classification feature dataset to train the preset model, the model learns the static feature differences between the normal and faulty states. After optimizing the parameters, a binary classification model is obtained. This model can directly judge whether there is an arc fault in the power grid at the current moment based on the single-window features.

[0066] The fluctuation feature dataset represents the dynamic changes of features. Its samples are stacked by the first combined features of multiple consecutive time windows, reflecting the evolution trend of features over time. When using the fluctuation feature dataset to train the preset model, the model focuses on learning the feature fluctuation rules and capturing the dynamic patterns during the occurrence and development of arc faults. Finally, a fluctuation model is trained, and this model can identify arc faults from the level of feature change trends.

[0067] By training the binary classification model and the fluctuation model separately, the dual utilization of static and dynamic features is realized, improving the accuracy and reliability of arc fault detection.

[0068] S105. Perform arc fault detection on the electrical signals in the preset second time period at the preset position through the binary classification model and the fluctuation model respectively, and obtain the first detection result and the second detection result.

[0069] In the embodiments of the present application, the preset second time period refers to the continuously set duration for arc fault detection. For example, the preset second time period can be 2000 ms.

[0070] In a specific embodiment, perform arc fault detection on the electrical signals in the preset second time period at the preset position through the binary classification model. Collect the electrical signals at the preset position and input them into the trained binary classification model for analysis. The binary classification model can output the first detection result. Perform arc fault detection on the electrical signals in the preset second time period at the preset position through the fluctuation model. Collect the electrical signals at the preset position and input them into the trained fluctuation model for analysis. The fluctuation model can output the second detection result.

[0071] The binary classification model can provide high-precision single-point detection capabilities, and the fluctuation model reduces misjudgments caused by short-term interference through temporal correlation. The combination of the two can improve the accuracy of arc fault detection.

[0072] Optionally, the above steps: performing arc fault detection on the electrical signals in the preset second time period at the preset position through the binary classification model and the fluctuation model respectively to obtain the first detection result and the second detection result may include the following steps: A501. Collect the third electrical signal data at the preset position by the first data acquisition device at the first sampling frequency within the preset second time period; A502. Detect the third electrical signal data through the binary classification model based on the first detection frequency to obtain the first detection result; A503. Collect the fourth electrical signal data at the preset position by the second data acquisition device at the second sampling frequency within the preset second time period; A504. Detect the fourth electrical signal data through the fluctuation model based on the second detection frequency to obtain the second detection result; the second detection frequency is less than the first detection frequency.

[0073] In a specific embodiment, within the preset second time period, the third electrical signal data at the preset position is collected by the first data acquisition device at the first sampling frequency. Then, the third electrical signal data is detected through the binary classification model based on the first detection frequency to obtain the first detection result.

[0074] Within the preset second time period, the fourth electrical signal data at the preset position is collected by the second data acquisition device at the second sampling frequency. Then, the fourth electrical signal data is detected through the fluctuation model based on the second detection frequency to obtain the second detection result.

[0075] Among them, the second detection frequency is less than the first detection frequency. For example, the first detection frequency can be once every 10 ms, and the second detection frequency can be once every 100 ms. If the preset second time period is 2000 ms, it can be determined that the first detection result includes 200 data, and the second detection result includes 20 data.

[0076] Through the differential sampling strategy and detection frequency, the binary classification model can capture the characteristics of sudden faults in real time and trigger a rapid response, while the fluctuation model confirms the authenticity of the faults through temporal analysis and reduces false alarms. Through this collaborative mechanism of high-frequency early warning and trend verification formed by the dual models, the detection accuracy of arc faults can be improved.

[0077] S106. Determine the target arc fault detection result at the preset position according to the first detection result and the second detection result.

[0078] In a specific embodiment, the first detection result is the output result of a binary classification model, which is used to capture the arc characteristics within a single time window in real time. For example, by analyzing the time-frequency feature matrix of each 10 ms window through the binary classification model, the sudden change of harmonic energy or the distortion of the current waveform can be quickly identified to achieve high-frequency single-point fault warning. The second detection result is the output result of a fluctuation model, which is used to analyze the dynamic evolution trend of the characteristics of consecutive time windows. For example, by integrating the feature tensors of multiple windows through the fluctuation model, it is judged whether the harmonic energy shows an increasing trend or whether the current waveform distortion continues to intensify, and false alarms caused by short-term interference are filtered out.

[0079] Based on the first detection result and the second detection result, the target arc fault detection result at a preset position can be determined. Only when both the binary classification model and the fluctuation model identify an arc synchronously is it determined that an arc fault has occurred, improving the accuracy and reliability of the detection.

[0080] Optionally, the first detection result includes: p first categories; p is a positive integer; the second detection result includes: q second categories; q is a positive integer less than p; the categories include one of the following: normal category, arc category; the above step: determining the target arc fault detection result at a preset position according to the first detection result and the second detection result may include the following steps: A601. Select q first categories corresponding to the q second categories at the detection output result time point from the p first categories; the q first categories correspond to the q second categories one by one; A602. Perform a target determination step on the q first categories and the q second categories to obtain q third categories; Among them, the target determination step is as follows: Obtain a reference first category and a reference second category corresponding to the reference first category among the q second categories; the reference first category is any one of the q first categories; If both the reference first category and the reference second category are the arc category, determine that the reference third category is the arc category; otherwise, determine that the reference third category is the normal category; the reference third category is the third category corresponding to the reference first category and the reference second category among the q third categories; A603. If there are at least k third categories among the q third categories that are the arc category, determine that there is an arc fault at the preset position; otherwise, determine that there is no arc fault at the preset position; k is a positive integer less than q.

[0081] Among them, the first detection result includes: p first categories; p is a positive integer; the second detection result includes: q second categories; q is a positive integer less than p. For example, if the preset second time period is 2000 ms, the first detection frequency is to detect once every 10 ms through a binary classification model, and the second detection frequency is to detect once every 100 ms through a fluctuation model, then p is 200 and q is 20. Among them, the category includes one of the following: normal category, arc category.

[0082] In a specific embodiment, q first categories corresponding to the q second categories at the detection output result time points are selected from the p first categories, where the q first categories and the q second categories are in one-to-one correspondence. Specifically, at every 100 ms, the fluctuation model outputs a detection result, and at the 100th ms, the binary classification model outputs ten detection results. At this time, the tenth output detection result of the binary classification model is corresponded to the detection result output by the fluctuation model for joint detection.

[0083] Performing a target determination step on the q first categories and the q second categories can obtain q third categories. Specifically, when both the first category and the second category are determined to be the arc category, the third category is the arc category; otherwise, the third category is the normal category.

[0084] If there are at least k third categories that are arc categories among the q third categories, it can be determined that there is an arc fault at the preset position; otherwise, it can be determined that there is no arc fault at the preset position, where k is a positive integer less than q. For example, if the preset second time period is 2000 ms and twenty joint determinations are performed, if there are at least 10 third categories that are arc categories, it can be determined that there is an arc fault at the preset position, and the proportion is one-half.

[0085] Please refer to Figure 10 , Figure 10 which is an application scenario diagram of an alternating current arc detection method based on current and harmonic fluctuations provided by an embodiment of the present application. As shown in the figure, the binary classification model detects with a 10-ms time window and outputs a series of detection results (0 represents normal, 1 represents arc fault) within 2000 ms, reflecting its fast judgment ability for the electrical signal characteristics in each short time window and being able to capture the possible arc fault characteristics in a timely manner. The fluctuation model analyzes with a 100-ms time window and also outputs corresponding results (0 represents normal, 1 represents arc fault) within the same 2000 ms, reflecting the dynamic change trend of the electrical signal characteristics within a longer time range (100 ms), filtering short-term interference, and avoiding possible false alarms of the binary classification model.

[0086] The final detection result combines the outputs of the two models. As can be seen from the figure, if both models output 1, it is comprehensively determined that there is an arc fault; otherwise, it is determined to be normal. This method utilizes the advantages of the fast detection of the binary classification model and the trend analysis of the fluctuation model to complement each other, improving the accuracy and reliability of AC arc fault detection and being able to more effectively identify whether there is an arc fault in the electrical system during actual operation.

[0087] In summary, by implementing the embodiments of the present application, in a preset first time period, the first data acquisition device is used to collect the first electrical signal data at a preset position in the target power grid at a first sampling frequency, and the harmonic characteristics in the first electrical signal data are extracted. At the same time, in the preset first time period, the second data acquisition device is used to collect the second electrical signal data at the preset position at a second sampling frequency, and the current waveform characteristics in the second electrical signal data are extracted; a binary classification feature data set is determined according to the harmonic characteristics and the current waveform characteristics; a fluctuation feature data set is determined according to the harmonic characteristics and the current waveform characteristics; based on the binary classification feature data set and the fluctuation feature data set, a preset model is trained respectively to obtain a binary classification model and a fluctuation model; the binary classification model and the fluctuation model are used to perform arc fault detection on the electrical signals in a preset second time period at the preset position respectively to obtain a first detection result and a second detection result; the target arc fault detection result at the preset position is determined according to the first detection result and the second detection result. It can be seen that by jointly performing arc fault detection using the binary classification model and the fluctuation model, the detection accuracy of the faulty arc is improved.

[0088] Please refer to Figure 11 , Figure 11 FIG. is a schematic structural diagram of an AC arc detection device based on current and harmonic fluctuations provided by an embodiment of the present application. The AC arc detection device 200 based on current and harmonic fluctuations includes: a data acquisition module 201, a first data set processing module 202, a second data set processing module 203, a model training module 204, an arc fault detection module 205, and a detection determination module 206. Among them, The data acquisition module 201 is configured to collect the first electrical signal data at a preset position in the target power grid at a first sampling frequency through the first data acquisition device in a preset first time period, and extract the harmonic characteristics in the first electrical signal data. At the same time, in the preset first time period, the second data acquisition device is used to collect the second electrical signal data at the preset position at a second sampling frequency, and extract the current waveform characteristics in the second electrical signal data; the first sampling frequency is greater than the second sampling frequency; The first data set processing module 202 is configured to determine a binary classification feature data set according to the harmonic characteristics and the current waveform characteristics; The second data set processing module 203 is configured to determine a fluctuation feature data set according to the harmonic feature and the current waveform feature; The model training module 204 is configured to train a preset model based on the binary classification feature data set and the fluctuation feature data set respectively to obtain a binary classification model and a fluctuation model; The arc fault detection module 205 is configured to perform arc fault detection on the electrical signals in a preset second time period at the preset position through the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result; The detection determination module 206 is configured to determine a target arc fault detection result at the preset position according to the first detection result and the second detection result.

[0089] Optionally, in terms of extracting the harmonic feature from the first electrical signal data, the data acquisition module 201 is further specifically configured to: Determine the power frequency period corresponding to the target power grid; Determine a target window according to the power frequency period; Extract n frequency point channels from the first electrical signal data based on a preset short-time fast Fourier transform with the target window; n is a positive integer; Determine a first classification label corresponding to the first electrical signal data; the first classification label includes one of the following: normal label, arc label; Construct the harmonic feature according to the n frequency point channels and the first classification label.

[0090] Optionally, in terms of extracting the current waveform feature from the second electrical signal data, the data acquisition module 201 is further specifically configured to: Extract a waveform matrix from the second electrical signal data based on the target window; Determine a second classification label corresponding to the second electrical signal data; the second classification label includes one of the following: normal label, arc label; Determine the current waveform feature according to the waveform matrix and the second classification label.

[0091] Optionally, in terms of determining the binary classification feature data set according to the harmonic feature and the current waveform feature, the first data set processing module 202 is further specifically configured to: Combine the harmonic feature and the current waveform feature to obtain a target combined feature; Normalize the target combined feature to obtain a first combined feature; Determine the target category corresponding to the first combined feature according to the first classification label and the second classification label; the target category includes one of the following: normal category, arc category; Determine the binary classification feature dataset according to the first combined feature and the target category.

[0092] Optionally, the harmonic feature includes multiple harmonic features, and the current waveform feature includes multiple current waveform features; in terms of determining the fluctuation feature dataset according to the harmonic feature and the current waveform feature, the second dataset processing module 203 is further specifically configured to: Determine multiple first combined features according to the multiple harmonic features and the multiple current waveform features; Combine the multiple first combined features into a second combined feature; Determine the category corresponding to the second combined feature according to the number of first combined features belonging to the normal category in the second combined feature; Determine the fluctuation feature dataset according to the second combined feature and the category corresponding to the second combined feature.

[0093] Optionally, in terms of performing arc fault detection on the electrical signal in the preset second time period at the preset position through the binary classification model and the fluctuation model to obtain a first detection result and a second detection result, the arc fault detection module 205 is further specifically configured to: Collect third electrical signal data at the preset position by the first data acquisition device at the first sampling frequency within the preset second time period; Detect the third electrical signal data through the binary classification model based on the first detection frequency to obtain the first detection result; Collect fourth electrical signal data at the preset position by the second data acquisition device at the second sampling frequency within the preset second time period; Detect the fourth electrical signal data through the fluctuation model based on the second detection frequency to obtain the second detection result; the second detection frequency is less than the first detection frequency.

[0094] Optionally, the first detection result includes: p first categories; p is a positive integer; the second detection result includes: q second categories; q is a positive integer less than p; the category includes one of the following: normal category, arc category; in terms of determining the target arc fault detection result at the preset position according to the first detection result and the second detection result, the detection determination module 206 is further specifically configured to: Select q first categories corresponding to the q second categories at the detection output result time point from the p first categories; the q first categories correspond one-to-one with the q second categories; Perform a target determination step on the q first categories and the q second categories to obtain q third categories; Among them, the target determination step is as follows: Obtain a reference first category and a reference second category corresponding to the reference first category among the q second categories; the reference first category is any one of the q first categories; If both the reference first category and the reference second category are the arc category, determine the reference third category as the arc category; otherwise, determine the reference third category as the normal category; the reference third category is the third category corresponding to the reference first category and the reference second category among the q third categories; If there are at least k third categories among the q third categories that are the arc category, determine that there is an arc fault at the preset position; otherwise, determine that there is no arc fault at the preset position; k is a positive integer less than q.

[0095] The AC arc detection device 200 described in this application based on current and harmonic fluctuations can collect the first electrical signal data of a preset position in the target power grid at a first sampling frequency by the first data acquisition device within a preset first time period, extract the harmonic characteristics in the first electrical signal data, and at the same time, collect the second electrical signal data of the preset position at a second sampling frequency by the second data acquisition device within the preset first time period, extract the current waveform characteristics in the second electrical signal data; determine a binary classification feature dataset according to the harmonic characteristics and the current waveform characteristics; determine a fluctuation feature dataset according to the harmonic characteristics and the current waveform characteristics; train a preset model based on the binary classification feature dataset and the fluctuation feature dataset respectively to obtain a binary classification model and a fluctuation model; perform arc fault detection on the electrical signals in a preset second time period at the preset position through the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result; determine the target arc fault detection result of the preset position according to the first detection result and the second detection result. It can be seen that by jointly performing arc fault detection through the binary classification model and the fluctuation model, the detection accuracy of faulty arcs is improved.

[0096] Please refer to Figure 12 , Figure 12It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include a processor, a memory, a communication interface, and one or more programs. The processor, the memory, and the communication interface may be interconnected via a bus. The above one or more programs are stored in the above memory and are configured to be executed by the above processor. In the embodiment of the present application, the above program includes instructions for performing the following steps: Collect first electrical signal data at a preset position in a target power grid by a first data acquisition device at a first sampling frequency within a preset first time period, and extract harmonic features in the first electrical signal data. At the same time, collect second electrical signal data at the preset position by a second data acquisition device at a second sampling frequency within the preset first time period, and extract current waveform features in the second electrical signal data. The first sampling frequency is greater than the second sampling frequency; Determine a binary classification feature data set according to the harmonic features and the current waveform features; Determine a fluctuation feature data set according to the harmonic features and the current waveform features; Train a preset model based on the binary classification feature data set and the fluctuation feature data set respectively to obtain a binary classification model and a fluctuation model; Perform arc fault detection on the electrical signals in a preset second time period at the preset position through the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result; Determine a target arc fault detection result at the preset position according to the first detection result and the second detection result.

[0097] The electronic device described in this application can collect the first electrical signal data at a preset position in the target power grid through the first data acquisition device at a first sampling frequency within a preset first time period, extract the harmonic characteristics in the first electrical signal data, and at the same time, collect the second electrical signal data at the preset position through the second data acquisition device at a second sampling frequency within the preset first time period, and extract the current waveform characteristics in the second electrical signal data; determine a binary classification feature dataset according to the harmonic characteristics and the current waveform characteristics; determine a fluctuation feature dataset according to the harmonic characteristics and the current waveform characteristics; train a preset model based on the binary classification feature dataset and the fluctuation feature dataset respectively to obtain a binary classification model and a fluctuation model; perform arc fault detection on the electrical signals in a preset second time period at the preset position through the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result; determine the target arc fault detection result at the preset position according to the first detection result and the second detection result. It can be seen that by jointly performing arc fault detection through the binary classification model and the fluctuation model, the detection accuracy of the fault arc is improved.

[0098] An embodiment of this application also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiment, and the above computer includes an electronic device.

[0099] An embodiment of this application also provides a computer program product, where the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute part or all of the steps of any method recorded in the above method embodiment. The computer program product can be a software installation package, and the above computer includes an electronic device.

[0100] Those of ordinary skill in the art can understand all or part of the processes in the above method embodiments. These processes can be completed by a computer program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The foregoing storage medium includes: various media such as ROM or random access memory RAM, magnetic disk, or optical disc that can store program code.

[0101] The steps of the methods or algorithms described in the embodiments of this application can be implemented in a hardware manner or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), register, hard disk, removable hard disk, compact disc read-only memory (CD-ROM), or any other form of storage medium well-known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also exist as discrete components in the terminal device or the management device.

[0102] Those skilled in the art should be able to realize that in one or more of the above examples, the functions described in the embodiments of this application can be fully or partially implemented through software, hardware, firmware, or any combination thereof. When implemented using software, it can be fully or partially implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server, data center, etc. that contains one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a digital video disc (DVD)), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0103] Each device and product described in the above embodiments includes various modules / units, which can be software modules / units, hardware modules / units, or partially software modules / units and partially hardware modules / units. For example, for each device and product applied to or integrated into a chip, the various modules / units it includes can all be implemented in the form of hardware such as circuits. Alternatively, at least some of the modules / units can be implemented in the form of software programs that run on the processor integrated inside the chip, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits. For each device and product applied to or integrated into a chip module, the various modules / units it includes can all be implemented in the form of hardware such as circuits. Different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components of the chip module. Alternatively, at least some of the modules / units can be implemented in the form of software programs that run on the processor integrated inside the chip module, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits. For each device and product applied to or integrated into a terminal device, the various modules / units it includes can all be implemented in the form of hardware such as circuits. Different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components inside the terminal device. Alternatively, at least some of the modules / units can be implemented in the form of software programs that run on the processor integrated inside the terminal device, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits.

[0104] The specific implementation manners described above further elaborate on the objectives, technical solutions, and beneficial effects of the embodiments of the present application. It should be understood that the above are only the specific implementation manners of the embodiments of the present application and are not used to limit the protection scope of the embodiments of the present application. Any modifications, equivalent replacements, improvements, etc. made based on the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. An AC arc detection method based on current and harmonic fluctuations, characterized in that A control device applied to an arc detection system, the arc detection system further comprising: a first data acquisition device, a second data acquisition device; the method comprising: Collecting first electrical signal data at a preset position in a target power grid by the first data acquisition device at a first sampling frequency within a preset first time period, extracting harmonic features in the first electrical signal data, and at the same time, collecting second electrical signal data at the preset position by the second data acquisition device at a second sampling frequency within the preset first time period, extracting current waveform features in the second electrical signal data; the first sampling frequency is greater than the second sampling frequency; Determining a binary classification feature dataset according to the harmonic features and the current waveform features; Determining a fluctuation feature dataset according to the harmonic features and the current waveform features; Training a preset model based on the binary classification feature dataset and the fluctuation feature dataset respectively to obtain a binary classification model and a fluctuation model; Performing arc fault detection on the electrical signals in a preset second time period at the preset position through the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result; Determining a target arc fault detection result at the preset position according to the first detection result and the second detection result.

2. The method according to claim 1, wherein The extracting of the harmonic features in the first electrical signal data includes: Determining the power frequency period corresponding to the target power grid; Determining a target window according to the power frequency period; Extracting n frequency point channels in the first electrical signal data based on a preset short-time fast Fourier transform with the target window; n is a positive integer; Determining a first classification label corresponding to the first electrical signal data; the first classification label includes one of the following: normal label, arc label; Constructing the harmonic features according to the n frequency point channels and the first classification label.

3. The method according to claim 2, characterized in that, The extracting of the current waveform features in the second electrical signal data includes: Extracting a waveform matrix in the second electrical signal data based on the target window; Determining a second classification label corresponding to the second electrical signal data; the second classification label includes one of the following: normal label, arc label; Determining the current waveform features according to the waveform matrix and the second classification label.

4. The method according to claim 3, wherein The determining of the binary classification feature dataset according to the harmonic features and the current waveform features includes: Combining the harmonic features and the current waveform features to obtain a target combined feature; Normalizing the target combined feature to obtain a first combined feature; Determining a target category corresponding to the first combined feature according to the first classification label and the second classification label; the target category includes one of the following: normal category, arc category; Determining the binary classification feature dataset according to the first combined feature and the target category.

5. The method according to claim 4, wherein The harmonic features include multiple harmonic features, and the current waveform features include multiple current waveform features; The determining of the fluctuation feature dataset according to the harmonic features and the current waveform features includes: Determining multiple first combined features according to the multiple harmonic features and the multiple current waveform features; Combine the multiple first combined features to form a second combined feature; Determine the category corresponding to the second combined feature according to the number of first combined features belonging to the normal category in the second combined feature; Determine the fluctuation feature dataset according to the second combined feature and the category corresponding to the second combined feature.

6. The method according to any one of claims 1-5, characterized in that, The arc fault detection of the electrical signal in the preset second time period at the preset position by the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result includes: Collect the third electrical signal data of the preset position by the first data acquisition device at the first sampling frequency within the preset second time period; Detect the third electrical signal data by the binary classification model based on the first detection frequency to obtain the first detection result; Collect the fourth electrical signal data of the preset position by the second data acquisition device at the second sampling frequency within the preset second time period; Detect the fourth electrical signal data by the fluctuation model based on the second detection frequency to obtain the second detection result; the second detection frequency is less than the first detection frequency.

7. The method according to claim 6, wherein The first detection result includes: p first categories; p is a positive integer; the second detection result includes: q second categories; q is a positive integer less than p; the category includes one of the following: normal category, arc category; the determining the target arc fault detection result of the preset position according to the first detection result and the second detection result includes: Select q first categories corresponding to the q second categories at the detection output result time point from the p first categories; the q first categories correspond to the q second categories one by one; Perform a target determination step on the q first categories and the q second categories to obtain q third categories; Wherein, the target determination step is as follows: Obtain a reference first category and a reference second category corresponding to the reference first category among the q second categories; the reference first category is any one of the q first categories; If both the reference first category and the reference second category are the arc category, determine the reference third category as the arc category; otherwise, determine the reference third category as the normal category; the reference third category is the third category corresponding to the reference first category and the reference second category among the q third categories; If at least k of the q third categories are the arc category, determine that there is an arc fault at the preset position; otherwise, determine that there is no arc fault at the preset position; k is a positive integer less than q.

8. An alternating current arc detection device based on current and harmonic fluctuations, characterized in that A control device applied to an arc detection system, the arc detection system further includes: a first data acquisition device, a second data acquisition device; the AC arc detection device based on current and harmonic fluctuations includes: a data acquisition module, a first dataset processing module, a second dataset processing module, a model training module, an arc fault detection module, a detection determination module, wherein, The data acquisition module is used to collect first electrical signal data at a preset position in the target power grid through the first data acquisition device at a first sampling frequency within a preset first time period, extract harmonic features in the first electrical signal data, and at the same time, collect second electrical signal data at the preset position through the second data acquisition device at a second sampling frequency within the preset first time period, and extract current waveform features in the second electrical signal data; the first sampling frequency is greater than the second sampling frequency; The first data set processing module is used to determine a binary classification feature data set according to the harmonic features and the current waveform features; The second data set processing module is used to determine a fluctuation feature data set according to the harmonic features and the current waveform features; The model training module is used to train a preset model based on the binary classification feature data set and the fluctuation feature data set respectively to obtain a binary classification model and a fluctuation model; The arc fault detection module is used to perform arc fault detection on the electrical signals in a preset second time period at the preset position through the binary classification model and the fluctuation model respectively to obtain a first detection result and a second detection result; The detection determination module is used to determine a target arc fault detection result at the preset position according to the first detection result and the second detection result.

9. An electronic device, characterized in that, Comprising: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and are configured to be executed by the processor, and the programs include instructions for performing the steps in the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program includes program instructions, and the program instructions, when executed by the processor, cause the processor to execute the method according to any one of claims 1-7.

Images