Method and device for determining arc fault information and electronic equipment

Abstract

The invention discloses a method and device for determining arc fault information and electronic equipment. The method comprises the following steps: receiving a fault information determination request of a target circuit; obtaining an initial current signal in response to the fault information determination request; according to the initial current signal, determining first current signals corresponding to the target circuit in a plurality of half-wave periods and second current signals corresponding to the target circuit in a plurality of full-wave periods; determining an in-half-wave signal feature and an inter-half-wave signal feature according to the plurality of first current signals; determining a cycle signal characteristic corresponding to the target circuit according to the plurality of second current signals; and determining target arc fault information corresponding to the target circuit according to the in-half-wave signal characteristics, the inter-half-wave signal characteristics and the cycle signal characteristics. According to the method and the device, the technical problem that the accuracy of the fault information determined according to the randomness characteristics is low due to the fact that the determined randomness characteristics are inaccurate in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method, device and electronic equipment for determining arc fault information. Background Art

[0002] Arc fault identification is crucial for ensuring the safe operation of electrical systems, preventing fire hazards, protecting life and property, and maintaining stable and reliable equipment operation. Currently, arc fault identification is primarily based on extracting the random characteristics of current. However, this method suffers from inaccurate random characteristics, resulting in low accuracy in fault information determined based on these characteristics.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, and electronic device for determining arc fault information, so as to at least solve the technical problem in related technologies that the accuracy of fault information determined based on random characteristics is low due to inaccurate random characteristics determined.

[0005] According to one aspect of an embodiment of the present invention, a method for determining arc fault information is provided, comprising: receiving a fault information determination request of a target circuit, wherein the fault information determination request is used to determine the arc fault information of the target circuit; in response to the fault information determination request, obtaining an initial current signal, wherein the initial current signal is a current signal corresponding to a loop in the target circuit in which the probability of an arc fault occurring is greater than a predetermined threshold; determining, based on the initial current signal, first current signals corresponding to the target circuit over multiple half-wave cycles and second current signals corresponding to the target circuit over multiple full-wave cycles; and determining, based on multiple A first current signal is used to determine the intra-half-wave signal characteristics and the inter-half-wave signal characteristics, wherein the intra-half-wave signal characteristics are the signal change characteristics of the current signal of the target circuit within the half-wave period, and the inter-half-wave signal characteristics are the characteristics reflecting the signal difference between the current signals of adjacent half-wave periods; based on multiple second current signals, the inter-cycle signal characteristics corresponding to the target circuit are determined, wherein the inter-cycle signal characteristics are used to represent the periodic signal characteristics of the current signal of the target circuit on the full-wave period; based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics, the target arc fault information corresponding to the target circuit is determined.

[0006] Optionally, based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics, the target arc fault information corresponding to the target circuit is determined, including: based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics, the fusion characteristics corresponding to the target circuit are determined; calling the fault information determination model, wherein the fault information determination model is provided with target model parameters, and the target model parameters are determined based on sample data and an initial determination model; based on the fusion characteristics and the fault information determination model, the target arc fault information corresponding to the target circuit is determined.

[0007] Optionally, before calling the fault information determination model, it also includes: determining an initial determination model, wherein the initial determination model is provided with initial model parameters; updating multiple initial sets according to the update parameters to obtain multiple first sets, and updating the multiple first sets according to the update parameters until a target set is obtained, wherein the multiple initial sets are respectively provided with initial model parameters, the error value corresponding to the target set is less than an error threshold, and the corresponding error value is determined based on the corresponding set and sample data; determining the fault information determination model based on the target set and the initial determination model.

[0008] Optionally, based on multiple first current signals, determining the signal characteristics within the half-wave and the signal characteristics between the half-waves includes: determining multiple sampling current values ​​corresponding to the multiple first current signals respectively, wherein the corresponding multiple sampling current values ​​are the current values ​​corresponding to the corresponding first current signals at multiple predetermined sampling points; determining the energy entropy value of the corresponding first current signal based on the corresponding multiple sampling current values, wherein the energy entropy value is used to reflect the energy distribution characteristics of the corresponding first current signal; determining the signal characteristics within the half-wave based on the energy entropy values ​​corresponding to the multiple first current signals respectively.

[0009] Optionally, based on multiple first current signals, the signal characteristics within the half-wave and the signal characteristics between the half-waves are determined, including: determining the first frequency domain signals corresponding to the multiple first current signals respectively; determining the multiple harmonic signal values ​​corresponding to the multiple first frequency domain signals respectively, wherein the corresponding multiple harmonic signal values ​​are the multiple signal amplitudes corresponding to the first frequency domain signals within multiple predetermined frequency ranges; based on the corresponding multiple harmonic signal values, determining the harmonic signal ratio of the corresponding first frequency domain signal; based on the multiple harmonic signal ratios, determining the signal characteristics between the half-waves.

[0010] Optionally, based on multiple second current signals, the inter-cycle signal characteristics corresponding to the target circuit are determined, including: determining the second frequency domain signals corresponding to the multiple second current signals respectively; determining the amplitude sums corresponding to the multiple second current signals respectively based on the multiple second frequency domain signals; determining the differential values ​​corresponding to the multiple second current signals respectively based on the multiple amplitude sums; and determining the inter-cycle signal characteristics corresponding to the target circuit based on the multiple differential values.

[0011] Optionally, after determining the target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics, it also includes: determining the arc fault location based on the target arc fault information; determining the number of arc faults corresponding to the arc fault location within a predetermined time period; and when the number of arc faults is greater than a predetermined number threshold, sending a cut-off instruction to the target circuit to disconnect the circuit loop corresponding to the arc fault location.

[0012] According to one aspect of an embodiment of the present invention, a device for determining arc fault information is provided, comprising: a receiving module for receiving a fault information determination request of a target circuit, wherein the fault information determination request is used to determine arc fault information of the target circuit; a responding module for acquiring an initial current signal in response to the fault information determination request, wherein the initial current signal is a current signal corresponding to a loop in the target circuit where the probability of an arc fault occurring is greater than a predetermined threshold; a first determining module for determining, based on the initial current signal, first current signals corresponding to the target circuit over multiple half-wave cycles and second current signals corresponding to the target circuit over multiple full-wave cycles; and a second determining module for determining, based on the initial current signal, first current signals corresponding to the target circuit over multiple half-wave cycles and second current signals corresponding to the target circuit over multiple full-wave cycles. , used to determine the intra-half-wave signal characteristics and inter-half-wave signal characteristics based on multiple first current signals, wherein the intra-half-wave signal characteristics are the signal change characteristics of the current signal of the target circuit within the half-wave period, and the inter-half-wave signal characteristics are the characteristics reflecting the signal difference between the current signals of adjacent half-wave periods; a third determination module, used to determine the inter-cycle signal characteristics corresponding to the target circuit based on multiple second current signals, wherein the inter-cycle signal characteristics are used to represent the periodic signal characteristics of the current signal of the target circuit on the full-wave period; a fourth determination module, used to determine the target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics.

[0013] According to one aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement any of the above methods for determining arc fault information.

[0014] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining arc fault information.

[0015] In an embodiment of the present invention, a fault information determination request of a target circuit is received, wherein the fault information determination request is used to determine arc fault information of the target circuit; in response to the fault information determination request, an initial current signal is obtained, wherein the initial current signal is a current signal corresponding to a loop in the target circuit where the probability of an arc fault occurring is greater than a predetermined threshold; based on the initial current signal, first current signals corresponding to the target circuit in multiple half-wave cycles and second current signals corresponding to the target circuit in multiple full-wave cycles are determined; based on the multiple first current signals, intra-half-wave signal characteristics and inter-half-wave signal characteristics are determined, wherein the intra-half-wave signal characteristics are signal change characteristics of the current signal of the target circuit within a half-wave cycle, and the inter-half-wave signal characteristics are characteristics reflecting the signal difference between current signals in adjacent half-wave cycles; based on the multiple second current signals, inter-cycle signal characteristics corresponding to the target circuit are determined, wherein the inter-cycle signal characteristics are used to represent the target circuit The invention discloses a method for determining the target arc fault information corresponding to the target circuit based on the periodic signal characteristics of the current signal of the circuit in the full wave cycle; a method for determining the target arc fault information corresponding to the target circuit based on the signal characteristics within the half wave, the signal characteristics between the half waves and the signal characteristics between the cycles, by determining the signal characteristics within the half wave and the signal characteristics between the half waves based on multiple first current signals, and determining the signal characteristics between the cycles corresponding to the target circuit based on multiple second current signals, thereby achieving the purpose of determining the target arc fault information corresponding to the target circuit based on the signal characteristics within the half wave, the signal characteristics between the half waves and the signal characteristics between the cycles, because the signal characteristics within the half wave can reflect the high frequency characteristics of the signal, the signal characteristics between the half waves can reflect the low frequency characteristics of the signal, and the full wave cycle characteristics can reflect the overall characteristics of the signal, thereby achieving the technical effect of improving the accuracy of the determined fault information, and thus solving the technical problem in the related art that the accuracy of the fault information determined based on the random characteristics is low due to the inaccurate determined random characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 is a flow chart of a method for determining arc fault information according to an embodiment of the present invention;

[0018] Figure 2 Schematic diagram of voltage and current waveforms before and after an arc fault on a resistive load provided by an optional embodiment of the present invention;

[0019] Figure 3 Schematic diagram of voltage and current waveforms before and after an arc fault on a resistive-inductive load provided by an optional embodiment of the present invention;

[0020] Figure 4 Schematic diagram of voltage and current waveforms before and after an arc fault on an inductive load provided by an optional embodiment of the present invention;

[0021] Figure 5 This is a schematic diagram of voltage and current waveforms before and after an arc fault on a nonlinear load provided by an optional embodiment of the present invention;

[0022] Figure 6 This is another schematic diagram of voltage and current waveforms before and after an arc fault on a nonlinear load provided by an optional embodiment of the present invention;

[0023] Figure 7 This is another schematic diagram of voltage and current waveforms before and after an arc fault on a nonlinear load provided by an optional embodiment of the present invention;

[0024] Figure 8 This is a diagram showing the effect of distinguishing between the normal state and the fault state of a load device under multi-time-scale random characteristic quantities provided by an optional embodiment of the present invention;

[0025] Figure 9 is a flow chart of an arc fault detection method provided by an optional embodiment of the present invention;

[0026] Figure 10 is a flow chart of an arc determination method provided by an optional embodiment of the present invention;

[0027] Figure 11 4 is a structural block diagram of an apparatus for determining arc fault information according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" 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 necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] According to an embodiment of the present invention, an embodiment of a method for determining arc fault information is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 1 FIG. 1 is a flow chart of a method for determining arc fault information according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0033] Step S102: receiving a fault information determination request of a target circuit, wherein the fault information determination request is used to determine arc fault information of the target circuit.

[0034] In step S102 provided in the present application, a fault information determination request of a target circuit is received.

[0035] Herein, a target circuit is involved, and the target circuit refers to a circuit for which arc fault information needs to be determined.

[0036] Herein, a fault information determination request is involved, and the fault information determination request refers to a request for triggering a process of determining arc fault information of a target circuit.

[0037] Among them, arc fault information is involved. Arc fault information refers to information about arc faults in the target circuit, for example, whether there is an arc fault in the target circuit, and if so, the type, location, intensity and other detailed information of the arc fault.

[0038] In this step, a fault information determination request of the target circuit is received, which is a basic step for obtaining arc fault information of the target circuit. After receiving the fault information determination request, the target circuit is analyzed to determine whether an arc fault has occurred in the target circuit and the detailed information of the arc fault.

[0039] Step S104 , in response to the fault information determination request, obtaining an initial current signal, wherein the initial current signal is a current signal corresponding to a loop in the target circuit where the probability of an arc fault occurring is greater than a predetermined threshold.

[0040] In step S104 provided in this application, an initial current signal is acquired.

[0041] Among them, a predetermined threshold is involved. The predetermined threshold refers to a pre-set probability threshold of an arc fault occurring in a circuit loop, so as to filter out loops with lower arc fault risks in the target circuit and focus on detecting circuit loop areas with higher arc fault risks.

[0042] In this step, in response to a detected fault information confirmation request, circuits with an arc fault probability greater than a predetermined threshold are automatically screened and current signals from these circuits are acquired to obtain an initial current signal for further analysis and confirmation. This step significantly improves the efficiency of arc fault detection, reduces unnecessary data processing, and conserves computing resources.

[0043] Step S106 , determining first current signals corresponding to the target circuit over a plurality of half-wave cycles and second current signals corresponding to the target circuit over a plurality of full-wave cycles based on the initial current signal.

[0044] In step S106 provided in the present application, first current signals corresponding to the target circuit over multiple half-wave cycles and second current signals corresponding to the target circuit over multiple full-wave cycles are determined.

[0045] Among them, half-wave cycles are involved. One cycle of alternating current includes two half-wave cycles, namely the positive half-wave cycle and the negative half-wave cycle.

[0046] Here, a first current signal is involved, and the first current signal refers to a current signal separated from the initial current signal and corresponding to multiple half-wave periods.

[0047] Among them, the full wave cycle is involved. The full wave cycle refers to a complete alternating current cycle, including continuous positive half-wave cycles and negative half-wave cycles.

[0048] Among them, a second current signal is involved, and the second current signal refers to a current signal separated from the initial current signal and corresponding to multiple full-wave cycles.

[0049] Through this step, the signal is divided into two main parts from the original collected initial current signal: one part is the signal segmentation performed for each half-wave cycle to obtain the first current signal, and the other part is the signal segmentation performed for each full-wave cycle to obtain the second current signal. By dividing the signal into half-wave and full-wave cycles for independent analysis, the multi-scale characteristics of the current signal can be captured more delicately, thereby extracting more targeted features, improving the accuracy and efficiency of arc fault recognition, enhancing the robustness of the system, and maintaining a high fault recognition rate under various complex situations.

[0050] Step S108, determining the intra-half-wave signal characteristics and the inter-half-wave signal characteristics based on the multiple first current signals, wherein the intra-half-wave signal characteristics are the signal change characteristics of the current signal of the target circuit within the half-wave period, and the inter-half-wave signal characteristics are the characteristics reflecting the signal difference between the current signals of adjacent half-wave periods.

[0051] In step S108 provided in the present application, intra-half-wave signal characteristics and inter-half-wave signal characteristics are determined.

[0052] Among them, the signal characteristics within the half-wave are involved. The signal characteristics within the half-wave period refer to the changing characteristics of the current signal within the half-wave period, such as the transient changes, pulse characteristics, and randomness of the current signal.

[0053] Among them, the half-wave signal characteristics are involved. The half-wave signal characteristics refer to the difference characteristics between the current signals of adjacent half-wave cycles, such as the phase difference of the current signal, the amplitude change, the irregularity of the waveform shape, etc.

[0054] Through this step, since arc current often shows extremely high randomness and impulse within a half-wave, analyzing the changes in the current signal within a single half-wave cycle can capture high-frequency transient changes, determine the signal characteristics within the half-wave, compare the differences between adjacent half-wave cycle signals, and determine the signal characteristics between half waves. This can reveal the asymmetry of the positive and negative half-waves of the current waveform under arc faults, and detect subtle symmetry destruction even in the low-frequency band, which is helpful for early detection of potential arc faults. Combining the signal characteristics within the half-wave and the signal characteristics between the half-waves, the randomness and asymmetry of the current signal can be comprehensively evaluated from different time scales, and the characteristics of the current signal in the target circuit can be fully understood and characterized, thereby improving the accuracy of the arc fault information determined subsequently.

[0055] In step S110 , a cycle-to-cycle signal characteristic corresponding to the target circuit is determined based on the plurality of second current signals, wherein the cycle-to-cycle signal characteristic is used to represent a periodic signal characteristic of the current signal of the target circuit over a full-wave period.

[0056] In step S110 provided in the present application, the inter-cycle signal characteristics corresponding to the target circuit are determined.

[0057] Among them, the inter-cycle signal characteristics are involved. The inter-cycle signal characteristics refer to the characteristic changes of the current signal on the time scale between different cycles, such as the high-frequency oscillation and random change characteristics of arc faults, and the periodic laws and stability characteristics of arc faults.

[0058] In this step, by analyzing the second current signal, that is, the change of current in multiple cycles, the inter-cycle signal characteristics of the target circuit can be determined, the periodic regularity and stability characteristics corresponding to the current signal of the target circuit can be determined, reflecting the overall characteristics of the signal and improving the accuracy of the arc fault information determined subsequently.

[0059] Step S112 , determining target arc fault information corresponding to the target circuit according to the intra-half-wave signal characteristics, the inter-half-wave signal characteristics, and the inter-cycle signal characteristics.

[0060] In step S112 provided in the present application, target arc fault information corresponding to the target circuit is determined.

[0061] Among them, the target arc fault information is involved. The target arc fault information refers to the exact status of the arc fault on the target circuit, for example, whether there is an arc fault in the target circuit, the arc fault type (such as series arc, parallel arc), intensity, duration, specific location and other detailed information.

[0062] In this step, after determining the intra-half-wave, inter-half-wave, and inter-cycle signal characteristics corresponding to the target circuit, a comprehensive analysis is performed on these characteristics to determine the target arc fault information corresponding to the target circuit. This step integrates signal characteristics at different time scales and performs real-time analysis of these multi-time scale signal characteristics, more meticulously capturing the diversity and complexity of arc faults, significantly improving detection accuracy and reliability.

[0063] Through the above steps S102-S112, a fault information determination request of the target circuit can be received, wherein the fault information determination request is used to determine the arc fault information of the target circuit; in response to the fault information determination request, an initial current signal is obtained, wherein the initial current signal is a current signal corresponding to a loop in the target circuit where the probability of an arc fault occurring is greater than a predetermined threshold; based on the initial current signal, first current signals corresponding to the target circuit in multiple half-wave cycles and second current signals corresponding to the target circuit in multiple full-wave cycles are determined; based on the multiple first current signals, intra-half-wave signal characteristics and inter-half-wave signal characteristics are determined, wherein the intra-half-wave signal characteristics are signal change characteristics of the current signal of the target circuit within the half-wave cycle, and the inter-half-wave signal characteristics are characteristics reflecting the signal difference between current signals in adjacent half-wave cycles; based on the multiple second current signals, inter-cycle signal characteristics corresponding to the target circuit are determined, wherein the inter-cycle signal characteristics are used to represent The invention discloses a method for determining the target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics, by determining the intra-half-wave signal characteristics and the inter-half-wave signal characteristics based on multiple first current signals, and determining the inter-cycle signal characteristics corresponding to the target circuit based on multiple second current signals, thereby achieving the purpose of determining the target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics. Since the intra-half-wave signal characteristics can reflect the high-frequency characteristics of the signal, the inter-half-wave signal characteristics can reflect the low-frequency characteristics of the signal, and the full-wave cycle characteristics can reflect the overall characteristics of the signal, the technical effect of improving the accuracy of the determined fault information is achieved, thereby solving the technical problem in the related art that the fault information determined based on the random characteristics has a low accuracy rate due to the inaccurate determined random characteristics.

[0064] As an optional embodiment, the target arc fault information corresponding to the target circuit is determined based on the signal characteristics within the half-wave, the signal characteristics between the half-waves and the signal characteristics between the cycles, including: determining the fusion characteristics corresponding to the target circuit based on the signal characteristics within the half-wave, the signal characteristics between the half-waves and the signal characteristics between the cycles; retrieving the fault information determination model, wherein the fault information determination model is provided with target model parameters, and the target model parameters are determined based on the sample data and the initial determination model; determining the target arc fault information corresponding to the target circuit based on the fusion characteristics and the fault information determination model.

[0065] In this embodiment, specific steps of determining target arc fault information corresponding to a target circuit based on intra-half-wave signal characteristics, inter-half-wave signal characteristics, and inter-cycle signal characteristics are described.

[0066] This involves fusion features, which are derived by combining intra-half-wave signal features, inter-half-wave signal features, and inter-cycle signal features. Fusion features consider the characteristics of the target circuit's current signal at different time scales and can more comprehensively reflect the complexity of arc faults.

[0067] Among them, a fault information determination model is involved. The fault information determination model refers to a pre-trained model used to determine the target arc fault information corresponding to the target circuit based on the fusion characteristics of the input current signal.

[0068] This involves target model parameters, which refer to the parameter set used to optimally identify arc faults, such as the penalty coefficient and kernel function parameters of a support vector machine (SVM), or the weights and biases of a neural network.

[0069] Among them, sample data is involved. Sample data refers to the data set used to train and optimize the fault information determination model, which usually includes the fusion features corresponding to the current signal under normal circuit operation status and the fusion features corresponding to different types of arc fault current signals, as well as the corresponding label information (i.e. sample arc fault information, such as whether a fault has occurred, the type of fault, etc.).

[0070] Among them, the initial determination model is involved. The initial determination model refers to the initial fault information determination model, which is the starting point for training the fault information determination model. It is necessary to gradually optimize the initial model parameters corresponding to the initial determination model during the training process to improve the ability to accurately judge arc fault information.

[0071] In this step, the current signal of the target circuit is first analyzed to extract intra-half-wave signal features, inter-half-wave signal features, and inter-cycle signal features. These features are then fused to form a more comprehensive and complex fusion feature representation of arc fault characteristics. Subsequently, a pre-trained fault information determination model is invoked. This model possesses optimal target model parameters learned and optimized from a large amount of sample data. Based on the input fusion features, the model can accurately determine whether an arc fault exists in the target circuit, as well as specific fault information such as type, intensity, and duration, to obtain the target arc fault information corresponding to the target circuit.

[0072] Through this step, by integrating signal features at different time scales, the system can more comprehensively capture the characteristics of arc faults, thereby improving the accuracy and robustness of fault detection. At the same time, the target arc fault information corresponding to the target circuit is automatically determined through the fault information determination model, thereby improving the accuracy of the determined fault information and the robustness of the system.

[0073] As an optional embodiment, before calling the fault information determination model, it also includes: determining an initial determination model, wherein the initial determination model is set with initial model parameters; updating multiple initial sets according to the update parameters to obtain multiple first sets, and updating the multiple first sets according to the update parameters until a target set is obtained, wherein the multiple initial sets are respectively set with initial model parameters, the error value corresponding to the target set is less than the error threshold, and the corresponding error value is determined based on the corresponding set and sample data; determining the fault information determination model based on the target set and the initial determination model.

[0074] In this embodiment, specific steps of determining the fault information determination model are described.

[0075] Among them, the error threshold is involved. The error threshold refers to a preset error upper limit. When the error value of the error determination model is lower than the error threshold, it means that the performance of the fault information determination model has reached or is close to expectations, and the training or optimization process can be stopped.

[0076] Among them, the error value is involved. The error value refers to the degree of difference between the arc fault information result predicted by the error determination model and the actual arc fault information, which is usually quantified by a loss function or an error function.

[0077] In this step, first, an initial determination model with initial model parameters is set, and then, multiple initial sets containing the initial model parameters are updated using update parameters until a model parameter set is found so that when the sample fusion features in the given sample data are input into the error determination model, the error value between the predicted arc fault information and the actual fault information is less than the error threshold. Finally, this model parameter set is determined as the target set, and based on the target set, the final fault information determination model is determined.

[0078] Through this step, an optimization algorithm (such as the Hippo optimization algorithm) is used to intelligently update the model parameters, so that the determined fault information determination model can better adapt to the characteristics of the target circuit, including different load types, working conditions and fault modes, thereby improving the generalization ability and prediction accuracy of the model, reducing false alarms and missed alarms, and ensuring the accurate determination of arc fault information.

[0079] As an optional embodiment, based on multiple first current signals, the signal characteristics within the half-wave and the signal characteristics between the half-waves are determined, including: determining multiple sampling current values ​​corresponding to the multiple first current signals, wherein the corresponding multiple sampling current values ​​are the current values ​​corresponding to the corresponding first current signals at multiple predetermined sampling points; based on the corresponding multiple sampling current values, determining the energy entropy value of the corresponding first current signal, wherein the energy entropy value is used to reflect the energy distribution characteristics of the corresponding first current signal; based on the energy entropy values ​​corresponding to the multiple first current signals, determining the signal characteristics within the half-wave.

[0080] In this embodiment, the specific steps of determining the signal characteristics within a half-wave based on a plurality of first current signals are described.

[0081] In this step, first, the first current signal is collected at multiple predetermined time points corresponding to the half-wave period to obtain multiple sampled current values. The sampled current value is a digital representation of the first current signal, which can lay a data foundation for the subsequent extraction of signal characteristics within the half-wave. Next, based on the multiple sampled current values, multiple energy values ​​of each first current signal are determined, and the multiple energy values ​​of each first current signal are analyzed, corresponding to the energy entropy value of the first current signal, to reflect the energy distribution characteristics of the first current signal in time or frequency. The higher the energy entropy value, the stronger the randomness of the signal energy distribution. Afterwards, using the determined energy entropy value, the system further analyzes the characteristics of the current signal within the half-wave, thereby determining the signal characteristics within the half-wave. This helps to capture high-frequency pulses and instability of the current signal in arc faults.

[0082] Through this step, the current signal is collected in real time, and the energy distribution and randomness of the current signal within the half-wave are analyzed to determine the energy entropy value. Since the energy entropy of the current signal within the half-wave is analyzed, the subtle changes in randomness and instability in the arc burning process can be captured. The energy entropy value, as a measure of randomness, can enhance the robustness of the arc fault detection model, so that it can still maintain a high detection accuracy under different loads and working conditions. Therefore, determining the signal characteristics within the half-wave of the target circuit based on the energy entropy value can improve the system's ability to accurately identify signs of arc faults, especially in an environment with complex signals and high noise. The calculation of the energy entropy value can highlight the fault characteristics in the signal.

[0083] As an optional embodiment, based on multiple first current signals, the signal characteristics within the half-wave and the signal characteristics between the half-waves are determined, including: determining the first frequency domain signals corresponding to the multiple first current signals respectively; determining the multiple harmonic signal values ​​corresponding to the multiple first frequency domain signals respectively, wherein the corresponding multiple harmonic signal values ​​are the multiple signal amplitudes corresponding to the first frequency domain signals within multiple predetermined frequency ranges; based on the corresponding multiple harmonic signal values, determining the harmonic signal ratio of the corresponding first frequency domain signal; based on the multiple harmonic signal ratios, determining the signal characteristics between the half-waves.

[0084] In this embodiment, the specific steps of determining the half-wave signal characteristics based on a plurality of first current signals are described.

[0085] Herein, a first frequency domain signal is involved, and the first frequency domain signal refers to a signal value obtained after frequency domain transformation of the first current signal.

[0086] Among them, the harmonic signal ratio is involved, and the harmonic signal ratio refers to the ratio of the harmonic signal value corresponding to the even harmonic to the harmonic signal value corresponding to the odd harmonic.

[0087] In this step, first, a plurality of first current signals are converted into a frequency domain range using a method such as Fourier transform to obtain a plurality of first frequency domain signals. Then, a plurality of first frequency domain signal values ​​within a predetermined frequency domain range are determined to obtain a plurality of harmonic signal values. Even harmonic signal values ​​and odd harmonic signal values ​​are determined from the plurality of harmonic signal values. When an arc fault occurs, nonlinear distortion, current pulses and instability in the arc discharge process, and changes in the current path will destroy the positive and negative half-wave symmetry of the current waveform, which is reflected as an abnormal increase in the even harmonic component. By determining the ratio of the even harmonic signal value to the odd harmonic signal value, the harmonic signal ratio corresponding to the first frequency domain signal is obtained. The half-wave signal feature is determined based on the harmonic signal ratio. The half-wave signal feature can accurately reflect the positive and negative half-wave symmetry of the target circuit current signal.

[0088] As an optional embodiment, determining the inter-cycle signal characteristics corresponding to the target circuit based on multiple second current signals includes: determining the second frequency domain signals corresponding to the multiple second current signals respectively; determining the amplitude sums corresponding to the multiple second current signals respectively based on the multiple second frequency domain signals; determining the differential values ​​corresponding to the multiple second current signals respectively based on the multiple amplitude sums; and determining the inter-cycle signal characteristics corresponding to the target circuit based on the multiple differential values.

[0089] In this embodiment, specific steps of determining the inter-cycle signal characteristics corresponding to the target circuit based on a plurality of second current signals are described.

[0090] Herein, a second frequency domain signal is involved, and the second frequency domain signal refers to a signal obtained by performing frequency domain transformation on the second current signal.

[0091] The amplitude sum is involved, and the amplitude sum refers to the sum of the amplitudes of the second frequency domain signal values ​​corresponding to multiple sampling points in the second frequency domain signal.

[0092] Among them, the differential value is involved. The differential value refers to the difference between the amplitude and the amplitude of the second frequency domain signal between adjacent cycles, which is used to quantify the randomness and instability of the signal characteristics between cycles.

[0093] In this step, first, the second current signal is converted into a second frequency domain signal through frequency domain transformation. Next, the sum of the amplitudes of the frequency components of the second frequency domain signal is determined to obtain the amplitude sum of each second frequency domain signal. Then, by determining the difference between the amplitude sums of the second frequency domain signals between adjacent cycles, the differential values ​​corresponding to the multiple second current signals are determined to quantify the degree of random change of the signal between consecutive cycles. Finally, by analyzing the multiple differential values, the inter-cycle signal characteristics of the target circuit are determined, especially the instability characteristics related to the arc fault. Through this step, the frequency domain analysis and differential calculation of the inter-cycle signal are carried out to determine the inter-cycle characteristics of the target circuit, effectively capture the randomness and instability of the current signal caused by the arc fault, and improve the accuracy of the fault information determined subsequently.

[0094] As an optional embodiment, after determining the target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics, it also includes: determining the arc fault location based on the target arc fault information; determining the number of arc faults corresponding to the arc fault location within a predetermined time period; and when the number of arc faults is greater than a predetermined number threshold, sending a cut-off instruction to the target circuit to disconnect the circuit loop corresponding to the arc fault location.

[0095] In this embodiment, the specific steps of sending a cut-off instruction to a target circuit are described.

[0096] Among them, the arc fault location is involved. The arc fault location refers to the precise location of the arc fault in the target circuit determined based on the target arc fault information.

[0097] Among them, the number of arc faults is involved. The number of arc faults refers to the number of arc faults occurring at the arc fault location recorded by the arc fault detection system within a certain time interval, that is, a predetermined time period.

[0098] Among them, a predetermined number threshold is involved. The predetermined number threshold refers to the pre-set upper limit of the number of arc faults. When the number of arc faults at the arc fault location within a predetermined time period exceeds the predetermined number threshold, the system will automatically trigger the cut-off action to ensure safety.

[0099] Among them, a cut-off instruction is involved, and the cut-off instruction refers to an instruction for cutting off the circuit loop corresponding to the arc fault position.

[0100] In this step, after arc fault information detection is completed and target arc fault information corresponding to the target circuit is obtained, the specific location of the arc fault is further determined based on the target arc fault information. The arc fault location is then calculated, and the number of arc faults occurring at the arc fault location within a predetermined time period is counted. When the number of arc faults exceeds a predetermined threshold, a disconnection command is sent to the target circuit to disconnect the power supply to the faulty area. This mechanism ensures that the system can respond quickly when frequent arc activity poses a safety threat, preventing serious consequences such as fire.

[0101] Based on the above embodiment and optional embodiment, an optional implementation manner is provided, which is described in detail below.

[0102] In related technologies, the series arc fault detection method mainly focuses on detecting current. The reason is that the fault current information of the series circuit is less affected by the location of the arc fault point. Only a single monitoring point needs to be installed at the household busbar to achieve fault monitoring of the downstream line. The series arc fault detection method using current information mainly extracts fault features from the time domain, frequency domain and other transformation domains of the current signal to construct fault detection criteria. Its main features include the use of harmonic features, high-frequency features, singularity features and randomness features. Among them, harmonic and high-frequency features are insufficient in distinguishing nonlinear load currents; zero-break features are easily weakened by the inductive components in the load and are difficult to distinguish from switching power supply load currents; waveform distortion features are greatly affected by the load type and have poor applicability to nonlinear loads. The load currents of a large number of nonlinear loads have waveform features that are the same or similar to those of linear load fault currents. In addition, some current fault characteristics (such as harmonic content) will also be affected by the load power; some loads also have the current characteristics of series fault arcs when starting, which may cause misjudgment; some loads such as arcs generated by arc welding machines and brushed motors when working and arcs generated when plugging and unplugging sockets have fault characteristics similar to series fault arcs, which increases the difficulty of detecting series fault arcs; for weak series arc faults with very small arc currents, the fault characteristic quantities in the current waveform are often not obvious, making this type of fault even more difficult to detect.

[0103] Since randomness can overcome the influence of the diversity of load current waveforms, it is another key feature of fault detection. Currently, methods for detecting arc fault information by determining randomness mainly include: calculating the difference between adjacent cycle current signals and combining the root mean square (RMS) method to measure the irregular changes in the current waveform after the fault; analyzing the adjacent cycle differences of the current signal and combining wavelet threshold denoising and signal normalization to extract arc fault characteristics; characterizing randomness by combining the numerical changes of adjacent wave current differences with their time domain distribution; using low-frequency cosine similarity to characterize the random characteristics of arc waveforms and combining high-frequency energy to identify fault arcs; using the Pearson correlation coefficient to characterize randomness and using a sliding window to derive the Pearson coefficient to amplify the similarity coefficient mutation.

[0104] Currently, methods for extracting random features primarily include extracting fault features using adjacent wave differences and measuring waveform similarity between cycles. However, the adjacent wave difference method often loses waveform features when extracting fault features, and sudden changes in current during normal load operation or load startup can lead to misjudgments. Furthermore, differences in current differential values ​​under different loads and operating conditions can affect threshold settings and, in turn, accuracy. The method of measuring waveform similarity between cycles approaches zero when waveform similarity increases after the arc stabilizes, which still leaves this method with significant limitations in certain situations. Overall, both methods only explore random features from the perspective of adjacent waves. This one-sided approach limits the method's applicability, as the randomness of arc faults is not only reflected between cycles but is also significant within and between half-waves.

[0105] In view of this, an optional embodiment of the present invention provides a series arc fault detection method that integrates multi-time-scale random features, which can solve the problem that the series arc fault detection method has low applicability, misjudgment and missed judgment due to the variety of load types existing in the current low-voltage AC distribution lines. It can identify the random characteristics of the current itself within half-waves, between half-waves, and between cycles, and proposes to use the characteristic energy entropy, odd-even harmonic content ratio, differential frequency domain amplitude and three characteristics of the current signal to comprehensively characterize the random characteristics of the fault current, covering the three frequency domain dimensions of low frequency, high frequency and full frequency, and performing a full-range arc randomness description, which greatly improves the universality and accuracy of series arc fault identification and detection, and establishes an arc fault detection model using the support vector machine (SVM) optimized by the Hippo optimization algorithm (HO), which has excellent generalization and accuracy.

[0106] The following specifically describes the detailed steps of the series arc fault detection method provided by an optional embodiment of the present invention.

[0107] S1. Receive a request for determining fault information of a target circuit.

[0108] S2. In response to a fault information determination request, obtain an initial current signal.

[0109] It should be noted that the random characteristics of arc fault current are mainly composed of the fault current component (i arc (t), same as the initial current signal above) leads to the fault current component i arc (t) depends on the arc voltage source u arc (t), so we can analyze u arc (t) Extract the current randomness characteristics.

[0110] Figure 2 Schematic diagram of voltage and current waveforms before and after an arc fault on a resistive load provided by an optional embodiment of the present invention, as shown in FIG. Figure 2 As shown, the blue line is the current waveform of the resistive load, the red line is the voltage waveform of the resistive load, the left side is the voltage and current waveforms of the resistive load under normal conditions, and the right side is the arc voltage waveform and arc current waveform of the resistive load when an arc fault occurs. Figure 3 Schematic diagram of voltage waveform and current waveform before and after arc fault of resistive and inductive load provided by an optional embodiment of the present invention, as shown in FIG. Figure 3 As shown, the blue line is the current waveform of the resistive-inductive load, the red line is the voltage waveform of the resistive-inductive load, the left side is the voltage and current waveforms of the resistive-inductive load under normal conditions, and the right side is the arc voltage waveform and arc current waveform of the resistive-inductive load when an arc fault occurs. Figure 4 Schematic diagram of voltage and current waveforms before and after an arc fault of an inductive load provided by an optional embodiment of the present invention, as shown in FIG. Figure 4 As shown, the blue line is the current waveform of the inductive load, the red line is the voltage waveform of the inductive load, the left side is the voltage and current waveforms of the inductive load under normal conditions, and the right side is the arc voltage waveform and arc current waveform of the inductive load when an arc fault occurs. Figure 5 Schematic diagram of voltage and current waveforms before and after an arc fault of a nonlinear load provided by an optional embodiment of the present invention. Figure 5 As shown, the blue line is the current waveform of a nonlinear load, the red line is the voltage waveform of a nonlinear load, the left side is the voltage and current waveform of a nonlinear load under normal conditions, and the right side is the arc voltage waveform and arc current waveform of a nonlinear load when an arc fault occurs. Figure 6 FIG. 1 is another schematic diagram of voltage and current waveforms before and after an arc fault of a nonlinear load provided by an optional embodiment of the present invention. Figure 6As shown, the blue line is the current waveform of another nonlinear load, the red line is the voltage waveform of another nonlinear load, the left side is the voltage and current waveform of another nonlinear load under normal conditions, and the right side is the arc voltage waveform and arc current waveform of another nonlinear load when an arc fault occurs. Figure 7 FIG. 1 is another schematic diagram of voltage and current waveforms before and after an arc fault of a nonlinear load provided by an optional embodiment of the present invention. Figure 7 As shown, the blue line is the current waveform of another nonlinear load, the red line is the voltage waveform of another nonlinear load, the left side is the voltage and current waveforms of another nonlinear load under normal conditions, and the right side is the arc voltage waveform and arc current waveform of another nonlinear load when an arc fault occurs.

[0111] The arc voltage waveform varies under different loads. In summary, the macroscopic manifestation of arc randomness is reflected in the arcing and arcing extinction spikes within the arc voltage half-wave, the waveform profile between half-waves, and the arc voltage oscillation differences between cycles. The arcing and arcing extinction spikes and arc voltage oscillations are high-frequency characteristic differences, while the waveform profile between half-waves is a low-frequency difference.

[0112] However, the dimmer load has a high-frequency mutation characteristic under normal working conditions, which is due to the instantaneous current mutation when the thyristor is turned on and off; the microwave oven load has an asymmetric waveform profile between half waves when it is working normally, which is caused by the physical properties of the magnetron; the computer load has high-frequency oscillations when it is working normally, which is caused by the high-frequency characteristics of the switching power supply.

[0113] Table 1 is a result table of determining arc fault information of load equipment based on the arc current characteristic waveform and normal current characteristic waveform of load equipment, provided by an optional embodiment of the present invention. As shown in Table 1, due to the overlap between arc fault characteristics and normal working state characteristics of the load, a single characteristic quantity may not be able to effectively distinguish between the two, resulting in missed judgment or misjudgment. The joint effect of the high-frequency pulse within the current half-wave (the same as the above-mentioned signal characteristics within the half-wave), the waveform contour between the half-waves (the same as the above-mentioned signal characteristics between the half-waves), and the random identification of fault arcs by the high-frequency oscillation between cycles (the same as the above-mentioned signal characteristics between cycles) at different time scales can effectively reduce the probability of misjudgment and missed judgment.

[0114] Table 1

[0115]

[0116] According to the above analysis, due to the arc voltage u arc (t) determines the fault current component i arc(t), which leads to the corresponding randomness of the series fault current i(t). Therefore, the fault arc can be identified by detecting the randomness of the high-frequency pulses within the current half-wave, the waveform contours between half-waves, and the high-frequency oscillations between cycles.

[0117] The following describes in detail the steps for determining the randomness of high-frequency pulses within a half-wave, waveform profiles between half-waves, and high-frequency oscillations between cycles.

[0118] S3. Determine, based on the initial current signal, first current signals corresponding to the target circuit over multiple half-wave periods and second current signals corresponding to the target circuit over multiple full-wave periods.

[0119] S4. Determine intra-half-wave signal characteristics and inter-half-wave signal characteristics based on the multiple first current signals.

[0120] For the detection of the randomness of the waveform profile between half-waves of the current, the fault current half-wave full-domain current characteristic energy value is for:

[0121]

[0122] Where i is the waveform number; N is the number of sampling points per cycle (the number of sampling points corresponding to the above-mentioned predetermined sampling points); For the i-th i M (n) Half-wave sequence after bandpass filtering (same as the above sampled current value).

[0123] Entropy is used to characterize the fault energy distribution characteristics, energy entropy value The calculation formula is:

[0124]

[0125] Among them, the energy occurrence probability P j The corresponding calculation formula is:

[0126]

[0127] Where, E j is the energy of the jth sampling point.

[0128] When testing for randomness between current half-waves, the primary characteristic of the current waveform is central symmetry between the positive and negative half-waves when there is no fault, and the even harmonic content is very low. However, when an arc fault occurs, nonlinear distortion, current pulses, instability, and changes in the current path during arc discharge disrupt the symmetry between the positive and negative half-waves, resulting in an abnormal increase in even harmonic components.

[0129] The sum of the 2nd, 4th, 6th, 8th, and 10th harmonic amplitudes is compared with the sum of the 7th harmonic amplitude to obtain the amplitude sum ratio (similar to the harmonic signal ratio described above) as the fault characteristic. Comparing the sum of the even-order harmonic amplitudes with the 7th harmonic amplitude both amplifies the fault magnitude and eliminates the influence of different device power.

[0130] The odd-even harmonic ratio R is defined as follows:

[0131]

[0132] Among them, |H2|, |H4|, |H7|, |H6|, |H8|, |H 10 | are the amplitudes of the 2nd, 4th, 6th, 7th, 8th and 10th harmonics respectively.

[0133] S5. Determine inter-cycle signal characteristics corresponding to the target circuit based on the plurality of second current signals.

[0134] To detect the randomness of high-frequency oscillations between adjacent cycles of the fault current, we use differential processing between adjacent cycles to highlight significant differences caused by these random high-frequency oscillations. To specifically characterize this feature, we introduce the full-band spectrum amplitude sum (the same as the amplitude sum corresponding to the second current signal mentioned above). By quantizing the frequency domain energy and summing it, we can highlight the increase in full-band amplitude after an arc fault.

[0135] Full-band spectrum amplitude and V total The formula is:

[0136]

[0137] Among them, V total is the amplitude sum of the entire frequency band, X(f) is the signal after Fourier transformation (same as the second current signal above); f max It is half the sampling frequency (i.e., the Nyquist frequency).

[0138] S6. Determine target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics, and the inter-cycle signal characteristics.

[0139] To overcome the problems of false positives and missed detections during arc detection, a method based on the fusion of multi-timescale and multi-stochastic features was proposed. Theoretically, the randomness of high-frequency pulses within a half-wave, waveform profiles between half-waves, and high-frequency oscillations between cycles complement each other to fully capture the complex random variations of arc faults, improving the accuracy and robustness of fault detection. Figure 8 This is an effect diagram of distinguishing the normal state and fault state of the load equipment under the multi-time-scale random characteristic quantity provided by the optional embodiment of the present invention, such as Figure 8As shown in the figure, the black mark indicates the load sample during normal operation, and the red mark indicates the load sample during an arc fault. It can be seen that in the coordinate system space constructed by the multi-time-scale random feature quantity, the characteristic distance between normal samples and fault samples is obvious, and there is no aliasing, which proves the feasibility of feature fusion.

[0140] Furthermore, an optional embodiment of the present invention proposes the use of a support vector machine (SVM, the same as the aforementioned fault information determination model) to fuse multi-timescale features and identify arc fault samples. The parameters that require optimization (the same as the initial model parameters) of the initial SVM (the same as the aforementioned initial determination model) are the penalty parameter C and the kernel parameter g. An optional embodiment of the present invention proposes a method for arc fault detection that combines the Hippopotamus optimization algorithm (HO) and SVM. Figure 9 is a flow chart of an arc fault detection method provided by an optional embodiment of the present invention, such as Figure 9 As shown in the figure, the Hippopotamus optimization algorithm effectively performs a global search for the penalty parameter C and kernel parameter g of the SVM model by simulating the natural behavior of hippos (foraging, swimming, and hunting). This overcomes the problem of traditional optimization methods easily falling into local optimal solutions and significantly improves the SVM model's ability to classify and generalize arc faults. Experimental results show that the SVM model optimized by the Hippopotamus optimization algorithm has significantly improved its accuracy, especially under complex loads and variable operating conditions, and can stably identify arc faults.

[0141] To prevent the instability and randomness of arc combustion from interfering with the diagnostic model's identification results and reduce the fault diagnosis model's misjudgment rate, an optional embodiment of the present invention also proposes a judgment method based on continuous arc accumulation. National standard GB / T31143 requires that when an arc generator is used to generate an arc, the interruption time should not exceed 2.5 times the specified limit. After comprehensive consideration, the judgment time was set to 0.1s, which is less than the standard's minimum interruption limit of 0.12s and is applicable to all current levels. Figure 10 Flowchart of the arc judgment method provided by an optional embodiment of the present invention, such as Figure 10 As shown in the figure, the upper limit of the cumulative number of arc fault half-cycles within 0.1s is set to 8. When the accumulated arc fault count reaches 8 half-cycles, a line disconnection signal is issued. Where A is the maximum number of half-cycles within 0.1s, the threshold is 10; C is the number of fault half-cycles, the threshold is 8.

[0142] Through the above optional implementation, at least the following beneficial effects can be achieved:

[0143] (1) Compared with the traditional method of detecting arc faults by only using inter-cycle random features, this method proposes to add two time scale random features, namely, intra-half-wave and inter-half-wave, to identify arc faults. The multi-time scale random feature quantity covers three frequency domain scales, namely low frequency, high frequency, and full frequency domain. At the same time, the randomness of arc faults is described by combining different dimensions of time domain scale. The mutual complementation between features greatly reduces misjudgment and missed judgment.

[0144] (2) The Hippo algorithm effectively improves the performance of SVM and enhances the robustness and generalization ability of the model;

[0145] (3) The continuous arc judgment method can avoid the interference of the instability and randomness of arc burning on the identification results of the diagnostic model and reduce the misjudgment rate of the fault diagnosis model.

[0146] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0148] Example 2

[0149] According to an embodiment of the present invention, a device for implementing the above-mentioned method for determining arc fault information is also provided. Figure 11 FIG. 1 is a structural block diagram of an apparatus for determining arc fault information according to an embodiment of the present invention. Figure 11 As shown, the apparatus includes: a receiving module 1102, a responding module 1104, a first determining module 1106, a second determining module 1108, a third determining module 1110 and a fourth determining module 1112. The apparatus will be described in detail below.

[0150] A receiving module 1102 is configured to receive a fault information determination request of a target circuit, wherein the fault information determination request is used to determine arc fault information of the target circuit; a response module 1104 is connected to the above-mentioned receiving module 1102, and is configured to respond to the fault information determination request and obtain an initial current signal, wherein the initial current signal is a current signal corresponding to a loop in the target circuit where the probability of an arc fault occurring is greater than a predetermined threshold; a first determination module 1106 is connected to the above-mentioned response module 1104, and is configured to determine, based on the initial current signal, first current signals corresponding to the target circuit over multiple half-wave cycles and second current signals corresponding to the target circuit over multiple full-wave cycles; a second determination module 1108 is connected to the above-mentioned first determination module 1106, and is configured to determine, based on the initial current signal, first current signals corresponding to the target circuit over multiple half-wave cycles and second current signals corresponding to the target circuit over multiple full-wave cycles. Multiple first current signals are used to determine the intra-half-wave signal characteristics and inter-half-wave signal characteristics, wherein the intra-half-wave signal characteristics are the signal change characteristics of the current signal of the target circuit within the half-wave period, and the inter-half-wave signal characteristics are the characteristics reflecting the signal difference between the current signals of adjacent half-wave periods; a third determination module 1110 is connected to the above-mentioned second determination module 1108, and is used to determine the inter-cycle signal characteristics corresponding to the target circuit based on the multiple second current signals, wherein the inter-cycle signal characteristics are used to represent the periodic signal characteristics of the current signal of the target circuit on the full-wave period; a fourth determination module 1112 is connected to the above-mentioned third determination module 1110, and is used to determine the target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics.

[0151] It should be noted here that the above-mentioned receiving module 1102, response module 1104, first determination module 1106, second determination module 1108, third determination module 1110 and fourth determination module 1112 correspond to steps S102 to S112 in the method for determining arc fault information. The instances and application scenarios implemented by the multiple modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0152] Example 3

[0153] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement any of the above methods for determining arc fault information.

[0154] Example 4

[0155] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining arc fault information.

[0156] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0157] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0159] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0160] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0161] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0162] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for determining arc fault information, characterized in that: include: receiving a fault information determination request of a target circuit, wherein the fault information determination request is used to determine arc fault information of the target circuit; In response to the fault information determination request, obtaining an initial current signal, wherein the initial current signal is a current signal corresponding to a loop in the target circuit where the probability of an arc fault occurring is greater than a predetermined threshold; Determining, based on the initial current signal, first current signals corresponding to the target circuit over a plurality of half-wave cycles and second current signals corresponding to the target circuit over a plurality of full-wave cycles; Determining, based on the plurality of first current signals, intra-half-wave signal characteristics and inter-half-wave signal characteristics, wherein the intra-half-wave signal characteristics are signal variation characteristics of the current signal of the target circuit within a half-wave period, and the inter-half-wave signal characteristics are characteristics reflecting signal differences between current signals in adjacent half-wave periods; Determining, based on the plurality of second current signals, an inter-cycle signal characteristic corresponding to the target circuit, wherein the inter-cycle signal characteristic is used to represent a periodic signal characteristic of the current signal of the target circuit over a full-wave period; Target arc fault information corresponding to the target circuit is determined based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics, and the inter-cycle signal characteristics.

2. The method according to claim 1, characterized in that The determining target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics, and the inter-cycle signal characteristics includes: Determining a fusion feature corresponding to the target circuit based on the intra-half-wave signal feature, the inter-half-wave signal feature, and the inter-cycle signal feature; Retrieving a fault information determination model, wherein the fault information determination model is provided with target model parameters, and the target model parameters are determined based on sample data and an initial determination model; Target arc fault information corresponding to the target circuit is determined based on the fusion feature and the fault information determination model.

3. The method according to claim 2, characterized in that Before retrieving the fault information determination model, the method further includes: determining an initial determination model, wherein the initial determination model is set with initial model parameters; Updating multiple initial sets according to update parameters to obtain multiple first sets, and updating the multiple first sets according to the update parameters until a target set is obtained, wherein the multiple initial sets are respectively provided with initial model parameters, and an error value corresponding to the target set is less than an error threshold, and the corresponding error value is determined based on the corresponding set and sample data; The fault information determination model is determined according to the target set and the initial determination model.

4. The method according to claim 1, wherein The determining of intra-half-wave signal characteristics and inter-half-wave signal characteristics based on the plurality of first current signals includes: Determine a plurality of sampling current values ​​corresponding to the plurality of first current signals, wherein the corresponding plurality of sampling current values ​​are current values ​​corresponding to the first current signals at a plurality of predetermined sampling points; Determining an energy entropy value of the corresponding first current signal based on the corresponding plurality of sampled current values, wherein the energy entropy value is used to reflect an energy distribution characteristic of the corresponding first current signal; The signal characteristics within the half-wave are determined according to the energy entropy values ​​respectively corresponding to the multiple first current signals.

5. The method according to claim 1, wherein The determining of intra-half-wave signal characteristics and inter-half-wave signal characteristics based on the plurality of first current signals includes: Determine first frequency domain signals corresponding to the plurality of first current signals respectively; Determine a plurality of harmonic signal values ​​corresponding to the plurality of first frequency domain signals, wherein the corresponding plurality of harmonic signal values ​​are a plurality of signal amplitudes corresponding to the first frequency domain signals within a plurality of predetermined frequency ranges; Determining a harmonic signal ratio of the corresponding first frequency domain signal according to the corresponding multiple harmonic signal values; The half-wave signal characteristics are determined according to a plurality of harmonic signal ratios.

6. The method according to claim 1, characterized in that Determining the inter-cycle signal characteristics corresponding to the target circuit based on the plurality of second current signals includes: Determine second frequency domain signals corresponding to the plurality of second current signals respectively; Determine the sum of amplitudes corresponding to the plurality of second current signals respectively according to the plurality of second frequency domain signals; Determining differential values ​​corresponding to the plurality of second current signals respectively according to the plurality of amplitude sums; The inter-cycle signal characteristics corresponding to the target circuit are determined according to the plurality of differential values.

7. The method according to any one of claims 1 to 6, characterized in that After determining the target arc fault information corresponding to the target circuit based on the intra-half-wave signal characteristics, the inter-half-wave signal characteristics, and the inter-cycle signal characteristics, the method further includes: determining an arc fault location according to the target arc fault information; Determining the number of arc faults corresponding to the arc fault location within a predetermined time period; When the number of arc faults is greater than a predetermined number threshold, a cut-off instruction is sent to the target circuit to disconnect the circuit loop corresponding to the arc fault position.

8. A device for determining arc fault information, characterized in that: include: a receiving module, configured to receive a fault information determination request of a target circuit, wherein the fault information determination request is used to determine arc fault information of the target circuit; a response module, configured to obtain an initial current signal in response to the fault information determination request, wherein the initial current signal is a current signal corresponding to a loop in the target circuit where the probability of an arc fault occurring is greater than a predetermined threshold; a first determining module, configured to determine, based on the initial current signal, first current signals corresponding to the target circuit over a plurality of half-wave cycles and second current signals corresponding to the target circuit over a plurality of full-wave cycles; a second determining module, configured to determine, based on the plurality of first current signals, an intra-half-wave signal feature and an inter-half-wave signal feature, wherein the intra-half-wave signal feature is a signal variation feature of the current signal of the target circuit within a half-wave period, and the inter-half-wave signal feature is a feature reflecting a signal difference between current signals in adjacent half-wave periods; a third determining module, configured to determine, based on the plurality of second current signals, an inter-cycle signal characteristic corresponding to the target circuit, wherein the inter-cycle signal characteristic is used to represent a periodic signal characteristic of the current signal of the target circuit over a full-wave period; The fourth determination module is used to determine the target arc fault information corresponding to the target circuit according to the intra-half-wave signal characteristics, the inter-half-wave signal characteristics and the inter-cycle signal characteristics.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining arc fault information according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining arc fault information according to any one of claims 1 to 7.

Images