Arc fault detection method, system and equipment

Abstract

The invention discloses an arc fault detection method, system and device. The method comprises the following steps: inputting a reference analog current time-domain signal and an actual analog current time-domain signal which are matched with an actual analog current time-domain signal of a DC bus to be measured into a time-domain waveform differential amplification module to obtain time-domain signal difference data; inputting actual simulation current frequency domain data corresponding to the actual simulation current time domain signal and reference simulation current frequency domain data into a frequency domain waveform differential amplification module to obtain frequency domain signal difference value data; and inputting the time domain signal difference value data and the frequency domain signal difference value data into a pre-constructed target arc fault detection model for feature recognition to obtain an arc fault detection result. According to the method, the accuracy and rapidity of arcing fault judgment of the whole system are effectively improved, and the false alarm rate during non-arcing is effectively reduced, so that a more reliable guarantee is provided for safe and stable operation of an electrical system.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical safety detection, and in particular, to an arc fault detection method, system and device. Background Art

[0002] In the field of electrical systems, arc faults are one of the key factors leading to serious safety accidents such as electrical fires. Traditional arc fault detection methods have many drawbacks, such as high false alarm rates, poor detection sensitivity and slow response times, which seriously affect the safety and stability of electrical systems. Summary of the Invention

[0003] The present invention provides an arc fault detection method, system and device to solve the technical problems of high false alarm rates, poor detection sensitivity and slow response times in the prior art.

[0004] According to one aspect of the present invention, there is provided an arc fault detection method, which is applied to an arc fault detection device in an arc fault detection system. The arc fault detection system includes: an arc fault detection device, a time-domain waveform differential amplification module and a frequency-domain waveform differential amplification module; wherein, the arc fault detection device is externally connected to the time-domain waveform differential amplification module and the frequency-domain waveform differential amplification module respectively; the method includes:

[0005] Input a reference analog current time-domain signal that matches the actual analog current time-domain signal of the DC bus to be measured and the actual analog current time-domain signal into the time-domain waveform differential amplification module to obtain time-domain signal difference data;

[0006] Input the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal into the frequency-domain waveform differential amplification module to obtain frequency-domain signal difference data;

[0007] Input the time-domain signal difference data and the frequency-domain signal difference data into a pre-constructed target arc fault detection model for feature recognition to obtain an arc fault detection result.

[0008] According to another aspect of the present invention, there is provided an arc fault detection system, including: an arc fault detection device, a time-domain waveform differential amplification module and a frequency-domain waveform differential amplification module;

[0009] wherein, the arc fault detection device is externally connected to the time-domain waveform differential amplification module and the frequency-domain waveform differential amplification module respectively;

[0010] The arc fault detection device is used to execute the arc fault detection method according to any embodiment of the present invention.

[0011] According to another aspect of the present invention, there is provided an arc fault detection device, including: The arc fault detection device includes:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the arc fault detection method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the arc fault detection method according to any embodiment of the present invention when executed.

[0016] According to another aspect of the present invention, there is provided a computer program product including a computer program which implements the arc fault detection method according to any embodiment of the present invention when executed by a processor.

[0017] The technical solution of the embodiment of the present invention configures an independent and integrated time-domain waveform differential amplification module and a frequency-domain waveform differential amplification module, and externally connects the arc fault detection device to the time-domain waveform differential amplification module and the frequency-domain waveform differential amplification module respectively; and the time-domain waveform differential amplification module performs differential amplification on the actual analog current time-domain signal and the reference analog current time-domain signal on the DC bus to be measured, and the frequency-domain waveform differential amplification module performs differential amplification on the actual analog current frequency-domain data and the reference analog current frequency-domain data, without adding additional computational load to the arc fault detection device, solving the technical problems of slow response time and poor detection sensitivity in the prior art, and effectively improving the accuracy and rapidity of the overall system's arc fault discrimination; and, by inputting the time-domain signal difference data and the frequency-domain signal difference data into a pre-constructed target arc fault detection model for feature recognition to obtain the arc fault detection result, fully taking into account the differences in time-frequency domain signals during arcing and non-arcing, effectively reducing the false alarm rate during non-arcing, thereby providing a more reliable guarantee for the safe and stable operation of the electrical system.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a flowchart of an arc fault detection method provided by an embodiment of the present invention;

[0021] Figure 2 It is a flowchart of another arc fault detection method provided by an embodiment of the present invention;

[0022] Figure 3 It is a flowchart of yet another arc fault detection method provided by an embodiment of the present invention;

[0023] Figure 4a It is a schematic diagram of the configuration of a reference simulated current time-domain signal under different normal operating conditions provided by an embodiment of the present invention;

[0024] Figure 4b It is a schematic diagram of the configuration of another reference simulated current time-domain signal under different normal operating conditions provided by an embodiment of the present invention;

[0025] Figure 5 It is a schematic diagram of the configuration of a reference simulated current frequency-domain data under normal operating conditions provided by an embodiment of the present invention;

[0026] Figure 6 It is a flowchart of yet another arc fault detection method provided by an embodiment of the present invention;

[0027] Figure 7 It is a flowchart of yet another arc fault detection method provided by an embodiment of the present invention;

[0028] Figure 8 It is a flowchart of yet another arc fault detection method provided by an embodiment of the present invention;

[0029] Figure 9 It is a block diagram of the structure of an arc fault detection system provided by an embodiment of the present invention;

[0030] Figure 10 It is a block diagram of the structure of another arc fault detection system provided by an embodiment of the present invention;

[0031] Figure 11 It is a block diagram of the structure of yet another arc fault detection system provided by an embodiment of the present invention;

[0032] Figure 12It is a structural block diagram of another arc fault detection system provided by an embodiment of the present invention;

[0033] Figure 13a It is a schematic diagram of the implementation of an actual simulated current time-domain signal and a reference simulated current time-domain signal provided by an embodiment of the present invention;

[0034] Figure 13b It is a schematic diagram of the implementation of time-domain signal difference data provided by an embodiment of the present invention;

[0035] Figure 14a It is a schematic diagram of the implementation of actual simulated current frequency-domain data and reference simulated current frequency-domain data provided by an embodiment of the present invention;

[0036] Figure 14b It is a schematic diagram of the implementation of frequency-domain signal difference data provided by an embodiment of the present invention;

[0037] Figure 15a It is another schematic diagram of the implementation of an actual simulated current time-domain signal and a reference simulated current time-domain signal provided by an embodiment of the present invention;

[0038] Figure 15b It is another schematic diagram of the implementation of time-domain signal difference data provided by an embodiment of the present invention;

[0039] Figure 16a It is another schematic diagram of the implementation of actual simulated current frequency-domain data and reference simulated current frequency-domain data provided by an embodiment of the present invention;

[0040] Figure 16b It is another schematic diagram of the implementation of frequency-domain signal difference data provided by an embodiment of the present invention;

[0041] Figure 17 It is a structural block diagram of an arc fault detection device provided by an embodiment of the present invention. Detailed implementation manners

[0042] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] It should be noted that the terms "first", "second", etc. in the specification, claims and the above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0044] The present invention provides an arc fault detection method, which differentially amplifies and then acquires the time-domain information and frequency-domain information of the current during non-arc and arc states through two analog circuits, namely a pre-constructed time-domain waveform differential amplification module and a frequency-domain waveform differential amplification module. This method not only fully takes into account the differences in time-domain information between arc and non-arc states, but also comprehensively considers the differences in frequency-domain information between arc and non-arc states. Moreover, the differences are processed by differential filtering and amplification through analog circuits, without adding an extra workload to the controller, effectively improving the accuracy and rapidity of arc fault discrimination of the overall system, while reducing the false alarm rate during normal non-arc states, providing a more reliable guarantee for the safe and stable operation of the electrical system.

[0045] In one embodiment, Figure 1 is a flowchart of an arc fault detection method provided by an embodiment of the present invention. This embodiment is applicable to the situation of determining whether there is an arc fault in a circuit. This method can be executed by an arc fault detection device, which can be implemented in the form of hardware and / or software, and the arc fault detection device can be configured in an arc fault detection system. Among them, the arc fault detection system includes: an arc fault detection device, a time-domain waveform differential amplification module, and a frequency-domain waveform differential amplification module; wherein, the arc fault detection device is externally connected to the time-domain waveform differential amplification module and the frequency-domain waveform differential amplification module respectively. It should be noted that both the time-domain waveform differential amplification module and the frequency-domain waveform differential amplification module in the present invention are independent and integrable modules; the arc fault detection device can be a single-chip microcomputer, which is used to detect whether there is a disconnected or ground-connected wire on the DC bus to be measured, so as to avoid causing fire or safety hazards.

[0046] As Figure 1 shown, the method includes:

[0047] S110. Input the reference analog current time-domain signal and the actual analog current time-domain signal that match the actual analog current time-domain signal of the DC bus to be measured into the time-domain waveform differential amplification module to obtain time-domain signal difference data.

[0048] In an example, the DC bus refers to the common connection point or conductor for centrally distributing direct current in a power system. Generally, the DC bus can be composed of copper bars, cables or busbars, and is used to connect multiple DC power sources, loads or energy storage devices to achieve the collection and distribution of electrical energy; the DC bus to be measured refers to the DC bus that needs to be detected for arc faults; the DC bus to be measured can be deployed on various DC devices to be measured. For example, the DC devices to be measured can include, but are not limited to, at least one of the following: energy storage converters, photovoltaic power generation systems, frequency converters and other electrical devices.

[0049] In an example, the actual analog current time-domain signal refers to the continuous-time current waveform obtained directly from the DC bus to be measured under the current operating conditions, and its signal amplitude and time are both continuous variables; the reference analog current time-domain signal refers to the continuous-time current waveform of the DC bus to be measured under normal operating conditions. Among them, the normal operating conditions refer to the operating conditions without arcing faults; not having an arcing fault can also be referred to as not having an arc fault.

[0050] In an embodiment, the reference analog current time-domain signal that matches the actual analog current time-domain signal of the DC bus to be measured refers to the analog current time-domain signal that matches the amplitude and phase of the actual analog current time-domain signal of the DC bus to be measured and has no arcing faults. In an example, when matching the actual analog current time-domain signal and the reference analog current time-domain signal, not only the amplitude and phase need to be matched, but also the amplitude and phase of the peak fluctuation need to be matched to ensure that when the current peak of the actual analog current time-domain signal of the DC bus to be measured fluctuates and there is no arcing fault, the reference analog current time-domain signal that matches the actual analog current time-domain signal can be accurately found, thereby ensuring the accuracy of finding the reference analog current time-domain signal.

[0051] In one example, the time-domain waveform differential amplification module refers to a module that has the function of comparing and amplifying the actual analog current time-domain signal and the reference analog current time-domain signal. In an embodiment, the reference analog current time-domain signal and the actual analog current time-domain signal that match the actual analog current time-domain signal of the DC bus to be measured can be input into the time-domain waveform differential amplification module, and the comparator configured in the time-domain waveform differential amplification module is used to compare the reference analog current time-domain signal and the actual analog current time-domain signal, and output a piece of data representing the comparison result between the reference analog current time-domain signal and the actual analog current time-domain signal, and input the data representing the comparison result between the reference analog current time-domain signal and the actual analog current time-domain signal into the amplification module to obtain time-domain signal difference data.

[0052] S120. Input the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal into the frequency-domain waveform differential amplification module to obtain frequency-domain signal difference data.

[0053] In one example, the actual analog current frequency-domain data refers to the frequency-domain data obtained by performing Fourier transform on the actual analog time-domain current signal directly obtained from the DC bus to be measured under the current operating condition; the reference analog current frequency-domain data refers to the frequency-domain data obtained by performing Fourier transform on the reference analog current time-domain signal of the DC bus to be measured configured in advance under the normal operating condition. Among them, the normal operating condition refers to the operating condition without arc fault; without arc fault can also be referred to as without arcing fault.

[0054] In one example, after obtaining the actual analog current time-domain signal of the DC bus to be measured, perform Fourier transform on the actual analog current time-domain signal to obtain the actual analog current frequency-domain data, and search for the reference analog current frequency-domain data that matches its amplitude and phase. In one example, after obtaining the actual analog current time-domain signal of the DC bus to be measured, the reference analog current time-domain signal that matches the amplitude and phase of the actual analog current time-domain signal can be searched for, and Fourier transform is performed on the reference analog current time-domain signal to obtain the reference analog current frequency-domain data.

[0055] In one example, the frequency-domain waveform differential amplification module refers to a module that has the function of comparing and amplifying the actual analog current frequency-domain data and the reference analog current frequency-domain data. In an embodiment, the reference analog current frequency-domain data matching the actual analog current frequency-domain data of the DC bus to be measured and the actual analog current frequency-domain data can be input into the frequency-domain waveform differential amplification module, and a comparator configured in the frequency-domain waveform differential amplification module is used to compare the reference analog current frequency-domain data and the actual analog current frequency-domain data, outputting a data representing the comparison result between the reference analog current frequency-domain data and the actual analog current frequency-domain data, and inputting the data representing the comparison result between the reference analog current frequency-domain data and the actual analog current frequency-domain data into the amplification module to obtain frequency-domain signal difference data.

[0056] S130. Input the time-domain signal difference data and the frequency-domain signal difference data into a pre-constructed target arc fault detection model for feature recognition to obtain an arc fault detection result.

[0057] In one example, the target arc fault detection model refers to a model that is pre-trained and constructed for detecting arc faults. Exemplarily, the target arc fault detection model can be a supervised learning model or an unsupervised learning model; in the case where the target arc fault detection model is a supervised learning model, it can be a neural network model.

[0058] In one example, the construction process of the target arc fault detection model may include the following steps:

[0059] Step 1. Obtain original training sample data.

[0060] Among them, the original training sample data includes sample data with two different labels. For example, the labels can include: arc fault occurs; arc fault does not occur.

[0061] Step 2. Perform data preprocessing operations on the original training sample data to obtain target training sample data.

[0062] Step 3. Identify and extract the time-domain features and frequency-domain features associated with the target training sample data with two different labels.

[0063] Step 4. Select a type for the initial arc fault detection model.

[0064] Exemplarily, the initial arc fault detection model can be supervised learning. For example, the supervised learning model can be a random forest, an LSTM model, or a neural network model.

[0065] Step 5. Use the target training sample data to perform iterative training on the initial arc fault detection model to obtain the target arc fault detection model.

[0066] Pre-configure the evaluation metrics for the arc fault detection model, and use the evaluation metrics to evaluate an arc fault detection model obtained through training until the output result of the trained arc fault detection model reaches the threshold of the evaluation metrics, thereby obtaining the target arc fault detection model.

[0067] Exemplarily, the evaluation metrics may include but are not limited to one of the following: accuracy, recall rate, etc. It should be noted that the training and construction process of the target arc fault detection model can be executed locally on the arc fault detection device or in the cloud server connected to the arc fault detection device. In one example, if the computing power of the arc fault detection device supports the model training process and the storage space of the arc fault detection device can ensure the accuracy of model training, the training process can be executed locally on the arc fault detection device. In one example, the training process can also be executed in the cloud server to ensure the efficiency and accuracy of model training.

[0068] In one example, the arc fault detection result is used to indicate whether an arc fault or arcing fault occurs in the DC bus to be measured. Exemplarily, the arc fault detection result includes: arcing fault occurs and arcing fault does not occur.

[0069] In the embodiment, both the time-domain signal difference data output by the time-domain waveform differential amplification module and the frequency-domain signal difference data output by the frequency-domain waveform differential amplification module are analog data, that is, presented in the form of analog signals. At this time, the analog-to-digital converter in the arc fault detection device can be used to perform analog-to-digital conversion on the time-domain signal difference data and the frequency-domain signal difference data respectively, and input the time-domain signal difference data and the frequency-domain signal difference data in the form of digital signals obtained by the conversion into the pre-constructed target arc fault detection model, so that the target arc fault detection model performs feature recognition on the time-domain signal difference data and the frequency-domain signal difference data to determine whether an arc fault occurs, thereby obtaining the arc fault detection result.

[0070] The technical solution of this embodiment configures an independent and integrated time-domain waveform differential amplification module and a frequency-domain waveform differential amplification module, and externally connects the arc fault detection device to the time-domain waveform differential amplification module and the frequency-domain waveform differential amplification module respectively; and the time-domain waveform differential amplification module differentially amplifies the actual analog current time-domain signal and the reference analog current time-domain signal on the DC bus to be measured, and the frequency-domain waveform differential amplification module differentially amplifies the actual analog current frequency-domain data and the reference analog current frequency-domain data, without adding additional computational load to the arc fault detection device, solving the technical problems of slow response time and poor detection sensitivity in the prior art, and effectively improving the accuracy and rapidity of the overall system's arc fault discrimination; and, by inputting the time-domain signal difference data and the frequency-domain signal difference data into a pre-constructed target arc fault detection model for feature recognition to obtain the arc fault detection result, fully taking into account the differences in time-frequency domain signals during arcing and non-arcing, effectively reducing the false alarm rate during non-arcing, thereby providing a more reliable guarantee for the safe and stable operation of the electrical system.

[0071] In one embodiment, Figure 2 It is a flowchart of another arc fault detection method provided by an embodiment of the present invention. This embodiment explains the acquisition process of the actual analog current time-domain signal on the basis of the above embodiment. The arc fault detection system in this embodiment further includes: a current acquisition sensor and a first filter amplification module; wherein, the output end of the current acquisition sensor is connected to the input end of the first filter amplification module; the output end of the first filter amplification module is respectively connected to the input ends of the arc fault detection device and the time-domain waveform differential amplification module.

[0072] As Figure 2 shown, the arc fault detection method in this embodiment includes the following steps:

[0073] S210. Real-time obtain the actual analog current time-domain signal associated with the DC bus to be measured.

[0074] Among them, the actual analog current time-domain signal is obtained by the current acquisition sensor real-time collecting the original analog current time-domain signal on the DC bus to be measured, and the first filter amplification module filters and amplifies the original analog current time-domain signal. In one example, the current acquisition sensor is a device for real-time capturing, converting and outputting current signals. For example, the current acquisition sensor can be a magnetic ring; the original analog current time-domain signal refers to the unprocessed current time-domain signal directly collected by the current acquisition sensor from the DC bus to be measured; the actual analog current time-domain signal refers to the current time-domain signal after filtering and amplifying the original analog current time-domain signal.

[0075] During the actual operation process, the current acquisition sensor can be nested on the DC bus to be measured, so as to collect the analog current time-domain signal of the DC bus to be measured in real time, obtain the original analog current time-domain signal, and use the filter amplification module to filter and amplify the original analog current time-domain signal to obtain the actual analog current time-domain signal. During the actual operation process, due to the different models of the current acquisition sensors, there will also be signal differences between the actually acquired analog current time-domain signal and the reference analog current time-domain signal. In order to minimize the signal difference between the actual analog current time-domain signal and the reference analog current time-domain signal, during the system operation, a sensor with the same model and specification as the current acquisition sensor used to collect the reference analog current time-domain signal can be selected to collect the current signal of the DC bus to be measured in real time, and the original analog current time-domain signal can be obtained.

[0076] During the operation of the arc fault detection system, the arc fault detection device can collect signals of 0 - 3.3 volts (V), while the original analog current time-domain signal collected by the current acquisition sensor for the DC bus to be measured is 100 millivolts (mV). The filter in the first filter amplification module can be used to perform band-pass filtering on the actual analog current time-domain signal to screen out the actual analog current time-domain signal within the target frequency range. At the same time, in order to ensure that the arc fault detection device can collect the actual analog current time-domain signal more accurately, the original analog current time-domain signal can be amplified so that the filtered and amplified actual analog current time-domain signal is within 0 - 3.3V. For example, the target frequency can be all the actual analog current time-domain signals within 16KHz - 100KHz, and all the actual analog current time-domain signals within 16KHz - 100KHz can be amplified to obtain the actual analog time-domain signal between 1 - 1.7V.

[0077] S220. Input the reference analog current time-domain signal and the actual analog current time-domain signal that match the actual analog current time-domain signal of the DC bus to be measured into the time-domain waveform differential amplification module to obtain time-domain signal difference data.

[0078] S230. Input the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal into the frequency-domain waveform differential amplification module to obtain frequency-domain signal difference data.

[0079] S240. Input the time-domain signal difference data and the frequency-domain signal difference data into the pre-constructed target arc fault detection model for feature recognition to obtain the arc fault detection result.

[0080] Based on the technical solution of the above embodiment, in this embodiment, the original analog current time-domain signal on the DC bus to be measured is collected in real time by a current acquisition sensor, and the original analog current time-domain signal is filtered and amplified by a first filter amplification module to obtain an actual analog current time-domain signal, so that the voltage value of the actual analog current time-domain signal is within the voltage range supported by the arc fault detection device, ensuring the acquisition effectiveness of the arc fault detection device for the actual analog current time-domain signal, and further ensuring the detection accuracy of the arc fault detection result.

[0081] In one embodiment, Figure 3 is a flowchart of another arc fault detection method provided by an embodiment of the present invention. This embodiment further elaborates on the determination process of the reference analog current time-domain signal and the determination process of the time-domain signal difference data on the basis of the above embodiment. In this embodiment, the time-domain waveform differential amplification module includes: a first comparator and a second filter amplification module; wherein, the input terminals of the first comparator are respectively connected to the arc fault detection device and the output terminal of the first filter amplification module, the output terminal of the first comparator is connected to the input terminal of the second filter amplification module, and the output terminal of the second filter amplification module is connected to the arc fault detection device. As Figure 3 shown, this embodiment includes the following steps:

[0082] S310. Perform analog-to-digital conversion on the actual analog current time-domain signal of the DC bus to be measured to obtain an actual digital current time-domain signal.

[0083] In one example, the actual digital current time-domain signal refers to the signal obtained by performing analog-to-digital conversion on the actual analog current time-domain signal, and this actual digital current time-domain signal is a combination of a timestamp and a quantization amplitude. Exemplarily, an analog-to-digital converter (ADC) can be used to perform analog-to-digital conversion on the actual analog current time-domain signal to obtain the actual digital current time-domain signal.

[0084] S320. Search for a reference digital current time-domain signal that matches the actual digital current time-domain signal from a pre-constructed target reference current database.

[0085] In one example, the process of constructing the target reference current database includes: using a current acquisition sensor to collect currents under different normal operating conditions at a specific sampling frequency, obtaining reference analog current time-domain signals under different normal operating conditions. During the collection process, the current magnitude range of the fault detection system under various normal operating conditions can be covered as much as possible as the reference analog current time-domain signals, and the reference analog current time-domain signals under different normal operating conditions are stored in the memory of the arc fault detection device; at the same time, the reference analog current time-domain signals under different normal operating conditions need to be Fourier-transformed to obtain reference analog current frequency-domain data under different normal operating conditions. It can be understood that the target reference current database contains two parts of data: one is the reference analog current time-domain signal under normal operating conditions; the other is the reference analog current frequency-domain data under normal operating conditions.

[0086] Figure 4a is a schematic diagram of the configuration of the reference analog current time-domain signal under different normal operating conditions provided by an embodiment of the present invention; Figure 4b is another schematic diagram of the configuration of the reference analog current time-domain signal under different normal operating conditions provided by an embodiment of the present invention. As Figure 4a shown, the peak current of the reference analog current time-domain signal is relatively stable and has no obvious change; as Figure 4b shown, the peak current of the reference analog current time-domain signal also shows regular fluctuations.

[0087] Figure 5 is a schematic diagram of the configuration of the reference analog current frequency-domain data under normal operating conditions provided by an embodiment of the present invention. As Figure 5 shown, the amplitude of the spectrum of the reference analog current frequency-domain data under normal operating conditions is relatively large at the switching frequency and the multiple frequencies of the switching frequency.

[0088] In the processing stage of the current time-domain signal, the actually collected real digital current time-domain signal can be matched with the reference digital current time-domain signal stored in the arc fault detection device, that is, the amplitude and phase of the real digital current time-domain signal are matched with those of the reference digital current time-domain signal. At the same time, the amplitude and phase of the peak fluctuation in the digital current time-domain signal also need to be matched with those of the peak fluctuation in the reference digital current time-domain signal, and the reference digital current time-domain signal obtained by matching these two is used as the reference digital current time-domain signal matched with the actual digital current time-domain signal.

[0089] S330. Perform digital-to-analog conversion on the reference digital current time-domain signal to obtain a reference analog current time-domain signal.

[0090] Adopt a high-performance digital-to-analog converter (DAC) to convert the matched reference digital current time-domain signal into a reference analog current time-domain signal, so that the reference analog current time-domain signal is as consistent as possible with the normal component of the actual analog current time-domain signal in terms of amplitude and phase.

[0091] S340. Input the reference analog current time-domain signal and the actual analog current time-domain signal that match the actual analog current time-domain signal of the DC bus to be measured into the first comparator in the time-domain waveform differential amplification module to obtain the original time-domain signal difference result.

[0092] In an example, the original time-domain signal difference result refers to the data used to characterize the difference between the reference analog current time-domain signal and the actual analog current time-domain signal. In the embodiment, the actual analog current time-domain signal collected from the DC bus to be measured and the reference analog current time-domain signal that matches the actual analog current time-domain signal found in the arc fault detection device are input into the first comparator to compare the actual analog current time-domain signal and the reference analog current time-domain signal through the first comparator to obtain the original time-domain signal difference result.

[0093] S350. Input the original time-domain signal difference result into the second filter amplification module to obtain the time-domain signal difference data.

[0094] In an example, the second filter amplification module includes: a filter and an amplifier. In the embodiment, the original time-domain signal difference result can be differentially amplified through the second filter amplification module, that is, the reference analog current time-domain signal and the actual analog current time-domain signal are differentially amplified to highlight the difference between the reference analog current time-domain signal and the actual analog current time-domain signal.

[0095] During the operation of the arc fault detection system, the filter in the second filter amplification module can be used to perform band-pass filtering on the original time-domain signal difference result to screen out the time-domain signal difference data within the target frequency. At the same time, in order to ensure that the arc fault detection device can collect the time-domain signal difference data more accurately, the original time-domain signal difference result can be amplified so that the filtered and amplified original time-domain signal difference result is within the target voltage range. For example, the target frequency can be 16KHz - 100KHz, and the target voltage range is 0 - 3.3V. All the original time-domain signal difference results can be filtered and amplified to obtain the time-domain signal difference data within 16KHz - 100KHz and between 1 - 1.7V.

[0096] S360. Input the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal into the frequency-domain waveform differential amplification module to obtain the frequency-domain signal difference data.

[0097] S370. Input the time-domain signal difference data and the frequency-domain signal difference data into the pre-constructed target arc fault detection model for feature recognition to obtain the arc fault detection result.

[0098] Based on the above embodiment, the technical solution of this embodiment performs analog-to-digital conversion on the actual analog current time-domain signal of the DC bus to be measured to obtain the actual digital current time-domain signal, and searches for the reference digital current time-domain signal matching the actual digital current time-domain signal from the pre-constructed target reference current database. Then, perform digital-to-analog conversion on the reference digital current time-domain signal to obtain the reference analog current time-domain signal, and highlight the difference between the actual analog current time-domain signal and the reference analog current time-domain signal through the first comparator and the second filter amplification module, thereby improving the accuracy of arc fault judgment and reducing the false alarm rate during normal non-arc conditions.

[0099] In one embodiment, Figure 6 is the flowchart of another arc fault detection method provided by an embodiment of the present invention. This embodiment further details the determination process of the reference analog current frequency-domain data and the determination process of the frequency-domain signal difference data on the basis of the above embodiment. In this embodiment, the frequency-domain waveform differential amplification module includes: a second comparator and a third filter amplification module; wherein, the input end of the second comparator is connected to the output end of the arc fault detection device, the output end of the second comparator is connected to the input end of the third filter amplification module, and the output end of the third filter amplification module is connected to the arc fault detection device. As Figure 6 shown, the arc fault detection method in this embodiment includes the following steps:

[0100] S410. Input the reference analog current time-domain signal matching the actual analog current time-domain signal of the DC bus to be measured and the actual analog current time-domain signal into the time-domain waveform differential amplification module to obtain the time-domain signal difference data.

[0101] S420. Perform analog-to-digital conversion and Fourier transform on the actual analog current time-domain signal to obtain the corresponding actual digital current frequency-domain data.

[0102] In one example, the actual digital current frequency-domain data refers to the spectral representation obtained by performing analog-to-digital conversion and Fourier transform on the actual analog current time-domain signal. Exemplarily, the actual analog current time-domain signal can be subjected to analog-to-digital conversion by an analog-to-digital converter (ADC) to obtain the actual digital current time-domain signal; then, the actual digital current time-domain signal is subjected to Fourier transform to obtain the actual digital current frequency-domain data.

[0103] S430. Respectively perform digital-to-analog conversion on the actual digital current frequency-domain data and the associated reference digital current frequency-domain data to obtain the corresponding actual analog current frequency-domain data and reference analog current frequency-domain data.

[0104] In an embodiment, one digital-to-analog converter can be used to perform digital-to-analog conversion on the actual digital current frequency-domain data to obtain the corresponding actual analog current frequency-domain data; and one digital-to-analog converter can be used to perform digital-to-analog conversion on the reference digital current frequency-domain data to obtain the corresponding reference analog current frequency-domain data.

[0105] S440. Input the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal into the second comparator in the frequency-domain waveform differential amplification module to obtain the original frequency-domain signal difference result.

[0106] In one example, the original frequency-domain signal difference result refers to the data used to characterize the difference between the reference analog current frequency-domain data and the actual analog current frequency-domain data. In an embodiment, the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal are input into the second comparator in the frequency-domain waveform differential amplification module, so that the second comparator compares the actual analog current frequency-domain data and the reference analog current frequency-domain data to obtain the original frequency-domain signal difference result.

[0107] S450. Input the original frequency-domain signal difference result into the third filter amplification module to obtain the frequency-domain signal difference data.

[0108] In one example, the third filter amplification module includes: a filter and an amplifier. In an embodiment, the original frequency-domain signal difference result can be differentially amplified by the third filter amplification module, that is, the reference analog current frequency-domain data and the actual analog current frequency-domain data are differentially amplified to highlight the difference between the reference analog current frequency-domain data and the actual analog current frequency-domain data.

[0109] S460. Input the time-domain signal difference data and the frequency-domain signal difference data into a pre-constructed target arc fault detection model for feature recognition to obtain the arc fault detection result.

[0110] Based on the technical solution of the above embodiment, in this embodiment, by performing analog-to-digital conversion and Fourier transform on the actual simulated current time-domain signal, the corresponding actual digital current frequency-domain data is obtained, and the reference digital current frequency-domain data matching the actual digital current frequency-domain data is searched from the pre-constructed target reference current database. Then, the reference digital current frequency-domain data is subjected to digital-to-analog conversion to obtain the reference analog current frequency-domain data, and the difference between the actual analog current frequency-domain data and the reference analog current frequency-domain data is highlighted through the second comparator and the third filter amplification module, thereby improving the accuracy of arc fault judgment and reducing the false alarm rate during normal non-arc drawing.

[0111] In one embodiment, Figure 7 is a flowchart of another arc fault detection method provided by an embodiment of the present invention. This embodiment further details the determination process of the arc fault detection result on the basis of the above embodiment. As Figure 7 shown, the arc fault detection method in this embodiment includes the following steps:

[0112] S510. Input the reference analog current time-domain signal matching the actual analog current time-domain signal of the DC bus to be measured and the actual analog current time-domain signal into the time-domain waveform differential amplification module to obtain time-domain signal difference data.

[0113] S520. Input the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal into the frequency-domain waveform differential amplification module to obtain frequency-domain signal difference data.

[0114] S530. Input the time-domain signal difference data and the frequency-domain signal difference data into the pre-constructed target arc fault detection model for feature recognition and normalization to obtain a fault detection value.

[0115] Input the time-domain signal difference data and the frequency-domain signal difference data into the pre-constructed target arc fault detection model for feature recognition to identify frequency-domain features and time-domain features, and normalize the frequency-domain features and time-domain features to obtain a fault detection value. In the actual operation process, it can be pre-configured that the fault detection value obtained after normalizing the frequency-domain features and time-domain features is within 0 - 65535.

[0116] S540. When the fault detection value reaches the pre-configured arc drawing threshold, determine that the arc fault detection result of the DC bus to be measured is an arc drawing fault.

[0117] In one example, the arcing threshold refers to a threshold value used to characterize whether an arcing fault occurs. In an embodiment, when the fault detection value reaches the pre-configured arcing threshold, it is determined that an arcing fault occurs in the DC bus to be tested, that is, the arc fault detection result is an arcing fault. Exemplarily, the arcing threshold may be 5000, and the fault detection value may be 6500, at which time it is determined that the arc fault detection result of the DC bus to be tested is an arcing fault.

[0118] S550: When the fault detection value reaches a pre-configured arcing threshold, determine that the arc fault detection result of the DC bus to be tested is that no arcing fault occurs.

[0119] In an embodiment, when the fault detection value does not reach the pre-configured arcing threshold, it is determined that the DC bus to be tested does not have an arcing fault, that is, the arc fault detection result is that no arcing fault occurs. Exemplarily, if the fault detection value is 6500 and the arcing threshold is 4000, then it is determined that the arc fault detection result of the DC bus to be tested is that no arcing fault occurs.

[0120] In one embodiment, after inputting the time domain signal difference data and the frequency domain signal difference data into the pre-built target arc fault detection model for feature recognition and obtaining the arc fault detection result, it includes: if the arc fault detection result is an arcing fault, sending a stop operation instruction and a fault alarm instruction to the DC device to be tested associated with the DC bus to be tested, so that the DC device to be tested stops running. In one example, the stop operation instruction is used to control the DC device to be tested to stop working; the fault alarm instruction is used to send a fault notification message to the staff associated with the DC device to be tested, for example, the fault alarm instruction can be sent to the mobile terminal (such as a smart phone, a laptop) associated with the DC device to be tested. In the case of detecting an arcing fault in the DC bus, a stop operation instruction can be sent to the DC device to be tested through the arc fault detection device to control the DC device to be tested to stop running, and a fault alarm instruction can be sent to the DC device to be tested to send an alarm notification to the staff associated with the DC device to be tested, so that the staff can conduct inspection and repair in time.

[0121] In one embodiment, the arc fault detection method also includes: when the arc fault detection result of the DC bus to be tested is that the actual duration of no arc fault reaches a first preset duration, automatically extracting the current waveform characteristics of the actual analog current time domain signal associated with the DC bus to be tested; using the current waveform characteristics to update the target reference current database at the previous moment, and removing the expired waveform characteristics in the target reference current database at the previous moment to obtain the target reference current database at the current moment.

[0122] In one example, the first preset duration refers to the duration threshold that is pre-configured for the DC bus under test without an arc fault; the actual duration refers to the actual duration that the DC bus under test has not had an arc fault; the expired waveform feature refers to the relevant current waveform features that are obsolete or no longer applicable in the target reference current database; among them, the obsolete current waveform feature refers to the relevant waveform features that exceed the validity period and lose their reference value; the no-longer-applicable current waveform feature refers to the features collected at the initial stage of establishing the target reference current database, but cannot be achieved and do not appear during actual operation; for example, the rated current of the inverter is 40A, and relevant current waveform features of 45A can be collected at the initial stage of establishing the target reference current database, but during actual operation, due to the limited number of on-site photovoltaic panels, the actual current of the inverter is generally about 30A. At this time, the relevant current waveform features of 45A can be excluded. When the actual duration of the arc fault detection result of the DC bus under test without an arc fault reaches the first preset duration, it can be considered that the DC bus under test continuously determines the current operating condition as the normal operating condition. To improve the detection performance of the arc fault detection device, an update mechanism can be automatically triggered. Specifically, various data under the current operating condition can be automatically collected and analyzed, including but not limited to the amplitude and phase information of key parameters such as real-time current and peak current, and the numerical values of representative current waveform features can be extracted. Then, the numerical values of these new current waveform features are compared and fused with the existing data in the target reference current database at the previous moment. For the expired waveform features, the arc fault detection device can automatically exclude or correct them; for the newly discovered waveform features, they can be completely stored in the target reference current database to achieve real-time update and optimization of the target reference current database. This continuous update mechanism enables the system to always maintain an accurate understanding of the normal operating condition, thereby effectively improving the detection ability of the system in tasks such as arc discrimination and ensuring the long-term stable and efficient operation of the system.

[0123] In one embodiment, Figure 8 is a flowchart of another arc fault detection method provided by an embodiment of the present invention. As a preferred embodiment, the process of arc fault detection is described. As Figure 8 shown, the arc fault detection method in this embodiment includes the following steps:

[0124] S610. Collect the actual analog current time-domain signal of the DC bus under test.

[0125] S620. Perform analog-to-digital conversion on the actual analog current time-domain signal to obtain the actual digital current time-domain signal.

[0126] S630. Search for the reference digital current time-domain signal that matches the actual digital current time-domain signal.

[0127] S640. Perform digital-to-analog conversion on the reference digital current time-domain signal to obtain the reference analog current time-domain signal.

[0128] S650. Perform differential filtering and amplification on the actual analog current time-domain signal and the reference analog current time-domain signal to obtain the time-domain signal difference data.

[0129] S660. Perform Fourier transform on the actual digital current time-domain signal to obtain the actual digital current frequency-domain data.

[0130] S670. Perform Fourier transform on the reference digital current time-domain signal to obtain the reference digital current frequency-domain data.

[0131] S680. Perform digital-to-analog conversion on the reference digital current frequency-domain data to obtain the reference analog current frequency-domain data.

[0132] S690. Perform digital-to-analog conversion on the actual digital current frequency-domain data to obtain the actual analog current frequency-domain data.

[0133] S6100. Synchronously output the reference analog current frequency-domain data and the actual analog current frequency-domain data.

[0134] S6110. Perform differential filtering and amplification on the reference analog current frequency-domain data and the actual analog current frequency-domain data to obtain the frequency-domain signal difference data.

[0135] S6120. Input the time-domain signal difference data and the frequency-domain signal difference data into the arc fault detection model for feature recognition and normalization to obtain the fault detection value.

[0136] S6130. Determine whether the fault detection data is greater than the pre-configured arcing threshold. If so, execute S6140; if not, return to execute S610.

[0137] S6140. Send a stop operation instruction and a fault alarm instruction.

[0138] It should be noted that there is no sequential execution order between S660 and S670, and between S680 and S690. They can be executed in parallel or sequentially.

[0139] After obtaining the time domain signal difference data between the actual analog current time domain signal currently collected in real time and the reference analog current time domain signal, as well as the frequency domain signal difference data between the actual analog current frequency domain data and the reference analog current frequency domain data, feature recognition can be performed through the arc fault detection model, and the recognition result can be normalized into a numerical fault detection value. When the fault detection value is greater than the arcing threshold, it is determined that an arcing fault has occurred in the current DC bus to be tested, and the DC equipment to be tested associated with the DC bus to be tested is controlled to stop running and an alarm is issued; if the fault detection value is less than the arcing threshold, the current state is maintained and the above monitoring process is repeated.

[0140] The dual-channel processing architecture of time domain matching differential amplification and frequency domain synchronous differential amplification is adopted. The time / frequency domain difference between the normal operating condition and the actual current signal collected in real time is directly amplified at the physical level through the two analog circuits of the time domain waveform differential amplification module and the frequency domain waveform differential amplification module, breaking through the computing power limitation of traditional digital filtering. In addition, through the DAC reverse reconstruction technology, the stored reference digital current time domain signal under normal operating conditions is converted into the corresponding reference analog current time domain signal in real time, and the phase is aligned, and the millisecond-level dynamic error extraction is realized through the hardware circuit. The frequency domain processing pioneered the dual DAC synchronous output mechanism, and the FFT spectrum of the actual analog current frequency domain data obtained in real time and the reference spectrum of the reference analog current frequency domain data in the target reference current database are directly differentially filtered and amplified in the analog domain to enhance the frequency domain information difference. Then, the time domain signal difference data and the frequency domain signal difference data are feature recognized through the pre-created artificial intelligence arc fault detection model, making the judgment of arcing fault more accurate.

[0141] At the hardware level, the physical-level characteristics of the original signal are enhanced through analog circuits (for example, time-domain waveform differential amplification modules and frequency-domain waveform differential amplification modules); at the same time, the algorithm layer analyzes and identifies the time / frequency difference characteristics through the arc fault detection module of the neural network to achieve highly anti-interference arcing identification.

[0142] In one embodiment, Figure 9 1 is a structural block diagram of an arc fault detection system provided by an embodiment of the present invention. Figure 9 As shown, the arc fault detection system in this embodiment includes: an arc fault detection device 710, a time domain waveform differential amplification module 720 and a frequency domain waveform differential amplification module 730;

[0143] Wherein, the arc fault detection device 710 is externally connected to the time domain waveform differential amplification module 720 and the frequency domain waveform differential amplification module 730 respectively;

[0144] The arc fault detection device is used to execute the arc fault detection method described in any one of the above embodiments.

[0145] In an embodiment, the arc fault detection device 710 inputs a reference analog current time domain signal and an actual analog current time domain signal that match the actual analog current time domain signal of the DC bus to be tested into the time domain waveform differential amplification module 720 to obtain time domain signal difference data; the arc fault detection device 710 inputs the actual analog current frequency domain data corresponding to the actual analog current time domain signal, and the reference analog current frequency domain data corresponding to the reference analog current time domain signal into the frequency domain waveform differential amplification module 730 to obtain frequency domain signal difference data; the time domain signal difference data and the frequency domain signal difference data are input into a pre-constructed target arc fault detection model for feature recognition to obtain an arc fault detection result.

[0146] The technical solution of this embodiment configures an independent and integrated time domain waveform differential amplification module and a frequency domain waveform differential amplification module, and externally connects the arc fault detection device to the time domain waveform differential amplification module and the frequency domain waveform differential amplification module respectively; and differentially amplifies the actual analog current time domain signal and the reference analog current time domain signal on the DC bus to be tested through the time domain waveform differential amplification module, and differentially amplifies the actual analog current frequency domain data and the reference analog current frequency domain data through the frequency domain waveform differential amplification module, without adding additional calculation amount to the arc fault detection device, thereby effectively improving the accuracy and rapidity of the overall system arc fault judgment; and, by inputting the time domain signal difference data and the frequency domain signal difference data into a pre-built target arc fault detection model for feature recognition, an arc fault detection result is obtained, which fully takes into account the difference between the time and frequency domain signals during arcing and non-arcing, and effectively reduces the false alarm rate during non-arcing, thereby providing a more reliable guarantee for the safe and stable operation of the electrical system.

[0147] In one embodiment, Figure 10 is a structural block diagram of another arc fault detection system provided by an embodiment of the present invention. Figure 9 Based on the arc fault detection system shown in FIG. Figure 10 As shown, the arc fault detection system in this embodiment further includes: a current acquisition sensor 740 and a first filtering and amplifying module 750; wherein the output end of the current acquisition sensor 740 is connected to the input end of the first filtering and amplifying module 750; the output end of the first filtering and amplifying module 750 is respectively connected to the input end of the arc fault detection device 710 and the time domain waveform differential amplification module 720;

[0148] The original analog current time domain signal on the DC bus to be tested is collected in real time by the current collection sensor 740, and the original analog current time domain signal is filtered and amplified by the first filtering and amplifying module 750 to obtain the actual analog current time domain signal.

[0149] In one embodiment, Figure 11 is a structural block diagram of another arc fault detection system provided by an embodiment of the present invention. This embodiment is based on the arc fault detection system shown above Figure 10 and further explains the arc fault detection system. As shown in Figure 11 , the time-domain waveform differential amplification module 720 in this embodiment includes: a first comparator 7201 and a second filter amplification module 7202; wherein, the input terminals of the first comparator 7201 are respectively connected to the output terminals of the arc fault detection device 710 and the first filter amplification module 750, the output terminal of the first comparator 7201 is connected to the input terminal of the second filter amplification module 7202, and the output terminal of the second filter amplification module 7202 is connected to the arc fault detection device 710;

[0150] Input the reference analog current time-domain signal and the actual analog current time-domain signal that match the actual analog current time-domain signal of the DC bus to be measured into the first comparator 7201 in the time-domain waveform differential amplification module 720 to obtain the original time-domain signal difference result; filter and amplify the original time-domain signal difference result through the second filter amplification module 7202 to obtain the time-domain signal difference data. The frequency-domain waveform differential amplification module 730 includes: a second comparator 7301 and a third filter amplification module 7302; wherein, the input terminal of the second comparator 7301 is connected to the output terminal of the arc fault detection device 710, the output terminal of the second comparator 7301 is connected to the input terminal of the third filter amplification module 7302, and the output terminal of the third filter amplification module 7302 is connected to the arc fault detection device 710;

[0151] Input the actual analog current frequency-domain data corresponding to the actual analog current time-domain signal and the reference analog current frequency-domain data corresponding to the reference analog current time-domain signal into the second comparator 7301 in the frequency-domain waveform differential amplification module 730 to obtain the original frequency-domain signal difference result;

[0152] Filter and amplify the original frequency-domain signal difference result through the third filter amplification module 7302 to obtain the frequency-domain signal difference data.

[0153] It should be noted that for the explanations and determination processes of various parameters in the arc fault detection system, reference can be made to the descriptions of the corresponding parameters in the above arc fault detection method, which will not be elaborated here.

[0154] It should be noted that the parameters such as the cut-off frequency, passband bandwidth, and stopband attenuation of the filters included in the first filter amplification module, the second filter amplification module, and the third filter amplification module in the present invention can be the same or different, and can be set according to the actual situation; similarly, the amplification multiples of the amplifiers included in the first filter amplification module, the second filter amplification module, and the third filter amplification module can be the same or different, and can be set according to the actual situation.

[0155] In one embodiment, Figure 12 is a structural block diagram of another arc fault detection system provided by an embodiment of the present invention. As a preferred embodiment, the structure of the arc fault detection system is described in detail. The current acquisition sensor in this embodiment is a magnetic ring, such as Figure 12 shown, the arc fault detection system in this embodiment includes:

[0156] During the operation of the system, a current acquisition sensor (such as a magnetic ring) of the same specification as that for acquiring the current data under normal operating conditions is selected to collect the current original analog current time-domain signal in real time; then the original analog current time-domain signal r1 is filtered and amplified by the first filter amplification module to obtain the actual analog current time-domain signal r3; in the time-domain signal processing stage, first, the actual analog current time-domain signal r3 collected in real time is subjected to analog-to-digital conversion by ADC1 to obtain the actual digital current time-domain signal; at the same time, the actual digital current time-domain signal is matched with the reference digital current time-domain signal stored in the arc fault detection device under normal operating conditions. Since, as Figure 4b shown, the current peak value under normal operating conditions will also fluctuate, so when matching the actual digital current time-domain signal collected in real time with the current under normal operating conditions, not only the amplitude and phase need to be matched, but also the amplitude and phase of the peak value fluctuation need to be matched to obtain the reference digital current time-domain signal r2_in. Subsequently, the high-performance digital-to-analog converter DAC1 is used to convert the matched reference digital current time-domain signal r2_in into the reference analog current frequency-domain data r2_out, so that the reference analog current time-domain signal r2_out is as consistent as possible with the normal component of the actual analog current time-domain signal in terms of amplitude and phase. Then, the actual analog current time-domain signal r3 and the reference analog current time-domain signal r2_out output by DAC1 are differentially amplified through an analog circuit to highlight the difference between the two. The amplification multiple of the amplifier is flexibly adjusted according to the actual situation to achieve the purpose of optimizing the signal processing effect. Finally, the amplified analog signal r4 is accurately converted into a digital signal through a high-precision analog-to-digital converter (ADC2) to obtain the time-domain signal difference data.

[0157] In the frequency-domain signal processing stage, perform FFT on the actual digital current time-domain signal to obtain the actual digital current frequency-domain data f2_in. Synchronously output both the real-time acquired actual digital current frequency-domain data f2_in and the matched reference digital current frequency-domain data f1_in under normal operating conditions using digital-to-analog converters (DAC2 and DAC3) to obtain the actual analog current frequency-domain data f2_out and the reference analog current frequency-domain data f1_out. Perform differential amplification on the frequency-domain waveform using the frequency-domain waveform differential amplification module to highlight the difference f3 between the two in the frequency domain, and then collect it through an analog-to-digital converter (ADC3) to obtain the frequency-domain signal difference data.

[0158] In this embodiment, by dynamically searching for the amplitude-phase joint characteristics of the current and peak current under normal operating conditions, quickly match the reference analog current time-domain signal that matches the real-time acquired actual analog current time-domain signal, and output it as a reference.

[0159] Figure 13a It is a schematic diagram of the implementation of an actual analog current time-domain signal and a reference analog current time-domain signal provided by an embodiment of the present invention. As Figure 13a shown, it shows Figure 4a In the working condition shown, when an arcing fault occurs, the input waveform of the time-domain differential amplification module, where the solid line is the real-time acquired actual analog current time-domain signal r3, that is, the arcing current signal at this time, and the dashed line is the stored reference digital current time-domain signal r2_in under the normal operating condition matched by the present invention, and after conversion by DAC1, the reference analog current time-domain signal r2_out is output to the inverting input terminal of the operational amplifier. It can be Figure 13a seen that there is a difference between the actual analog current time-domain signal r3 and the stored reference analog current time-domain signal r2_out under normal operating conditions in the time domain during arcing, mainly manifested as irregular fluctuations and abnormal mutations in the arcing current peak, but it is not obvious. Through the method described in the present invention, r1 and r2_out are differentially amplified through the time-domain differential amplification module for feature enhancement. At this time, r4 is obtained, and r4 passes through ADC2 as the time-domain feature for arcing discrimination, and this filtering differential amplification does not require computing time to meet the response time requirement.

[0160] Figure 13b It is a schematic diagram of the implementation of a time-domain signal difference data provided by an embodiment of the present invention. As Figure 13b shown, Figure 13b shows Figure 4aUnder the shown working conditions, the differences in the output waveforms of r4 during arcing (when r3 is the arcing signal at this time) and non-arcing (when r3 is the non-arcing signal at this time). In the figure, the solid line is the waveform of r4 output by the analog circuit during non-arcing, and the dashed line is the waveform of r4 output by the analog circuit during arcing. It can be seen that after the analog circuit differentially amplifies the time-domain signals during arcing and non-arcing, its characteristics are enhanced, and the arcing signal and the non-arcing signal can be more clearly distinguished in the time domain, improving the accuracy of arcing discrimination and reducing the false alarm rate.

[0161] Figure 14a is a schematic diagram of the implementation of the actual analog current frequency-domain data and the reference analog current frequency-domain data provided by an embodiment of the present invention. As Figure 14a shown, it shows Figure 4a under the shown working conditions, when an arcing fault occurs, the reference digital current frequency-domain data f1_in under normal operating conditions stored and output as the reference analog current frequency-domain data f1_out by DAC2, the actual digital current frequency-domain data f2_in collected by ADC1 and analyzed by FFT, and the actual analog current frequency-domain data f2_out output by DAC3. Through Figure 14a , the amplitude of the reference analog current frequency-domain data f1_out during non-arcing is relatively large mainly at the switching frequency and its multiples. For the actual analog current frequency-domain data f2_out during arcing, not only is the amplitude large at the switching frequency, but also the amplitude is large at other frequencies, but the difference is not very obvious. Through the method of the present invention, the reference analog current frequency-domain data f1_out and the actual analog current frequency-domain data f2_out are differentially amplified by the analog circuit for feature enhancement. At this time, f3 is obtained, and f3 is used as the frequency-domain feature for arcing discrimination through ADC3. And this filtering differential amplification does not require computing time to meet the response time requirement.

[0162] Figure 14b is a schematic diagram of the implementation of the frequency-domain signal difference data provided by an embodiment of the present invention. As Figure 14b shown, Figure 14b is the output waveform f3 after differential amplification by the analog circuit of the present invention under the working conditions shown in Figure 4a . Among them, the solid line is the waveform of f3 output by the analog circuit during non-arcing (when f2_out is the non-arcing signal at this time), and the dashed line is the waveform of f3 output by the analog circuit during arcing (when f2_out is the arcing signal at this time). It can be seen that compared with Figure 14a , Figure 14b it can more clearly distinguish the current characteristics during arcing from those during non-arcing, highlighting the difference and improving the accuracy of arcing discrimination.

[0163] Figure 15aIt is another schematic diagram of the implementation of the actual simulated current time-domain signal and the reference simulated current time-domain signal provided by the embodiment of the present invention. As Figure 15a shown, it shows the differential input waveform of the time-domain differential amplification module when an arcing fault occurs under the working condition shown in Figure 4b . Among them, the solid line is the actual simulated current time-domain signal r3 collected in real time, that is, the arcing current signal at this time, and the dotted line is the matched stored reference digital current time-domain signal r2_in under the normal operating condition described in the present invention, which is converted into the reference simulated current time-domain signal r2_out through DAC1 and output to the inverting input terminal of the operational amplifier.

[0164] Figure 15b It is another schematic diagram of the implementation of the time-domain signal difference data provided by the embodiment of the present invention. As Figure 15b shown, Figure 15b it shows the difference in the output waveforms of r4 during arcing (r3 is the arcing signal at this time) and non-arcing (r3 is the non-arcing signal at this time) under the working condition shown in Figure 4b . In the figure, the solid line is the r4 waveform output by the analog circuit during non-arcing, and the dotted line is the r4 waveform output by the analog circuit during arcing. It can be seen that under the working condition shown in Figure 4b , after the enhancement of the analog circuit characteristics, the arcing signal can also be well recognized.

[0165] Figure 16a It is another schematic diagram of the implementation of the actual simulated current frequency-domain data and the reference simulated current frequency-domain data provided by the embodiment of the present invention. As Figure 16a shown, it shows that when an arcing fault occurs under the working condition shown in Figure 4b , the reference digital current frequency-domain data f1_in stored under the normal operating condition is output as the reference digital analog current frequency-domain data f1_out through DAC2, the actual digital current frequency-domain data f2_in collected by ADC1 and analyzed by FFT, and the actual digital analog current frequency-domain data f2_out output by DAC3.

[0166] Figure 16b It is another schematic diagram of the implementation of the frequency-domain signal difference data provided by the embodiment of the present invention. As Figure 16b shown, Figure 16b it is the output waveform f3 after differential amplification by the analog circuit described in the present invention under the working condition shown in Figure 4b . Among them, the solid line is the f3 waveform output by the analog circuit during non-arcing (f2_out is the non-arcing signal at this time), and the dotted line is the f3 waveform output by the analog circuit during arcing (f2_out is the arcing signal at this time). It can be seen that compared with Figure 16a , Figure 16b during arcing, it can more clearly distinguish the current characteristics from those during non-arcing, highlighting the difference and improving the accuracy of arcing discrimination.

[0167] In summary, the present invention uses two analog circuits, namely the time-domain waveform differential amplification module and the frequency-domain waveform differential amplification module, to perform differential amplification and feature enhancement on the arcing and non-arcing signals in the time domain and frequency domain, which can effectively improve the accuracy of arcing discrimination under different working conditions and provide a strong guarantee for the safe operation of the electrical system.

[0168] Figure 17 is a structural block diagram of an arc fault detection device provided by an embodiment of the present invention, as Figure 17 shown, which shows a schematic structural diagram of an arc fault detection device 10 that can be used to implement the embodiments of the present invention. The arc fault detection device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The arc fault detection device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0169] As Figure 17 shown, the arc fault detection device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the arc fault detection device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0170] Multiple components in the arc fault detection device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the arc fault detection device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0171] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the arc fault detection method.

[0172] In some embodiments, the arc fault detection method may be implemented as a computer program tangibly embodied in a computer-readable storage medium. In some embodiments, part or all of the computer program may be loaded and / or installed onto the arc fault detection device via the ROM and / or the communication unit. When the computer program is loaded into the RAM and executed by the logic processing module and the main controller, one or more steps of the arc fault detection method described above may be executed. Alternatively, in other embodiments, the logic processing module and the main controller may be configured to execute the arc fault detection method in any other suitable manner (e.g., by means of firmware).

[0173] The various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0174] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0175] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0176] To provide for interaction with a user, the systems and techniques described herein can be implemented on an arc fault detection device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the arc fault detection device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0177] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0178] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0179] An embodiment of the present invention also provides a computer program product, including a computer program which, when executed by a processor, can implement the arc fault detection method provided in any embodiment of the present application.

[0180] In the process of implementing the computer program product, computer program code for performing the operations of the present application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0181] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0182] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for detecting an arc fault, characterized in that: An arc fault detection device used in an arc fault detection system, the arc fault detection system comprising: an arc fault detection device, a time domain waveform differential amplification module and a frequency domain waveform differential amplification module; wherein the arc fault detection device is externally connected to the time domain waveform differential amplification module and the frequency domain waveform differential amplification module respectively; the method comprising: Inputting a reference analog current time domain signal that matches the actual analog current time domain signal of the DC bus to be tested and the actual analog current time domain signal into the time domain waveform differential amplification module to obtain time domain signal difference data; Inputting actual analog current frequency domain data corresponding to the actual analog current time domain signal and reference analog current frequency domain data corresponding to the reference analog current time domain signal into the frequency domain waveform differential amplification module to obtain frequency domain signal difference data; The time domain signal difference data and the frequency domain signal difference data are input into a pre-built target arc fault detection model for feature recognition to obtain an arc fault detection result.

2. The method according to claim 1, characterized in that The arc fault detection system further includes: a current acquisition sensor and a first filtering and amplifying module; wherein the output end of the current acquisition sensor is connected to the input end of the first filtering and amplifying module; the output end of the first filtering and amplifying module is respectively connected to the input end of the arc fault detection device and the time domain waveform differential amplifying module; the method further includes: Acquire the actual analog current time domain signal associated with the DC bus to be tested in real time; wherein, the actual analog current time domain signal is obtained by collecting the original analog current time domain signal on the DC bus to be tested in real time through the current acquisition sensor, and filtering and amplifying the original analog current time domain signal through the first filtering and amplifying module.

3. The method according to claim 1, characterized in that Before inputting the reference analog current time domain signal matching the actual analog current time domain signal of the DC bus to be measured and the actual analog current time domain signal into the time domain waveform differential amplification module to obtain the time domain signal difference data, the method further includes: Performing analog-to-digital conversion on the actual analog current time-domain signal of the DC bus to be tested to obtain an actual digital current time-domain signal; Searching for a reference digital current time-domain signal that matches the actual digital current time-domain signal from a pre-built target reference current database; The reference digital current time domain signal is converted from digital to analog to obtain a reference analog current time domain signal.

4. The method according to any one of claims 1 to 3, characterized in that: The time domain waveform differential amplification module includes: a first comparator and a second filtering and amplifying module; wherein the input end of the first comparator is connected to the arc fault detection device and the output end of the first filtering and amplifying module respectively, the output end of the first comparator is connected to the input end of the second filtering and amplifying module, and the output end of the second filtering and amplifying module is connected to the arc fault detection device; The step of inputting a reference analog current time domain signal that matches the actual analog current time domain signal of the DC bus to be tested and the actual analog current time domain signal into the time domain waveform differential amplification module to obtain time domain signal difference data includes: Inputting a reference analog current time domain signal that matches the actual analog current time domain signal of the DC bus to be tested and the actual analog current time domain signal into a first comparator in the time domain waveform differential amplification module to obtain an original time domain signal difference result; The original time domain signal difference result is input into the second filtering and amplifying module to obtain the time domain signal difference data.

5. The method according to any one of claims 1 to 3, characterized in that: Before inputting the actual analog current frequency domain data corresponding to the actual analog current time domain signal and the reference analog current frequency domain data corresponding to the reference analog current time domain signal into the frequency domain waveform differential amplification module to obtain the frequency domain signal difference data, the method further includes: Performing analog-to-digital conversion and Fourier transform on the actual analog current time domain signal to obtain corresponding actual digital current frequency domain data; The actual digital current frequency domain data and the associated reference digital current frequency domain data are respectively converted from digital to analog to obtain corresponding actual analog current frequency domain data and reference analog current frequency domain data.

6. The method according to claim 5, characterized in that The frequency domain waveform differential amplification module includes: a second comparator and a third filtering and amplification module; wherein the input end of the second comparator is connected to the output end of the arc fault detection device, the output end of the second comparator is connected to the input end of the third filtering and amplification module, and the output end of the third filtering and amplification module is connected to the arc fault detection device; The actual analog current frequency domain data corresponding to the actual analog current time domain signal and the reference analog current frequency domain data corresponding to the reference analog current time domain signal are input into the frequency domain waveform differential amplification module to obtain frequency domain signal difference data, including: Inputting the actual analog current frequency domain data corresponding to the actual analog current time domain signal and the reference analog current frequency domain data corresponding to the reference analog current time domain signal into the second comparator in the frequency domain waveform differential amplification module to obtain the original frequency domain signal difference result; The original frequency domain signal difference result is input into the third filtering and amplifying module to obtain frequency domain signal difference data.

7. The method according to any one of claims 1 to 3, characterized in that: The step of inputting the time domain signal difference data and the frequency domain signal difference data into a pre-built target arc fault detection model for feature recognition to obtain an arc fault detection result includes: Inputting the time domain signal difference data and the frequency domain signal difference data into a pre-built target arc fault detection model for feature recognition and normalization to obtain a fault detection value; When the fault detection value reaches a pre-configured arcing threshold, determining that the arc fault detection result of the DC bus to be tested is an arcing fault; When the fault detection value reaches a pre-configured arcing threshold, it is determined that the arc fault detection result of the DC bus to be tested is that no arcing fault occurs.

8. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: When the arc fault detection result of the DC bus to be tested is that the actual duration of no arc fault has reached a first preset duration, automatically extracting the current waveform characteristics of the actual analog current time domain signal associated with the DC bus to be tested; The target reference current database at the previous moment is updated by using the current waveform feature, and outdated waveform features in the target reference current database at the previous moment are removed to obtain the target reference current database at the current moment.

9. An arc fault detection system, characterized in that: include: Arc fault detection equipment, time domain waveform differential amplification module and frequency domain waveform differential amplification module; Wherein, the arc fault detection device is externally connected to the time domain waveform differential amplification module and the frequency domain waveform differential amplification module respectively; The arc fault detection device is used to execute the arc fault detection method according to any one of claims 1 to 8.

10. An arc fault detection device, characterized in that: include: The arc fault detection device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can perform the arc fault detection method according to any one of claims 1 to 8.

Images