Sudden fault arc diagnosis method and device based on multi-source signal fusion

Abstract

The invention discloses a sudden fault arc diagnosis method and device based on multi-source signal fusion. The method comprises the following steps: synchronously acquiring an infrasonic wave signal and a current signal of a low-voltage line through an infrasonic wave sensor and a high-precision current sensor; preprocessing the infrasonic wave signal and the current signal to obtain a preprocessed infrasonic wave signal and a preprocessed current signal; performing feature extraction on the preprocessed infrasonic wave signal and the preprocessed current signal to obtain infrasonic wave features and current features; determining the final fault probability of each detection window according to the infrasonic wave features and the current features; and when the final fault probability continuous preset detection window satisfies a preset condition, determining that the fault arc exists in the low-voltage line.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical safety monitoring, and more particularly, to a method and device for diagnosing sudden fault arcs based on multi-source signal fusion. Background Art

[0002] In low-voltage electrical systems, sudden fault arcs are a common fault phenomenon that can lead to serious consequences such as equipment damage and fires. Traditional fault arc detection methods mainly rely on the analysis of electrical parameters such as current and voltage. However, these methods have problems such as insufficient detection sensitivity, poor anti-interference ability, and high requirements for current sampling rate when dealing with low-voltage sudden fault arcs. In recent years, detection techniques based on infrasound characteristics have gradually attracted attention. Infrasound signals are low-frequency signals with the characteristics of low frequency, long wavelength, and long propagation path. Infrasound signals can reflect the physical process of arc faults. Infrasound detection has become an emerging direction due to its strong anti-electromagnetic interference and the ability to capture the initial signal vibration of arcs, providing new ideas for the diagnosis of fault arcs. However, the existing technology has the following defects: 1) Currently, there is a lack of a feature extraction method for arc infrasound; 2) It is not integrated with current detection, making it difficult to distinguish early real arcs from interference events. Summary of the Invention

[0003] In view of the deficiencies of the prior art, the present invention provides a method and device for diagnosing sudden fault arcs based on multi-source signal fusion.

[0004] According to one aspect of the present invention, a method for diagnosing sudden fault arcs based on multi-source signal fusion is provided, including: Synchronously collecting infrasound signals and current signals of a low-voltage line through an infrasound sensor and a high-precision current sensor; Performing preprocessing operations on the infrasound signal and the current signal respectively to obtain a preprocessed infrasound signal and a preprocessed current signal; Performing feature extraction on the preprocessed infrasound signal and the preprocessed current signal respectively to obtain infrasound features and current features; Determining the final fault probability of each detection window according to the infrasound features and the current features; When the final fault probability continuously satisfies a preset condition in a preset number of detection windows, it is determined that there is a fault arc in the low-voltage line.

[0005] Optionally, the sampling frequency band of the infrasound signal is 0.1~20 Hz; the acquisition frequency of the current signal is 20 kHz.

[0006] Optionally, performing preprocessing on the infrasound signal to obtain a preprocessed infrasound signal, including: Perform windowing operation on the infrasound signal using a Hamming window with a frame length of 200 ms and a frame shift of 50 ms to obtain the windowed infrasound signal; Perform discrete wavelet transform on the windowed infrasound signal using the sym4 wavelet basis to obtain the preprocessed infrasound signal.

[0007] Optionally, the formula for the Hamming window is: where N is the window length, n is the sampling point number.

[0008] Optionally, preprocess the current signal to obtain the preprocessed current signal, including: Suppress noise of the current signal using a Butterworth filter to obtain the current signal with noise suppressed, where the cut-off frequency of the Butterworth filter is 2 kHz - 20 kHz; Frame the current signal with noise suppressed according to a frame length of 50 ms and a frame shift of 25 ms, and apply a Hamming window to each frame signal to obtain the preprocessed current signal.

[0009] Optionally, the infrasound features include energy entropy and envelope peak ratio, where the calculation steps for energy entropy are: Perform 5-layer wavelet packet decomposition on the preprocessed infrasound signal using the db4 wavelet basis to generate 32 frequency bands, where the 32 frequency bands are equally spaced within 1 - 20 Hz; Extract the energy of the i th frequency band among the 32 frequency bands respectively; Determine the total energy of the 32 frequency bands according to the energy of each frequency band among the 32 frequency bands; Normalize the total energy to obtain the normalized total energy; Calculate the energy entropy according to the normalized total energy.

[0010] Optionally, the calculation steps for the envelope peak ratio are: Perform Hilbert transform on the preprocessed infrasound signal to obtain the envelope; Calculate the envelope peak ratio of the signal EPAR = max(A(t) / RMS(A(T))) based on the envelope, where RMS is the root mean square value of the envelope and A(t) is the envelope.

[0011] Optionally, extract features from the preprocessed current signal to obtain current features, including: Perform fast Fourier transform on the preprocessed current signal and calculate the power spectral density of the preprocessed current signal; Divide the power spectral density into characteristic frequency bands and extract current features.

[0012] Optionally, the current features include high-frequency energy ratio, main peak frequency offset, and spectral entropy. Feature frequency bands are divided for the power spectral density, and current features are extracted, including: Extract three frequency bands of 2 kHz - 5 kHz, 5 kHz - 10 kHz, and 10 kHz - 20 kHz, calculate the energy proportion of each frequency band, and determine the high-frequency energy ratio; Calculate the offset of the main peak frequency of the power spectral density from the normal operating condition to determine the main peak frequency offset; Calculate the spectral entropy based on the power spectral density , where , is the power spectral density at frequency ; is the normalized power probability distribution.

[0013] According to another aspect of the present invention, a sudden fault arc diagnosis device based on multi-source signal fusion is provided, including: An acquisition module for synchronously acquiring infrasonic signals and current signals of a low-voltage line through an infrasonic sensor and a high-precision current sensor; A preprocessing module for respectively performing preprocessing operations on the infrasonic signal and the current signal to obtain a preprocessed infrasonic signal and a preprocessed current signal; An extraction module for respectively performing feature extraction on the preprocessed infrasonic signal and the preprocessed current signal to obtain infrasonic features and current features; A determination module for determining the final fault probability of each detection window according to the infrasonic features and the current features; A judgment module for judging that there is a fault arc in the low-voltage line when the final fault probability continuously satisfies a preset condition in a preset number of detection windows.

[0014] According to yet another aspect of the present invention, a computer-readable storage medium is provided, where the storage medium stores a computer program, and the computer program is used to execute the method described in any of the above aspects of the present invention.

[0015] According to yet another aspect of the present invention, an electronic device is provided, the electronic device includes: a processor; a memory for storing executable instructions of the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the above aspects of the present invention.

[0016] Therefore, through the infrasound signal processing technology, the present invention significantly improves the early diagnosis sensitivity of small-current fault arcs, can effectively identify weak arc signals that are difficult to detect by traditional methods; the fusion of current characteristic signal processing algorithms enhances the anti-interference ability of the system in complex electromagnetic environments and greatly reduces the false alarm rate; the non-contact sensing method simplifies the installation and maintenance process and reduces the deployment cost; the multi-dimensional feature fusion technology improves the recognition accuracy of different types of arcs and provides a reliable basis for early fault warning; these technical features together constitute an efficient and reliable fault arc diagnosis solution for low-voltage distribution systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The exemplary embodiments of the present invention can be more fully understood by referring to the following drawings: Figure 1 is a schematic flowchart of a method for diagnosing sudden fault arcs based on multi-source signal fusion provided by an exemplary embodiment of the present invention; Figure 2 is a time-domain waveform diagram of multiple sudden arc discharges received by an infrasound sensor provided by an exemplary embodiment of the present invention; Figure 3 is a frequency-domain waveform diagram of multiple sudden arc discharges received by an infrasound sensor provided by an exemplary embodiment of the present invention; Figure 4 is a frequency-domain waveform diagram of multiple sudden arc discharges received by an infrasound sensor provided by an exemplary embodiment of the present invention; Figure 5 is a schematic structural diagram of a device for diagnosing sudden fault arcs based on multi-source signal fusion provided by an exemplary embodiment of the present invention; Figure 6 is the structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein.

[0019] It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present invention.

[0020] Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate an inevitable logical order between them.

[0021] It should also be understood that in the embodiments of the present invention, "a plurality of" may mean two or more, and "at least one" may mean one, two or more.

[0022] It should also be understood that for any component, data or structure mentioned in the embodiments of the present invention, in the absence of a clear definition or contrary indication in the context, it is generally understood as one or more.

[0023] In addition, the term "and / or" in the present invention is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally represents an "or" relationship between the associated objects before and after.

[0024] It should also be understood that the description of each embodiment of the present invention emphasizes the differences between the embodiments, and their similarities can be referred to each other. For the sake of brevity, they will not be elaborated one by one.

[0025] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0026] The following description of at least one exemplary embodiment is actually merely illustrative and in no way limits the present invention and its application or use.

[0027] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be regarded as part of the specification.

[0028] It should be noted that like reference numerals and letters denote like items in the following figures, and thus, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0029] The embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, and so on.

[0030] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system-executable instructions (such as program modules) executed by a computer system. Generally, program modules can include routines, programs, target programs, components, logics, data structures, etc., which perform specific tasks or implement specific abstract data types. The computer system / server can be implemented in a distributed cloud computing environment where tasks are executed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0031] Exemplary method Figure 1 is a schematic flowchart of a sudden fault arc diagnosis method based on multi-source signal fusion provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as Figure 1 As shown, the sudden fault arc diagnosis method 100 based on multi-source signal fusion includes the following steps: Step 101, synchronously collect the infrasound signal and current signal of the low-voltage line through an infrasound sensor and a high-precision current sensor; Step 102, perform preprocessing operations on the infrasound signal and the current signal respectively to obtain a preprocessed infrasound signal and a preprocessed current signal; Step 103, perform feature extraction on the preprocessed infrasound signal and the preprocessed current signal respectively to obtain infrasound features and current features; Step 104, determine the final fault probability of each detection window according to the infrasound features and the current features; Step 105, when the final fault probability continuously satisfies the preset conditions in the preset detection window, determine that there is a fault arc in the low-voltage line.

[0032] Specifically, the characteristic waveform of the early fault arc signal in complex power consumption scenarios is complex and dynamically changing, which poses high requirements for the diagnostic sensitivity of the fault arc signal waveform. A method for early diagnosis of low-voltage fault arcs based on multi-source signal fusion proposed by the present invention can quickly and sensitively extract the characteristics of the fault arc signal, analyze the signal characteristics, report useful diagnostic information according to the characteristics, solve the problem of missed reports, ensure the effectiveness of signal diagnosis, and solve the problems of long arc response time and poor anti-interference ability in the prior art. The method proposed by the present invention decomposes the infrasound signal and current signal of the fault arc in complex scenarios, decomposes the signal in the time domain, frequency domain, and energy domain, obtains the arc time domain and frequency domain information of complex power consumption scenarios, and constructs the characteristics of the infrasound signal and current signal of the fault arc in complex power consumption scenarios; calculates the energy entropy and envelope peak ratio of the infrasound signal of the fault arc, and at the same time calculates the high-frequency harmonic distortion rate, current change rate, and high-frequency noise energy ratio characteristics of the fault arc current signal, inputs the infrasound characteristics and current characteristics into the cascade classifier, screens out suspected fault samples, and if the fault probability is greater than the output threshold and lasts for 3 detection windows, it is determined as an arc fault.

[0033] (1) Signal acquisition and preprocessing Synchronously collect the infrasound signal of the low-voltage line through an infrasound sensor and a high-precision current sensor S(t) and the current signal I(t) , where the sampling frequency band of the infrasound signal is (0.1~20Hz), and the current acquisition frequency is 20kHz.

[0034] For the infrasound signal, since the length of the collected sound sample is too long, it is difficult to extract the characteristic value in the whole infrasound signal. It is necessary to perform preprocessing operations on the signal, perform frame division and windowing operations on the signal, and use a Hamming window with a frame length of 200ms and a frame shift of 50ms for frame division and windowing operations to suppress spectral leakage. The formula of the Hamming window is: In the formula, N is the window length.

[0035] Perform discrete wavelet transform (DWT) on the windowed signal, select the sym4 wavelet basis, and remove environmental noise by the soft threshold method.

[0036] For the line current signal, use a Butterworth filter (cutoff frequency 2kHz - 20kHz) to suppress power frequency and ultra-high frequency noise, divide the current signal into frames with a frame length of 50ms and a frame shift of 25ms, and apply a Hann window to each frame to reduce spectral leakage.

[0037] (2) Infrasound feature extraction 1) Extract the time-frequency domain features of the preprocessed signal. Due to the discharge instability of the faulty arc, the infrasonic energy is dispersed within the frequency band, and the entropy value is significantly higher than that of mechanical vibration (concentrated main frequency). For example, Figure 2 , Figure 3 and Figure 4 as shown, first calculate the energy entropy of the faulty infrasonic signal: ① Perform 5-layer wavelet packet decomposition on the signal (select the db4 wavelet basis) to generate 32 frequency bands (equally spaced within 1 - 20 Hz); ② Extract the energy i of the th frequency band, where is the node coefficient of the i th frequency band; ③ Normalize the total energy , and calculate the energy entropy value .

[0038] 2) The arc infrasound exhibits intermittent pulse characteristics, and the envelope peak is significantly higher than the background fluctuation. Calculate the envelope peak ratio of the faulty infrasound signal: Perform Hilbert transform on the preprocessed infrasound signal. The Hilbert transform is: ; The analytic signal is: ; Obtain the envelope line , where is the original signal, and is the signal after Hilbert transform.

[0039] Calculate the envelope peak ratio of the signal based on the envelope line EPAR = max(A(t) / RMS(A(T))), where RMS is the root mean square value of the envelope.

[0040] ④ Input H, EPAR into the support vector machine classifier and output the fault probability .

[0041] (3) Current feature extraction First, perform fast Fourier transform (FFT) on each frame of the faulty arc current signal to calculate the power spectral density . The formula is: where is the sampling rate, and is the Hanning window function.

[0042] Secondly, perform feature frequency band division, and extract the high-frequency energy ratio, main peak frequency offset, and spectral entropy: ①Extract three frequency bands of 2 kHz - 5 kHz, 5 kHz - 10 kHz, and 10 kHz - 20 kHz, and calculate the energy proportion of each frequency band. E 1 ， E 2 ，E 3 。

[0043] ②Detect the main peak frequency of the power spectrum. f peak and calculate its offset from the normal operating condition. ； ③Calculate the spectral entropy based on the power spectrum distribution. H s , which characterizes the spectral complexity, and the formula is: ④Input E 1 , E 2 , E 3 , , H s into the support vector machine classifier and output the fault probability. 。

[0044] (3) Multimodal diagnosis module . According to data statistical analysis, , the effect is optimal. When the final fault probability > 80% and lasts for 3 detection windows, it is determined as an arc fault.

[0045] (4) Alarm and communication module When it is determined that there is an arc fault, trigger a local alarm and upload it to the cloud platform.

[0046] Thus, through the infrasonic wave signal processing technology, the present invention significantly improves the early diagnosis sensitivity of small - current fault arcs, can effectively identify weak arc signals that are difficult to detect by traditional methods; the fusion of current characteristic signal processing algorithms enhances the anti - interference ability of the system in complex electromagnetic environments and greatly reduces the false alarm rate; the non - contact sensing method simplifies the installation and maintenance process and reduces the deployment cost; the multi - dimensional feature fusion technology improves the recognition accuracy of different types of arcs and provides a reliable basis for early fault warning; these technical characteristics together constitute an efficient and reliable fault arc diagnosis solution for low - voltage distribution systems.

[0047] Exemplary apparatus Figure 5It is a schematic structural diagram of a sudden fault arc diagnosis device based on multi-source signal fusion provided by an exemplary embodiment of the present invention. As Figure 5 shown, the device 500 includes: An acquisition module 510, configured to synchronously acquire infrasonic signals and current signals of a low-voltage line through an infrasonic sensor and a high-precision current sensor; A preprocessing module 520, configured to perform preprocessing operations on the infrasonic signal and the current signal respectively to obtain a preprocessed infrasonic signal and a preprocessed current signal; An extraction module 530, configured to perform feature extraction on the preprocessed infrasonic signal and the preprocessed current signal respectively to obtain infrasonic features and current features; A determination module 540, configured to determine the final fault probability of each detection window according to the infrasonic features and the current features; A determination module 550, configured to determine that there is a fault arc in the low-voltage line when the final fault probability continuously satisfies a preset condition in a preset detection window.

[0048] Optionally, the sampling frequency band of the infrasonic signal is 0.1~20Hz; the acquisition frequency of the current signal is 20kHz.

[0049] Optionally, the preprocessing of the infrasonic signal in the preprocessing module 520 to obtain the preprocessed infrasonic signal includes: A first acquisition sub-module, configured to perform minute-by-minute windowing on the infrasonic signal by using a Hamming window with a frame length of 200ms and a frame shift of 50ms to obtain a windowed infrasonic signal; A second acquisition sub-module, configured to perform discrete wavelet transform on the windowed infrasonic signal by using a sym4 wavelet basis to obtain a preprocessed infrasonic signal.

[0050] Optionally, the formula of the Hamming window is: where N is the window length, n is the sampling point number.

[0051] Optionally, the preprocessing of the current signal in the preprocessing module 520 to obtain the preprocessed current signal includes: A third acquisition sub-module, configured to perform noise suppression on the current signal by using a Butterworth filter to obtain a current signal after noise suppression, where the cut-off frequency of the Butterworth filter is 2kHz-20kHz; A fourth acquisition sub-module, configured to frame the current signal after noise suppression with a frame length of 50ms and a frame shift of 25ms, and apply a Hamming window to each frame signal to obtain a preprocessed current signal.

[0052] Optionally, the infrasound features in the extraction module 530 include energy entropy and envelope peak ratio. The calculation steps of the energy entropy are as follows: Using the db4 wavelet basis, perform 5-layer wavelet packet decomposition on the preprocessed infrasound signal to generate 32 frequency bands, where the 32 frequency bands are equally spaced within 1 - 20 Hz; Extract the energy of the i th frequency band among the 32 frequency bands respectively; Determine the total energy of the 32 frequency bands according to the energy of each frequency band among the 32 frequency bands; Perform normalization processing on the total energy to obtain the normalized total energy; Calculate the energy entropy according to the normalized total energy.

[0053] Optionally, the calculation steps of the envelope peak ratio are as follows: Perform Hilbert transform on the preprocessed infrasound signal to obtain the envelope; Calculate the envelope peak ratio of the signal based on the envelope EPAR = max(A(t) / RMS(A(T))), where RMS is the root mean square value of the envelope, and A(t) is the envelope.

[0054] Optionally, the extraction module 530 performs feature extraction on the preprocessed current signal to obtain current features, including: A calculation sub-module for performing fast Fourier transform on the preprocessed current signal and calculating the power spectral density of the preprocessed current signal; An extraction sub-module for performing feature frequency band division on the power spectral density and extracting current features.

[0055] Optionally, the current features include high-frequency energy ratio, main peak frequency offset, and spectral entropy, and the extraction sub-module includes: An extraction unit for extracting three frequency bands of 2 kHz - 5 kHz, 5 kHz - 10 kHz, and 10 kHz - 20 kHz, calculating the energy proportion of each frequency band, and determining the high-frequency energy ratio; A first calculation unit for calculating the offset of the main peak frequency of the power spectral density from the normal working condition to determine the main peak frequency offset; A second calculation unit for calculating the spectral entropy based on the power spectral density , where , is the power spectral density at frequency ; is the normalized power probability distribution.

[0056] Exemplary electronic device Figure 6 This is the structure of the electronic device provided by an exemplary embodiment of the present invention. AsFigure 6 As shown, the electronic device 60 includes one or more processors 61 and a memory 62.

[0057] The processor 61 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0058] The memory 62 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 61 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may further include: an input device 63 and an output device 64, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0059] In addition, the input device 63 may further include, for example, a keyboard, a mouse, and so on.

[0060] The output device 64 may output various information to the outside. The output device 64 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, and so on.

[0061] Of course, for simplicity, Figure 6 only some of the components related to the present invention in the electronic device are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device may further include any other appropriate components.

[0062] Exemplary computer program product and computer-readable storage medium In addition to the above methods and devices, embodiments of the present invention may also be computer program products, which include computer program instructions that, when run by a processor, cause the processor to execute the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above of this specification.

[0063] The computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present invention. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The programming code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0064] In addition, an embodiment of the present invention may also be a computer-readable storage medium storing computer program instructions that, when run by a processor, cause the processor to execute the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above of this specification.

[0065] The computer-readable storage medium may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0066] The basic principles of the present invention have been described above in connection with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details disclosed above are only for the purposes of illustration and facilitating understanding, and are not limitations. The above details do not limit the present invention to necessarily adopt the above specific details for implementation.

[0067] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments may be referred to each other. For system embodiments, since they basically correspond to method embodiments, they are described relatively simply, and the relevant parts may refer to the partial description of the method embodiments.

[0068] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms that mean "including but not limited to" and can be used interchangeably with each other. The words "or" and "and" used herein refer to the phrase "and / or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with it.

[0069] The methods and systems of the present invention can be implemented in many ways. For example, the methods and systems of the present invention can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the specific order described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the methods according to the present invention. Therefore, the present invention also covers the recording medium storing the programs for executing the methods according to the present invention.

[0070] It should also be noted that in the systems, equipment, and methods of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0071] The above description has been given for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.

Claims

1. A method for sudden fault arc diagnosis based on multi-source signal fusion, characterized in that: include: The infrasound wave signal and current signal of the low-voltage line are synchronously collected through the infrasound wave sensor and the high-precision current sensor; Preprocessing the infrasound wave signal and the current signal respectively to obtain a preprocessed infrasound wave signal and a preprocessed current signal; Performing feature extraction on the preprocessed infrasound wave signal and the preprocessed current signal respectively to obtain infrasound wave features and current features; Determining a final fault probability of each detection window according to the infrasound wave characteristics and the current characteristics; When the final fault probability continuously satisfies a preset condition within a preset detection window, it is determined that a fault arc exists in the low-voltage line.

2. The method according to claim 1, characterized in that The sampling frequency range of the infrasound signal is 0.1-20 Hz; the sampling frequency of the current signal is 20 kHz.

3. The method according to claim 1, characterized in that: Preprocessing the infrasound wave signal to obtain a preprocessed infrasound wave signal includes: Performing a minute-by-minute windowing operation on the infrasound signal using a Hamming window with a frame length of 200 ms and a frame shift of 50 ms to obtain a windowed infrasound signal; The windowed infrasound signal is subjected to discrete wavelet transform using the sym4 wavelet basis to obtain the preprocessed infrasound signal.

4. The method according to claim 3, characterized in that The formula of the Hamming window is: In the formula, N is the window length, n is the sampling point number.

5. The method according to claim 1, characterized in that Preprocessing the current signal to obtain a preprocessed current signal includes: Using a Butterworth filter to suppress noise on the current signal to obtain a current signal after noise suppression, wherein the cutoff frequency of the Butterworth filter is 2kHz-20kHz; The noise-suppressed current signal is divided into frames with a frame length of 50 ms and a frame shift of 25 ms, and a Hamming window is applied to each frame signal to obtain the preprocessed current signal.

6. The method according to claim 1, characterized in that The infrasound wave characteristics include energy entropy and envelope peak ratio, wherein the energy entropy is calculated by: Using the db4 wavelet basis, the pre-processed infrasound signal is decomposed into a 5-layer wavelet packet to generate 32 frequency bands, wherein the 32 frequency bands are equally spaced within 1-20 Hz; Extract the first i The energy of each frequency band; Determining a total energy of the 32 frequency bands based on the energy of each of the 32 frequency bands; Normalizing the total energy to obtain normalized total energy; The energy entropy is calculated according to the normalized total energy.

7. The method according to claim 6, characterized in that The calculation steps of the envelope peak ratio are: Performing Hilbert transform on the preprocessed infrasound signal to obtain an envelope; The envelope peak ratio EPAR=max(A(t) / RMS(A(T))) of the signal is calculated based on the envelope curve, where RMS is the root mean square value of the envelope and A(t) is the envelope curve.

8. The method according to claim 1, characterized in that Extracting features from the preprocessed current signal to obtain current features includes: Performing a fast Fourier transform on the preprocessed current signal to calculate the power spectral density of the preprocessed current signal; The power spectrum density is divided into characteristic frequency bands to extract the current characteristics.

9. The method according to claim 8, characterized in that The current characteristics include high-frequency energy ratio, main peak frequency offset and spectral entropy, and the power spectrum density is divided into characteristic frequency bands to extract the current characteristics, including: Extract three frequency bands of 2kHz~5kHz, 5kHz~10kHz, and 10kHz~20kHz, calculate the energy proportion of each frequency band, and determine the high-frequency energy ratio; Calculating the offset of the main peak frequency of the power spectrum density from the normal operating condition to determine the main peak frequency offset; Calculate the spectral entropy based on the power spectral density ,in , For frequency f k The power spectral density at ; is the normalized power probability distribution.

10. A sudden fault arc diagnosis device based on multi-source signal fusion, characterized in that: include: An acquisition module is used to synchronously acquire the infrasound signal and current signal of the low-voltage line through an infrasound sensor and a high-precision current sensor; A preprocessing module, used to perform preprocessing operations on the infrasound wave signal and the current signal respectively, to obtain a preprocessed infrasound wave signal and a preprocessed current signal; An extraction module, used to extract features from the preprocessed infrasound wave signal and the preprocessed current signal respectively, to obtain infrasound wave features and current features; A determination module, used to determine a final fault probability of each detection window according to the infrasound wave characteristics and the current characteristics; The determination module is used to determine whether a fault arc exists in the low-voltage line when the final fault probability continuously satisfies a preset condition in a preset detection window.

11. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 9.

12. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 9.

Images