Extremely simple auxiliary method and system for judging electrical fault based on electric arc acoustic spectrum

Abstract

The invention discloses an extremely simple auxiliary method and system for judging an electrical fault based on an arc acoustic spectrum, and belongs to the technical field of electrical fire investigation and system evidence collection. Electrical abnormal events are accurately positioned through monitoring video audio track data processing and abnormal event windowing; according to the calculation of the energy sudden increase ratio, the peak count value and the high-frequency proportion increase amount, the calculation process of the electrical abnormal event is simplified, and the calculation efficiency is improved; according to the method, the index threshold value is calculated, simple result judgment is carried out through the index threshold value, various data in the calculation process are recorded, an auxiliary judgment evidence packet is formed, evidence storage traceability of the calculation process is achieved, and due to the simplified calculation process, the requirement for calculation power resources is greatly reduced, and high adaptability is achieved in the actual application scene.

Description

Technical Field

[0001] This invention belongs to the field of electrical fire investigation and system evidence collection technology, specifically involving a simplified auxiliary method and system for judging electrical faults based on the acoustic spectrum of electric arc. Background Technology

[0002] Electrical faults (especially arc discharges) are a major cause of electrical fires, equipment damage, and power system instability. In electrical fire investigations, traditional acoustic diagnostic methods for electrical faults rely primarily on professionals using specialized audio pickup equipment for on-site data collection, combined with subjective listening and spectral observation based on personal experience. With the widespread adoption of security systems, numerous surveillance videos and their built-in or attached audio tracks have formed a comprehensive and continuously operating network of acoustic sensors. However, traditional acoustic diagnostic techniques struggle to identify acoustic events characteristic of arc discharges from these unprofessional, noisy, and inconsistent-quality surveillance audio tracks. Furthermore, these diagnostic techniques largely depend on the experience of the inspectors, failing to establish a standardized and traceable chain of evidence.

[0003] In recent years, some acoustic-based fault detection solutions have emerged. These solutions are mostly concentrated in specific industrial scenarios, relying on high-fidelity, close-range dedicated acoustic sensors and employing complex signal processing and pattern recognition algorithms (such as deep learning models, high-order spectral analysis, multi-feature fusion, etc.) for fault diagnosis and analysis. However, although these solutions are effective in some closed-loop industrial environments, their fault detection models often require a large amount of labeled data for training, and their algorithms are complex. This makes it difficult to verify and trace the calculation process and requires a large amount of computing resources. As a result, they are difficult to deploy and maintain in large-scale real-time monitoring scenarios, and therefore difficult to directly apply to the analysis of massive, heterogeneous surveillance video audio tracks.

[0004] As mentioned above, how to provide a simplified auxiliary method and system for judging electrical faults based on the acoustic spectrum of electric arcs, which has a streamlined calculation process, is traceable and verifiable, and has high implementability. Summary of the Invention

[0005] The purpose of this invention is to provide a simplified auxiliary method and system for judging electrical faults based on the acoustic spectrum of electric arc, so as to solve the above-mentioned problems existing in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, comprising: The original monitoring video audio track data is obtained, and the original monitoring video audio track data is subjected to DC removal and normalization processing to obtain pre-monitoring video audio track data. The pre-monitoring video audio track data is then subjected to bandpass filtering to obtain monitoring video audio track data. Audio feature points are located in the monitoring video audio track data to obtain audio feature points. Based on the audio feature points, an electrical abnormality event window is determined according to a preset window length. An electrical system baseline window of the same length as the electrical abnormality event window is selected in the monitoring video audio track data according to the window length. For the electrical anomaly event window and the electrical system baseline window, the root mean square value of the electrical anomaly event window and the root mean square value of the electrical system baseline window are calculated respectively. Based on the root mean square value of the electrical anomaly event window and the root mean square value of the electrical system baseline window, the energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is generated, and the spike count value in the electrical anomaly event window is calculated. The pre-monitoring video audio track data is subjected to high-frequency filtering to obtain high-frequency monitoring video audio track data. High-frequency electrical abnormality event window and high-frequency electrical system baseline window corresponding to the electrical abnormality event window and the electrical system baseline window are selected from the high-frequency monitoring video audio track data, and the high-frequency ratio increase is calculated based on the high-frequency electrical abnormality event window and the high-frequency electrical system baseline window. Obtain a preset index threshold, and based on the index threshold, classify and judge the energy surge ratio, the peak count value, and the high frequency ratio increase, obtain the classification judgment result, generate an electrical fault auxiliary judgment conclusion and generate an auxiliary judgment evidence package based on the classification judgment result.

[0007] In one possible design, the original surveillance video audio track data is acquired, and the original surveillance video audio track data is subjected to DC removal and normalization processing to obtain pre-surveillance video audio track data. Then, the pre-surveillance video audio track data is bandpass filtered to obtain surveillance video audio track data, including: Obtain the original surveillance video audio track data and calculate the average DC component in the original surveillance video audio track data; In the original surveillance video audio track data, the average DC component is removed to complete the DC removal process; Obtain a preset normalization target value, and perform amplitude normalization processing on the original monitoring video audio track data after DC removal processing according to the normalization target value, so as to reduce the amplitude of the original monitoring video audio track data after DC removal processing to obtain the pre-monitoring video audio track data. Obtain preset filtering parameters, and perform bandpass filtering on the pre-monitored video audio track data according to the filtering parameters to obtain the monitoring video audio track data. The filtering parameters include high-pass cutoff frequency, low-pass cutoff frequency, filtering slope, and filtering gain.

[0008] In one possible design, audio feature points are located in the monitoring video audio track data to obtain audio feature points. Based on the audio feature points, an electrical anomaly event window is determined according to a preset window length. Then, according to the window length, an electrical system baseline window of equal length to the electrical anomaly event window is selected from the monitoring video audio track data, including: An electric arc acoustic spectrum of the monitoring video is generated based on the audio track data of the monitoring video. The amplitude of the electric arc acoustic spectrum of the monitoring video is statistically analyzed to obtain abnormal amplitude waveform segments. The midpoint of the abnormal amplitude waveform segment is taken as the audio feature point. Obtain a preset window length, wherein the window length represents the length of the time interval of the selected time window; Based on the audio feature points, a window is selected in the arc acoustic spectrum of the monitoring video according to the window length to obtain a time window with the time corresponding to the audio feature points as the intermediate time and the window length as the time interval length of the window, which is used as the electrical abnormal event window. The amplitude of the arc acoustic spectrum of the monitoring video is statistically analyzed to select a stable amplitude waveform segment. A window is then drawn on the stable amplitude waveform segment according to the window length, and a time window of the same length as the electrical abnormal event window is selected as the electrical system baseline window. The electrical abnormal event window and the stable amplitude waveform segment do not overlap.

[0009] In one possible design, the root mean square (RMS) values ​​of the electrical anomaly event window and the electrical system baseline window are calculated, respectively. Based on these RMS values, the energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is generated, including: The root mean square value of the electrical anomaly event window is calculated using the following formula (1) for the electrical anomaly event window and the electrical system baseline window. and the root mean square value of the baseline window of the electrical system : (1) in, This indicates the total number of audio sampling points in the electrical anomaly event window. This indicates the total number of audio sampling points in the baseline window of the electrical system. This is the index number of the audio sampling point. This represents the amplitude value of the audio sampling point, and the total number of audio sampling points in the electrical anomaly event window. The total number of audio sampling points in the baseline window of the electrical system The quantities are the same; Based on the root mean square value of the electrical anomaly event window and the baseline window root mean square value of the electrical system The energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is calculated using the following formula (2). : (2) Among them, the root mean square value of the electrical abnormal event window The baseline window root mean square value of the electrical system The difference between them is used to represent the decibel difference between the electrical anomaly event window and the electrical system baseline window.

[0010] In one possible design, calculating the spike count value in the electrical anomaly event window includes: For the electrical anomaly event window, based on the amplitude values ​​of each audio sampling point in the electrical anomaly event window. Calculate the energy envelope value of each audio sampling point. And based on the energy envelope value of each audio sampling point The mean energy envelope of each audio sampling point in the electrical anomaly event window is calculated. and energy envelope standard deviation ; Based on the amplitude values ​​of each audio sampling point in the electrical anomaly event window The energy envelope mean and the energy envelope standard deviation The abnormal event detection threshold is calculated using the following formula (3). : (3) Using the aforementioned abnormal event detection threshold The energy envelope value for each audio sampling point Filter the data to select the energy envelope values. The abnormal event detection threshold is higher than the threshold. The audio sampling points are used as peak event sampling points; The number of sampling points for each spike event is counted to obtain the spike count value. .

[0011] In one possible design, the pre-monitoring video audio track data undergoes high-frequency filtering to obtain high-frequency monitoring video audio track data. High-frequency electrical anomaly event windows and high-frequency electrical system baseline windows, corresponding to the electrical anomaly event window and the electrical system baseline window, are selected from the high-frequency monitoring video audio track data. Based on the high-frequency electrical anomaly event windows and the high-frequency electrical system baseline windows, the high-frequency proportion increase is calculated, including: Obtain preset high-frequency filtering parameters, and perform bandpass filtering on the pre-monitored video audio track data according to the high-frequency filtering parameters to obtain high-frequency monitoring video audio track data; Obtain the time segment corresponding to the electrical anomaly event window and the time segment corresponding to the electrical system baseline window, so as to select a time window with the same time segment in the high-frequency monitoring video audio track data according to the time segment corresponding to the electrical anomaly event window, and select a time window with the same time segment in the high-frequency monitoring video audio track data according to the time segment corresponding to the electrical system baseline window, so as to select a time window with the same time segment in the high-frequency monitoring video audio track data, so as to select a high-frequency electrical system baseline window; The root mean square value of the high-frequency electrical anomaly event window is calculated using the following formula (4) for the electrical anomaly event window and the electrical system baseline window. and the root mean square value of the baseline window of the high-frequency electrical system : (4) in, This indicates the total number of audio sampling points in the high-frequency electrical anomaly event window. This represents the total number of audio sampling points in the baseline window of the high-frequency electrical system. This is the index number of the audio sampling point. This represents the amplitude value of the audio sampling point, and the total number of audio sampling points in the high-frequency electrical anomaly event window. The total number of audio sampling points in the baseline window of the high-frequency electrical system The quantities are the same; Based on the root mean square value of the electrical anomaly event window The baseline window root mean square value of the electrical system The root mean square value of the high-frequency electrical abnormal event window and the root mean square value of the baseline window of the high-frequency electrical system The high-frequency power ratio of the event window of the high-frequency electrical abnormality event window is calculated using the following formula (5). The baseline window high-frequency power ratio of the baseline window of the high-frequency electrical system. : (5) Among them, the root mean square value of the high-frequency electrical abnormal event window With the root mean square value of the electrical anomaly event window The difference between them is used to represent the decibel difference between the high-frequency electrical anomaly event window and the electrical anomaly event window, and the root mean square value of the high-frequency electrical system baseline window. The baseline window root mean square value of the electrical system The difference between them is used to represent the decibel difference between the high-frequency electrical system baseline window and the electrical system baseline window; Based on the high-frequency electrical anomaly event window, the high-frequency power ratio of the event window. The baseline window high-frequency power ratio of the baseline window of the high-frequency electrical system. The increase in the proportion of high-frequency frequencies is calculated using the following formula (6): (6) in, This represents an increase in the proportion of high-frequency transactions.

[0012] In one possible design, a preset index threshold is obtained. Based on the index threshold, the energy surge ratio, the peak count value, and the increase in the high-frequency proportion are classified and judged to obtain a classification judgment result. Based on the classification judgment result, an electrical fault auxiliary judgment conclusion is generated, and an auxiliary judgment evidence package is generated, including: Obtain preset indicator thresholds, wherein the indicator thresholds include energy surge ratio threshold, peak count value threshold, and high frequency ratio increase threshold; Using the energy surge ratio threshold, a first-level judgment is performed on the energy surge ratio to obtain a first-level judgment result. Using the peak count value threshold, a second-level judgment is performed on the peak count value to obtain a second-level judgment result. Using the high-frequency ratio increase threshold, a third-level judgment is performed on the high-frequency ratio increase to obtain a third-level judgment result. The first-level judgment result, the second-level judgment result, and the third-level judgment result all represent whether the standard is met or not. The results of the first-level judgment, the second-level judgment, and the third-level judgment are integrated to form a graded judgment result, and the number of qualified results in the graded judgment result is counted. Obtain a preset electrical fault auxiliary judgment conclusion table, and generate electrical fault auxiliary judgment conclusions based on the electrical fault auxiliary judgment conclusion table and the number of indicators that meet the standards. The electrical fault auxiliary judgment conclusion table is used to characterize the mapping relationship between the number of indicators that meet the standards and the electrical fault auxiliary judgment conclusions. The original monitoring video audio track data, the monitoring video audio track data, the audio feature points, the energy surge ratio, the peak count value, the high frequency ratio increase, the indicator threshold, and the classification judgment result are integrated to form an auxiliary judgment evidence package.

[0013] Secondly, the present invention provides a simplified auxiliary system for judging electrical faults based on the acoustic spectrum of an electric arc, comprising: The data acquisition unit is used to acquire the original monitoring video audio track data, perform DC removal and normalization processing on the original monitoring video audio track data to obtain the pre-monitoring video audio track data, and perform bandpass filtering on the pre-monitoring video audio track data to obtain the monitoring video audio track data. The window selection unit is used to locate audio feature points in the monitoring video audio track data, obtain audio feature points, determine an electrical abnormal event window based on the audio feature points according to a preset window length, and select an electrical system baseline window of the same length as the electrical abnormal event window in the monitoring video audio track data according to the window length. The first index calculation unit is used to calculate the root mean square value of the electrical abnormal event window and the root mean square value of the electrical system baseline window for the electrical abnormal event window and the electrical system baseline window, respectively; based on the root mean square value of the electrical abnormal event window and the root mean square value of the electrical system baseline window, generate the energy surge ratio of the electrical abnormal event window relative to the electrical system baseline window, and calculate the peak count value in the electrical abnormal event window. The second indicator calculation unit is used to perform high-frequency filtering on the pre-monitoring video audio track data to obtain high-frequency monitoring video audio track data. It selects the high-frequency electrical abnormal event window and the high-frequency electrical system baseline window corresponding to the electrical abnormal event window and the electrical system baseline window from the high-frequency monitoring video audio track data, and calculates the high-frequency ratio increase based on the high-frequency electrical abnormal event window and the high-frequency electrical system baseline window. An auxiliary judgment unit is used to obtain a preset index threshold, and based on the index threshold, to make a graded judgment on the energy surge ratio, the peak count value and the high frequency ratio increase, to obtain a graded judgment result, and to generate an electrical fault auxiliary judgment conclusion and an auxiliary judgment evidence package based on the graded judgment result.

[0014] Thirdly, the present invention provides an electronic device comprising a memory, a processor, and a transceiver connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc as described in the first aspect or any possible design of the first aspect.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc as described in the first aspect or any possible design of the first aspect.

[0016] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform a simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in the first aspect or any possible design of the first aspect.

[0017] Beneficial Effects: This invention provides a simplified auxiliary method and system for judging electrical faults based on the acoustic spectrum of an electric arc, including: First, acquiring original monitoring video audio track data, performing DC removal and normalization processing on the original monitoring video audio track data to obtain pre-monitoring video audio track data, and performing bandpass filtering on the pre-monitoring video audio track data to obtain monitoring video audio track data; Second, locating audio feature points in the monitoring video audio track data to obtain audio feature points, and determining an electrical abnormality event window based on the audio feature points according to a preset window length, and selecting an electrical system baseline window of the same length as the electrical abnormality event window from the monitoring video audio track data according to the window length; Then, calculating the root mean square value of the electrical abnormality event window and the root mean square value of the electrical system baseline window for the electrical abnormality event window and the electrical system baseline window respectively, and determining the electrical abnormality event window based on the electrical abnormality event window. The energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is generated using the root mean square value of the window and the root mean square value of the window of the electrical system baseline, and the peak count value in the electrical anomaly event window is calculated. Then, high-frequency filtering is applied to the pre-monitoring video audio track data to obtain high-frequency monitoring video audio track data. High-frequency electrical anomaly event windows and high-frequency electrical system baseline windows corresponding to the electrical anomaly event window and the electrical system baseline window are selected from the high-frequency monitoring video audio track data, and the high-frequency proportion increase is calculated based on the high-frequency electrical anomaly event windows and the high-frequency electrical system baseline windows. Finally, a preset index threshold is obtained, and based on the index threshold, the energy surge ratio, the peak count value, and the high-frequency proportion increase are classified and judged to obtain a classification judgment result. An auxiliary judgment conclusion on electrical faults and an auxiliary judgment evidence package are generated based on the classification judgment result. By monitoring video audio track data processing and abnormal event windowing, electrical anomalies can be accurately located. The calculation process for electrical anomalies is simplified by calculating the energy surge ratio, peak count value, and high frequency ratio increase, thus improving calculation efficiency. Furthermore, simple result judgment is performed through indicator thresholds, and various data in the calculation process are recorded to form an auxiliary judgment evidence package, realizing the evidence preservation and traceability of the calculation process. Due to the simplified calculation process, the demand for computing resources is greatly reduced, making it highly adaptable to practical application scenarios. Attached Figure Description

[0018] Figure 1This is a flowchart illustrating a simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, provided in an embodiment of the present invention. Figure 2 A schematic diagram of the functional structure of a simplified auxiliary system for judging electrical faults based on the acoustic spectrum of an electric arc provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0020] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0021] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0022] Example: like Figure 1 As shown, the first aspect of this embodiment provides a simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, which may include, but is not limited to, the following steps: S1. Obtain the original monitoring video audio track data, perform DC removal and normalization processing on the original monitoring video audio track data to obtain the pre-monitoring video audio track data, and perform bandpass filtering on the pre-monitoring video audio track data to obtain the monitoring video audio track data. S2. Locate audio feature points in the monitoring video audio track data to obtain audio feature points, and determine an electrical abnormal event window based on the audio feature points according to a preset window length, and select an electrical system baseline window of the same length as the electrical abnormal event window in the monitoring video audio track data according to the window length. S3. For the electrical anomaly event window and the electrical system baseline window, calculate the root mean square value of the electrical anomaly event window and the root mean square value of the electrical system baseline window, respectively. Based on the root mean square value of the electrical anomaly event window and the root mean square value of the electrical system baseline window, generate the energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window, and calculate the spike count value in the electrical anomaly event window. S4. Perform high-frequency filtering on the pre-monitoring video audio track data to obtain high-frequency monitoring video audio track data. Select the high-frequency electrical abnormality event window and the high-frequency electrical system baseline window corresponding to the electrical abnormality event window and the electrical system baseline window from the high-frequency monitoring video audio track data, and calculate the high-frequency ratio increase based on the high-frequency electrical abnormality event window and the high-frequency electrical system baseline window. S5. Obtain a preset index threshold, and based on the index threshold, classify and judge the energy surge ratio, the peak count value and the high frequency ratio increase, obtain the classification judgment result, generate an electrical fault auxiliary judgment conclusion and generate an auxiliary judgment evidence package based on the classification judgment result.

[0023] In one possible design, step S1 involves acquiring the original monitoring video audio track data, performing DC removal and normalization processing on the original monitoring video audio track data to obtain pre-monitoring video audio track data, and then performing bandpass filtering on the pre-monitoring video audio track data to obtain the monitoring video audio track data. This step can be decomposed into, but is not limited to, the following steps S11-S14, specifically including: S11. Obtain the original monitoring video audio track data and calculate the average DC component in the original monitoring video audio track data; S12. Remove the average DC component from the original monitoring video audio track data to complete the DC removal process; S13. Obtain a preset normalization target value, and perform amplitude normalization processing on the original monitoring video audio track data that has completed DC removal processing according to the normalization target value, so as to reduce the amplitude of the original monitoring video audio track data that has completed DC removal processing, and obtain the pre-monitoring video audio track data. S14. Obtain preset filtering parameters, and perform bandpass filtering on the pre-monitored video audio track data according to the filtering parameters to obtain monitoring video audio track data, wherein the filtering parameters include high-pass cutoff frequency, low-pass cutoff frequency, filtering slope and filtering gain.

[0024] It should be noted that the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of electric arc provided in this embodiment has eliminated DC offset (DC removal processing), standardized and unified amplitude reference (amplitude normalization processing) for the monitoring video audio track data, and highlighted the arc-related frequency band (bandpass filtering) to ensure that the calculation and analysis of the data in the subsequent auxiliary method have consistency and comparability.

[0025] In one possible design, step S2 involves locating audio feature points in the monitoring video audio track data to obtain these audio feature points. Based on these audio feature points, an electrical anomaly event window is determined according to a preset window length. Then, an electrical system baseline window of equal length to the electrical anomaly event window is selected from the monitoring video audio track data according to the window length. This can be broken down into steps S21-S24, specifically including: S21. Generate an acoustic spectrum of the monitoring video arc based on the monitoring video audio track data, perform amplitude statistics on the monitoring video arc acoustic spectrum to obtain abnormal amplitude waveform segments, and take the midpoint of the abnormal amplitude waveform segment as an audio feature point. S22. Obtain a preset window length, wherein the window length represents the length of the time interval of the selected time window; S23. Based on the audio feature points, according to the window length, a window is selected in the arc acoustic spectrum of the monitoring video to obtain a time window with the time corresponding to the audio feature points as the intermediate time and the window length as the time interval length of the window, which is used as the electrical abnormal event window. S24. Perform amplitude statistics on the acoustic spectrum of the electric arc in the monitoring video to select a stable amplitude waveform segment. Window the stable amplitude waveform segment according to the window length to select a time window of the same length as the electrical abnormal event window as the electrical system baseline window. The electrical abnormal event window and the stable amplitude waveform segment do not overlap.

[0026] It should be noted that the simplified auxiliary method provided in this embodiment, through this equal-length windowing method, ensures that all subsequent calculations are based on a fair benchmark of equal length, same source, and same processing, so as to ensure that the results (electrical fault auxiliary judgment conclusions) obtained by the simplified auxiliary method provided in this embodiment have the reliability of results and the verifiability of indicators.

[0027] Specifically, when selecting windows, abnormal amplitude waveform segments can be obtained based on amplitude statistics. Multiple audio feature points are selected within these abnormal amplitude waveform segments, and each audio feature point can indicate an abnormality in the arc acoustic spectrum (including a sudden increase in amplitude, the appearance of dense pulses, or a significant increase in high-frequency components). Multiple time intervals are selected around each audio feature point using a preset window length (preferably 2.0000s) as electrical abnormal event windows, thus obtaining multiple electrical abnormal event windows. For each electrical abnormal event window, a non-overlapping, equal-length electrical system baseline window is selected to form multiple event-baseline matching window pairs. For each pair of event-baseline matching window pairs, the subsequent calculation process is executed independently, which provides batch processing functionality for electrical fire investigations, avoids the efficiency reduction caused by single-line calculations, and improves the efficiency of auxiliary diagnosis.

[0028] In one possible design, step S3 involves calculating the root mean square (RMS) value of the electrical anomaly event window and the root mean square (RMS) value of the electrical system baseline window, respectively. Based on these two values, an energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is generated. This step can be decomposed, but is not limited to, the following steps S31-S3, specifically including: S31. Calculate the root mean square value of the electrical anomaly event window and the electrical system baseline window using the following formula (1). and the root mean square value of the baseline window of the electrical system : (1) in, This indicates the total number of audio sampling points in the electrical anomaly event window. This indicates the total number of audio sampling points in the baseline window of the electrical system. This is the index number of the audio sampling point. This represents the amplitude value of the audio sampling point, and the total number of audio sampling points in the electrical anomaly event window. The total number of audio sampling points in the baseline window of the electrical system The quantities are the same; S32. Based on the root mean square value of the electrical anomaly event window and the baseline window root mean square value of the electrical system The energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is calculated using the following formula (2). : (2) Among them, the root mean square value of the electrical abnormal event window The baseline window root mean square value of the electrical system The difference between them is used to represent the decibel difference between the electrical anomaly event window and the electrical system baseline window.

[0029] In one possible design, step S3, calculating the spike count value in the electrical anomaly event window, can be broken down into steps S33-S35, specifically including: S33. For the electrical anomaly event window, based on the amplitude values ​​of each audio sampling point in the electrical anomaly event window... Calculate the energy envelope value of each audio sampling point. And based on the energy envelope value of each audio sampling point The mean energy envelope of each audio sampling point in the electrical anomaly event window is calculated. and energy envelope standard deviation ; S34. Based on the amplitude values ​​of each audio sampling point in the electrical anomaly event window. The energy envelope mean and the energy envelope standard deviation The abnormal event detection threshold is calculated using the following formula (3). : (3) Using the aforementioned abnormal event detection threshold The energy envelope value for each audio sampling point Filter the data to select the energy envelope values. The abnormal event detection threshold is higher than the threshold. The audio sampling points are used as peak event sampling points; S35. Count the number of sampling points for each spike event to obtain the spike count value. .

[0030] It should be noted that the simplified auxiliary method in this embodiment, when sampling peak events, may include, but is not limited to, setting a sampling interval (e.g., 20 ms) to ensure that there is no duplicate sampling of abnormal events between different peak event sampling points, thus ensuring the accuracy of the statistical peak count value. The accuracy.

[0031] In one possible design, in step S4, high-frequency filtering is performed on the pre-monitoring video audio track data to obtain high-frequency monitoring video audio track data. High-frequency electrical anomaly event windows and high-frequency electrical system baseline windows corresponding to the electrical anomaly event window and the electrical system baseline window are selected from the high-frequency monitoring video audio track data. The high-frequency proportion increase is calculated based on the high-frequency electrical anomaly event windows and the high-frequency electrical system baseline windows. This can be, but is not limited to, decomposed into the following steps S41-S45, specifically including: S41. Obtain preset high-frequency filtering parameters, and perform bandpass filtering on the pre-monitored video audio track data according to the high-frequency filtering parameters to obtain high-frequency monitoring video audio track data; S42. Obtain the time segment corresponding to the electrical anomaly event window and the time segment corresponding to the electrical system baseline window, so as to select a time window with the same time segment in the high-frequency monitoring video audio track data according to the time segment corresponding to the electrical anomaly event window, and select a time window with the same time segment in the high-frequency monitoring video audio track data according to the time segment corresponding to the electrical system baseline window, so as to select a high-frequency electrical system baseline window; S43. Calculate the root mean square value of the high-frequency electrical anomaly event window and the electrical system baseline window using the following formula (4). and the root mean square value of the baseline window of the high-frequency electrical system : (4) in, This indicates the total number of audio sampling points in the high-frequency electrical anomaly event window. This represents the total number of audio sampling points in the baseline window of the high-frequency electrical system. This is the index number of the audio sampling point. This represents the amplitude value of the audio sampling point, and the total number of audio sampling points in the high-frequency electrical anomaly event window. The total number of audio sampling points in the baseline window of the high-frequency electrical system The quantities are the same; S44. Based on the root mean square value of the electrical anomaly event window The baseline window root mean square value of the electrical system The root mean square value of the high-frequency electrical abnormal event window and the root mean square value of the baseline window of the high-frequency electrical system The high-frequency power ratio of the event window of the high-frequency electrical abnormality event window is calculated using the following formula (5). The baseline window high-frequency power ratio of the baseline window of the high-frequency electrical system. : (5) Among them, the root mean square value of the high-frequency electrical abnormal event window With the root mean square value of the electrical anomaly event window The difference between them is used to represent the decibel difference between the high-frequency electrical anomaly event window and the electrical anomaly event window, and the root mean square value of the high-frequency electrical system baseline window. The baseline window root mean square value of the electrical system The difference between them is used to represent the decibel difference between the high-frequency electrical system baseline window and the electrical system baseline window; S45. Based on the high-frequency electrical anomaly event window, the high-frequency power ratio of the event window. The baseline window high-frequency power ratio of the baseline window of the high-frequency electrical system. The increase in the proportion of high-frequency frequencies is calculated using the following formula (6): (6) in, This represents an increase in the proportion of high-frequency transactions.

[0032] In one possible design, step S5 involves obtaining a preset index threshold. Based on the index threshold, the energy surge ratio, the peak count value, and the increase in the high-frequency proportion are classified and judged to obtain a classification judgment result. An auxiliary judgment conclusion on electrical faults and an auxiliary judgment evidence package are generated based on the classification judgment result. This can be broken down into, but is not limited to, the following steps S51-S55, specifically including: S51. Obtain preset indicator thresholds, wherein the indicator thresholds include energy surge ratio threshold, peak count value threshold, and high frequency ratio increase threshold; S52. Using the energy surge ratio threshold, a first-level judgment is performed on the energy surge ratio to obtain a first-level judgment result. Using the peak count value threshold, a second-level judgment is performed on the peak count value to obtain a second-level judgment result. Using the high-frequency ratio increase threshold, a third-level judgment is performed on the high-frequency ratio increase to obtain a third-level judgment result. The first-level judgment result, the second-level judgment result, and the third-level judgment result all represent whether the standard is met or not. S53. Integrate the first-level judgment results, the second-level judgment results, and the third-level judgment results to form a graded judgment result, and count the number of compliances in the graded judgment results; S54. Obtain a preset electrical fault auxiliary judgment conclusion table, and generate an electrical fault auxiliary judgment conclusion based on the electrical fault auxiliary judgment conclusion table and the number of indicators that meet the standards. The electrical fault auxiliary judgment conclusion table is used to characterize the mapping relationship between the number of indicators that meet the standards and the electrical fault auxiliary judgment conclusion. S55. Integrate the original monitoring video audio track data, the monitoring video audio track data, the audio feature points, the energy surge ratio, the peak count value, the high frequency ratio increase, the indicator threshold, and the classification judgment result to form an auxiliary judgment evidence package.

[0033] In one possible implementation, the simplified auxiliary method provided in this embodiment, after forming the auxiliary judgment evidence package in step S5, may also include, but is not limited to, the following steps S56-S5, specifically: S56. The auxiliary judgment evidence package is sent to the electrical fault diagnosis database for storage; S56. Extract the auxiliary judgment evidence package from the electrical fault diagnosis database through the data monitoring terminal, extract its features to obtain auxiliary judgment feature evidence, and perform structured processing and format standardization processing on the auxiliary judgment feature evidence to obtain auxiliary judgment standard feature evidence. S56. Obtain a preset event card template, fill the auxiliary judgment standard feature evidence into the event card template, and form the current electrical anomaly auxiliary diagnosis event card; S57. The current electrical anomaly auxiliary diagnostic event card is visualized through the data monitoring terminal.

[0034] It should be noted that in the simplified auxiliary method provided in this embodiment, the energy surge ratio, the peak count value, and the high frequency ratio increase are graded and judged according to preset indicator thresholds (e.g., the energy surge ratio threshold is 5, the peak count value threshold is 4, and the high frequency ratio increase is 0.25). It is only necessary to judge whether the calculated value is higher than the indicator threshold. If it is higher, the indicator is considered to meet the standard; otherwise, the indicator is considered to fail to meet the standard. Based on the number of indicators that meet the standard, a corresponding electrical fault auxiliary judgment conclusion is generated (e.g., when the number of indicators that meet the standard exceeds 2, the current electrical abnormal event is taken as the key target and the event is given priority for fusion analysis).

[0035] like Figure 2 As shown, the second aspect of this embodiment provides a hardware system for implementing the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc as described in the first aspect of the embodiment, including: The data acquisition unit is used to acquire the original monitoring video audio track data, perform DC removal and normalization processing on the original monitoring video audio track data to obtain the pre-monitoring video audio track data, and perform bandpass filtering on the pre-monitoring video audio track data to obtain the monitoring video audio track data. The window selection unit is used to locate audio feature points in the monitoring video audio track data, obtain audio feature points, determine an electrical abnormal event window based on the audio feature points according to a preset window length, and select an electrical system baseline window of the same length as the electrical abnormal event window in the monitoring video audio track data according to the window length. The first index calculation unit is used to calculate the root mean square value of the electrical abnormal event window and the root mean square value of the electrical system baseline window for the electrical abnormal event window and the electrical system baseline window, respectively; based on the root mean square value of the electrical abnormal event window and the root mean square value of the electrical system baseline window, generate the energy surge ratio of the electrical abnormal event window relative to the electrical system baseline window, and calculate the peak count value in the electrical abnormal event window. The second indicator calculation unit is used to perform high-frequency filtering on the pre-monitoring video audio track data to obtain high-frequency monitoring video audio track data. It selects the high-frequency electrical abnormal event window and the high-frequency electrical system baseline window corresponding to the electrical abnormal event window and the electrical system baseline window from the high-frequency monitoring video audio track data, and calculates the high-frequency ratio increase based on the high-frequency electrical abnormal event window and the high-frequency electrical system baseline window. An auxiliary judgment unit is used to obtain a preset index threshold, and based on the index threshold, to make a graded judgment on the energy surge ratio, the peak count value and the high frequency ratio increase, to obtain a graded judgment result, and to generate an electrical fault auxiliary judgment conclusion and an auxiliary judgment evidence package based on the graded judgment result.

[0036] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0037] like Figure 3 As shown, the third aspect of this embodiment provides an electronic device, including: a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc as described in the first aspect of the embodiment.

[0038] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0039] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee transceiver (a low-power LAN protocol based on the IEEE 802.15.4 standard), a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0040] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0041] The fourth aspect of this embodiment provides a storage medium that stores instructions containing the simplified auxiliary method for judging electrical faults based on the arc acoustic spectrum as described in the first aspect of the embodiment. That is, the storage medium stores instructions that, when the instructions are run on a computer, execute the simplified auxiliary method for judging electrical faults based on the arc acoustic spectrum as described in the first aspect of the embodiment.

[0042] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0043] The working process, working details, and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0044] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc as described in the first aspect of this embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0045] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, characterized in that, include: The original monitoring video audio track data is obtained, and the original monitoring video audio track data is subjected to DC removal and normalization processing to obtain pre-monitoring video audio track data. The pre-monitoring video audio track data is then subjected to bandpass filtering to obtain monitoring video audio track data. Audio feature points are located in the monitoring video audio track data to obtain audio feature points. Based on the audio feature points, an electrical abnormality event window is determined according to a preset window length. An electrical system baseline window of the same length as the electrical abnormality event window is selected in the monitoring video audio track data according to the window length. For the electrical anomaly event window and the electrical system baseline window, the root mean square value of the electrical anomaly event window and the root mean square value of the electrical system baseline window are calculated respectively. Based on the root mean square value of the electrical anomaly event window and the root mean square value of the electrical system baseline window, the energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is generated, and the spike count value in the electrical anomaly event window is calculated. The pre-monitoring video audio track data is subjected to high-frequency filtering to obtain high-frequency monitoring video audio track data. High-frequency electrical abnormality event window and high-frequency electrical system baseline window corresponding to the electrical abnormality event window and the electrical system baseline window are selected from the high-frequency monitoring video audio track data, and the high-frequency ratio increase is calculated based on the high-frequency electrical abnormality event window and the high-frequency electrical system baseline window. Obtain a preset index threshold, and based on the index threshold, classify and judge the energy surge ratio, the peak count value, and the high frequency ratio increase, obtain the classification judgment result, generate an electrical fault auxiliary judgment conclusion and generate an auxiliary judgment evidence package based on the classification judgment result.

2. The simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in claim 1, is characterized in that... The process involves acquiring raw surveillance video audio track data, performing DC removal and normalization on the raw surveillance video audio track data to obtain pre-surveillance video audio track data, and then performing bandpass filtering on the pre-surveillance video audio track data to obtain surveillance video audio track data, including: Obtain the original surveillance video audio track data and calculate the average DC component in the original surveillance video audio track data; In the original surveillance video audio track data, the average DC component is removed to complete the DC removal process; Obtain a preset normalization target value, and perform amplitude normalization processing on the original monitoring video audio track data after DC removal processing according to the normalization target value, so as to reduce the amplitude of the original monitoring video audio track data after DC removal processing to obtain the pre-monitoring video audio track data. Obtain preset filtering parameters, and perform bandpass filtering on the pre-monitored video audio track data according to the filtering parameters to obtain the monitoring video audio track data. The filtering parameters include high-pass cutoff frequency, low-pass cutoff frequency, filtering slope, and filtering gain.

3. The simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in claim 1, is characterized in that... The monitoring video audio track data is used to locate audio feature points, and an electrical anomaly event window is determined based on the audio feature points according to a preset window length. Then, an electrical system baseline window of equal length to the electrical anomaly event window is selected from the monitoring video audio track data according to the window length, including: An electric arc acoustic spectrum of the monitoring video is generated based on the audio track data of the monitoring video. The amplitude of the electric arc acoustic spectrum of the monitoring video is statistically analyzed to obtain abnormal amplitude waveform segments. The midpoint of the abnormal amplitude waveform segment is taken as the audio feature point. Obtain a preset window length, wherein the window length represents the length of the time interval of the selected time window; Based on the audio feature points, a window is selected in the arc acoustic spectrum of the monitoring video according to the window length to obtain a time window with the time corresponding to the audio feature points as the intermediate time and the window length as the time interval length of the window, which is used as the electrical abnormal event window. The amplitude of the arc acoustic spectrum of the monitoring video is statistically analyzed to select a stable amplitude waveform segment. A window is then drawn on the stable amplitude waveform segment according to the window length, and a time window of the same length as the electrical abnormal event window is selected as the electrical system baseline window. The electrical abnormal event window and the stable amplitude waveform segment do not overlap.

4. The simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in claim 1, is characterized in that... For the electrical anomaly event window and the electrical system baseline window, the root mean square value of the electrical anomaly event window and the root mean square value of the electrical system baseline window are calculated respectively. Based on the root mean square values ​​of the electrical anomaly event window and the electrical system baseline window, the energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is generated, including: The root mean square value of the electrical anomaly event window is calculated using the following formula (1) for the electrical anomaly event window and the electrical system baseline window. and the root mean square value of the baseline window of the electrical system : （1） in, This indicates the total number of audio sampling points in the electrical anomaly event window. This indicates the total number of audio sampling points in the baseline window of the electrical system. This is the index number of the audio sampling point. This represents the amplitude value of the audio sampling point, and the total number of audio sampling points in the electrical anomaly event window. The total number of audio sampling points in the baseline window of the electrical system The quantities are the same; Based on the root mean square value of the electrical anomaly event and the baseline window root mean square value of the electrical system The energy surge ratio of the electrical anomaly event window relative to the electrical system baseline window is calculated using the following formula (2). : （2） Among them, the root mean square value of the electrical abnormal event window The baseline window root mean square value of the electrical system The difference between them is used to represent the decibel difference between the electrical anomaly event window and the electrical system baseline window.

5. The simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in claim 4, is characterized in that... Calculate the spike count value in the electrical anomaly event window, including: For the electrical anomaly event window, based on the amplitude values ​​of each audio sampling point in the electrical anomaly event window. Calculate the energy envelope value of each audio sampling point. And based on the energy envelope value of each audio sampling point The mean energy envelope of each audio sampling point in the electrical anomaly event window is calculated. and energy envelope standard deviation ; Based on the amplitude values ​​of each audio sampling point in the electrical anomaly event window The energy envelope mean and the energy envelope standard deviation The abnormal event detection threshold is calculated using the following formula (3). : （3） Using the aforementioned abnormal event detection threshold The energy envelope value for each audio sampling point Filter the data to select the energy envelope values. The abnormal event detection threshold is higher than the threshold. The audio sampling points are used as peak event sampling points; The number of sampling points for each spike event is counted to obtain the spike count value. .

6. The simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in claim 4, is characterized in that... The pre-monitoring video audio track data is subjected to high-frequency filtering to obtain high-frequency monitoring video audio track data. High-frequency electrical anomaly event windows and high-frequency electrical system baseline windows corresponding to the electrical anomaly event window and the electrical system baseline window are selected from the high-frequency monitoring video audio track data. The high-frequency proportion increase is calculated based on the high-frequency electrical anomaly event windows and the high-frequency electrical system baseline windows, including: Obtain preset high-frequency filtering parameters, and perform bandpass filtering on the pre-monitored video audio track data according to the high-frequency filtering parameters to obtain high-frequency monitoring video audio track data; Obtain the time segment corresponding to the electrical anomaly event window and the time segment corresponding to the electrical system baseline window, so as to select a time window with the same time segment in the high-frequency monitoring video audio track data according to the time segment corresponding to the electrical anomaly event window, and select a time window with the same time segment in the high-frequency monitoring video audio track data according to the time segment corresponding to the electrical system baseline window, so as to select a time window with the same time segment in the high-frequency monitoring video audio track data, so as to select a high-frequency electrical system baseline window; The root mean square value of the high-frequency electrical anomaly event window is calculated using the following formula (4) for the electrical anomaly event window and the electrical system baseline window. and the root mean square value of the baseline window of the high-frequency electrical system : （4） in, This indicates the total number of audio sampling points in the high-frequency electrical anomaly event window. This represents the total number of audio sampling points in the baseline window of the high-frequency electrical system. This is the index number of the audio sampling point. This represents the amplitude value of the audio sampling point, and the total number of audio sampling points in the high-frequency electrical anomaly event window. The total number of audio sampling points in the baseline window of the high-frequency electrical system The quantities are the same; Based on the root mean square value of the electrical anomaly event The baseline window root mean square value of the electrical system The root mean square value of the high-frequency electrical abnormal event window and the root mean square value of the baseline window of the high-frequency electrical system The high-frequency power ratio of the event window of the high-frequency electrical abnormality event window is calculated using the following formula (5). The baseline window high-frequency power ratio of the baseline window of the high-frequency electrical system. : （5） Among them, the root mean square value of the high-frequency electrical abnormal event window With the root mean square value of the electrical abnormality event window The difference between them represents the decibel difference between the high-frequency electrical anomaly event window and the electrical anomaly event window, and the root mean square value of the high-frequency electrical system baseline window. The baseline window root mean square value of the electrical system The difference between them is used to represent the decibel difference between the high-frequency electrical system baseline window and the electrical system baseline window; Based on the high-frequency electrical anomaly event window, the high-frequency power ratio of the event window. The baseline window high-frequency power ratio of the baseline window of the high-frequency electrical system. The increase in the proportion of high-frequency frequencies is calculated using the following formula (6): （6） in, This represents an increase in the proportion of high-frequency transactions.

7. The simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in claim 1, is characterized in that... Obtain a preset indicator threshold, and based on the indicator threshold, classify and judge the energy surge ratio, the peak count value, and the increase in the high-frequency proportion to obtain a classification judgment result. Generate an auxiliary judgment conclusion on electrical faults and an auxiliary judgment evidence package based on the classification judgment result, including: Obtain preset indicator thresholds, wherein the indicator thresholds include energy surge ratio threshold, peak count value threshold, and high frequency ratio increase threshold; Using the energy surge ratio threshold, a first-level judgment is performed on the energy surge ratio to obtain a first-level judgment result. Using the peak count value threshold, a second-level judgment is performed on the peak count value to obtain a second-level judgment result. Using the high-frequency ratio increase threshold, a third-level judgment is performed on the high-frequency ratio increase to obtain a third-level judgment result. The first-level judgment result, the second-level judgment result, and the third-level judgment result all represent whether the standard is met or not. The results of the first-level judgment, the second-level judgment, and the third-level judgment are integrated to form a graded judgment result, and the number of qualified results in the graded judgment result is counted. Obtain a preset electrical fault auxiliary judgment conclusion table, and generate electrical fault auxiliary judgment conclusions based on the electrical fault auxiliary judgment conclusion table and the number of indicators that meet the standards. The electrical fault auxiliary judgment conclusion table is used to characterize the mapping relationship between the number of indicators that meet the standards and the electrical fault auxiliary judgment conclusions. The original monitoring video audio track data, the monitoring video audio track data, the audio feature points, the energy surge ratio, the peak count value, the high frequency ratio increase, the indicator threshold, and the classification judgment result are integrated to form an auxiliary judgment evidence package.

8. A simplified auxiliary system for judging electrical faults based on the acoustic spectrum of an electric arc, characterized in that, The simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc, as described in any one of claims 1 to 7, includes: The data acquisition unit is used to acquire the original monitoring video audio track data, perform DC removal and normalization processing on the original monitoring video audio track data to obtain the pre-monitoring video audio track data, and perform bandpass filtering on the pre-monitoring video audio track data to obtain the monitoring video audio track data. The window selection unit is used to locate audio feature points in the monitoring video audio track data, obtain audio feature points, determine an electrical abnormal event window based on the audio feature points according to a preset window length, and select an electrical system baseline window of the same length as the electrical abnormal event window in the monitoring video audio track data according to the window length. The first index calculation unit is used to calculate the root mean square value of the electrical abnormal event window and the root mean square value of the electrical system baseline window for the electrical abnormal event window and the electrical system baseline window, respectively; based on the root mean square value of the electrical abnormal event window and the root mean square value of the electrical system baseline window, generate the energy surge ratio of the electrical abnormal event window relative to the electrical system baseline window, and calculate the peak count value in the electrical abnormal event window. The second indicator calculation unit is used to perform high-frequency filtering on the pre-monitoring video audio track data to obtain high-frequency monitoring video audio track data. It selects the high-frequency electrical abnormal event window and the high-frequency electrical system baseline window corresponding to the electrical abnormal event window and the electrical system baseline window from the high-frequency monitoring video audio track data, and calculates the high-frequency ratio increase based on the high-frequency electrical abnormal event window and the high-frequency electrical system baseline window. An auxiliary judgment unit is used to obtain a preset index threshold, and based on the index threshold, to make a graded judgment on the energy surge ratio, the peak count value and the high frequency ratio increase, to obtain a graded judgment result, and to generate an electrical fault auxiliary judgment conclusion and an auxiliary judgment evidence package based on the graded judgment result.

9. An electronic device, characterized in that, The device includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the simplified auxiliary method for judging electrical faults based on the acoustic spectrum of an electric arc as described in any one of claims 1 to 7.

Images