Method, device and equipment for monitoring external damage of buried cable and medium

Abstract

The invention relates to the technical field of power equipment monitoring, in particular to a method, device, equipment and medium for monitoring external damage of a buried cable, and the method comprises the steps: collecting radar signals of a surrounding environment in real time based on a millimeter wave radar unit, and detecting whether there is engineering mechanical equipment in the surrounding environment through a trained engineering mechanical equipment recognition model; if it is detected that the engineering mechanical equipment exists in the surrounding environment, the relative position between the intelligent ground nail and the engineering mechanical equipment is calculated, a voiceprint signal of the surrounding environment is collected based on a voiceprint collection unit, and the category of the engineering mechanical equipment is obtained by entering an engineering mechanical equipment category recognition model library; and collecting vibration signals of the surrounding environment based on the three-axis vibration unit, and calculating the distance between the vibration source and the buried cable. Therefore, based on an artificial intelligence algorithm in combination with multiple features, the engineering machinery equipment category and the vibration source position of the external damage behavior are accurately identified, and the monitoring accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power equipment monitoring, and in particular to a method, device, equipment and medium for monitoring external damage of underground cables. Background Art

[0002] It is extremely important to prevent underground cables from external damage. When planning the cable laying, try to avoid areas with frequent construction, geologically unstable areas, and areas that are easily damaged by external forces; set up obvious cable markings on the ground, such as cable piles, signs, etc.; and formulate a strict inspection system to inspect the cable lines regularly.

[0003] Smart ground nails are intelligent devices used to monitor the conditions of specific areas (such as around cables), and play an important role in ensuring infrastructure safety and improving operation and maintenance efficiency. However, most smart ground nails on the market currently use simple vibration threshold judgment to monitor, which cannot judge complex vibration conditions, easily leading to frequent false alarms and failing to meet the needs of accurate early warning. Summary of the invention

[0004] In order to overcome the deficiencies in the prior art, the present application provides a method, device, equipment and medium for monitoring external rupture of buried cables, which can accurately identify external rupture behavior based on artificial intelligence algorithms and combine multiple features to improve monitoring accuracy.

[0005] In a first aspect, the present application provides a method for monitoring external damage of an underground cable, which is applied to smart ground nails, wherein the smart ground nails are deployed at intervals above the underground cable that is resistant to external damage, and the method comprises the following steps:

[0006] Based on the millimeter wave radar unit, radar signals of the surrounding environment are collected in real time, and the collected radar signals are input into the trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment;

[0007] If construction machinery equipment is detected in the surrounding environment, the relative position between the smart ground nail and the construction machinery equipment is calculated according to the collected radar signal, and the voiceprint signal of the surrounding environment is collected based on the voiceprint collection unit, and the vibration signal of the surrounding environment is collected based on the three-axis vibration unit;

[0008] The collected voiceprint signal is input into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment; and the distance between the vibration source and the engineering machinery equipment is calculated based on the collected vibration signal.

[0009] In a possible implementation, the method further includes the following steps:

[0010] The relative position between the smart ground nail and the engineering machinery equipment, the type of the engineering machinery equipment, and the distance between the vibration source and the buried cable are sent to the cloud platform in real time for visual display; and if the distance between the vibration source and the buried cable is less than a set threshold, an alarm is issued.

[0011] In a possible implementation manner, calculating the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal includes the following steps:

[0012] The collected radar signals are formed into a series of three-element arrays including azimuth, distance and intensity; wherein the azimuth measurement range and the distance measurement range of the millimeter wave radar unit are evenly divided into a plurality of arrays;

[0013] Mapping a series of the three-element arrays onto a predefined grid to construct a two-dimensional matrix, and traversing all elements in the two-dimensional matrix to mark elements with intensity values ​​greater than a set threshold as possible valid signal points;

[0014] Peak detection is performed on the possible valid signal points, and a clustering algorithm is used to determine the cell position where the engineering machinery equipment is located, and the relative position between the smart ground nail and the engineering machinery equipment is obtained according to the cell position and the distance step for constructing the two-dimensional matrix.

[0015] In a possible implementation manner, inputting the collected voiceprint signal into a construction machinery equipment category recognition model library for comparison to obtain the category of the construction machinery equipment includes the following steps:

[0016] Preprocessing the collected voiceprint signal to obtain a voiceprint frame sequence to be measured; the preprocessing includes at least one of windowing, framing, and denoising;

[0017] Extracting features from the voiceprint frame sequence to be tested to obtain feature data of the voiceprint to be tested;

[0018] The voiceprint feature data to be tested is input into the engineering machinery equipment category recognition model library for comparison, the similarity between the voiceprint feature data to be tested and each feature vector in the engineering machinery equipment category recognition model library is calculated, and the category of the engineering machinery equipment is determined according to the similarity; wherein the engineering machinery equipment category recognition model library stores feature vectors of voiceprint signals of different categories of engineering machinery equipment under different working conditions.

[0019] In a possible implementation manner, calculating the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal comprises the following steps:

[0020] Performing Fourier transform on the vibration signals of the three axes collected to obtain a frequency domain signal of each axis, and calculating the corresponding amplitude spectrum and phase spectrum of the frequency domain signal of each axis;

[0021] Selecting a reference axis from the three axes and calculating the phase differences of the other two axes relative to the reference axis;

[0022] The distance between the vibration source and the engineering machinery equipment is calculated according to the phase difference and the wave speed.

[0023] In a possible implementation manner, the distance between the vibration source and the engineering machinery equipment is calculated by the following formula:

[0024]

[0025] Where v is the wave velocity, Δφ is the phase difference, and f is the frequency of the vibration signal.

[0026] In a second aspect, the present application provides a device for monitoring external damage of underground cables, which is applied to smart ground nails, wherein the smart ground nails are deployed at intervals above the underground cables that are resistant to external damage, and the device comprises:

[0027] The first monitoring module is used to collect radar signals of the surrounding environment in real time based on the millimeter wave radar unit, and input the collected radar signals into a trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment;

[0028] The second monitoring module is used to calculate the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal if the existence of engineering machinery equipment is detected in the surrounding environment, and collect the voiceprint signal of the surrounding environment based on the voiceprint collection unit, and collect the vibration signal of the surrounding environment based on the three-axis vibration unit;

[0029] The measuring module is used to input the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment; and calculate the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal.

[0030] In a third aspect, the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for monitoring external damage of buried cables as described in any one of the first aspects are performed.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for monitoring external damage of a buried cable as described in any one of the first aspects are executed.

[0032] The present embodiment provides a method, device, equipment and medium for monitoring external damage of buried cables. The method collects radar signals of the surrounding environment in real time based on a millimeter wave radar unit, and inputs the collected radar signals into a trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment; if it is detected that there is engineering machinery equipment in the surrounding environment, the relative position between the smart ground nail and the engineering machinery equipment is calculated based on the collected radar signals, and the soundprint signal of the surrounding environment is collected based on the soundprint collection unit, and the vibration signal of the surrounding environment is collected based on the three-axis vibration unit; the collected soundprint signal is input into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment; and the distance between the vibration source and the engineering machinery equipment is calculated based on the collected vibration signal. Therefore, based on the artificial intelligence algorithm combined with multiple features, the category and position of the engineering machinery equipment with external damage behavior can be accurately identified, and the distance between the vibration source and the engineering machinery equipment is calculated, thereby improving the monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A flow chart of a method for monitoring external damage of an underground cable according to an embodiment of the present application is shown;

[0035] Figure 2 A flow chart of calculating the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal according to an embodiment of the present application is shown;

[0036] Figure 3 A flowchart of inputting the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment is shown in an embodiment of the present application;

[0037] Figure 4 A flow chart of calculating the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal according to an embodiment of the present application is shown;

[0038] Figure 5A schematic diagram of the structure of a device for monitoring external damage of a buried cable according to an embodiment of the present application is shown;

[0039] Figure 6 A structural block diagram of an electronic device described in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0041] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0042] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0043] In view of the technical problems raised by the background technology, the present application provides a method, device, equipment and medium for monitoring external damage of buried cables, which can accurately identify external damage behavior based on artificial intelligence algorithm combined with multiple features and improve monitoring accuracy.

[0044] In one embodiment, see the attached specification Figure 1 The present application provides a method for monitoring external damage of underground cables, which is applied to smart ground nails. The smart ground nails are deployed at intervals above the underground cables that are resistant to external damage. The method includes the following steps:

[0045] S1. Collecting radar signals of the surrounding environment in real time based on the millimeter wave radar unit, and inputting the collected radar signals into a trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment;

[0046] S2. If it is detected that there is engineering machinery in the surrounding environment, the relative position between the smart ground nail and the engineering machinery is calculated according to the collected radar signal, and the voiceprint signal of the surrounding environment is collected based on the voiceprint collection unit, and the vibration signal of the surrounding environment is collected based on the three-axis vibration unit;

[0047] S3, inputting the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment; and calculating the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal.

[0048] In order to clearly understand the technical solution of the embodiment of the present invention, the application scenario can be illustrated first. In this application, the smart ground nails are deployed above the cables that need to be protected from external force damage. For example, one is installed every 20 meters, and the prefabricated cement base is used to achieve rapid installation, deployment and replacement, covering the key areas along the cable. The configured millimeter wave radar unit, voiceprint collection unit and three-axis vibration unit monitor in real time whether the construction machinery and equipment such as hook machines, excavators, impact drills, and cutting machines are working in the area, and issue early warnings to avoid cable damage, thereby reducing unplanned power outages caused by external cable damage and improving the stability of power supply.

[0049] In step S1, the millimeter wave radar unit transmits electromagnetic waves in the millimeter wave frequency band through the antenna in real time. These electromagnetic waves will be reflected after encountering an object, and the reflected waves are received by the radar antenna. By measuring the echo signals at different azimuth angles, the position information of the target object in space can be constructed, thereby realizing the imaging of the surrounding environment. Among them, the imaging principle of the millimeter wave radar unit should be a technical means well known to those skilled in the art, and will not be elaborated here.

[0050] In the present application, the smart ground nail is also equipped with a monitoring host, which pre-stores algorithms and models for identifying engineering machinery and equipment (such as excavators, hook machines, impact drills, cutting machines, etc.) and external breaking behaviors. These algorithms and models are based on a large amount of experimental data and actual scene training, and can identify the unique characteristic patterns of different engineering machinery and equipment. For example, the shape of the excavator's mechanical arm, the movement mode, etc. will show specific features in the radar image. The algorithm can determine whether there is an excavator in the image and whether it is in working condition (i.e., carrying out external breaking behavior) by analyzing these features.

[0051] In one embodiment, a construction machinery equipment recognition model is constructed based on a convolutional neural network (CNN), and a labeled data set is used for training. The data set is a large amount of radar echo data containing various construction machinery equipment collected using a millimeter wave radar unit, as well as the corresponding labeled types of construction machinery equipment (excavators, hook machines, impact drills, cutting machines, etc.) and whether external damage behavior is involved. In order to ensure the diversity and comprehensiveness of the data set, different scenarios should be covered, including different weather conditions (sunny, cloudy, rainy, etc.), different terrains (flat land, mountainous areas, construction sites, etc.) and different equipment operating states (stationary, moving, working, etc.). The collected radar signal is input into the trained construction machinery equipment recognition model, and it can be obtained whether there is construction machinery equipment in the surrounding environment that is performing external damage behavior.

[0052] In step S2, when the presence of engineering machinery equipment is detected in the surrounding environment, on the one hand, it is necessary to calculate the relative position between the smart ground nail and the engineering machinery equipment based on the collected radar signal; on the other hand, the voiceprint collection unit and the three-axis vibration unit are started to further collect the voiceprint signal and vibration signal of the surrounding environment.

[0053] See the instruction manual Figure 2 , the calculating the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal comprises the following steps:

[0054] S201, forming a series of three-element arrays including azimuth, distance and intensity from the collected radar signals; wherein the azimuth measurement range and the distance measurement range of the millimeter wave radar unit are evenly divided into a plurality of arrays;

[0055] S202, mapping a series of the three-element arrays onto a predefined grid to construct a two-dimensional matrix, and traversing all elements in the two-dimensional matrix to mark elements with intensity values ​​greater than a set threshold as possible valid signal points;

[0056] S203, performing peak detection on the possible valid signal points, and using a clustering algorithm to determine the cell position where the engineering machinery equipment is located, and obtaining the relative position between the smart ground nail and the engineering machinery equipment according to the cell position and the distance step for constructing the two-dimensional matrix.

[0057] Specifically, in step S201, the measurement range of the millimeter wave radar unit azimuth is 0°-360°, and a data point can be recorded every 10°, which is divided into 36 azimuth data; the distance monitoring range of the millimeter wave radar unit is 10 meters, and a data point can be recorded every 0.5 meters, which is divided into 20 distance unit data. For each measurement moment, a series of (azimuth, distance, intensity) three-element array data is obtained.

[0058] In step S202, these three-element array data are mapped to a predefined grid to construct an N*M two-dimensional matrix R:

[0059]

[0060] Among them, N = 36, which is the number of azimuths; M = 20, which is the number of distances. For each three-element array (azimuth, distance, intensity), find the corresponding matrix position (i, j) (where i corresponds to the azimuth number and j corresponds to the distance unit number), and fill the intensity value into the position to form a matrix element rij, which represents the target echo intensity at the jth distance under the i-th azimuth. In addition, according to the characteristics of the millimeter-wave radar unit and the actual environmental noise level, a suitable threshold is set. This threshold is used to distinguish between valid signals (possibly reflected echoes from target objects) and noise (such as clutter and interference signals in the environment). Traverse all elements in the matrix R and mark the elements with intensity values ​​greater than the set threshold as possible valid signal points for further analysis.

[0061] In step S203, for the points marked as possible valid signals, local maxima or significant peaks are searched in the surrounding neighborhood. This is because the reflected echo of the target object may form a strong signal peak at certain locations, corresponding to the key features of the target object or the parts with strong reflection. The target object here is the detected engineering machinery equipment. Since a single target may generate responses in multiple adjacent cells, a clustering algorithm is used to group these related points together, determine the cell location of the target, and find the distance cell number j of the target in the matrix. Then according to the formula D=d min +j*Δd to calculate the target distance, that is, the relative position between the smart ground nail and the engineering machinery equipment. min is the minimum distance, which is set to zero here, and Δd is the distance step length when constructing the two-dimensional matrix (0.5 meters in this embodiment).

[0062] In step S3, see the attached manual Figure 3 The step of inputting the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment includes the following steps:

[0063] S301, preprocessing the collected voiceprint signal to obtain a voiceprint frame sequence to be measured; the preprocessing includes at least one of windowing, framing, and denoising;

[0064] S302, extracting features from the voiceprint frame sequence to be tested to obtain feature data of the voiceprint to be tested;

[0065] S303. Input the voiceprint feature data to be tested into the engineering machinery equipment category recognition model library for comparison, calculate the similarity between the voiceprint feature data to be tested and each feature vector in the engineering machinery equipment category recognition model library, and determine the category of the engineering machinery equipment according to the similarity; wherein the engineering machinery equipment category recognition model library stores feature vectors of voiceprint signals of different categories of engineering machinery equipment under different working conditions.

[0066] In step S301, in order to avoid interference with subsequent feature extraction and recognition, the collected voiceprint data is preprocessed. For example, preprocessing is performed using windowing and framing methods. The windowing operation is to reduce the spectrum leakage problem caused by signal truncation; framing is to divide the continuous audio signal into a series of short frames, each of which can be regarded as a relatively stable sound segment, which is convenient for subsequent processing. Furthermore, after windowing and framing, the background noise is removed in each frame to improve the signal-to-noise ratio of the signal and make the voiceprint signal clearer.

[0067] In step S302, the voiceprint frame sequence to be tested is obtained by preprocessing the voiceprint signal, and the frequency domain signal (DFT) is obtained by Fourier transform, and the signal is converted from the time domain to the frequency domain in order to analyze the frequency components of the signal; then the frequency domain signal is processed by the Mel filter group. The Mel filter group simulates the nonlinear perception characteristics of the human ear to the sound frequency, and converts the frequency axis to the Mel scale, so that the resolution is higher in the low frequency band and the resolution is relatively low in the high frequency band, which is more in line with the human ear's perception of sound. After that, the logarithmic energy is calculated, and the logarithm of the signal energy after processing by the Mel filter group is taken, which helps to compress the dynamic range and highlight the important features in the signal. Then, the discrete cosine transform (DCT) is used for processing to further extract the characteristics of the signal, and finally the audio signal is converted into the Mel cepstrum domain. In the Mel cepstrum domain, the first-order differential coefficient ΔWT and the second-order differential coefficient Δ 2 WT, the first-order differential coefficient ΔWT reflects the rate of change of the voiceprint signal over time, that is, the dynamic characteristics, and the second-order differential coefficient Δ 2 WT, as a balancing factor, can further enhance the expressiveness of features. 2 WT is weighted and then combined with the static characteristic WT of the voiceprint signal to obtain the voiceprint feature data NewWT to be tested. The calculation formula is NewWT=WT+a*ΔWT+b*Δ 2 WT.

[0068] In step S303, a variety of distance measurement methods (such as Euclidean distance, cosine similarity, etc.) can be used to measure the similarity between the voiceprint feature data to be tested and each feature vector in the engineering machinery equipment category recognition model library, and then according to the set threshold or decision rule, it is determined which engineering machinery equipment category the voiceprint feature data to be tested is closest to, so as to output the corresponding machine name as the recognition result.

[0069] See the instruction manual Figure 4 , the step of calculating the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal comprises the following steps:

[0070] P301, performing Fourier transform on the vibration signals of the three axes collected to obtain a frequency domain signal of each axis, and calculating the corresponding amplitude spectrum and phase spectrum of the frequency domain signal of each axis;

[0071] P302, select a reference axis from the three axes, and calculate the phase difference of the other two axes relative to the reference axis;

[0072] P303. Calculate the distance between the vibration source and the engineering machinery equipment according to the phase difference and the wave speed.

[0073] In step P301, vibration signals in three orthogonal directions (X, Y, Z) are collected simultaneously based on a triaxial vibration unit, including vibration velocity, vibration frequency, amplitude, etc. The vibration signal is preprocessed, including filtering to remove noise and unnecessary frequency components; baseline correction is performed to eliminate DC offset in the signal. And the time domain signal is converted into a frequency domain signal by fast Fourier transform (FFT).

[0074] In step P302, the phase difference method is used to measure the phase difference of the vibration signal on different axes. For example, the X axis is selected as the reference axis, and then the phase difference of the other two axes relative to the reference axis is calculated. This can be achieved by comparing the complex representations of the two, then the phase difference of the Y axis relative to the X axis is:

[0075] Δφ(f)=∠Y(f)-∠X(f)

[0076] Among them, ∠ represents the phase angle of a complex number (i.e., phase angle). Specifically, there is a complex number expression in the following form:

[0077] X(f)=A X e jφx

[0078] Y(f)=A Y e jφx

[0079] Then the phase difference can be expressed as Δφ=φ Y -φX , where A X and A Y are the amplitudes of the X-axis and Y-axis signals, respectively, and φX and φY are the corresponding phase angles. Similarly, the phase difference of the Z-axis relative to the X-axis can be calculated.

[0080] In step P303, using the formula Calculate the distance between the vibration source and the smart ground nail in the Z-axis and Y-axis directions; where v is the wave velocity, Δφ is the phase difference, and f is the frequency of the vibration signal.

[0081] Furthermore, by calculating the distances in these two directions, the position of the vibration source in space can be determined, and then combined with other information (such as the relative position relationship between the smart ground nails and the buried cables, which is known at the time of deployment) to determine the distance between the vibration source and the buried cables.

[0082] Furthermore, in the present application, the relative position between the smart ground nail and the engineering machinery equipment, the type of the engineering machinery equipment, and the distance between the vibration source and the engineering machinery equipment are sent to the cloud platform in real time and displayed in a map visualization form; and if the distance between the vibration source and the buried cable is less than a set threshold (for example, 1 meter), a timely warning is issued, such as using text messages to notify the operation and maintenance personnel of an external breach at a certain location, so that timely prevention actions can be taken.

[0083] It can be seen that the method for monitoring the external breakage of underground cables provided by the present application conducts a comprehensive analysis of radar signals, voiceprint signals and vibration signals, improves the accuracy of judging the external breakage behavior of underground cables through multi-feature analysis, reduces the false alarm problem that may be caused by simple threshold analysis, and can promptly determine the location of the external breakage behavior and issue an early warning, thereby avoiding the emergency repair costs caused by cable damage and the economic losses caused by power outages.

[0084] Based on the same inventive concept, a device for monitoring external damage of buried cables is also provided in an embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the method for monitoring external damage of buried cables in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0085] As the instruction manual Figure 5 As shown, an embodiment of the present application provides a device for monitoring external damage of an underground cable, which is applied to smart ground nails. The smart ground nails are deployed at intervals above the underground cables that are protected from external damage. The device includes:

[0086] The first monitoring module 501 is used to collect radar signals of the surrounding environment in real time based on the millimeter wave radar unit, and input the collected radar signals into the trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment;

[0087] The second monitoring module 502 is used to calculate the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal if the existence of engineering machinery equipment is detected in the surrounding environment, and collect the voiceprint signal of the surrounding environment based on the voiceprint collection unit, and collect the vibration signal of the surrounding environment based on the triaxial vibration unit;

[0088] The measurement module 503 is used to input the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment; and calculate the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal.

[0089] In one embodiment, the device further comprises:

[0090] The display module is used to send the relative position between the smart ground nail and the engineering machinery equipment, the type of the engineering machinery equipment, and the distance between the vibration source and the buried cable to the cloud platform in real time for visual display; and if the distance between the vibration source and the buried cable is less than a set threshold, an alarm is issued.

[0091] In one embodiment, the second monitoring module 502 calculates the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal, including: forming the collected radar signal into a series of ternary arrays including azimuth, distance and intensity; wherein the azimuth measurement range and the distance measurement range of the millimeter wave radar unit are evenly divided into multiple groups; mapping a series of ternary arrays onto a predefined grid to construct a two-dimensional matrix, and traversing all elements in the two-dimensional matrix, marking the elements with intensity values ​​greater than a set threshold as possible valid signal points; performing peak detection on the possible valid signal points, and using a clustering algorithm to determine the cell position of the engineering machinery equipment, and obtaining the relative position between the smart ground nail and the engineering machinery equipment according to the cell position and the distance step for constructing the two-dimensional matrix.

[0092] In one embodiment, the measurement module 503 inputs the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment, including: preprocessing the collected voiceprint signal to obtain a voiceprint frame sequence to be measured; the preprocessing includes at least one of windowing, framing, and denoising; feature extraction of the voiceprint frame sequence to be measured to obtain voiceprint feature data to be measured; inputting the voiceprint feature data to be measured into the engineering machinery equipment category recognition model library for comparison, calculating the similarity between the voiceprint feature data to be measured and each feature vector in the engineering machinery equipment category recognition model library, and determining the category of the engineering machinery equipment according to the similarity; wherein the engineering machinery equipment category recognition model library stores feature vectors of voiceprint signals of different categories of engineering machinery equipment under different working conditions.

[0093] In one embodiment, the measurement module 503 performs feature extraction on the voiceprint frame sequence to be measured to obtain feature data of the voiceprint to be measured, including: performing Fourier transform on the voiceprint frame sequence to be measured to obtain a frequency domain signal; processing the frequency domain signal through a Mel filter group and a discrete cosine transform in sequence to obtain a Mel cepstrum domain, and calculating first-order differential coefficients and second-order differential coefficients in the Mel cepstrum domain; weighting the first-order differential coefficients and the second-order differential coefficients, and merging them with the static features of the voiceprint signal to obtain the feature data of the voiceprint to be measured.

[0094] In one embodiment, the measurement module 503 calculates the distance between the vibration source and the engineering machinery equipment based on the collected vibration signal, including: performing Fourier transform on the collected vibration signals of the three axes to obtain the frequency domain signal of each axis, and calculating the corresponding amplitude spectrum and phase spectrum of the frequency domain signal of each axis; selecting a reference axis from the three axes, and calculating the phase difference of the other two axes relative to the reference axis; calculating the distance between the vibration source and the engineering machinery equipment based on the phase difference and wave velocity.

[0095] The present application provides a device for monitoring external breakage of buried cables. The first monitoring module collects radar signals of the surrounding environment in real time based on a millimeter-wave radar unit, and inputs the collected radar signals into a trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment; if it is detected that there is engineering machinery equipment in the surrounding environment, the second monitoring module calculates the relative position between the smart ground nail and the engineering machinery equipment based on the collected radar signals, and collects the soundprint signals of the surrounding environment based on the soundprint collection unit, and collects the vibration signals of the surrounding environment based on the three-axis vibration unit; the collected soundprint signals are input into the engineering machinery equipment category recognition model library for comparison through the measurement module to obtain the category of the engineering machinery equipment; and the distance between the vibration source and the engineering machinery equipment is calculated based on the collected vibration signal. Thus, based on the artificial intelligence algorithm combined with multiple features, the category and position of the engineering machinery equipment with external breakage behavior can be accurately identified, and the distance between the vibration source and the engineering machinery equipment can be calculated, thereby improving the monitoring accuracy.

[0096] Based on the same concept of the present invention, the specification is attached Figure 6 As shown, the structure of an electronic device 600 provided in an embodiment of the present application includes: at least one processor 601, at least one network interface 604 or other user interface 603, a memory 605, and at least one communication bus 602. The communication bus 602 is used to realize the connection and communication between these components. The electronic device 600 optionally includes a user interface 603, including a display (for example, a touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (for example, a mouse, a trackball (trackball), a touch pad or a touch screen, etc.).

[0097] The memory 605 may include a read-only memory and a random access memory, and provides instructions and data to the processor 601. A portion of the memory 605 may also include a non-volatile random access memory (NVRAM).

[0098] In some implementations, the memory 605 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof:

[0099] Operating system 6051, including various system programs for implementing various basic services and processing hardware-based tasks;

[0100] The application module 6052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0101] In an embodiment of the present application, by calling the program or instructions stored in the memory 605, the processor 601 is used to execute steps in a method for monitoring external rupture of buried cables, and can accurately identify external rupture behavior based on an artificial intelligence algorithm combined with multiple features to improve monitoring accuracy.

[0102] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the method for monitoring external damage of buried cables are executed.

[0103] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned method for monitoring external damage of buried cables can be executed.

[0104] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0107] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0108] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for monitoring external damage of buried cables, characterized in that: Applied to smart ground nails, the smart ground nails are deployed at intervals above the buried cables that are protected from external force damage, and the method comprises the following steps: Based on the millimeter wave radar unit, radar signals of the surrounding environment are collected in real time, and the collected radar signals are input into the trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment; If construction machinery equipment is detected in the surrounding environment, the relative position between the smart ground nail and the construction machinery equipment is calculated according to the collected radar signal, and the voiceprint signal of the surrounding environment is collected based on the voiceprint collection unit, and the vibration signal of the surrounding environment is collected based on the three-axis vibration unit; The collected voiceprint signal is input into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment; and the distance between the vibration source and the engineering machinery equipment is calculated based on the collected vibration signal, and the distance between the vibration source and the buried cable is obtained based on the relative position between the smart ground nail and the buried cable.

2. A method for monitoring external damage of buried cables according to claim 1, characterized in that: The method further comprises the following steps: The relative position between the smart ground nail and the engineering machinery equipment, the type of the engineering machinery equipment, and the distance between the vibration source and the buried cable are sent to the cloud platform in real time for visual display; and if the distance between the vibration source and the buried cable is less than a set threshold, an alarm is issued.

3. A method for monitoring external damage of buried cables according to claim 1, characterized in that: The step of calculating the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal comprises the following steps: The collected radar signals are formed into a series of three-element arrays including azimuth, distance and intensity; wherein the azimuth measurement range and the distance measurement range of the millimeter wave radar unit are evenly divided into a plurality of arrays; Mapping a series of the three-element arrays onto a predefined grid to construct a two-dimensional matrix, and traversing all elements in the two-dimensional matrix to mark elements with intensity values ​​greater than a set threshold as possible valid signal points; Peak detection is performed on the possible valid signal points, and a clustering algorithm is used to determine the cell position where the engineering machinery equipment is located, and the relative position between the smart ground nail and the engineering machinery equipment is obtained according to the cell position and the distance step for constructing the two-dimensional matrix.

4. A method for monitoring external damage of buried cables according to claim 1, characterized in that: The step of inputting the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment comprises the following steps: Preprocessing the collected voiceprint signal to obtain a voiceprint frame sequence to be measured; the preprocessing includes at least one of windowing, framing, and denoising; Extracting features from the voiceprint frame sequence to be tested to obtain feature data of the voiceprint to be tested; The voiceprint feature data to be tested is input into the engineering machinery equipment category recognition model library for comparison, the similarity between the voiceprint feature data to be tested and each feature vector in the engineering machinery equipment category recognition model library is calculated, and the category of the engineering machinery equipment is determined according to the similarity; wherein the engineering machinery equipment category recognition model library stores feature vectors of voiceprint signals of different categories of engineering machinery equipment under different working conditions.

5. A method for monitoring external damage of underground cables according to claim 4, characterized in that: The step of extracting features from the voiceprint frame sequence to be tested to obtain feature data of the voiceprint to be tested comprises the following steps: Performing Fourier transform on the voiceprint frame sequence to be tested to obtain a frequency domain signal; The frequency domain signal is processed by a Mel filter bank and a discrete cosine transform in sequence to obtain a Mel cepstrum domain, and a first-order differential coefficient and a second-order differential coefficient are calculated in the Mel cepstrum domain; The first-order differential coefficient and the second-order differential coefficient are weighted and then combined with the static characteristics of the voiceprint signal to obtain the voiceprint feature data to be measured.

6. A method for monitoring external damage of buried cables according to claim 1, characterized in that: The step of calculating the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal comprises the following steps: Performing Fourier transform on the vibration signals of the three axes collected to obtain a frequency domain signal of each axis, and calculating the corresponding amplitude spectrum and phase spectrum of the frequency domain signal of each axis; Selecting a reference axis from the three axes and calculating the phase differences of the other two axes relative to the reference axis; The distance between the vibration source and the engineering machinery equipment is calculated according to the phase difference and the wave speed.

7. A method for monitoring external damage of underground cables according to claim 6, characterized in that: in, The distance between the vibration source and the engineering machinery equipment is calculated by the following formula: Where v is the wave velocity, Δφ is the phase difference, and f is the frequency of the vibration signal.

8. A device for monitoring external damage of buried cables, characterized in that: Applied to smart ground nails, the smart ground nails are deployed at intervals above the buried cables to prevent damage by external forces, and the device includes: The first monitoring module is used to collect radar signals of the surrounding environment in real time based on the millimeter wave radar unit, and input the collected radar signals into a trained engineering machinery equipment recognition model to detect whether there is engineering machinery equipment in the surrounding environment; The second monitoring module is used to calculate the relative position between the smart ground nail and the engineering machinery equipment according to the collected radar signal if the existence of engineering machinery equipment is detected in the surrounding environment, and collect the voiceprint signal of the surrounding environment based on the voiceprint collection unit, and collect the vibration signal of the surrounding environment based on the three-axis vibration unit; The measuring module is used to input the collected voiceprint signal into the engineering machinery equipment category recognition model library for comparison to obtain the category of the engineering machinery equipment; and calculate the distance between the vibration source and the engineering machinery equipment according to the collected vibration signal.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for monitoring external damage of buried cables as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for monitoring external damage of a buried cable as claimed in any one of claims 1 to 7 are executed.

Images