Cable external damage early warning method and device based on sound source time-frequency domain feature identification

Abstract

The invention discloses a cable external damage early warning method and device based on sound source time-frequency domain feature identification, and relates to the field of cable external damage prevention. The method comprises the following steps: acquiring construction signal data; the construction signal data is sound signal data collected in real time around the marking pile; processing the construction signal data based on an amplitude section to obtain time domain feature data; determining frequency domain data; the frequency domain data is obtained by performing fast Fourier transform on the construction signal data; performing weighting processing according to the time domain feature data and the frequency domain data to obtain processing data; carrying out numerical comparison on the processing data and the sample data under the condition of setting the total number of collection and identification times, and carrying out sound source identification according to an obtained comparison result to obtain an identification result; the sample data is obtained by performing time domain feature calculation and weighting processing on the destroyed source signal data; and determining early warning information according to the identification result. The invention aims to realize the early warning of the external damage condition of the cable.

Description

Technical Field

[0001] The present application relates to the field of cable external damage prevention, and in particular to a cable external damage warning method and device based on time-frequency domain feature identification of sound sources. Background Art

[0002] In order to avoid the potential safety hazards caused by direct exposure of cables to the outside world and to ensure the aesthetics of the city, many cables are laid underground. However, with the gradual development and advancement of urban infrastructure, many places need to dig foundations, which has caused serious safety crises for underground cables. Once the cables are accidentally dug, it will cause regional power outages and tripping, which will have a serious impact on residents' lives and corporate production. According to a survey and statistics of a certain area, the power outages caused by excavation of foundations for infrastructure projects have reached more than 60%, and the situation is very serious. At present, the main methods to reduce or eliminate external force damage to cable accidents are protective methods. By placing warning signs, the probability of damage is reduced; the unclear position of the warning sign or the change of the position of the warning sign due to external force will greatly affect the warning effect, and its effect is limited. It is also possible to design an outer tube when installing underground cables to enhance the anti-destruction performance and improve the strength against external forces; but the difficulty of laying underground cables is greatly increased, the protection cost is too high, and for large-scale engineering machinery, it can also cause damage to underground cables. Therefore, it is crucial to achieve early warning of cable external damage. Summary of the invention

[0003] The purpose of this application is to provide a cable external damage warning method and device based on the time-frequency domain feature identification of the sound source, which can realize the early warning of the cable external damage situation.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a cable external damage warning method based on the time-frequency domain feature identification of the sound source, comprising:

[0006] Acquire construction signal data; the construction signal data is sound signal data collected in real time around the marking pile;

[0007] The construction signal data is processed based on the amplitude segment to obtain time domain feature data; the amplitude segment is obtained by dividing the signal amplitude range corresponding to the pre-collected damage source signal data based on the sound source type in the time domain; the damage source signal data is the sound signal data emitted by the crusher when it is working; the sound source type is the breaker hammer hitting the ground or the crawler passing through the ground; the amplitude segment includes: a first segment and a second segment; the first segment and the second segment correspond to different sound source types;

[0008] Determine frequency domain data; the frequency domain data is obtained by performing fast Fourier transform on the construction signal data;

[0009] Performing weighted processing according to the time domain feature data and the frequency domain data to obtain processed data;

[0010] Numerical comparison is performed between each of the processed data and the sample data under the set total number of acquisition and identification times, and sound source identification is performed according to the comparison result to obtain an identification result; the sample data is obtained by calculating the time domain characteristics of the damage source signal data and performing weighted processing;

[0011] The warning information is determined according to the identification result.

[0012] Optionally, the construction signal data is processed based on the amplitude segment to obtain time domain feature data, specifically including:

[0013] Dividing the construction signal data into sections based on the amplitude sections to obtain a time domain signal of a first section and a time domain signal of a second section;

[0014] Based on the amplitude of the time domain signal of the first segment and the amplitude of the time domain signal of the second segment, the time domain feature calculation is performed to obtain the time domain feature data.

[0015] Optionally, the calculation formula of the time domain feature data is:

[0016]

[0017]

[0018] Among them, h is the time domain feature data; m is the number of sampling times; ΔP m P1 is the characteristic value of each sampling of the sound time domain signal; i is the time domain signal amplitude of the first segment; P2 i is the time domain signal amplitude of the second segment; It is the maximum amplitude of the sound time domain signal.

[0019] Optionally, the calculation formula for processing data is:

[0020] H = 4h + x;

[0021] Among them, H is the processed data; x is the frequency domain data.

[0022] Optionally, numerical comparison is performed between each of the processed data and the sample data under the set total number of acquisition and identification times, and sound source identification is performed according to the obtained comparison results to obtain an identification result, which specifically includes:

[0023] For any processed data, if the comparison result is that the similarity between the processed data and the sample data reaches the set threshold, the set value is added to the current trust value, and each processed data under the set total number of collection and identification times is traversed to obtain a cumulative trust value;

[0024] The trust cumulative value is compared with the trust threshold, and the sound source is identified according to the comparison result to obtain an identification result.

[0025] Optionally, the method for determining the sample data specifically includes:

[0026] Dividing the pre-collected damage source signal data into sections to obtain a first section of the damage source time domain signal and a second section of the damage source time domain signal;

[0027] Based on the amplitude of the destruction source time domain signal of the first segment and the amplitude of the destruction source time domain signal of the second segment, time domain feature calculation is performed to obtain destruction source time domain feature data;

[0028] Performing fast Fourier transform on the pre-collected damage source signal data to obtain the damage source signal frequency domain data;

[0029] The sample data is obtained by performing weighted processing on the time domain characteristic data of the damage source and the frequency domain data of the damage source signal.

[0030] In a second aspect, the present application provides a cable external damage warning device based on the time-frequency domain feature identification of the sound source, comprising:

[0031] A data acquisition module is used to acquire construction signal data; the construction signal data is sound signal data collected in real time around the marking pile;

[0032] A processing module is used to process the construction signal data based on the amplitude segment to obtain time domain feature data; the amplitude segment is obtained by dividing the construction signal data based on the sound source type in the time domain according to the signal amplitude range corresponding to the pre-collected damage source signal data; the damage source signal data is the sound signal data emitted by the crusher when it is working; the sound source type is the breaker hammer hitting the ground or the crawler passing through the ground; the amplitude segment includes: a first segment and a second segment; the first segment and the second segment correspond to different sound source types;

[0033] A frequency domain data determination module, used to determine frequency domain data; the frequency domain data is obtained by performing a fast Fourier transform on the construction signal data;

[0034] A weighted processing module, used for performing weighted processing according to the time domain feature data and the frequency domain data to obtain processed data;

[0035] A comparison module is used to compare the processed data with the sample data according to the total number of collection and identification times, and to identify the sound source according to the comparison results to obtain the identification results; the sample data is obtained by calculating the time domain characteristics of the damage source signal data and performing weighted processing;

[0036] The early warning module is used to determine early warning information according to the identification result.

[0037] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0038] The present application provides a cable external damage warning method and device based on the time-frequency domain feature identification of the sound source. The obtained construction signal data is processed based on the amplitude segment to obtain the time domain feature data, and then the construction signal data is subjected to fast Fourier transform to obtain the frequency domain data; based on the frequency domain data and the time domain feature data, weighted processing is performed to obtain the processed data. Then, a numerical comparison is performed based on the processed data and the sample data to identify the sound source, obtain the identification result, and then determine the warning information. The present application can detect abnormal conditions outside the cable in real time, and then send out a warning signal, that is, warning information, so as to achieve early warning of the cable external damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 It is a flow chart of the cable external damage warning method based on sound source identification;

[0041] Figure 2 A flow chart for performing sound recognition;

[0042] Figure 3 It is the time domain signal diagram;

[0043] Figure 4 It is a frequency domain signal diagram. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0046] At present, there are still early warning methods in the prior art, such as installing optical fiber vibration sensors in underground cables. When vibration (pressure) is generated on the ground, the inside of the optical fiber will be deformed, causing changes in the light inside the optical fiber. Through interference phenomena, according to different vibration signal characteristics, vibration signal recognition and positioning are achieved. However, this application uses a sound collection device to monitor external construction sound signals above the underground cable, and early warning and alarm of impending cable external damage are provided, so that construction personnel can stop in time and operation and maintenance personnel can perform maintenance and repair in time.

[0047] The design idea is to use sensors to monitor the physical parameters around the cable, such as air sound waves. By collecting data on these parameters in real time, it is possible to determine whether there is a potential risk of external damage. The data collected by the sensor will be transmitted to the central processing unit for data analysis and processing. The characteristic data of the real-time sound is obtained by extracting and analyzing the amplitude of the time domain signal and weighting the frequency domain data. Then, based on the sample data collected and processed in advance, the system can detect abnormal conditions outside the cable in real time, issue early warning signals, and take corresponding countermeasures to prevent the cable from being damaged. The specific implementation method is as follows.

[0048] like Figure 1 As shown, the embodiment of the present application provides a cable external damage warning method based on the time-frequency domain feature identification of the sound source, the method comprising:

[0049] Step 100: Acquire construction signal data. The construction signal data is sound signal data collected in real time around the marking pile.

[0050] Step 200: Process the construction signal data based on the amplitude segment to obtain time domain feature data. The amplitude segment is obtained by dividing the signal amplitude range corresponding to the pre-collected damage source signal data based on the sound source type in the time domain; the damage source signal data is the sound signal data emitted by the crusher when it is working; the sound source type is the breaker hammer hitting the ground or the crawler passing through the ground; the amplitude segment includes: a first segment and a second segment; the first segment and the second segment correspond to different sound source types.

[0051] Step 300: Determine frequency domain data. Frequency domain data is obtained by performing fast Fourier transform on construction signal data.

[0052] Step 400: Perform weighted processing according to the time domain feature data and the frequency domain data to obtain processed data.

[0053] Step 500: compare the values ​​of each processed data with the sample data under the set total number of acquisition and identification times, and identify the sound source according to the comparison results to obtain the identification results. The sample data is obtained by calculating the time domain characteristics of the damage source signal data and performing weighted processing.

[0054] Step 600: Determine warning information according to the identification result.

[0055] In one embodiment, the construction signal data is processed based on the amplitude segment to obtain time domain feature data, specifically including:

[0056] The sound signal received by the sound sensor is transmitted to the microcontroller through the DMA channel, and then the AD acquisition value is linearly transformed to obtain the corresponding voltage value. The voltage value represents the intensity of the sound signal. The conversion formula is as follows:

[0057]

[0058] In the formula, V represents the voltage conversion value, and A represents the AD conversion value of the sound signal, that is, the amplitude of the sound. The sampling voltage range is 0V-250V. The construction signal data is segmented based on the amplitude segment to obtain the time domain signal of the first segment and the time domain signal of the second segment. Figure 3 It can be seen that the tip of the crusher's sound time domain signal is mainly concentrated in the amplitude range of 150V to 250V, so the amplitude of the crusher's sound time domain signal is divided into two sections. The sound signal in the first section is the sound of the crusher hitting the ground, and the signal amplitude is between 200V and 250V; the sound signal in the second section is the sound of the crawler passing through the ground, and the signal amplitude is between 150V and 200V.

[0059] Based on the amplitude of the time domain signal of the first segment and the amplitude of the time domain signal of the second segment, the time domain feature calculation is performed to obtain the time domain feature data.

[0060] The calculation formula of time domain characteristic data is:

[0061]

[0062] Among them, h is the time domain feature data; m is the number of sampling times; ΔP m P1 is the characteristic value of each sampling of the sound time domain signal; i is the time domain signal amplitude of the first segment; P2 i is the time domain signal amplitude of the second segment; It is the maximum amplitude of the sound time domain signal.

[0063] The calculation formula for processing data is:

[0064] H=4h+x.

[0065] Among them, H is the processed data; x is the frequency domain data.

[0066] As an optional implementation, numerical comparison is performed between each processed data and sample data under the set total number of acquisition and identification times, and sound source identification is performed based on the obtained comparison results to obtain an identification result, which specifically includes:

[0067] For any processed data, if the comparison result is that the similarity between the processed data and the sample data reaches the set threshold, the set value is added to the current trust value, and each processed data under the set total number of collection and identification times is traversed to obtain the cumulative trust value.

[0068] The accumulated confidence value is compared with the confidence threshold, and the sound source is identified based on the comparison result to obtain an identification result.

[0069] In one embodiment, the method for determining sample data specifically includes:

[0070] The pre-collected damage source signal data is segmented to obtain a first segment of the damage source time domain signal and a second segment of the damage source time domain signal.

[0071] Based on the amplitude of the destruction source time domain signal of the first segment and the amplitude of the destruction source time domain signal of the second segment, the time domain feature calculation is performed to obtain the destruction source time domain feature data.

[0072] The pre-collected damage source signal data is subjected to fast Fourier transform to obtain the damage source signal frequency domain data.

[0073] The sample data is obtained by performing weighted processing on the time domain characteristic data of the damage source and the frequency domain data of the damage source signal.

[0074] like Figure 2 As shown, in practical application, the method mentioned in this application includes the following steps:

[0075] Step S1: Analyze and process the sample signal data of the crusher collected in advance, and set relevant parameters, including h s , n0 and t. Among them, h s It needs to be calculated in advance. n0 represents the number of times the current sound signal is identified as matching the source sound signal, and t represents the total number of acquisitions each time.

[0076] About parameter h sThe calculation involves processing the amplitude of the sound time domain signal. The crusher sound signal is collected by the front-end device, and the points where the amplitude of the crusher sound time domain signal is in the first section and the second section are found. The ratio of the amplitude difference between the two and the maximum amplitude is calculated as the criterion for the damage source sound signal.

[0077]

[0078] P s,max Represents the amplitude value of the crusher signal at the maximum amplitude point, P s,1 The amplitude of the time domain signal representing the crusher sound is at the point in the first section, P s,2 The amplitude of the time domain signal representing the crusher sound is at the amplitude value of the point in the second segment. See the schematic diagram of the time domain signal Figure 3 .

[0079] Collect the crusher sound signal within a period of time, and find the amplitude value P of the points where the amplitude of the time domain signal of all crusher sounds is in the first section and the second section s,1 , P s,2 The amplitude value of the point with the largest amplitude Then perform the following operation to find h s .

[0080]

[0081] The parameters n0 and t involve real-time acquisition of the sound of the damage source around the cable marker pile, mainly by collecting the sound signal at intervals through the front-end device and comparing the similarity with the sample data.

[0082] Step S2: Collect the sound signal emitted by the crusher during operation within a period of time, analyze and calculate its time domain feature quantity. Divide the amplitude of the time domain signal into two sections, namely the first section and the second section.

[0083] The amplitude of the crusher sound time domain signal is divided into two sections. The sound signal in the first section is the sound made when the crushing hammer hits the ground; the sound signal in the second section is the sound made when the crawler passes through the ground.

[0084] Step S3: The time domain signal of the crusher is transformed by FFT to obtain the spectrum data of the crusher. The frequency domain data and the time domain data are weighted. After the processing, the characteristic data of the crusher sound is obtained and used as the sample data.

[0085] The collected time domain signal of the crusher is transformed by FFT to obtain the corresponding spectrum diagram, and the sampling frequency f is set. sis 9984, and the number of sampling points N is 256. The FFT output sequence is an array of N points, each element of the array is 32 bits, of which the high 16 bits and the low 16 bits represent the real part and the imaginary part of the FFT result respectively.

[0086] Since the data type of lBUFOUT is long, we first define two variables a and b. We use the shift method to make a and b represent the high 16 bits and low 16 bits of long. Then we convert a and b into float types and multiply them by a certain gain. Then the signal amplitude of each frequency point is

[0087] Step S4: Real-time collection of crusher sound around the marked pile, and analysis and processing of its characteristic quantities. Similarly, the real-time collected sound signal data is weighted in the time domain and frequency domain to obtain real-time characteristic data, which is compared with the sample data. Figure 4 . Figure 4 The vertical axis refers to the amplitude (amplitude) of each frequency point in the frequency domain signal.

[0088] The sound signals of the damage sources around the cable marking piles are collected in real time, and the points where the amplitudes of the time domain signals of the surrounding damage source sounds are in the first section and the second section are found. Similarly, the ratio of the difference between the two and the maximum amplitude is calculated as the criterion for the crusher sound signal.

[0089]

[0090] Collect the sound signals of the damage sources around the marking piles in real time over a period of time, and find out the amplitude values ​​P1 and P2 of the points where the amplitude of the time domain signals of the damage sources around the marking piles is in the first section and the second section, and the amplitude value of the point with the largest amplitude. Then perform the following operation to find h.

[0091] P i =adc_buf[i],i=1,2,3,...,100.

[0092]

[0093] Represents the collected signal P i The amplitude value of the maximum point in the i represents the amplitude value of the time domain signal amplitude of the collected sound signal at the point within the first section, The amplitude value representing the time domain signal amplitude of the collected sound signal at the point within the second section.

[0094] When the calculation is finished, perform the following calculation.

[0095]

[0096] Next, the spectrum analysis is also performed and weighted with the time domain data.

[0097] The obtained time domain data and frequency domain data are weighted according to the following formula to obtain the sound sample data of the crusher. s , representing the frequency domain data of the crusher sound.

[0098] H s =4h s +x s .

[0099] The obtained time domain data and frequency domain data are weighted according to the following formula to obtain the sound sample data of the crusher. A small segment of spectrum data x is intercepted, which represents the frequency domain signal of the real-time collected sound.

[0100] H=4h+x.

[0101] Step S5: If the similarity between the real-time collected sound data and the sample data reaches a certain value, the current warning expectation is further improved, that is, the confidence that the current sound is the sound of the crusher is increased.

[0102] The criterion for real-time judgment of whether the collected sound signal segment conforms to the sound signal of the excavator is: when H≈H s When , the current sound signal segment is determined to be a crusher sample signal, which meets the expectation of early warning, and increases the confidence that the current sound is the crusher sound. H and H s The unit is pu. At this time, the formula for the similarity of the crusher sound is:

[0103]

[0104] S represents the similarity of the sound around the current cable marker pile to the sound of a crusher.

[0105] Step S6: When the trust level reaches a certain value, an early warning is issued.

[0106] Identify the similarity between the current sound and the crusher sound. Each time the collected signal segment is identified to be consistent with the sample data, it means that the current sound signal data is similar to the sample data, and the number of trusts is increased by one. If the number of trusts obtained by continuous collection and identification exceeds 3 times, the current sound is determined to be the sound of a crusher, and an active warning is issued.

[0107] In one embodiment, the front-end acquisition device uses the input AC coupling capacitor and input impedance of the sound amplifier to form a digital processing link, process the sound signal, extract the signal characteristics, and periodically acquire the sound signal in real time.

[0108] In one embodiment, the method for drawing the spectrum of the crusher is as follows: due to the symmetry of the FFT result, usually only the first half of the result, that is, the result less than half of the sampling frequency, is used. The frequency is used as the horizontal coordinate and the amplitude of each point is used as the vertical coordinate, and the spectrum of the crusher signal can be obtained.

[0109] In this application, intelligent cable marker piles are placed above the buried cables that need to be prevented from external damage. Four sound sensors are connected to the central processing device through DuPont cables. When the air sound wave signal caused by external construction approaches the sound sensor, the signal is amplified and transmitted to the central processing unit through the DuPont cable. The characteristics of the sound periodic signal are analyzed, and the alarm is triggered after the sound signal of the damage source is detected, which effectively plays a warning role, avoids regional power outages caused by damage to power cables, and greatly reduces the inspection workload of existing staff.

[0110] The sound sensor used in the present application only needs to ensure that the signal can be received. For example, the controller only needs to ensure that the corresponding trigger execution signal is issued when the trigger condition is met. For example, the alarm module only needs to issue an alarm under specific conditions. Any corresponding electronic devices that can meet the above basic functions can be used according to the requirements of the present invention.

[0111] Through the above design, the present application improves the work efficiency and patrol quality of the operation and maintenance personnel, and solves the problem of long patrol time and difficulty caused by laying cables in hidden spaces. The present application improves the accuracy of sound recognition.

[0112] Based on the same inventive concept, the embodiment of the present application also provides a cable damage warning device based on sound source time-frequency domain feature identification for implementing the cable damage warning method based on sound source time-frequency domain feature identification involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the cable damage warning device based on sound source time-frequency domain feature identification provided below can refer to the limitations of the cable damage warning method based on sound source time-frequency domain feature identification above, and will not be repeated here.

[0113] In an exemplary embodiment, a cable external damage warning device based on the time-frequency domain feature recognition of a sound source is provided, comprising:

[0114] The data acquisition module is used to acquire construction signal data; the construction signal data is sound signal data collected in real time around the marking pile.

[0115] A processing module is used to process the construction signal data based on the amplitude segment to obtain time domain feature data; the amplitude segment is obtained by dividing the time domain based on the sound source type and according to the signal amplitude range corresponding to the pre-collected damage source signal data; the damage source signal data is the sound signal data emitted by the crusher when it is working; the sound source type is the breaker hammer hitting the ground or the crawler passing through the ground; the amplitude segment includes: a first segment and a second segment; the first segment and the second segment correspond to different sound source types.

[0116] The frequency domain data determination module is used to determine the frequency domain data; the frequency domain data is obtained by performing fast Fourier transform on the construction signal data.

[0117] The weighted processing module is used to perform weighted processing according to the time domain feature data and the frequency domain data to obtain processed data.

[0118] The comparison module is used to compare the processed data with the sample data according to the total number of set acquisition and identification times, and to identify the sound source according to the comparison results to obtain the identification results; the sample data is obtained after calculating the time domain characteristics of the destruction source signal data and performing weighted processing.

[0119] The early warning module is used to determine early warning information according to the identification results.

[0120] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method, device and its core idea of ​​this application; at the same time, for those skilled in the art, according to the idea of ​​this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A cable external damage warning method based on the time-frequency domain feature identification of the sound source, characterized in that: The cable external damage warning method based on the time-frequency domain feature identification of the sound source includes: Acquire construction signal data; the construction signal data is sound signal data collected in real time around the marking pile; The construction signal data is processed based on the amplitude segment to obtain time domain feature data; the amplitude segment is obtained by dividing the signal amplitude range corresponding to the pre-collected damage source signal data based on the sound source type in the time domain; the damage source signal data is the sound signal data emitted by the crusher when it is working; the sound source type is the breaker hammer hitting the ground or the crawler passing through the ground; the amplitude segment includes: a first segment and a second segment; the first segment and the second segment correspond to different sound source types; Determine frequency domain data; the frequency domain data is obtained by performing fast Fourier transform on the construction signal data; Performing weighted processing according to the time domain feature data and the frequency domain data to obtain processed data; Numerical comparison is performed between each of the processed data and the sample data under the set total number of acquisition and identification times, and sound source identification is performed according to the comparison result to obtain an identification result; the sample data is obtained by calculating the time domain characteristics of the damage source signal data and performing weighted processing; The warning information is determined according to the identification result.

2. The cable external damage warning method based on the time-frequency domain feature identification of the sound source according to claim 1 is characterized in that: The construction signal data is processed based on the amplitude segment to obtain time domain feature data, specifically including: Dividing the construction signal data into sections based on the amplitude sections to obtain a time domain signal of a first section and a time domain signal of a second section; Based on the amplitude of the time domain signal of the first segment and the amplitude of the time domain signal of the second segment, the time domain feature calculation is performed to obtain the time domain feature data.

3. The cable external damage warning method based on the time-frequency domain feature identification of the sound source according to claim 2 is characterized in that: The calculation formula of the time domain characteristic data is: Among them, h is the time domain feature data; m is the number of sampling times; ΔP m P1 is the characteristic value of each sampling of the sound time domain signal; i is the time domain signal amplitude of the first segment; is the time domain signal amplitude of the second segment; It is the maximum amplitude of the sound time domain signal.

4. The cable external damage warning method based on the time-frequency domain feature identification of the sound source according to claim 3 is characterized in that: The calculation formula for the processed data is: H = 4h + x; Among them, H is the processed data; x is the frequency domain data.

5. The cable external damage warning method based on the time-frequency domain feature identification of the sound source according to claim 1 is characterized in that: Numerical comparison is performed between each of the processed data and the sample data under the set total number of collection and identification times, and sound source identification is performed based on the obtained comparison results to obtain identification results, which specifically include: For any processed data, if the comparison result is that the similarity between the processed data and the sample data reaches the set threshold, the set value is added to the current trust value, and each processed data under the set total number of collection and identification times is traversed to obtain a cumulative trust value; The trust cumulative value is compared with the trust threshold, and the sound source is identified according to the comparison result to obtain an identification result.

6. The cable external damage warning method based on the time-frequency domain feature identification of the sound source according to claim 1 is characterized in that: The method for determining the sample data specifically includes: Dividing the pre-collected damage source signal data into sections to obtain a first section of the damage source time domain signal and a second section of the damage source time domain signal; Based on the amplitude of the destruction source time domain signal of the first segment and the amplitude of the destruction source time domain signal of the second segment, time domain feature calculation is performed to obtain destruction source time domain feature data; Performing fast Fourier transform on the pre-collected damage source signal data to obtain the damage source signal frequency domain data; The sample data is obtained by performing weighted processing on the time domain characteristic data of the damage source and the frequency domain data of the damage source signal.

7. A cable external damage warning device based on the time-frequency domain feature identification of the sound source, characterized in that: The cable external damage warning device based on sound source identification includes: A data acquisition module is used to acquire construction signal data; the construction signal data is sound signal data collected in real time around the marking pile; A processing module is used to process the construction signal data based on the amplitude segment to obtain time domain feature data; the amplitude segment is obtained by dividing the construction signal data based on the sound source type in the time domain according to the signal amplitude range corresponding to the pre-collected damage source signal data; the damage source signal data is the sound signal data emitted by the crusher when it is working; the sound source type is the breaker hammer hitting the ground or the crawler passing through the ground; the amplitude segment includes: a first segment and a second segment; the first segment and the second segment correspond to different sound source types; A frequency domain data determination module, used to determine frequency domain data; the frequency domain data is obtained by performing a fast Fourier transform on the construction signal data; A weighted processing module, used for performing weighted processing according to the time domain feature data and the frequency domain data to obtain processed data; A comparison module is used to compare the processed data with the sample data according to the total number of collection and identification times, and to identify the sound source according to the comparison results to obtain the identification results; the sample data is obtained by calculating the time domain characteristics of the damage source signal data and performing weighted processing; The early warning module is used to determine early warning information according to the identification result.

Images