Fiber vibration signal recognition method and system based on image edge detection operator

Abstract

The present application relates to oil and gas pipeline signal identification technical field, disclose a kind of optical fiber vibration signal identification method and system based on image edge detection operator, comprising the following steps: obtaining artificial knocking signal spectrum diagram;The artificial knocking signal spectrum diagram is calculated by improving Sobel operator, for identifying optical fiber vibration signal;The artificial knocking signal spectrum diagram is different interval difference calculation, the optimal difference interval of the improved Sobel operator is obtained, then the optimal difference interval is used to the artificial knocking signal spectrum diagram Difference operation is carried out, then the artificial knocking spectrum diagram after the difference operation is processed by Sobel operator, for subsequent optical fiber vibration signal identification;Difference analysis is carried out using optimal difference interval, then using Sobel calculation method, enhance the signal of artificial percussion, after interval difference, artificial excavation signal and noise signal have been relatively obvious separation, and artificial excavation signal can be better identified.

Description

Technical Field

[0001] This invention relates to the field of oil and gas pipeline signal recognition technology, and in particular to a method and system for optical fiber vibration signal recognition based on image edge detection operators. Background Technology

[0002] In recent years, the mature development of fiber optic early warning technology has led to its widespread application in identification and early warning. This technology makes it possible to achieve ubiquitous sensing and monitoring of third-party construction operations along pipelines. However, due to the complex environment along pipelines, the background noise of fiber optic vibration signals is often relatively high. While it can accurately identify and alarm mechanical operations such as excavators under simple environmental conditions, in more complex environments, signals from mechanical excavation, especially manual excavation, are often masked by the background noise and cannot be identified. This is a problem that the fiber optic early warning industry urgently needs to solve.

[0003] To address the noise reduction problem of distributed optical fiber signals, research institutions both domestically and internationally have conducted a series of studies. Noise can transform high-quality distributed optical fiber signals into noisy, contaminated signals. General optical fiber early warning signal processing methods primarily employ time-domain analysis, filtering out noise signals by setting thresholds and focusing only on signals with larger amplitudes. This method can remove a significant amount of noise, making larger vibration early warning signals easier to identify, but it also masks smaller vibration signals, resulting in missing alarms. Subsequently, a method for detecting optical fiber vibration signals based on amplitude difference was proposed. This method utilizes the difference in amplitude of the backscattered Rayleigh signal to perform amplitude difference analysis, detecting and locating the optical fiber vibration signal by analyzing the changes in the peak value of the differential signal, thus improving the clarity of the alarm signal. Frequency-domain analysis methods, such as Fourier transform, map distributed optical fiber signals into the frequency domain for processing; however, they can only denoise stationary distributed optical fiber signals and cannot address non-stationary signals. Wavelet transform has better time-frequency characteristic analysis capabilities and can achieve superior noise reduction effects for distributed optical fiber signals. However, the precision of signal decomposition is limited, the processing speed is slow, it is difficult to combine with other methods, it is easy to smooth out abrupt changes, and the denoising effect needs further improvement. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method and system for identifying fiber optic vibration signals based on image edge detection operators. Applying Sobel operator technology to edge image recognition achieves better results and has a better denoising effect than traditional recognition algorithms.

[0005] This invention provides a method for identifying fiber optic vibration signals based on image edge detection operators, comprising: Step S1: Obtain the spectrum of the artificial tapping signal; Step S2: The spectrum of the artificially struck signal is calculated using an improved Sobel operator to identify the fiber optic vibration signal; Step S2 specifically involves: performing differential calculations at different intervals on the artificial knocking signal spectrum to obtain the optimal differential interval of the improved Sobel operator; then using the optimal differential interval to perform differential operations on the artificial knocking signal spectrum; and finally processing the differentially processed artificial knocking spectrum with the Sobel operator for subsequent fiber optic vibration signal identification.

[0006] Further, step S1 specifically involves: manually tapping the soil above the pipeline route, collecting the manual tapping signal through an optical fiber vibration system, and thus obtaining a manual tapping signal spectrum.

[0007] Furthermore, the formula for the improved Sobel operator is:

[0008] ; In the formula, n represents the step size, n is an integer, x represents the detected data, f represents the functional relationship, and g(x) is the calculation result of the square of the improved Sobel operator.

[0009] Further, in step S2, differential calculations are performed on the spectrum of the artificial knocking signal with differential intervals of 1, 100, 200, 300, or 400, respectively, and the optimal differential interval is determined based on the difference between the fiber vibration signal and the noise signal.

[0010] Furthermore, in step S2, the subsequent fiber optic vibration signal identification includes: The fiber optic vibration signal is identified by using signal amplitude and signal width as parameters to distinguish it from noise signals.

[0011] Furthermore, the optimal difference interval is in the range of 100-200.

[0012] Furthermore, in step S2, after processing the artificial tapping pattern after the difference operation with the Sobel operator, the processed signal is input into the deep learning model to identify the fiber vibration signal.

[0013] Furthermore, the deep learning model is a convolutional neural network model.

[0014] This invention also provides an optical fiber vibration signal recognition system based on an image edge detection operator, used to execute the optical fiber vibration signal recognition method based on an image edge detection operator described above, comprising the following modules: Manual tapping signal spectrum acquisition module: used to acquire the spectrum of manual tapping signals; An improved Sobel operator processing module is used to calculate the spectrum of the artificially struck signal using the improved Sobel operator, in order to identify the fiber optic vibration signal; The process of identifying fiber optic vibration signals by calculating the artificially struck signal spectrum using an improved Sobel operator involves: performing differential calculations at different intervals on the artificially struck signal spectrum to obtain the optimal differential interval of the improved Sobel operator; then performing differential operations on the artificially struck signal spectrum using the optimal differential interval; and finally processing the differentially processed artificially struck spectrum using the Sobel operator for subsequent fiber optic vibration signal identification.

[0015] The present invention also provides a computer-readable storage medium containing a computer program for executing the fiber optic vibration signal recognition method based on image edge detection operators described above.

[0016] The embodiments of the present invention have the following technical effects: This invention collects signals from manual digging, performs differential analysis using the optimal differential interval, and then uses the Sobel calculation method to amplify the signal. After differential interval analysis, the manual digging signal and noise signal are clearly separated, making it easier to identify the manual digging signal. The Sobel calculation then amplifies the manual digging signal, making it clearly identifiable. This enables a fiber optic early warning system to effectively detect and alert to manual digging signals. The Sobel operator is insensitive to noise and can even suppress noise. Applying the Sobel operator to edge image recognition achieves good results and has a better denoising effect than traditional recognition algorithms. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the fiber optic vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention; Figure 2 The original data, the differential calculation at one interval, and the spectrum calculated by Soble are provided in the fiber optic vibration signal recognition method based on image edge detection operator according to Embodiment 1 of the present invention. Figure 3The original data, the spectrum calculated by Soble with 100 intervals of difference, and the spectrum of the optical fiber vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention are shown. Figure 4 The spectrum is the original data, the spectrum calculated by Soble with 200 intervals of difference, and the spectrum of the fiber vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 5 This is the original data, the spectrum calculated by Soble with 300 intervals of difference, and the spectrum of the fiber vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 6 This is the original data, the spectrum calculated by Soble with 400 intervals of difference, and the spectrum of the fiber vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 7 This is a structural diagram of the fiber optic vibration signal recognition system based on image edge detection operator provided in Embodiment 2 of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0020] Example 1 Figure 1 This is a flowchart of the fiber optic vibration signal recognition method based on an image edge detection operator provided in Embodiment 1 of the present invention. See also... Figure 1 Specifically, it includes: Step S1: Obtain the spectrum of the artificial tapping signal; Specifically, the soil above the pipeline is manually tapped, and the tapping signal is collected through an optical fiber vibration system to obtain the tapping signal spectrum. Furthermore, in this embodiment, the clearer 17,500 frequency frequency of the collected signal spectrum is extracted from the tapping signal for data analysis.

[0021] Step S2: The spectrum of the artificially struck signal is calculated using an improved Sobel operator to identify the fiber optic vibration signal; Specifically, the artificial knocking signal spectrum is subjected to differential calculations at different intervals to obtain the optimal differential interval of the improved Sobel operator. Then, the optimal differential interval is used to perform differential operations on the artificial knocking signal spectrum. Finally, the artificial knocking spectrum after differential operations is processed by the Sobel operator for subsequent fiber optic vibration signal identification. Further, in step S2, differential calculations are performed on the spectrum of the artificial knocking signal with differential intervals of 1, 100, 200, 300, or 400, respectively, and the optimal differential interval is determined based on the difference between the fiber vibration signal and the noise signal. Furthermore, in step S2, the subsequent fiber optic vibration signal identification includes: The fiber optic vibration signal is identified by using signal amplitude and signal width as parameters to distinguish it from noise signals. The Sobel operator is one of the most important operators for image edge detection. It belongs to the discrete difference operator category and is mainly used to obtain the step values ​​of digital images. It is an improvement on the Prewitt operator and has two different sets of convolution factors, allowing for horizontal and vertical planar convolution of an image. Through the Sobel algorithm, approximate grayscale values ​​of the image can be obtained to detect the image's boundary positions. Sobel is a gradient calculation method, and the formula is: (1) In the formula, f represents the direction of the edge intensity at position (x, y) in an image. The formula for calculating the magnitude of the gradient vector is: (2) The specific calculations for gradient and magnitude involve weighting the values ​​in the current row or column, followed by averaging and differencing. The calculation methods are as follows: (3) (4) Since the fiber vibration signal in this embodiment is a one-dimensional signal, the calculation using the Sobel operator only needs to consider a single dimension, that is, only g. x The Sobel operator calculates the difference between two numbers, with the middle number being the difference between the two preceding and following numbers. However, in fiber optic vibration signals, the difference between these two numbers may not always yield the optimal result. It is necessary to experiment with differences at different distances between the preceding and following numbers until the optimal difference point is found. Therefore, the Sobel operator formula is simplified for calculating the signal amplitude in the spectrum: (5) To make the difference values ​​more obvious, the root mean of formula (4) is simplified to formula (6): (6) In the formula, n represents the step size, n is an integer, x represents the detected data, f represents the functional relationship, and g(x) is the calculation result of the square of the improved Sobel operator.

[0022] In order to obtain a better identification effect, this embodiment uses data collected at intervals of 1, 100, 200, 300 and 400 times in sequence, and inputs it into formulas (5) and (6) in the above-mentioned improved Sobel operator to calculate the signal amplitude and signal width, thereby obtaining a series of spectra. By observing the difference in signal amplitude and signal width in the spectra, the background noise and the artificial knocking signal can be distinguished. in, Figure 2 This refers to the original data, the spectrum calculated by the difference and Soble operation at one interval, in the fiber optic vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 2 As shown, the first row of the spectrum is the original acquired data of the artificial tapping signal. From the raw data, it can be seen that although the artificial tapping signal is relatively clear, there is significant overlap between the signal data and noise signals. For weaker artificial tapping signals, they are often obscured by noise and cannot be identified. To better identify the fiber optic vibration signal, a differential method is generally used for data analysis. Figure 2 The second row of the spectrum shows the spectrum after processing using a differential method with a difference interval of 1. It can be seen that the differential processing reduces the fundamental noise to some extent, making the vibration signal from manual tapping easier to identify. However, at the same time, the differential processing also causes some fiber optic vibration signal data to become thinner and weaker, making them harder to identify. Figure 2 The third row of the spectrum shows the results of the improved Sobel algorithm calculated on a signal with a difference interval of 1. Figure 2 As can be seen, after calculation, all negative data are converted to positive values ​​and the amplitude increases. This makes it possible to clearly distinguish the fiber vibration signal from the noise signal, achieving a good effect of distinguishing noise from useful fiber vibration signals. However, due to the loss of some signal data in the differential result, even after the Sobel algorithm is calculated, some signals will become weaker and harder to identify.

[0023] Figure 3 This is the original data, the spectrum calculated by Soble with 100 intervals of difference, and the spectrum obtained in the fiber optic vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 3 The first row is still the original data spectrum, the second row is the spectrum of the difference analysis results, and the third row is the spectrum calculated by Sobel; from Figure 3 The difference analysis results in the second row show that, compared to Figure 2 The difference results with an interval of 1, Figure 3The difference results with a 100-degree interval clearly distinguish the fiber vibration signal from the noise signal, making it easier to identify artificial knocking signals. The signal calculated and analyzed by the Sobel algorithm, taking the 6th signal peak as an example, shows a significant increase in both signal amplitude and width, with the signal amplitude increasing by about 1.5 times and the width increasing by about 2 times. Figure 2 In the Sobel calculation results, the fifth signal is not obvious, but in Figure 3 The signal is then clearly discernible.

[0024] Figure 4 This is the original data, the spectrum calculated by Soble with 200 intervals of difference, and the spectrum obtained in the fiber optic vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 4 The first row is still the original data plot, the second row is the difference analysis result data plot, and the third row is the Sobel calculated plot; from Figure 4 The difference analysis results in the second row show that, compared to Figure 2 Intervals of 1 and Figure 3 Difference results with an interval of 100. Figure 4 Even with a 200-degree difference, the fiber optic vibration signal and noise signal can be clearly distinguished, making it easier to differentiate artificial knocking signals. After analysis using the Sobel algorithm, the signal amplitude and width further increase; for example, the signal amplitude of the 6th signal peak is significantly larger than... Figure 2 The data increased by approximately two times, and the width also increased by approximately 2.5 times; the fifth signal in Figure 4 The difference is also clearly discernible. However, the difference results also show that the signals in the positive and negative regions are somewhat deviated. Specifically, the third signal has a range of 2200~2500 in the positive amplitude region and a range of 2000~2300 in the negative amplitude region. The data has shifted, and one signal has become two, which also causes the signal calculated by Sobel to have multiple peaks.

[0025] Figure 5 This is the original data, the spectrum calculated by Soble with 300 intervals of difference, and the spectrum of the fiber vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 5 The first row is still the original data plot, the second row is the difference analysis result data plot, and the third row is the Sobel calculated plot; from Figure 5 The difference analysis results in the second row show that, compared to Figure 2 The interval is 1. Figure 3 The interval is 100. Figure 4 Difference results with an interval of 200. Figure 5The differential results with a 300-degree interval clearly distinguish the fiber vibration signal from the noise signal. However, the data shift between the positive and negative signal regions is more pronounced after differential analysis. Furthermore, for similar impact signals, the peaks of the two differential signals even overlap. After analysis using the Sobel algorithm, taking the 6th signal peak as an example, the signal amplitude and width further increase, and the signal amplitude is significantly larger than... Figure 2 The data increased by approximately 2.5 times, and the width also increased by approximately 3 times; the fifth signal in Figure 5 The peaks are clearly discernible, but almost all Sobel calculations produce multi-peak signals, making it impossible to clearly distinguish the peak values ​​for similar striking signals.

[0026] Figure 6 This is the original data, the spectrum calculated by Soble with 400 intervals of difference, and the spectrum obtained in the fiber optic vibration signal recognition method based on image edge detection operator provided in Embodiment 1 of the present invention. Figure 6 The first row is still the original data plot, the second row is the difference analysis result data plot, and the third row is the Sobel calculated plot. Figure 6 The second row of the differential analysis results shows that, compared to the differential results in the previous figures, the fiber vibration signal and noise signal can still be clearly distinguished. However, the data shift between the positive and negative signal regions after differential analysis is very obvious, and even the two differential signals overlap and connect. After calculation and analysis using the Sobel algorithm, taking the 6th signal peak as an example, the signal amplitude and width further increase, and the signal amplitude is compared to... Figure 2 The data increased by about 3 times, and the width also increased by about 3.5 times. However, because the signals are all multi-peak signals, it is no longer possible to clearly distinguish similar tapping signals. Even tapping signals that are far apart show multiple signal peaks with large amplitudes, making them difficult to identify.

[0027] In summary, differential analysis of artificial tapping signals yields good results, but the difference interval significantly impacts the analysis outcome. A difference interval of 100-200 clearly distinguishes background noise from the artificial tapping signal; however, smaller or larger difference intervals result in either insufficient signal clarity or overlapping and misidentification. The Sobel algorithm significantly amplifies the artificial tapping signal, particularly after processing with a difference interval of 100-200, amplifying the amplitude and width of the signal and effectively identifying signal peaks. However, for differential data with larger intervals, Sobel processing produces multi-peak signals, sometimes even with individual peaks appearing consecutively, making it impossible to clearly identify individual peaks. Therefore, using a difference interval of 100-200 and applying Sobel analysis effectively identifies the artificial tapping signal.

[0028] In step S2, after processing the artificial knocking pattern after the difference operation with the Sobel operator, the processed signal is input into the deep learning model to identify the optical fiber vibration signal. In this embodiment, the artificial knocking pattern after the difference operation is processed by the Sobel operator, and the processed signal is used as the feature input of the deep learning model to train the deep learning model. The deep learning model is a convolutional neural network model. The trained deep learning model can automatically identify different optical fiber vibration signals according to the input features. Convolutional neural networks have a hierarchical structure that can progressively extract and combine features from low to high levels. This hierarchical structure helps to extract more abstract and meaningful features from the original signal, can automatically learn complex relationships between features, and can handle high-dimensional data. Deep learning technology can be used to extract image content features based on images, conduct targeted training, and achieve accurate recognition of feature content through inference. Among them, the Sobel operator is an algorithm that has been applied to edge image recognition in recent years. It is insensitive to noise and can even suppress noise. Applying the Sobel operator to edge image recognition can achieve good results and has a better denoising effect than traditional recognition algorithms.

[0029] Example 2 Figure 7 This is a structural diagram of the fiber optic vibration signal recognition system based on image edge detection operators provided in Embodiment 2 of the present invention, which includes the following modules: Manual tapping signal spectrum acquisition module: used to acquire the spectrum of manual tapping signals; An improved Sobel operator processing module is used to calculate the spectrum of the artificially struck signal using the improved Sobel operator, in order to identify the fiber optic vibration signal; The method of identifying fiber optic vibration signals by calculating the artificially struck signal spectrum using an improved Sobel operator involves: performing differential calculations at different intervals on the artificially struck signal spectrum to obtain the optimal differential interval of the improved Sobel operator; then performing differential operations on the artificially struck signal spectrum using the optimal differential interval; and finally processing the differentially processed artificially struck signal spectrum using the Sobel operator for subsequent fiber optic vibration signal identification.

[0030] Example 3 This embodiment also provides an electronic device, which includes one or more processors and a memory; A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.

[0031] The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and a processor may execute the program instructions to implement the fiber optic vibration signal recognition method based on image edge detection operators described in any embodiment of this application above, and / or other desired functions. Various contents such as initial extrinsic parameters and thresholds may also be stored in the computer-readable storage medium.

[0032] In one example, the electronic device may also include input and output devices, which are interconnected via a bus system and / or other forms of connection (not shown). The input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including warning messages, braking force, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0033] In addition, depending on the specific application, electronic devices may include any other suitable components.

[0034] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the fiber optic vibration signal recognition method based on image edge detection operators provided in any embodiment of this application.

[0035] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0036] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the fiber optic vibration signal recognition method based on image edge detection operators provided in any embodiment of this application.

[0037] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0038] It should be noted that the terminology used in this invention is for describing specific embodiments only and is not intended to limit the scope of this application. As shown in this specification, unless the context clearly indicates otherwise, words such as "a," "an," "an," and / or "the" do not specifically refer to the singular and may include the plural. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.

[0039] It should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," "linked," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific circumstances.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A fiber optic vibration signal recognition method based on image edge detection operators, characterized in that, Specifically, the following steps are included: Step S1: Obtain the spectrum of the artificial tapping signal; Step S2: The spectrum of the artificially struck signal is calculated using an improved Sobel operator to identify the fiber optic vibration signal; Step S2 specifically involves: performing differential calculations at different intervals on the artificial knocking signal spectrum to obtain the optimal differential interval of the improved Sobel operator; then using the optimal differential interval to perform differential operations on the artificial knocking signal spectrum; and finally processing the artificial knocking spectrum after differential operations with the improved Sobel operator for subsequent fiber optic vibration signal identification. In step S2, the formula for the improved Sobel operator is: ； In the formula, n represents the step size, n is an integer, x represents the detected data, f represents the functional relationship, and g(x) is the calculation result of the square of the improved Sobel operator; In step S2, differential calculations are performed on the spectrum of the artificial knocking signal with differential intervals of 1, 100, 200, 300, or 400, respectively, and the optimal differential interval is determined based on the difference between the fiber vibration signal and the noise signal. The optimal difference interval is in the range of 100-200.

2. The fiber optic vibration signal recognition method based on image edge detection operator according to claim 1, characterized in that, Step S1 specifically involves: manually tapping the soil above the pipeline route, collecting the manual tapping signal through an optical fiber vibration system, and thus obtaining the manual tapping signal spectrum.

3. The fiber optic vibration signal recognition method based on image edge detection operator according to claim 1, characterized in that, In step S2, the subsequent fiber optic vibration signal identification includes: The fiber optic vibration signal is identified by using signal amplitude and signal width as parameters to distinguish it from noise signals.

4. The fiber optic vibration signal recognition method based on image edge detection operator according to claim 1, characterized in that, In step S2, after the artificial tapping pattern after the difference operation is processed by the Sobel operator, the processed signal is input into the deep learning model to identify the fiber vibration signal.

5. The fiber optic vibration signal recognition method based on image edge detection operator according to claim 4, characterized in that, The deep learning model is a convolutional neural network model.

6. A fiber optic vibration signal recognition system based on an image edge detection operator, used to execute the fiber optic vibration signal recognition method based on an image edge detection operator as described in any one of claims 1-5, characterized in that, Includes the following modules: Manual tapping signal spectrum acquisition module: used to acquire the spectrum of manual tapping signals; An improved Sobel operator processing module is used to calculate the spectrum of the artificially struck signal using the improved Sobel operator, in order to identify the fiber optic vibration signal; The process of identifying fiber optic vibration signals by calculating the artificially struck signal spectrum using an improved Sobel operator involves: performing differential calculations at different intervals on the artificially struck signal spectrum to obtain the optimal differential interval of the improved Sobel operator; then performing differential operations on the artificially struck signal spectrum using the optimal differential interval; and finally processing the differentially processed artificially struck signal spectrum using the improved Sobel operator for subsequent fiber optic vibration signal identification. In step S2, the formula for the improved Sobel operator is: ； In the formula, n represents the step size, n is an integer, x represents the detected data, f represents the functional relationship, and g(x) is the calculation result of the square of the improved Sobel operator; In step S2, differential calculations are performed on the spectrum of the artificial knocking signal with differential intervals of 1, 100, 200, 300, or 400, respectively, and the optimal differential interval is determined based on the difference between the fiber vibration signal and the noise signal. The optimal difference interval is in the range of 100-200.

7. A computer-readable storage medium, characterized in that, It includes a computer program for executing the fiber optic vibration signal recognition method based on image edge detection operators as described in any one of claims 1-5.

Images