Mine pipe leakage monitoring method based on distributed optical fiber acoustic sensing technology

Abstract

This invention belongs to the field of pipeline monitoring technology, and particularly relates to a method, device, and equipment for monitoring mine pipe leaks based on distributed fiber optic acoustic sensing technology. The invention preprocesses the acquired raw ADS data to obtain preprocessed data, including compensation and noise reduction; after demodulation and phase dewinding, the preprocessed data is used to calculate the strain matrix; feature extraction is performed on the strain matrix to obtain a feature matrix, which includes time-domain features, frequency-domain features, time-frequency features, spatial features, and joint spatiotemporal features; the feature matrix is ​​normalized to obtain a normalized matrix; and feature analysis is performed on the normalized matrix to output decision results, achieving continuous monitoring of the entire pipeline without blind spots, as well as early warning and precise location capabilities.

Description

Technical Field

[0001] This invention belongs to the field of pipeline monitoring technology, and particularly relates to a method, device and equipment for monitoring mine pipe leaks based on distributed fiber optic acoustic sensing technology. Background Technology

[0002] The tailings slurry transported in the pipelines contains mineral powder particles, which cause wear and tear on the pipelines and are prone to leakage. The current on-site inspection method for tailings transport pipelines is too time-consuming, takes place in harsh environments, lacks specificity, and is inefficient. The "look, smell, question, and feel" approach relies entirely on regular inspections by operating personnel, which suffers from long monitoring cycles, high labor costs, and difficulty in diagnosing initial faults. If a leak is discovered during inspection, it must be reported and excavation and repair must be carried out; therefore, it is a reactive management measure, and the time of leak detection largely depends on the inspection personnel. Summary of the Invention

[0003] This application addresses the technical problems of difficult and inefficient monitoring and investigation of mine tailings pipeline leaks, which are often relegated to post-event management. It proposes a method, device, and equipment for monitoring mine pipeline leaks based on distributed fiber optic acoustic sensing technology. The method involves preprocessing the collected raw ADS data (including compensation and noise reduction) to obtain preprocessed data; demodulating and dewinding the preprocessed data to calculate a strain matrix; extracting features from the strain matrix to obtain a feature matrix, which includes time-domain features, frequency-domain features, time-frequency features, spatial features, and joint spatiotemporal features; normalizing the feature matrix to obtain a normalized matrix; and performing feature analysis on the normalized matrix to output decision results. This achieves continuous monitoring of the entire pipeline without blind spots, as well as early warning and precise location capabilities.

[0004] The specific technical solution is as follows: A method for monitoring mine pipe leaks based on distributed fiber optic acoustic sensing technology, the method comprising: The collected raw ADS data is preprocessed to obtain preprocessed data, and the preprocessing includes compensation and noise reduction. After demodulation and phase unwinding of the preprocessed data, strain calculation is performed to obtain the strain matrix; The strain matrix is ​​subjected to feature extraction to obtain a feature matrix, which includes time-domain features, frequency-domain features, time-frequency features, spatial features, and joint spatiotemporal features; The feature matrix is ​​normalized to obtain the normalized matrix; The decision results are output after performing feature analysis on the normalized matrix.

[0005] According to the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology, the preprocessing of the collected ADS raw data to obtain preprocessed data includes: After performing Stokes vector calculation on the acquired ADS raw data, the degree of polarization is calculated, and polarization compensation is performed based on the degree of polarization to obtain the compensation data. Furthermore, after performing discrete wavelet transform and adaptive thresholding on the compensation data, wavelet reconstruction is then performed to obtain the denoised data.

[0006] According to the mine pipe leakage monitoring method based on distributed optical fiber acoustic sensing technology, the feature analysis of the normalized matrix includes feature selection, dimensionality reduction, classification, and localization to obtain the analysis results.

[0007] According to the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology, the method further includes: Input the analysis results into the decision model and output the decision results.

[0008] This invention also provides a mine pipe leakage monitoring device based on distributed fiber optic acoustic sensing technology, comprising: The preprocessing module is used to preprocess the acquired raw ADS data to obtain preprocessed data. The preprocessing includes compensation and noise reduction. The calculation module is used to perform strain calculations on the preprocessed data after demodulation and phase unwinding to obtain the strain matrix; The feature extraction module is used to extract features from the strain matrix to obtain a feature matrix, which includes time-domain features, frequency-domain features, time-frequency features, spatial features, and joint spatiotemporal features. The normalization module is used to normalize the feature matrix to obtain a normalized matrix; The decision module is used to perform feature analysis on the normalized matrix and then output the decision results.

[0009] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology as described in any of the preceding claims.

[0010] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology as described in any of the preceding claims.

[0011] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology as described in any of the preceding claims.

[0012] The beneficial effects of this invention are as follows: (1) Through the innovation of physical layer of distributed optical fiber sensing, the basic capability of continuous monitoring of the entire pipeline without blind spots has been realized; (2) Through the innovation of multi-dimensional feature fusion algorithm layer, the core capability of high-accuracy intelligent recognition and classification has been realized; (3) Through the application layer innovation of dual-mode positioning, the value capabilities of early warning and precise positioning have been realized. Attached Figure Description

[0013] Figure 1 The diagram shows a flowchart of the mine pipe leakage monitoring method based on distributed optical fiber acoustic sensing technology provided by the present invention. Figure 2 This is a schematic diagram of the structure of the mine pipe leakage monitoring device based on distributed optical fiber acoustic sensing technology provided by the present invention.

[0014] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0015] In the following description, certain specific details are set forth in order to provide a thorough understanding of various embodiments. However, those skilled in the art will understand that the invention can be practiced without these details. In other instances, well-known structures have not been shown or described in detail to avoid unnecessarily obscuring the description of the embodiments. Unless the context otherwise requires, throughout the specification and appended claims, the word "comprising" should be interpreted in an open-ended, inclusive sense, i.e., as "including but not limited to".

[0016] Combination Figure 1 The mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology provided in this application includes the following: S100, Data Acquisition and Data Preprocessing The collected data is presented as follows: (1) in, The data consists of discrete raw data; n is the discrete-time index; m is the discrete-space index; The incident light pulse peak power is K; the effective scattering point number is K. The scattering amplitude coefficient represents the position. The reflectivity at the k-th scattering point; The scattering phase; Additive noise represents the sum of system noise and ambient noise.

[0017] in, ; The total number of samples taken over time. The total number of spatial samples, The time sampling interval is... This refers to spatial resolution.

[0018] The data preprocessing process transforms the raw data into a clean, usable strain signal, including polarization compensation, noise suppression, phase demodulation, and strain calculation.

[0019] Optionally, in the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology provided in this application embodiment, the polarization compensation method is as follows: S101, Stokes vector calculation: (2) S102, Polarization degree calculation: (3) S103, Compensation Formula: (4) Optionally, in the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology provided in this application embodiment, the noise suppression method is as follows: S111, Discrete Wavelet Transform: (5) in, S112, Threshold processing: (6) S113, Adaptive Threshold: (7) S114, Wavelet Reconstruction: (8) Optionally, in the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology provided in this application embodiment, the phase demodulation method is as follows: S121, 3×3 coupler demodulation: (9) S122, Phase unwinding: (10) in, Optionally, in the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology provided in this application embodiment, the strain calculation method is as follows: (11) in, To detect the wavelength of light, It is 104682. It is 0.78.

[0020] S200, Feature Extraction In feature extraction, a P-dimensional feature vector is extracted: (12) Feature matrix: F Extracting leakage-sensitive and distinguishable features from high-dimensional data, including time-domain feature extraction, frequency-domain feature extraction, time-frequency feature extraction, spatial feature extraction, and joint spatiotemporal feature extraction.

[0021] Optionally, in the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology provided in the embodiments of this application, the time-domain features include: mean, variance, standard deviation, root mean square, skewness, kurtosis, waveform factor, and peak factor.

[0022] Define the feature extraction window length as The data in the window is: (13) Mean: (14) variance: (15) Standard deviation: (16) Root mean square: (17) Skewness: (18) Kuroshi: (19) Waveform factor: (20) Peak factor: (twenty one) Optionally, in the mine pipe leakage monitoring method based on distributed optical fiber acoustic sensing technology provided in the embodiments of this application, the frequency domain characteristics include: spectral centroid, spectral bandwidth, spectral roll-off, spectral flatness, spectral entropy, spectral flux, and harmonic component ratio.

[0023] Among them, the basics of spectrum calculation: Window function (Hamming window): (twenty two) Window function normalization factor: (twenty three) Windowing signal: (twenty four) Discrete Fourier Transform: (25) Power spectral density: (26) Normalized power spectrum: (27) Then the centroid of the spectrum: (28) The sampling frequency; For frequency indexing.

[0024] Spectrum bandwidth: (29) Spectrum roll-off: (30) in, ; Spectral flatness: (31) Spectral entropy: (32) Spectral flux: (33) in This is the power spectrum of the previous window.

[0025] Harmonic component ratio: (34) in The fundamental frequency is obtained through the autocorrelation method; H is the harmonic order. for .

[0026] Optionally, in the mine pipe leakage monitoring method based on distributed optical fiber acoustic sensing technology provided in the embodiments of this application, the time-frequency characteristics include: time-frequency energy centroid in the time direction, time-frequency energy centroid in the frequency direction, time-frequency energy spread, instantaneous frequency mean variance, and time-frequency ridge slope.

[0027] Among them, the window function (Hamming window): (35) For window length, usually ; STFT calculation: (36) in, Time-spectral energy: (37) Time-frequency energy centroid in the time direction: (38) Center of gravity of time-frequency energy in the frequency direction: (39) in, The sampling frequency; For frequency indexing.

[0028] Time-frequency energy spread: (40) Instantaneous frequency mean and variance: (41) in, ; Time-frequency ridge slope: (42) in, Satisfy linear fit ; For time-frequency ridges, satisfying: .

[0029] Optionally, in the mine pipe leakage monitoring method based on distributed optical fiber acoustic sensing technology provided in the embodiments of this application, the spatial features include: spatial energy mean, spatial energy gradient, spatial attenuation coefficient, spatial autocorrelation coefficient, and spatial covariance matrix eigenvalues.

[0030] Spatial energy mean: (43) in, Spatial energy gradient: (44) Spatial attenuation coefficient: (45) in, Satisfying the exponential fit of space energy: (46) Spatial autocorrelation coefficient: (47) (48) (49) in, The spatial autocorrelation function is obtained through normalization. Take the relevant radius .

[0031] Eigenvalues ​​of the spatial covariance matrix: (50) -1 in, ; Let be the spatial covariance matrix. For each of the elements.

[0032] Optionally, in the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology provided in the embodiments of this application, the joint spatiotemporal characteristics include: propagation speed estimation, propagation attenuation, spatiotemporal consistency index, event duration, and event spatial range.

[0033] Propagation speed estimation: (51) in, and These are the two locations where the event was detected, and their arrival times are respectively... and .

[0034] Propagation attenuation: (52) Spatiotemporal consistency index: (53) in, (54) (55) The spatiotemporal covariance is obtained through normalization. Take the maximum value as .

[0035] Event duration: (56) in, The start time of the event. This is the end time of the event.

[0036] Event space range: (57) in, and It is the spatial boundary affected by the event.

[0037] S201, Feature Normalization Perform z-score normalization on each feature dimension: (58) in, (59); (60); After normalization, we get: (61) S300, Feature Analysis This includes feature selection, dimensionality reduction, classification, and localization.

[0038] For the feature dimension P, calculate: (62) Selection criteria: (63) Regarding dimensionality reduction: Define the covariance matrix: (64); This is the characteristic matrix after removing the mean.

[0039] Eigenvalue decomposition: (65) Dimensionality reduction mapping: (66) (67) For classification, Support Vector Machines (SVM) are used: Optimization issues: Decision function: (68) RBF kernel function: (69) For positioning, negative pressure wave positioning is used: Let the upstream sensor position be... and downstream sensor location Pressure wave velocity arrival time difference (70) Time difference calculation: (71) S400, Decision-making Define the recognition framework: (72) Basic probability allocation: For algorithm a, its output is consistent with the hypothesis. The confidence level is For two algorithms a and b: (73) Wherein the conflict coefficient is: (74) Final decision-making rules: (75) in: Confidence function Likelihood function ; ; .

[0040] The following describes the mine pipe leakage monitoring device based on distributed fiber optic acoustic sensing technology provided by the present invention. The mine pipe leakage monitoring device based on distributed fiber optic acoustic sensing technology described below can be referred to in correspondence with the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology described above.

[0041] Figure 2 This is a schematic diagram of the structure of the mine pipe leakage monitoring device based on distributed fiber optic acoustic sensing technology provided by the present invention, as shown below. Figure 2 As shown, the device includes the following: Preprocessing module 201 is used to preprocess the acquired ADS raw data to obtain preprocessed data, wherein the preprocessing includes compensation and noise reduction; The calculation module 202 is used to perform strain calculation to obtain the strain matrix after demodulating and unwinding the preprocessed data; The feature extraction module 203 is used to extract features from the strain matrix to obtain a feature matrix, wherein the feature matrix includes time-domain features, frequency-domain features, time-frequency features, spatial features, and joint spatiotemporal features; Normalization module 204 is used to normalize the feature matrix to obtain a normalized matrix; Decision module 205 is used to perform feature analysis on the normalized matrix and then output the decision results.

[0042] Figure 3An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840. The processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions from the memory 830 to execute a bioassay method for evaluating the resistance of poplar longhorn beetles.

[0043] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0044] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the bioassay method for evaluating the resistance of poplar longhorn beetle provided by the above methods.

[0045] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the bioassay method for evaluating the resistance of poplar longhorn beetles provided by the methods described above.

[0046] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0047] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0048] 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 of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0049] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it.

Claims

1. A method for monitoring mine pipe leaks based on distributed fiber optic acoustic sensing technology, characterized in that, The method includes: The collected raw ADS data is preprocessed to obtain preprocessed data, and the preprocessing includes compensation and noise reduction. After demodulation and phase unwinding of the preprocessed data, strain calculation is performed to obtain the strain matrix; The strain matrix is ​​subjected to feature extraction to obtain a feature matrix, which includes time-domain features, frequency-domain features, time-frequency features, spatial features, and joint spatiotemporal features; The feature matrix is ​​normalized to obtain the normalized matrix; The decision results are output after performing feature analysis on the normalized matrix.

2. The method for monitoring mine pipe leaks based on distributed fiber optic acoustic sensing technology according to claim 1, characterized in that, The preprocessing of the acquired ADS raw data to obtain preprocessed data includes: After performing Stokes vector calculation on the acquired ADS raw data, the degree of polarization is calculated, and polarization compensation is performed based on the degree of polarization to obtain the compensation data. Furthermore, after performing discrete wavelet transform and adaptive thresholding on the compensation data, wavelet reconstruction is then performed to obtain the denoised data.

3. The method for monitoring mine pipe leaks based on distributed fiber optic acoustic sensing technology according to claim 1, characterized in that, The feature analysis of the normalized matrix includes feature selection, dimensionality reduction, classification, and localization to obtain the analysis results.

4. The method for monitoring mine pipe leaks based on distributed fiber optic acoustic sensing technology according to claim 3, characterized in that, The method further includes: Input the analysis results into the decision model and output the decision results.

5. A mine pipe leakage monitoring device based on distributed fiber optic acoustic sensing technology, characterized in that, include: The preprocessing module is used to preprocess the acquired raw ADS data to obtain preprocessed data. The preprocessing includes compensation and noise reduction. The calculation module is used to perform strain calculations on the preprocessed data after demodulation and phase unwinding to obtain the strain matrix; The feature extraction module is used to extract features from the strain matrix to obtain a feature matrix, which includes time-domain features, frequency-domain features, time-frequency features, spatial features, and joint spatiotemporal features. The normalization module is used to normalize the feature matrix to obtain a normalized matrix; The decision module is used to perform feature analysis on the normalized matrix and then output the decision results.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the mine pipe leakage monitoring method based on distributed fiber optic acoustic sensing technology as described in any one of claims 1 to 4.

Images