Subway tunnel leaky coaxial cable fault early warning method and system
By collecting and processing leaked cable signal data in real time, combining time-frequency diagrams and MSSA-SVM models, the problems of discontinuous monitoring and inaccurate positioning in traditional systems are solved, efficient and low-cost fault warning is achieved, and the safety and reliability of subway operations are ensured.
Patent Information
- Application Number
- CN202510492998.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-18
- Publication Date
- 2025-07-18
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional leaked coaxial cable fault warning systems cannot achieve continuous and real-time monitoring, inaccurate positioning, easy to be disturbed, and have high maintenance costs, and cannot meet the real-time and reliability requirements of intelligent manufacturing technology for fault monitoring and early warning.
Real-time acquisition of tunnel leakage signal data, amplification and filtering, output time-frequency diagrams, combined with threshold setting method and MSSA-SVM model for fault warning judgment and positioning, and use distributed fiber sensors and phase-locked loop algorithm for signal processing.
Real-time monitoring of leaky cables and high-precision fault positioning are achieved, the accuracy of fault detection and anti-interference ability are improved, maintenance costs are reduced, and the safety and reliability of subway operations are ensured.
Smart Images
Figure CN120331878A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of subway tunnel monitoring, and particularly to a method and system for early warning of faults in leaky coaxial cables in subway tunnels Background Art In traditional leaky coaxial cable fault early warning systems, monitoring technologies based on single-point or quasi-distributed sensors are usually used. This technology mainly relies on sensors installed at specific positions or areas to monitor the status of leaky cables. However, these sensors usually can only provide limited information and often cannot achieve continuous and real-time monitoring of the entire leaky cable. In addition, traditional technologies also have deficiencies such as inaccurate positioning, susceptibility to interference, high maintenance costs, and slow alarm response
[0002] With the rapid development of intelligent manufacturing technology, the level of industrial automation and intelligence has been continuously improved, and the requirements for the real-time performance and reliability of fault monitoring and early warning of coaxial cables are also getting higher and higher. Therefore, developing a system that can continuously monitor and provide real-time early warning, high-precision positioning, strong anti-interference ability, low maintenance cost, and multi-parameter measurement is of great significance for improving work efficiency, reducing costs, and ensuring train operation safety Summary of the Invention
[0003] The purpose of the present invention is to provide a method and system for early warning of faults in leaky coaxial cables in subway tunnels, which can real-time monitor the status information of leaky cables, timely detect potential faults or anomalies, and also provide strong guarantees for the safety and reliability of subway operation
[0004] To achieve this purpose, the present invention adopts the following technical solutions: Provide a method for early warning of faults in leaky coaxial cables in subway tunnels, including the following steps: S1: Real-time collect the signal data of the tunnel leaky cable, amplify and filter the signal, and output a time-frequency diagram S2: Read the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and use the threshold setting method for fault early warning judgment and the MSSA-SVM model for accurate fault location S3: Output alarm information according to the fault early warning information and fault location information
[0005] As a preferred solution of the method for early warning of faults in leaky coaxial cables in subway tunnels, in step S1 of real-time collecting the signal data of the tunnel leaky cable, amplifying and filtering the signal, and outputting a time-frequency diagram, it includes: S11: Based on the designed amplification technology algorithm of the phase-locked loop, perform pre-amplification processing on the signal As a preferred solution of the method for early warning of faults in leaky coaxial cables in subway tunnels, the design steps of the amplification technology algorithm of the phase-locked loop include: S111: Design a loop filter. The transfer function of the loop filter is expressed as: where Kvco is the gain of the voltage - controlled oscillator, C1 and C2 are the capacitors in the filter, R is the resistor, N is the division ratio of the frequency divider, and KpD is the gain of the phase - detector. S112: Design a voltage - controlled oscillator. The transfer function of the voltage - controlled oscillator can be expressed as: where f0 is the center frequency of the VCO, Kvco is the gain of the VCO, and Vctrl is the control voltage. S113: Design a phase - detector: where Icp is the output current of the charge pump. S114: Adjust the PLL bandwidth. Adjust the PLL bandwidth to the target value, and redesign the parameters Kpllp and Kplli of the PI controller. According to the closed - loop transfer function of the second - order system: where ωn is the natural frequency and ξ is the damping ratio. S115: Calculate the PI controller parameters. Calculate the PI controller parameters according to the natural frequency and damping ratio: where ωn is the natural frequency and ξ is the damping ratio.
[0006] As an optimal scheme of the subway tunnel leaky coaxial cable fault warning method, in step S1 of collecting the signal data of the tunnel leaky cable in real time, amplifying, filtering the signal, and outputting the time - frequency diagram, it includes: S12: Signal framing: Divide the amplified signal into multiple small frames. S13: Compare with the time - frequency of the normal signal and preliminarily judge whether the leaky cable is faulty. S14: If so, apply the Fourier transform to each frame to convert the time - domain signal into a frequency - domain signal. S15: Apply the window function: Apply the window function to each frame to reduce the edge effect. S16: Combine the spectrum matrices: Combine the Fourier transform results of each frame into a spectrum matrix. S17: Output the time - frequency diagram: Draw the time - frequency diagram according to the spectrum matrix.
[0007] As a preferred solution for the fault warning method of the leaky coaxial cable in the subway tunnel, in step S2 of reading the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and using the threshold setting method for fault warning judgment and the MSSA-SVM model for accurate fault location, it includes: S21: Set the mean plus standard deviation threshold as Xy; S22: According to the output time-frequency diagram, read the eigenvalue data of the amplitude and phase information of the frequency components; S23: Set the mean standard deviation, compare the calculated mean and standard deviation X with the eigenvalue, and judge whether it exceeds the threshold; S24: If yes, use the MSSA-SVM model to lock the fault location.
[0008] As a preferred solution for the fault warning method of the leaky coaxial cable in the subway tunnel, in step S2 of reading the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and using the threshold setting method for fault warning judgment and the MSSA-SVM model for accurate fault location, it includes: S25: Set the percentile threshold as Hy; S26: According to the output time-frequency diagram, read the eigenvalue data of the amplitude and phase information of the frequency components; S27: Set the percentile value, calculate the specific percentile H according to the sorted data, compare it with the eigenvalue, and judge whether it exceeds the threshold; S28: If yes, use the MSSA-SVM model to lock the fault location.
[0009] As a preferred solution for the fault warning method of the leaky coaxial cable in the subway tunnel, the calculation of setting the threshold by the mean plus standard deviation method includes the following steps: S211: Calculate the mean: Use the AVERAGE function to calculate the mean of the data, and the formula is: where, x i is each data point, and n is the total number of data points; S212: Calculate the standard deviation: Use the STDEV.P or STDEV.S function to calculate the standard deviation, and the formula is: Use STDEV.P for population data and STDEV.S for sample data; S213: Set the threshold: Calculate the mean plus or minus one or more standard deviations to obtain the upper and lower limit thresholds: Among them, k is a constant, usually taking 1 or 2, representing the range of one or two standard deviations.
[0010] As an optimal solution of the subway tunnel leaky coaxial cable fault warning method, the calculation of setting the threshold by the percentile method includes the following steps: Calculate the threshold using the percentile formula, and the formula is: Among them, P is the percentile value, N is the total number of data points, the th value is the (P / 100×N)th value of the sorted data. If the calculation result is not an integer, it needs to be rounded up to the nearest integer.
[0011] The present invention also provides a subway tunnel leaky coaxial cable fault warning system, including: A data acquisition and processing module, which is used to collect the signal data of the tunnel leaky cable in real time, amplify and filter the signal, and output a time-frequency diagram; A fault warning and positioning module, which is used to read the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and use the threshold setting method to perform fault warning judgment and the MSSA-SVM model to perform accurate fault positioning; An alarm module, which is used to output alarm information according to the fault warning information and the fault positioning information.
[0012] The beneficial effects of the present invention: The subway tunnel leaky coaxial cable fault warning method and system proposed by the present invention can monitor the state information of the leaky cable in real time, discover potential faults or abnormalities in time, and can also provide strong guarantees for the safety and reliability of subway operation. Description of the Drawings
[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments of the present invention. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.
[0014] Figure 1 It is the flowchart of the subway tunnel leaky coaxial cable fault warning method described in an embodiment of the present invention; Figure 2 It is the structural schematic block diagram of the subway tunnel leaky coaxial cable fault warning system described in an embodiment of the present invention; Figure 3 It is the specific method flowchart of outputting alarm information according to the fault warning information and the fault positioning information described in an embodiment of the present invention. Detailed Embodiments
[0015] The following will describe the embodiments of the present disclosure in detail with reference to the accompanying drawings.
[0016] The following uses specific specific examples to illustrate the implementation manners of the present disclosure. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific implementation manners, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope protected by the present disclosure.
[0017] Referring to Figure 1 , an embodiment of the present invention provides a method for early warning of subway tunnel leaky coaxial cable faults, including the following steps: S1: Real-time collect the signal data of the tunnel leaky cable, amplify and filter the signal, and output a time-frequency diagram; S2: Read the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and use the threshold setting method for fault early warning judgment and the MSSA-SVM model for accurate fault location; S3: Output an alarm message according to the fault early warning information and the fault location information.
[0018] As described in step S1, select the installation position of the distributed optical fiber sensor unit according to the leaky cable position and scene requirements, install and debug the optical fiber sensing unit to ensure the normal operation of its signal and data transmission, and set parameters such as the detection range, sensitivity, positioning accuracy, spatial resolution, alarm threshold, and signal processing algorithm to real-time collect the signal data of the tunnel leaky cable, amplify and filter the signal, and output a time-frequency diagram.
[0019] As described in step S3, the alarm module can display the fault early warning information and the fault location information on the user interaction interface, and can use the method of sound and light reminder to notify the operation and maintenance personnel to handle the fault.
[0020] In some embodiments, in step S1 of real-time collecting the signal data of the tunnel leaky cable, amplifying and filtering the signal, and outputting a time-frequency diagram, it includes: S11: Based on the designed amplification technology of the phase-locked loop (PLL) algorithm, perform pre-amplification processing on the signal; As described in step S11, when designing a PLL, a set of key parameters need to be specified first, including loop bandwidth (ωn), noise bandwidth (Bn), damping factor (ζ), acquisition time (Tp), lock time (TL), etc. According to the characteristics of the input signal, select the type and operating frequency of the phase detector. At the same time, according to the requirements of the output signal, determine the operating frequency range of the VCO, and determine the PLL circuit model. Specify the order of the PLL (usually second order or third order), and accordingly select the circuit form of the loop filter.
[0021] The specific implementation steps are as follows: S111: Design the loop filter. The transfer function of the loop filter is expressed as: where Kvco is the gain of the voltage-controlled oscillator, C1 and C2 are the capacitors in the filter, R is the resistor, N is the division ratio of the frequency divider, and KpD is the gain of the phase detector; S112: Design the voltage-controlled oscillator. The transfer function of the voltage-controlled oscillator can be expressed as: where f0 is the center frequency of the VCO, Kvco is the gain of the VCO, and Vctrl is the control voltage; S113: Design the phase detector: where Icp is the output current of the charge pump; S114: Adjust the PLL bandwidth. Adjust the PLL bandwidth to the target value, and redesign the parameters Kpllp and Kplli of the PI controller. According to the closed-loop transfer function of the second-order system: where ωn is the natural frequency and ξ is the damping ratio; S115: Calculate the PI controller parameters. Calculate the PI controller parameters according to the natural frequency and damping ratio: where ωn is the natural frequency and ξ is the damping ratio.
[0022] In some embodiments, in step S1 of collecting the signal data of the tunnel leaky cable in real time, amplifying, filtering the signal, and outputting the time-frequency diagram, it includes: S12: Signal framing: Divide the amplified signal into multiple small frames; the length of each frame is usually n_fft. Set the frame shift (hop length), usually a part of the window length (such as 50% overlap).
[0023] S13: Compare the time-frequency of the normal signal, and preliminarily judge whether the leaky cable is faulty; S14: If so, apply the Fourier transform to each frame to convert the time-domain signal into a frequency-domain signal; S15: Apply a window function: Apply a window function (such as a Hamming window or a Hanning window) to each frame to reduce edge effects; S16: Combine the spectral matrices, and combine the Fourier transform results of each frame into a spectral matrix, where the rows represent frequencies and the columns represent time; S17: Output the time-frequency diagram: Draw a time-frequency diagram based on the spectral matrix, where the abscissa is time, the ordinate is frequency, and the z-axis is the signal energy / power.
[0024] In this embodiment, the short-time Fourier transform (STFT) algorithm decomposes different time-frequency components Among them, when the signal received by the distributed optical fiber sensing unit reaches the data processing center, it is amplified and then immediately filtered. The filtering method of the present invention is the short-time Fourier algorithm, which is used for frequency-domain analysis of non-periodic signals, retains the information in the time domain and the frequency domain, and performs preliminary fault judgment.
[0025] The short-time Fourier algorithm can perform frequency-domain analysis on non-periodic signals and retain the information in the time domain and the frequency domain. The selection of the window function has an important impact on the time resolution and the frequency resolution. The wider the window function, the higher the frequency resolution, but the lower the time resolution; the narrower the window function, the higher the time resolution, but the frequency resolution will decrease. The time-frequency resolution is uneven, the extraction of signal features is relatively rough, and it is more sensitive to high-frequency components.
[0026] The steps and algorithm of the short-time Fourier transform are as follows: Window function weighting: Apply a window function to the signal of each short time period. Commonly used window functions include Hamming windows, Hanning windows, etc.
[0027] The window function formula is: ω(n)=window function(n) Among them, ω(n) is the window function value, and n is the sample index. For example, the formula for the Hamming window is: where N is the length of the window function Calculate the Fourier transform of the frame: Calculate the Fourier transform of each windowed short-time period signal to obtain the spectrum of each frame. The mathematical expression of STFT is: Among them, x(t) is the input signal, w(t−τ) is the window function, τ represents the position of the window, and ω is the frequency variable.
[0028] Filtering Processing: Apply a filter in the time-frequency domain, such as Wiener filtering, to reduce noise or enhance the signal. The basic idea of Wiener filtering is to minimize the mean square value of the error, and its formula is: where S(f,t) is the power spectral density of the signal and N(f) is the power spectral density of the noise The above application of the window function, combination of the spectral matrix, and output of the time-frequency diagram are the key points of signal filtering. The following is an introduction and suggestions for them.
[0029] Application of the window function: The window function is mainly used to reduce spectral leakage and avoid spectral aliasing to ensure the accuracy of the transformation result. Common types of window functions include the Hanning window and the Hamming window, each having different characteristics and application scenarios. When choosing a window function, it is necessary to balance the requirements of time resolution and frequency resolution. Because the wider the window function, the higher the frequency resolution but the lower the time resolution; the narrower the window function, the higher the time resolution but the lower the frequency resolution will be.
[0030] Combination of the spectral matrix: After dividing the signal into frames and applying the FFT, a two-dimensional matrix formed by combining the spectral results of each frame in chronological order. The rows of this matrix represent the frequency components, the columns represent the time points, and the element values reflect the energy distribution of the signal at different times and frequencies.
[0031] Output of the time-frequency diagram: The horizontal axis of the time-frequency diagram represents time, the vertical axis represents frequency, and the color or grayscale value in the diagram reflects the intensity or energy of the signal at the corresponding time and frequency. Through the time-frequency diagram, the frequency characteristics of the signal changing with time can be intuitively observed, which is very useful for analyzing non-stationary signals or time-varying signals.
[0032] Based on these key steps, the following are some suggestions For stationary signals, a wider window can be selected to improve the frequency resolution. For non-stationary signals or scenarios requiring high time resolution, a narrower window should be chosen.
[0033] Select a window function with smooth spectral characteristics (such as the Hamming window, Hanning window) to reduce spectral leakage.
[0034] Adjust the window length and overlap length according to the signal length and sampling rate to balance the time resolution and frequency resolution; select an appropriate color mapping scheme according to the signal intensity and frequency distribution to enhance the readability of the time-frequency diagram.
[0035] Adjust parameters such as the brightness, contrast, and resolution of the image as needed to obtain a clearer time-frequency diagram.
[0036] Refer to Figure 3, in some embodiments, in step S2 of reading the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram and using the threshold setting method to perform fault warning judgment and the MSSA-SVM model to perform accurate fault location, it includes: S21: Set the mean plus standard deviation threshold as Xy; S22: According to the output time-frequency diagram, read the eigenvalue data of the amplitude and phase information of the frequency components; S23: Set the mean standard deviation, compare the calculated mean and standard deviation X with the eigenvalue, and determine whether it exceeds the threshold; S24: If so, use the MSSA-SVM model to lock the fault location.
[0037] In this embodiment, in step S2 of reading the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram and using the threshold setting method to perform fault warning judgment and the MSSA-SVM model to perform accurate fault location, it also includes: S25: Set the percentile threshold as Hy; S26: According to the output time-frequency diagram, read the eigenvalue data of the amplitude and phase information of the frequency components; S27: Set the percentile value, calculate the specific percentile H according to the sorted data, compare it with the eigenvalue, and determine whether it exceeds the threshold; S28: If so, use the MSSA-SVM model to lock the fault location.
[0038] Where the setting rules of the mean plus standard deviation threshold Xy and the percentile threshold Hy In fault detection, when using the mean plus standard deviation and percentile as features, the setting of the threshold is a key step, which directly affects the accuracy and efficiency of the detection. However, there is no fixed value for the setting of the threshold because it depends on multiple factors such as the specific application scenario, data characteristics, and fault type.
[0039] The mean plus standard deviation threshold Xy follows such a setting principle: Assume that the data is approximately normally distributed, and most data is concentrated around the mean. Select a multiple of the standard deviation (such as 1 time, 2 times, or 3 times) to determine the threshold to cover different proportions of the data. Identify and process outliers to avoid affecting the calculation of the mean and standard deviation. Set the threshold in combination with the specific business scenario and risk tolerance. Update the threshold regularly as the data changes to maintain its effectiveness. Verify the effectiveness of the threshold through historical data and real-time monitoring.
[0040] The percentile threshold Hy follows the following setting principle: First, sort the data from smallest to largest to determine the data distribution. Calculate the position of a specific percentile. If the calculated position is an integer, the value at that position is the desired percentile. If the position is not an integer, linear interpolation is required to estimate the percentile value. The percentile method is applicable to data with various distributions, including skewed distributions and data with unknown distributions. The threshold should be adjusted dynamically according to the data changes to maintain its effectiveness and adaptability. When setting the threshold, it is necessary to combine the specific business scenario and requirements and select an appropriate percentile as the threshold.
[0041] Specifically, the calculation of setting the threshold by the mean plus standard deviation method includes the following steps: S211: Calculate the mean: Use the AVERAGE function to calculate the mean of the data. The formula is: where, x i is each data point, and n is the total number of data points; S212: Calculate the standard deviation: Use the STDEV.P or STDEV.S function to calculate the standard deviation. The formula is: Use STDEV.P for population data and STDEV.S for sample data; S213: Set the threshold: Calculate the mean plus or minus one or more standard deviations to obtain the upper and lower limit thresholds: where, k is a constant, usually taking 1 or 2, representing the range of one or two standard deviations.
[0042] Specifically, the calculation of setting the threshold by the percentile method includes the following steps: Use the percentile formula to calculate the threshold. The formula is: where, P is the percentile value, N is the total number of data points, and the th value is the (P / 100×N)th value of the sorted data. If the calculation result is not an integer, it needs to be rounded up to the nearest integer.
[0043] The MSSA - SVM model is a fault warning system that combines the multi - feature sparrow search algorithm (MSSA) and support vector machine (SVM).
[0044] Referring to Figure 2 , an embodiment of the present invention also provides a subway tunnel leaky coaxial cable fault warning system, including: The data acquisition and processing module is used to collect the signal data of the tunnel leaky cable in real time, amplify and filter the signal, and output the time-frequency diagram; The fault warning and location module is used to read the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and use the threshold setting method for fault warning judgment and the MSSA-SVM model for accurate fault location; The alarm module is used to output alarm information according to the fault warning information and the fault location information.
[0045] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "middle", "length", "upper", "lower", "front", "rear", "vertical", "horizontal", "inner", "outer", "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.
[0046] In the present invention, unless otherwise clearly specified and limited, the first feature being "on" the second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. The meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically limited.
[0047] In the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection, an electrical connection or communication with each other; it may be directly connected, or indirectly connected through an intermediate medium, and may be the internal communication of two elements or the interaction relationship between two elements, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0048] The above is only to illustrate the embodiments of the present invention and is not intended to limit the present invention. For those skilled in the art, any modifications, equivalent replacements, improvements, etc. made without creative labor within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A fault warning method for a leaky coaxial cable in a subway tunnel, characterized in that, It includes the following steps: S1: Collect the signal data of the tunnel leaky cable in real time, amplify and filter the signal, and output the time-frequency diagram; S2: Read the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and use the threshold setting method for fault warning judgment and the MSSA-SVM model for accurate fault location; S3: Output alarm information according to the fault warning information and fault location information.
2. The subway tunnel leaky coaxial cable fault early warning method according to claim 1, characterized in that, In the step S1 of collecting the signal data of the tunnel leaky cable in real time, amplifying and filtering the signal, and outputting the time-frequency diagram, it includes: S11: Based on the designed amplification technology algorithm of the phase-locked loop, perform pre-amplification processing on the signal.
3. The subway tunnel leaky coaxial cable fault warning method according to claim 2, characterized in that, The design steps of the amplification technology algorithm of the phase-locked loop include: S111: Design a loop filter, and the transfer function of the loop filter is expressed as: where, Kvco is the gain of the voltage-controlled oscillator, C1 and C2 are the capacitors in the filter, R is the resistor, N is the frequency division ratio of the frequency divider, and KpD is the gain of the phase detector; S112: Design a voltage-controlled oscillator, and the transfer function of the voltage-controlled oscillator can be expressed as: where, f0 is the center frequency of the VCO, Kvco is the gain of the VCO, and Vctrl is the control voltage; S113: Design a phase detector: where, Icp is the output current of the charge pump; S114: Adjust the PLL bandwidth, adjust the PLL bandwidth to the target value, and re-design the parameters Kpllp and Kplli of the PI controller. According to the closed-loop transfer function of the second-order system: where, ωn is the natural frequency and ξ is the damping ratio; S115: Calculate the PI controller parameters, and calculate the PI controller parameters according to the natural frequency and damping ratio: where, ωn is the natural frequency and ξ is the damping ratio.
4. The subway tunnel leaky coaxial cable fault warning method according to claim 1, characterized in that In the step S1 of collecting the signal data of the tunnel leaky cable in real time, amplifying and filtering the signal, and outputting the time-frequency diagram, it includes: S12: Signal frame division: Divide the amplified signal into multiple small frames; S13: Compare with the time-frequency of the normal signal to preliminarily judge whether the leaky cable is faulty; S14: If so, apply the Fourier transform to each frame to convert the time-domain signal into a frequency-domain signal; S15: Apply a window function: Apply a window function to each frame to reduce the edge effect; S16: Combine the spectrum matrices, and combine the Fourier transform results of each frame into a spectrum matrix; S17: Output the time-frequency diagram: Draw the time-frequency diagram according to the spectrum matrix.
5. The subway tunnel leaky coaxial cable fault warning method according to claim 1, characterized in that, In the step S2 of reading the eigenvalue data of the amplitude and phase information of the frequency components according to the output time-frequency diagram, and using the threshold setting method for fault warning judgment and the MSSA-SVM model for accurate fault location, it includes: S21: Set the mean plus standard deviation threshold as Xy; S22: According to the output time-frequency diagram, read the eigenvalue data of the amplitude and phase information of the frequency components; S23: Set the mean standard deviation, compare the calculated mean and standard deviation X with the eigenvalue, and judge whether it exceeds the threshold; S24: If so, use the MSSA-SVM model to lock the fault location.
6. The subway tunnel leaky coaxial cable fault warning method according to claim 1, characterized in that In step S2 of reading the eigenvalue data of the amplitude and phase information of the frequency components from the output time-frequency diagram and using the threshold setting method for fault warning judgment and the MSSA-SVM model for accurate fault location, it includes: S25: Set the percentile threshold as Hy; S26: According to the output time-frequency diagram, read the eigenvalue data of the amplitude and phase information of the frequency components; S27: Set the percentile value, calculate the specific percentile H based on the sorted data, compare it with the eigenvalue, and judge whether it exceeds the threshold; S28: If so, use the MSSA-SVM model to lock the fault location.
7. The subway tunnel leaky coaxial cable fault warning method according to claim 5, characterized in that, The calculation of setting the threshold by the mean plus standard deviation method includes the following steps: S211: Calculate the mean: Use the AVERAGE function to calculate the mean of the data, and the formula is: where x i is each data point and n is the total number of data points; S212: Calculate the standard deviation: Use the STDEV.P or STDEV.S function to calculate the standard deviation, and the formula is: Use STDEV.P for the overall data and STDEV.S for the sample data; S213: Set the threshold: Calculate the mean plus or minus one or more standard deviations to obtain the upper and lower threshold values: Among them, k is a constant, usually taking 1 or 2, representing the range of one or two standard deviations.
8. The subway tunnel leaky coaxial cable fault warning method according to claim 6, characterized in that, The calculation of setting the threshold by the percentile method includes the following steps: Use the percentile formula to calculate the threshold, and the formula is: Among them, P is the percentile value, N is the total number of data points, and the th value is the (P / 100×N)th value of the sorted data. If the calculation result is not an integer, it needs to be rounded up to the nearest integer.
9. A subway tunnel leaky coaxial cable fault warning system, characterized in that, It includes: The data acquisition and processing module is used to collect the signal data of the tunnel leaky cable in real time, amplify and filter the signal, and output the time-frequency diagram; The fault warning and location module is used to read the eigenvalue data of the amplitude and phase information of the frequency components from the output time-frequency diagram, and use the threshold setting method for fault warning judgment and the MSSA-SVM model for accurate fault location; The alarm module is used to output alarm information according to the fault warning information and the fault location information.