Contact network cable state real-time monitoring method and sensing system based on distributed optical fiber sensing

Abstract

The invention discloses an overhead line system cable state real-time monitoring method and sensing system based on distributed optical fiber sensing. The Mach-Zehnder interference and phi-OTDR fusion type distributed optical fiber sensing system comprises a first light source, a second light source, a Mach-Zehnder interferometer, a phi-OTDR and a data acquisition and processing module. Raman amplifiers are arranged at the two ends of the Mach-Zehnder interferometer, so that the sensing distance is prolonged; the optical fiber sensing system extracts an interference optical signal and a backward Rayleigh scattering optical signal corresponding to a fault event after phase modulation when the fault event occurs; then processing the extracted backward Rayleigh scattering light signal to obtain intensity change information of a fault event, and demodulating the position of the fault event; and sending the two-dimensional optical signal into a pre-trained Swin Transform network model to extract a time domain feature, a frequency domain feature and a spatial domain feature, and identifying the type of a fault event through a classifier.

Description

Technical Field

[0001] The present invention belongs to the field of sensing and intelligent detection, and particularly relates to a method based on Mach-Zehnder interferometry and Real-time monitoring and sensing system of contact network cable status with integrated distributed optical fiber sensing. Background Art

[0002] The operation status detection of the contact network currently relies mainly on regular and irregular manual inspections, vehicle inspections, and inspection vehicle inspections. It is still unable to achieve continuous recording and monitoring of the operation status and technical parameters, and is unable to discover and eliminate problems in the operation status of the contact network in real time. The existing 6C system of the railway also lacks real-time online monitoring and detection capabilities, and mainly relies on cameras for high-definition imaging. In the later stage, many experienced engineering and technical personnel are required to perform manual image recognition and judgment. The amount of work is huge, the efficiency is low, and the data on the operation status of the contact network is relatively limited, which restricts the safety, reliability and maintenance efficiency of the contact network facilities.

[0003] In recent years, there have been cases where traffic has been affected by overhead contact network faults. In particular, additional conductors such as lightning arresters and overhead ground wires are directly connected to the integrated grounding system. Faults such as broken wires and falling off are difficult to identify and locate by traditional protection systems. Failure to timely determine and handle faults may expand the scope of overhead contact network faults and may even affect the safe passage of vehicles, which has a significant impact on driving efficiency, driving safety, and fault repair. Cable faults are difficult to detect early, are highly sporadic, and are difficult to locate, which directly affects the improvement of the reliability of the overhead contact network system. If the operating status of additional conductors can be monitored in real time, the fault information of additional conductors can be timely grasped, and corresponding maintenance strategies can be adopted according to the fault type to avoid the expansion of accidents, it will play an important role in improving the overall operational safety of the railway overhead contact network. At present, China has begun to use optical fiber technology to realize intelligent monitoring or fault location research on transmission lines. Tong Tongli et al. (Tong Tongli, Gao Yan, Wang Pengfei et al. Overhead line galloping monitoring method based on distributed optical fiber sensing technology combined with Wiener filtering [J]. Power Grid and Clean Energy, 2022, 38(09): 17-24.) proposed an electromagnetic interference-resistant, long-distance overhead line galloping monitoring method based on distributed optical fiber sensing technology combined with Wiener filtering. Wang Yougang (Wang Yougang. Research on distributed stress monitoring model of optical fiber composite overhead phase line based on LSTM [J]. Electric Power Big Data, 2023, 26(11): 33-40. DOI: 10.19317 / j.cnki.1008-083x.2023.11.004.) proposed a distributed stress detection method for optical fiber composite overhead phase line based on 1STM algorithm. Zhang Qi (Zhang Qi. Fault location and analysis of optical cables of power overhead lines based on Brillouin optical fiber sensing [D]. Harbin University of Science and Technology, 2022. DOI: 10.27063 / d.cnki.ghlgu.2022.000677.) In view of the technical bottlenecks and limitations existing in the current maintenance process of power overhead lines, a method for fault location and analysis of optical cables of power overhead lines based on Brillouin optical fiber sensing is proposed.

[0004] Although relevant research on intelligent monitoring of transmission lines has begun, its application scenarios, functional positioning and hierarchical architecture are quite different from those of the overhead contact network, making it difficult to meet the complex application conditions of railways. Therefore, it is necessary to develop and design a distributed optical fiber sensing cable condition monitoring equipment with simple structure, real-time monitoring, high recognition accuracy and high positioning accuracy for railway overhead contact wires in difficult and complex environments. Summary of the invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and to propose a real-time monitoring and sensing system for the state of overhead contact cables based on fused distributed optical fiber sensing, so as to solve the monitoring, identification and positioning technology of possible disconnection, loosening, lightning strikes, abnormal temperature rise and other conditions of the overhead contact wires in complex environments and operating conditions. In the long-distance and large-scale monitoring of the state of overhead contact cables, there are problems such as the inability to quickly and accurately identify, accurately locate and poor stability. Based on Mach-Zehnder interferometry and phase-sensitive optical time-domain reflectometry technology (hereinafter referred to as )'s fusion distributed optical fiber sensing system continuously monitors the state of the overhead line cable through the Mach-Zehnder interferometer sensing part, with a wide frequency response range; when a fault is detected, it is simultaneously based on Mach-Zehnder interferometer and The sensor light signal is recognized and The position information can be demodulated and multi-point positioning can be achieved, thus realizing the complementary advantages of the above two sensing systems.

[0006] A Mach-Zehnder interference A fusion distributed optical fiber sensing system, comprising a first light source, a second light source, a Mach-Zehnder interferometer, and data acquisition and processing modules;

[0007] The first light source is sequentially connected to the first fiber attenuator, the first fiber coupler and the input end of the Mach-Zehnder interferometer, and the output end of the Mach-Zehnder interferometer is sequentially connected to the first fiber coupler, the first photodetector and the data acquisition and processing module;

[0008] The second light source is connected in sequence to the second optical fiber attenuator, the semiconductor optical amplifier, and a data acquisition and processing module; the output ends of the semiconductor optical amplifier are respectively connected to the data acquisition and processing module and The pulse electrical signal used to transmit to the data acquisition and processing module as a trigger signal, and the pulse light to Said It includes a pulse optical amplifier, an optical fiber circulator, a Mach-Zehnder interferometer, an optical fiber circulator, and a second optical filter connected in sequence, wherein the second optical filter is connected in sequence to a second photodetector and a data acquisition and processing module;

[0009] The laser from the second light source enters the Mach-Zehnder interferometer through an optical fiber circulator and a dense wavelength division multiplexer, and is coupled into the sensing optical fiber together with the laser from the first light source;

[0010] Moreover, a first Raman amplifier is provided at the input end of the Mach-Zehnder interferometer, and a second Raman amplifier is provided at the output end of the Mach-Zehnder interferometer, thereby extending the sensing distance;

[0011] The data acquisition and processing module includes a signal extraction and preprocessing submodule, a positioning submodule and a fault identification submodule;

[0012] The signal extraction and preprocessing submodule is used to extract the Mach-Zehnder interferometer and The interference optical signal and the backscattered optical signal corresponding to the phase-modulated fault event of the fusion distributed optical fiber sensing subsystem are then preprocessed, that is, the endpoint detection of the interference optical signal and the moving average algorithm processing of the backscattered optical signal are performed;

[0013] The positioning submodule is used to perform difference calculation on the backward Rayleigh scattered light signal to demodulate the position of the fault event;

[0014] The fault identification submodule is used to convert the interference light signal and the backscattered Rayleigh light signal preprocessed by the signal extraction and preprocessing submodule into a two-dimensional time-frequency spectrum through wavelet transform, and then send the two-dimensional time-frequency spectrum to the pre-trained Swin Transformer network model to extract the time domain features, frequency domain features and spatial domain features of the light signal, and identify the type of the fault event through a classifier.

[0015] Furthermore, the splitting ratios of the first optical fiber coupler and the second optical fiber coupler are both 50:50, the wavelength of the first optical fiber coupler is 1550 nm, and the wavelength of the second optical fiber coupler is 1455 nm.

[0016] Furthermore, the output lights of the first Raman amplifier and the second Raman amplifier are in the 1455 nm band.

[0017] Furthermore, the central wavelength of the first optical filter is the central wavelength λ1±0.2 nm of the first light source, and only the laser light emitted by the first light source can pass through, so as to filter out the pulse light from the second light source.

[0018] Furthermore, the first light source and the second light source are narrow-band continuous light lasers with an operating wavelength of 1550nm and a maximum output power of 10mW.

[0019] Furthermore, the pre-set fault events include disconnection, loosening, lightning strike, abnormal temperature rise and no fault.

[0020] A real-time monitoring method for contact network cable status based on distributed optical fiber sensing, the method uses the Mach-Zehnder interferometer and Fusion distributed optical fiber sensing system, including:

[0021] Step 1: Real-time detection of interference light signals. When an abnormal condition occurs in the overhead line cable, the sensing light signal changes, and the phase-modulated interference light signal and the backscattered Rayleigh light signal are obtained.

[0022] Step 2: Remove the DC component of the interference light signal obtained from the fault event, perform endpoint detection, and obtain the interference light signal corresponding to the fault event;

[0023] Perform moving average algorithm and difference operation on the backscattered Rayleigh light signal obtained from the fault event to obtain the obvious intensity change information caused by the fault event and demodulate the location of the fault event at the same time;

[0024] Step 3: Perform wavelet transform on the interference light signal and backscattered light signal processed in step 2 to convert them into a two-dimensional time-frequency spectrum. Then, the two-dimensional time-frequency spectrum is sent to the pre-trained Swin Transformer network model to extract the time domain features, frequency domain features, and spatial domain features of the light signal, and the type of fault event is identified through the classifier.

[0025] The step 1 specifically includes:

[0026] When an abnormal condition occurs in the overhead line cable, it will cause changes in the sensor light signal; the Mach-Zehnder interferometer and In the fusion-type distributed optical fiber sensing system, the signal from the first light source passes through the first optical fiber attenuator, the first optical fiber coupler, the Mach-Zehnder interferometer, and the first optical fiber coupler in sequence to obtain the phase-modulated interference light signal, which is then sent to the data acquisition and processing module after passing through the first photoelectric detector to realize the feature extraction of the modulated light signal;

[0027] When an abnormal condition occurs in the overhead line cable, The back-Rayleigh scattered light signal from the second light source passes through the second optical fiber attenuator, semiconductor optical amplifier, pulse optical amplifier, optical fiber circulator, dense wavelength division multiplexer in sequence, enters the Mach-Zehnder interferometer and is transmitted in the sensing optical fiber. The continuous back-Rayleigh scattered light signal generated by it passes through the optical fiber circulator and the second optical filter to obtain the back-Rayleigh scattered light signal, and is sent to the data acquisition and processing module after passing through the second photoelectric detector to realize the back-Rayleigh scattered light signal feature extraction.

[0028] The processing of the backscattered Rayleigh light signal in step 2 includes:

[0029] A fixed backscattering curve is selected as the reference curve for the difference operation, and the Mach-Zehnder interferometer and The backscattered Rayleigh scattering signal curves collected by the fusion distributed optical fiber sensing system at other times are subtracted from the reference curve in turn to obtain the obvious intensity change information caused by the fault event, and the location information of the fault event is obtained by detecting the echo intensity change and its delay time.

[0030] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0031] The present invention adopts bidirectional distributed Raman amplification to uniformly amplify the transmission light along the optical fiber, effectively extending the sensing distance and improving the signal-to-noise ratio of the remote sensing optical signal;

[0032] right The sensor light signal is processed by algorithm to improve the positioning accuracy of fault events;

[0033] The present invention integrates Mach-Zehnder interferometer and The sensor light signal is used for feature extraction, and the light signal is converted into a two-dimensional time-frequency signal to extract the features of the fault event, which effectively enhances the ability of the deep learning model to extract the essential spatiotemporal characteristics of the fault event, thereby obtaining better event recognition and detection performance, increasing the accuracy of pattern recognition, and further reducing the false alarm rate of the system; and the adopted Swin Transformer network model can still maintain a fast recognition speed while ensuring a high recognition rate, meeting the needs of actual detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flow chart showing a method for real-time monitoring of contact network cable status based on distributed optical fiber sensing according to the present invention;

[0035] Figure 2 Shown are Mach-Zehnder interferometry and Schematic diagram of the fusion distributed optical fiber sensing system;

[0036] Figure 3 This is a flow chart of the network model structure of the Swin Transformer adopted in the present invention.

[0037] In the figure:

[0038] 1: First light source 2: Second light source 3: First optical fiber attenuator

[0039] 4, 13: first fiber coupler 5: first Raman amplifier 6: second Raman amplifier

[0040] 7, 8: Second fiber coupler 9: First wavelength division multiplexer

[0041] 10: Second wavelength division multiplexer 11: Third wavelength division multiplexer 12: Fourth wavelength division multiplexer

[0042] 14: Second optical fiber attenuator 15: Semiconductor optical amplifier

[0043] 16: Pulse optical amplifier 17: Fiber circulator 18: Dense wavelength division multiplexer

[0044] 19: First optical filter 20: Second optical filter 21: First photodetector

[0045] 22: Second photoelectric detector 23: Data acquisition card 24: Industrial computer DETAILED DESCRIPTION

[0046] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The described specific embodiments are only used to explain the present invention and are not intended to limit the present invention.

[0047] like Figure 1 As shown, a method for real-time monitoring of the state of overhead line cables based on distributed optical fiber sensing is provided. The real-time monitoring method utilizes a Mach-Zehnder interferometer and Fusion distributed fiber optic sensing system, the Mach-Zehnder interferometer and The integrated distributed fiber optic sensing system has five pre-set fault events, namely wire breakage, looseness, lightning strike, abnormal temperature rise and no fault. It can alarm according to the degree of harm caused by the fault event, reminding relevant personnel to intervene in time to ensure the safety of railway operations.

[0048] like Figure 2 As shown, the Mach-Zehnder interferometry and phase-sensitive optical time-domain reflectometry technology (hereinafter referred to as ) The fusion distributed optical fiber sensing system includes a first light source 1, a second light source 2, a Mach-Zehnder interferometer, and data acquisition and processing modules.

[0049] Figure 2 The schematic diagram of the fusion type distributed optical fiber sensor subsystem is shown, including a first light source 1, a second light source 2, a first optical fiber attenuator 3, a first optical fiber coupler 4, 13, a first Raman amplifier 5, a second Raman amplifier 6, a second optical fiber coupler 7, 8, a first wavelength division multiplexer 9, a second wavelength division multiplexer 10, a third wavelength division multiplexer 11, a fourth wavelength division multiplexer 12, a second optical fiber attenuator 14, a semiconductor optical amplifier 15, a pulse optical amplifier 16, an optical fiber circulator 17, a dense wavelength division multiplexer 18, a first optical filter 19, a second optical filter 20, a first photodetector 21, a second photodetector 22, and a data acquisition and processing module; the data acquisition and processing module includes a connected data acquisition card 23 and an industrial computer 24. The first light source 1 and the second light source 2 are narrow-band continuous light lasers, with central wavelengths of λ1 (1550.12nm) and λ2 (1550.92nm) respectively, and a maximum output power of 10mW. The data acquisition card 23 is used to collect the sensor electrical signals transmitted back by the first and second photoelectric detectors 21, 22, and the industrial computer 24 is used to analyze and demodulate the received signals to obtain the fault location and identify the fault event. The wavelength of the first optical fiber coupler 4, 13 is 1550nm, and the wavelength of the second optical fiber coupler 7, 8 is 1455nm.

[0050] All the fiber optic couplers mentioned in this article have a splitting ratio of 50:50.

[0051] The first optical fiber attenuator 3 has an input end and an output end, wherein the input end is connected to the first light source 1 , and the output end is connected to the first optical fiber coupler 4 .

[0052] The first optical fiber coupler 4 has an input end and two output ends, and its input end is connected to the output end of the first optical fiber attenuator 3. The attenuated optical signal is divided into two optical signals with the same power by the first optical fiber coupler 4 and transmitted to the first wavelength division multiplexer 9 and the dense wavelength division multiplexer 18.

[0053] The first fiber coupler 13 has two input ends and one output end, the output end of which is connected to the first photodetector 21, and the two input ends are respectively connected to the third wavelength division multiplexer 11 and the first optical filter 19. The central wavelength of the first optical filter 19 is λ1±0.2nm, and only the laser emitted by the first light source 1 can pass through, so as to filter out the pulse light from the second light source.

[0054] The input end of the second optical fiber coupler 7 is connected to the first Raman amplifier 5, and the two output ends are connected to the first wavelength division multiplexer 9 and the second wavelength division multiplexer 10 respectively; the input end of the second optical fiber coupler 8 is connected to the second Raman amplifier 6, and the two output ends are connected to the third wavelength division multiplexer 11 and the fourth wavelength division multiplexer 12 respectively; and the output light of the first Raman amplifier 5 and the second Raman amplifier 6 is in the 1455nm band.

[0055] The first wavelength division multiplexer 9 is connected to the third wavelength division multiplexer 11 via the sensing optical fiber, and the second wavelength division multiplexer 10 is connected to the fourth wavelength division multiplexer 12 via the sensing optical fiber; and the second wavelength division multiplexer 10 is also connected to the dense wavelength division multiplexer 18, and the fourth wavelength division multiplexer 12 is connected to the first optical filter 19.

[0056] The second optical filter 20 is used to filter out noise.

[0057] The second light source 2 is connected to the input end of the second optical fiber attenuator 14, and the output end of the second optical fiber attenuator 14 is connected to the input end of the semiconductor optical amplifier 15. The output end of the semiconductor optical amplifier 15 is respectively connected to the data acquisition card 23 and the pulse optical amplifier 16, which is used to transmit the pulse electrical signal to the data acquisition card 23 and transmit the pulse light to the pulse optical amplifier 16; the output end of the pulse optical amplifier 16 is connected to the optical fiber circulator 17, which is a three-port circulator, and is respectively connected to the output end of the pulse optical amplifier 16, the input end of the dense wavelength division multiplexer 18 and the input end of the second optical filter 20. The output end of the second optical filter 20 is connected to the second photodetector 22, and the output end of the second photodetector 22 is connected to the data acquisition card 23, and the data acquisition card 23 is connected to the industrial computer.

[0058] The method for real-time monitoring of contact network cable status based on distributed optical fiber sensing comprises:

[0059] Step 1: Real-time detection of interference light signals

[0060] S101: When an abnormal condition occurs in the overhead line cable, it will cause a change in the sensor light signal; the Mach-Zehnder interferometer and In the fusion-type distributed optical fiber sensing system, the signal from the first light source 1 passes through the first optical fiber attenuator 3, the first optical fiber coupler 4, the Mach-Zehnder interferometer, and the first optical fiber coupler 13 in sequence, and then obtains the phase-modulated interference light signal, and the data is collected by the first photoelectric detector 21 and the data acquisition card 23 and sent to the industrial computer 24 to realize the feature extraction of the modulated light signal;

[0061] Specific:

[0062] The laser emitted by the first light source 1 is transmitted to the first fiber coupler 4 through the first fiber attenuator 3. The first fiber coupler 4 divides the signal light into two beams and enters the Mach-Zehnder interferometer for interference. After passing through the sensing fiber, interference occurs in the second fiber coupler 13. In order to extend the sensing distance, the Mach-Zehnder interferometer introduces bidirectional distributed Raman amplification. The output light of the first Raman amplifier 5 and the second Raman amplifier 6 is in the 1455nm band and is divided into two paths through the second fiber coupler 7, 8. Then, the output light enters the sensing fiber from the first wavelength division multiplexer 9, the second wavelength division multiplexer 10, the third wavelength division multiplexer 11 and the fourth wavelength division multiplexer 12 respectively to amplify the transmission light. After the interference, the signal light is transmitted to the first photodetector 21 and then enters the industrial computer 24 through the data acquisition card 23.

[0063] S102: When an abnormal condition occurs in the overhead line cable, The back-scattered Rayleigh light signal is processed; that is, the signal from the second light source 2 in the Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system passes through the second optical fiber attenuator 14, the semiconductor optical amplifier 15, and then enters That is, after passing through the pulse optical amplifier 16, the optical fiber circulator 17, and the dense wavelength division multiplexer 18, it enters the Mach-Zehnder interferometer and is transmitted in the sensing optical fiber. The continuous backward Rayleigh scattered light signal generated by it is then obtained through the optical fiber circulator 17 and the second optical filter 20. The data is then collected by the second photoelectric detector 22 and the data acquisition card 23 and sent to the industrial computer 24 to realize the feature extraction of the backward Rayleigh scattered light signal.

[0064] The laser emitted by the second light source 2 is transmitted to the semiconductor optical amplifier 15 through the second optical fiber attenuator 14, wherein the pulse electrical signal is used as the trigger signal of the data acquisition card 23 for data acquisition. The pulse light enters the pulse light amplifier 16 for amplification, enters one end of the dense wavelength division multiplexer 18 through the optical fiber circulator 17, and is coupled into the sensing optical fiber together with the laser from the first light source 1; the central wavelength of the first optical filter 19 is λ1±0.2nm, and only the laser emitted by the first light source 1 can pass through. When the pulse light signal from the second light source (with a central wavelength of λ2) is transmitted in the sensing optical fiber, a continuous backward Rayleigh scattered light signal is generated, and then passes through the optical fiber circulator 17, enters the second optical filter 20 to filter out noise, is received by the second photodetector 22, and enters the industrial computer 24 through the data acquisition card 23.

[0065] Step 2: Preprocess the interference light signal and backscattered light signal obtained from the fault event to obtain phase change information

[0066] S201: extract the interference optical signal modulated by the fault event obtained in step 1, perform preprocessing of DC removal and endpoint detection, and construct a one-dimensional time series signal of the fault event.

[0067] When an abnormal condition occurs in the contact network cable (i.e., the external vibration, strain, temperature, etc. of the optical fiber changes, which will cause changes in optical parameters such as the intensity, phase, frequency, and polarization state of the transmitted light), it will cause changes in the sensor light signal. Different fault events have different phase modulations on the optical fiber, and the corresponding interference light signal characteristics are also different. Therefore, step one analyzes and processes external events by detecting the changes in the amplitude of the optical signal caused by the phase change.

[0068] The industrial computer 24 expresses the interference intensity I of the modulated optical signal obtained after removing the DC component and endpoint detection as:

[0069]

[0070] A0 represents the amplitude value of the continuous laser signal, φ(t) represents the phase change information introduced by the external event, and τ represents the time delay of the optical signal reaching the first photodetector 21. Due to different external fault events, the phase modulation φ(t) generated is also different, so the optical signal received by the industrial computer 24 also has different characteristics.

[0071] S202: Extract the back Rayleigh scattered light signal modulated by the fault event obtained in step 1, use a moving average algorithm to pre-process the acquired back Rayleigh scattered light signal to improve its signal-to-noise ratio, and construct a one-dimensional time series signal of the fault event; at the same time, perform a difference operation on the back Rayleigh scattered light signal to demodulate the position of the fault event.

[0072] In order to obtain the intensity change information caused by the fault event after the moving average operation, a fixed backscattering Rayleigh curve is selected as the reference curve for the difference operation, and the Mach-Zehnder interferometer and The backscattered Rayleigh signal curves collected by the fusion distributed optical fiber sensing system at other times are subtracted from the reference curves in turn, and the obvious intensity change information caused by the fault event can be obtained. The location information of the fault event can be obtained by detecting the echo intensity change and its delay time.

[0073] When an abnormal condition occurs in the overhead line cable, the change in the phase of the backscattered Rayleigh light is proportional to the amplitude of the fault event on the sensing fiber acting on the Mach-Zehnder interferometer, which will cause the backscattered Rayleigh light intensity at the corresponding position to change, while the backscattered Rayleigh light intensity at other positions that are not affected by the fault event remains basically unchanged. In the process of long-distance sensing and monitoring, since the sensing fiber has a certain transmission loss, the backscattered Rayleigh light is easily affected by external environmental noise and circuit additional noise.

[0074] The light field of the backward Rayleigh scattered light signal collected by the industrial computer 24 can be expressed as E R . Assume that the sensing fiber with a length of L can be divided into N small segments, and the length of each small segment is ΔL=L / N. The length of a small segment is consistent with the width of the pulse light. These N small segments are equivalent to N reflectors with low reflectivity and reflectivity related to the wavelength of the incident light. These reflectors can be regarded as the vector superposition of scatterers in each small segment within the length ΔL. Assume that there are R randomly uniformly distributed Rayleigh scatterers within each small segment of the sensing fiber. The polarization states of these scatterers are consistent and independent of each other. Then the vector field sum of these scatterers within the kth small segment is:

[0075]

[0076] Among them A k ,θ k 、ai and is considered a random variable, A k is the sum of the amplitude vectors of the R Rayleigh scatterers in the kth small segment of the sensing optical fiber, θ k is the phase vector sum of the R Rayleigh scatterers in the kth segment of the sensing fiber, a i is the amplitude of the i-th Rayleigh scatterer in the sensing fiber within the length ΔL, is the phase value of the i-th Rayleigh scatterer in the sensing optical fiber within the length ΔL.

[0077] The multiple Rayleigh backscattered lights generated at the kth segment of the sensing optical fiber will interfere due to their strong coherence. The light field after coherent superposition can be expressed as:

[0078]

[0079] Where E0 is the electric field of the incident light field, and α is the loss coefficient of the sensing optical fiber.

[0080] Formula (3) shows that the coherence results of multiple backward Rayleigh scattered lights in a certain section of sensing fiber can be expressed by the complex superposition of the amplitude and phase of the scatterer in this section of sensing fiber. By analyzing the amplitude change of the backward Rayleigh scattering curve, the phase change caused by the change of external physical quantity can be detected.

[0081] Among them, Raman pumping, Mach-Zehnder interferometry transmission light and The evolution law of the detection light pulse power along the optical fiber can be simplified as follows:

[0082]

[0083] The boundary conditions are: R + (0) = P R,in + , P R - (L) = P R,in - , P S + (0) = P S,in + , P P + (0) = P P,in + The superscripts + and - respectively represent the forward and backward transmission signals, P R + (z) and P R - (z) is the Raman pump light transmitted forward and backward along the optical fiber, P S +(z) is the forward transmission optical signal of Mach-Zehnder interferometry, P P + (z) Yes The probe light pulse, α i represents the loss coefficient, ω i represents the angular frequency of the optical signal, i=R, S, P correspond to the optical signals with the center wavelengths of 1455nm, 1550.12nm and 1550.92nm respectively, and g R It represents the Raman gain coefficient of 1455nm optical signal to 1550nm optical signal. The power distribution of the Rayleigh scattering curve is expressed by α BS P p (0)G(z)2Δz, Δz is obtained from the detection light pulse, α BS is the Rayleigh scattering coefficient, G(z) is the network gain, which can be calculated by Pp(z) / Pp(0).

[0084] Step 3: The interference light signal and the back Rayleigh scattered light signal processed in step 2 are sent together into the trained multi-category feature extraction deep learning network structure.

[0085] Pre-trained deep learning networks

[0086] 6000 samples were collected and processed in advance to verify the feasibility and effectiveness of the proposed model. The data set size collected by the Mach-Zehnder interferometer is 3000. The size of the collected data set is 3000. 1200 groups of optical signals of five fault events (broken wire, loose, lightning strike, abnormal temperature rise and no fault) are pre-selected. The training data, verification data and test data are randomly set and selected in a ratio of 8:1:1, and there is no overlap between the data. The interference light signal and the back-Rayleigh scattered light signal obtained by the fusion distributed fiber optic sensing system are trained using the Swin Transformer algorithm model. The Swin Transformer model can maintain a fast recognition speed while ensuring a high recognition rate, meeting the needs of actual detection. During the training phase, the weight parameters officially provided by Swin Transformer are used as the initialization parameters of the model, and the parameters are fine-tuned using a self-made data set so that the trained model has the best detection effect. The labeled training set and validation set images are trained for 150 epochs in the adjusted Swin Transformer network model to generate the corresponding best training result weight file best.pt.

[0087] Figure 3A flow chart of a multi-category feature extraction deep learning network structure is shown. The two-dimensional time-frequency spectrum of the fault event is sent to the Swin Transformer network model, and after Patch Partiton, Linear Embedding, Patch Merging and two consecutive Swint Blocks based on sliding window self-attention are performed in multiple levels, and then after classification based on a multi-layer perceptron (MLP), the recognition result is finally output. In an embodiment of the present invention, the parameters of the model are adjusted according to the type and characteristics of the fault event to train the neural network model, and the model has a high recognition accuracy and classification and recognition stability. The trained Swin Transformer algorithm model is saved as a multi-category feature extraction deep learning network, and the one-dimensional time series signals obtained in S201 and S202 in step two are trained and recognized together in the multi-category feature extraction deep learning network structure.

[0088] Processing optical signals

[0089] The one-dimensional time series sensor signal obtained in step 2 S201 and S202 is converted into a two-dimensional time spectrum through wavelet transform, and then the two-dimensional time spectrum is further sent to the pre-trained Swin Transformer algorithm model to adaptively extract the time domain features, frequency domain features and spatial domain features of the optical signal, and finally the specific fault event can be identified and detected through the classifier. This feature enhancement method of converting one-dimensional time series signals into two dimensions can effectively enhance the ability of the deep learning model to adaptively extract typical effective features of sensor signals while expanding the dimension of the original sensor feature information.

[0090] Wavelet transform introduces a variable width time-frequency window, which makes it possible to better capture various characteristics of the signal. The core idea is to create a mother wavelet function of finite length or fast decay, generate multiple sub-wavelet functions through different scaling and translation, and finally match them with the input signal to analyze the time-frequency information of the signal at different scales and time positions, thereby obtaining the time-frequency representation of the signal.

[0091] The specific implementation process is as follows: If the Mach-Zehnder fiber interferometer and The obtained sensor light signal can be expressed as x(t), and the time spectrum W(τ, f) obtained by wavelet transform of x(t) can be expressed as:

[0092]

[0093] Among them, ψ a,bis the mother wavelet function, a is the transformation scale factor, and b is the translation factor. Since a and b are continuous values, there can be an infinite number of sub-wavelets, which can be matched with the original signal. This makes the wavelet transform have better adaptive change ability of time-frequency resolution than the short-time Fourier transform, and can better highlight the local time-frequency characteristics of the signal.

[0094] S303: For the two-dimensional time-frequency signal recognition in S302, precision, recall and F1-Score are used as evaluation indicators, and the event with the largest mAP (mean Average Precision) is taken as the final recognized event, that is, the intrusion event to which the current disturbance belongs is determined.

[0095] Finally, the fault event type, location and time of occurrence are displayed and recorded on the industrial computer. For the five pre-set fault events, namely disconnection, loosening, lightning strike, abnormal temperature rise and no fault, alarms are issued according to the degree of harm of the fault event to remind relevant personnel to intervene in time to ensure the safety of railway operations.

[0096] Although the preferred embodiments of the present invention have been described above in conjunction with the accompanying drawings, the present invention is not limited to the above-mentioned specific embodiments, which are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which fall within the scope of protection of the present invention.

Claims

1. A Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system, characterized in that: It includes a first light source (1), a second light source (2), a Mach-Zehnder interferometer, a φ-OTDR, and a data acquisition and processing module; The first light source (1) is sequentially connected to the first optical fiber attenuator (3), the first optical fiber coupler (4) and the input end of the Mach-Zehnder interferometer, and the output end of the Mach-Zehnder interferometer is sequentially connected to the first optical fiber coupler (13), the first photodetector (21) and the data acquisition and processing module; The second light source (2) is sequentially connected to a second optical fiber attenuator (14), a semiconductor optical amplifier (15), a φ-OTDR, and a data acquisition and processing module; the output end of the semiconductor optical amplifier (15) is respectively connected to the data acquisition and processing module and the φ-OTDR, and is used to transmit a pulse electrical signal to the data acquisition and processing module as a trigger signal, and transmit pulse light to the φ-OTDR; the φ-OTDR comprises a pulse optical amplifier (16), an optical fiber circulator (17), a Mach-Zehnder interferometer, an optical fiber circulator (17), and a second optical filter (20) which are sequentially connected; the second optical filter (20) is sequentially connected to a second photodetector (22) and the data acquisition and processing module; The laser light from the second light source (2) enters the Mach-Zehnder interferometer via an optical fiber circulator (17) and a dense wavelength division multiplexer (18), and is coupled together with the laser light from the first light source (1) into the sensing optical fiber; Furthermore, a first Raman amplifier (5) is provided at the input end of the Mach-Zehnder interferometer, and a second Raman amplifier (6) is provided at the output end of the Mach-Zehnder interferometer, thereby extending the sensing distance; The data acquisition and processing module includes a signal extraction and preprocessing submodule, a positioning submodule and a fault identification submodule; The signal extraction and preprocessing submodule is used to extract the interference light signal and the backscattered Rayleigh light signal corresponding to the phase-modulated fault event of the Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing subsystem; then preprocess the extracted light signal, that is, perform endpoint detection on the interference light signal and perform moving average algorithm processing on the backscattered Rayleigh light signal; The positioning submodule is used to perform difference calculation on the backward Rayleigh scattered light signal to demodulate the position of the fault event; The fault identification submodule is used to convert the interference light signal and the backscattered Rayleigh light signal preprocessed by the signal extraction and preprocessing submodule into a two-dimensional time-frequency spectrum through wavelet transform, and then send the two-dimensional time-frequency spectrum to the pre-trained Swin Transformer network model to extract the time domain features, frequency domain features and spatial domain features of the light signal, and identify the type of the fault event through a classifier.

2. The Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system according to claim 1, characterized in that: The splitting ratios of the first optical fiber coupler (4, 13) and the second optical fiber coupler (7, 8) are both 50:50, the wavelength of the first optical fiber coupler (4, 13) is 1550 nm, and the wavelength of the second optical fiber coupler (7, 8) is 1455 nm.

3. The Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system according to claim 1, characterized in that: The output light of the first Raman amplifier (5) and the second Raman amplifier (6) is in the 1455nm band.

4. The Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system according to claim 1, characterized in that: The central wavelength of the first optical filter (19) is the central wavelength λ1±0.2 nm of the first light source, and only the laser light emitted by the first light source (1) can pass through, and is used to filter out the pulse light from the second light source (2).

5. The Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system according to claim 1, characterized in that: The first light source (1) and the second light source (2) are narrow-band continuous light lasers with an operating wavelength of 1550 nm and a maximum output power of 10 mW.

6. The Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system according to claim 1, characterized in that: The preset fault events include wire break, looseness, lightning strike, abnormal temperature rise and no fault.

7. A method for real-time monitoring of contact network cable status based on distributed optical fiber sensing, the method utilizing the Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system as claimed in any one of claims 1 to 5, comprising: Step 1: Real-time detection of interference light signals. When an abnormal condition occurs in the overhead line cable, the sensing light signal changes, and the phase-modulated interference light signal and the backscattered Rayleigh light signal are obtained. Step 2: Remove the DC component of the modulated optical signal obtained from the fault event, perform endpoint detection, and obtain the interference optical signal corresponding to the fault event; Perform moving average algorithm and difference operation on the backscattered Rayleigh light signal obtained from the fault event to obtain the obvious intensity change information caused by the fault event and demodulate the location of the fault event at the same time; Step 3: Perform wavelet transform on the interference light signal and backscattered light signal processed in step 2 to convert them into a two-dimensional time-frequency spectrum. Then, the two-dimensional time-frequency spectrum is sent to the pre-trained Swin Transformer network model to extract the time domain features, frequency domain features, and spatial domain features of the light signal, and the type of fault event is identified through the classifier.

8. The real-time monitoring method according to claim 7, characterized in that Step 1 specifically includes: When an abnormal condition occurs in the overhead line cable, it will cause a change in the sensing optical signal; the signal from the first light source (1) in the Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system passes through the first optical fiber attenuator (3), the first optical fiber coupler (4), the Mach-Zehnder interferometer, and the first optical fiber coupler (13) in sequence to obtain a phase-modulated interference optical signal, which is then sent to a data acquisition and processing module after passing through a first photoelectric detector (21) to realize the extraction of modulated optical signal features; When an abnormal condition occurs in the overhead line cable, the back Rayleigh scattered light signal of the φ-OTDR is detected at the same time. The signal from the second light source (2) passes through the second optical fiber attenuator (14), the semiconductor optical amplifier (15), the pulse optical amplifier (16), the optical fiber circulator (17), and the dense wavelength division multiplexer (18) in sequence, enters the Mach-Zehnder interferometer and is transmitted in the sensing optical fiber. The continuous back Rayleigh scattered light signal generated by the back Rayleigh scattered light signal is then obtained through the optical fiber circulator (17) and the second optical filter (20). The back Rayleigh scattered light signal is then sent to the data acquisition and processing module after passing through the second photoelectric detector (22) to realize the extraction of the back Rayleigh scattered light signal characteristics.

9. The real-time monitoring method according to claim 7, characterized in that The processing of the backscattered Rayleigh light signal in step 2 includes: A fixed backscattering curve is selected as a reference curve for the difference operation, and the backscattering signal curves at other times collected by the Mach-Zehnder interferometer and φ-OTDR fusion distributed optical fiber sensing system are sequentially differenced with the reference curve to obtain the obvious intensity change information caused by the fault event, and the location information of the fault event is obtained by detecting the echo intensity change and its delay time.

Images