Optical fiber state monitoring method, device, equipment, medium and product

Abstract

The invention discloses an optical fiber state monitoring method, device, equipment, medium and product, and the method comprises the steps: carrying out the polarization state detection of signal light transmitted by an optical fiber link, and monitoring a change event of the polarization state; when the change event of the polarization state is monitored, collecting state data of the optical fiber link at a preset first frequency; and determining the intruded position in the optical fiber according to the state data. According to the scheme, the polarization state change event is monitored, the state monitoring process is actively triggered, intrusion identification is carried out, abnormal state identification can be carried out before a fault, and an optical fiber transmission interruption fault is prevented.

Description

Technical Field

[0001] The present invention relates to the field of optical transmission and bearing technology, and in particular to an optical fiber status monitoring method, device, equipment, medium and product. Background Art

[0002] As the physical layer medium of the optical transmission system, optical fiber link resources are the foundation of the entire optical communication system. With the development of optical network technology and the expansion of its application, massive optical fibers have been laid in various environments. Currently, from access to metropolitan areas to backbones, they have basically covered all cities and villages, carrying all kinds of information that is necessary for human daily life and survival. However, when optical fiber links are in use, the security of optical fiber links is becoming increasingly fragile due to the artificial digging of optical cables caused by construction projects, as well as interruptions caused by natural disasters and the aging of optical cables themselves.

[0003] Because the existing technology can only respond after signal transmission is interrupted when performing optical fiber status monitoring, it is unable to prevent optical fiber line failures. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes an optical fiber status monitoring method, device, equipment, medium and product, which can identify abnormal status before failure and prevent the occurrence of optical fiber transmission interruption failure.

[0005] An embodiment of the present invention provides a method for monitoring optical fiber status, the method comprising:

[0006] Perform polarization state detection on the signal light transmitted in the optical fiber link and monitor the change event of polarization state;

[0007] When a polarization state change event is detected, collecting state data of the optical fiber link at a preset first frequency;

[0008] The disturbed position in the optical fiber is determined according to the status data.

[0009] Preferably, performing polarization state detection on signal light transmitted by the optical fiber link and monitoring polarization state change events include:

[0010] Coherently coupling the signal light transmitted by the optical fiber link with the local oscillator light generated locally;

[0011] Performing coherent detection on the coherently coupled optical signal;

[0012] Detect changes in the polarization directions of the signal light and the local oscillation light, and identify polarization state change events.

[0013] Furthermore, detecting changes in polarization directions of the signal light and the local oscillator light and identifying polarization state change events includes:

[0014] detecting directions of electric vectors of the signal light and the local oscillator light, and taking a direction difference between the direction of the electric vector of the signal light and the direction of the electric vector of the local oscillator light as the change;

[0015] When the direction difference is not within a preset first range, it is determined that a polarization state change event occurs.

[0016] Preferably, collecting the status data of the optical fiber link at a preset first frequency includes:

[0017] adjusting the sampling frequency of the built-in optical time domain reflectometer from the initial second frequency to the first frequency, and collecting the attenuation curve of the optical signal intensity over the distance on the optical fiber link as the state data;

[0018] The first frequency is greater than the second frequency.

[0019] Preferably, determining the disturbed position in the optical fiber according to the status data comprises:

[0020] According to the comparison between the attenuation curve of the optical signal in the state data and the standard attenuation curve in the preset standard state data, the intrusion event meeting the preset conditions is identified;

[0021] The disturbed location is determined according to the distribution location of the disturbed events.

[0022] Furthermore, the intrusion events meeting the preset conditions are identified, including:

[0023] Calculating the attenuation rates of the attenuation curve at different positions and the attenuation rates of the standard attenuation curve at different positions;

[0024] Calculating the error rate of attenuation rates at different positions on the attenuation curve and the standard attenuation curve;

[0025] When the error rate at a certain location exceeds a preset fluctuation range, the intrusion event is identified.

[0026] Preferably, the method further comprises:

[0027] Extracting abnormal status data of a fiber optic link of a preset length at the disturbed location;

[0028] The attenuation characteristics of the abnormal state data are extracted and input into a pre-trained vibration recognition model to identify the vibration intensity and vibration frequency of the disturbed position.

[0029] Furthermore, the method further comprises:

[0030] A corresponding intrusion event type is matched from a preset event type library according to the vibration intensity and the vibration frequency.

[0031] Preferably, the vibration recognition model training process specifically includes:

[0032] Collecting state data of optical signals in optical fiber links with different vibration intensities and frequencies;

[0033] Extracting the intrusion features corresponding to the intrusion positions in the different state data as training data;

[0034] The extracted different training data are used as input, and the corresponding vibration intensity and vibration frequency are used as labels to train the preset deep learning model;

[0035] The trained model is used as the vibration recognition model.

[0036] An embodiment of the present invention further provides an optical fiber status monitoring device, the device comprising:

[0037] A polarization state monitoring module is used to detect the polarization state of the signal light transmitted by the optical fiber link and monitor the change event of the polarization state;

[0038] A data acquisition module, used for acquiring state data of the optical fiber link at a preset first frequency when a change event of the polarization state is monitored;

[0039] The position determination module is used to determine the disturbed position in the optical fiber according to the state data.

[0040] Preferably, the polarization state monitoring module is specifically used for:

[0041] Coherently coupling the signal light transmitted by the optical fiber link with the local oscillator light generated locally;

[0042] Performing coherent detection on the coherently coupled optical signal;

[0043] Detect changes in the polarization directions of the signal light and the local oscillation light, and identify polarization state change events.

[0044] Furthermore, the polarization state monitoring module is also specifically used for:

[0045] detecting directions of electric vectors of the signal light and the local oscillator light, and taking a direction difference between the direction of the electric vector of the signal light and the direction of the electric vector of the local oscillator light as the change;

[0046] When the direction difference is not within a preset first range, it is determined that a polarization state change event occurs.

[0047] Preferably, the data acquisition module is specifically used for:

[0048] adjusting the sampling frequency of the built-in optical time domain reflectometer from the initial second frequency to the first frequency, and collecting the attenuation curve of the optical signal intensity over the distance on the optical fiber link as the state data;

[0049] The first frequency is greater than the second frequency.

[0050] Preferably, the location determination module is specifically used for:

[0051] According to the comparison between the attenuation curve of the optical signal in the state data and the standard attenuation curve in the preset standard state data, the intrusion event meeting the preset conditions is identified;

[0052] The disturbed location is determined according to the distribution location of the disturbed events.

[0053] Furthermore, the location determination module is also specifically used for:

[0054] Calculating the attenuation rates of the attenuation curve at different positions and the attenuation rates of the standard attenuation curve at different positions;

[0055] Calculating the error rate of attenuation rates at different positions on the attenuation curve and the standard attenuation curve;

[0056] When the error rate at a certain location exceeds a preset fluctuation range, the intrusion event is identified.

[0057] Preferably, the device further comprises a vibration recognition module, which is used for:

[0058] Extracting abnormal status data of a fiber optic link of a preset length at the disturbed location;

[0059] The attenuation characteristics of the abnormal state data are extracted and input into a pre-trained vibration recognition model to identify the vibration intensity and vibration frequency of the disturbed position.

[0060] Furthermore, the device also includes an intrusion identification module, which is used to:

[0061] A corresponding intrusion event type is matched from a preset event type library according to the vibration intensity and the vibration frequency.

[0062] Furthermore, the vibration recognition model training process specifically includes:

[0063] Collecting state data of optical signals in optical fiber links with different vibration intensities and frequencies;

[0064] Extracting the intrusion features corresponding to the intrusion positions in the different state data as training data;

[0065] The extracted different training data are used as input, and the corresponding vibration intensity and vibration frequency are used as labels to train the preset deep learning model;

[0066] The trained model is used as the vibration recognition model.

[0067] An embodiment of the present invention further provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the optical fiber status monitoring method as described in any of the above embodiments is implemented.

[0068] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the optical fiber status monitoring method as described in any of the above embodiments.

[0069] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the steps of any of the above methods when executed by a processor.

[0070] The present invention provides a method, device, equipment, medium and product for monitoring the state of an optical fiber. The method detects the polarization state of the signal light transmitted by the optical fiber link and monitors the change event of the polarization state. When the change event of the polarization state is detected, the state data of the optical fiber link is collected at a preset first frequency. The disturbed position in the optical fiber is determined according to the state data. The present application scheme monitors the polarization state change event, actively triggers the state monitoring process, and performs intrusion identification. It can identify abnormal states before a fault occurs, and prevent the occurrence of optical fiber transmission interruption faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is a flowchart of a method for monitoring optical fiber status provided by an embodiment of the present invention;

[0072] Figure 2 is a schematic diagram of the structure of an optical fiber transmission link provided by an embodiment of the present invention;

[0073] Figure 3 is a schematic diagram for comparing attenuation curves provided by an embodiment of the present invention;

[0074] Figure 4 is a structural schematic diagram of an optical fiber status monitoring device provided by an embodiment of the present invention;

[0075] Figure 5 It is a structural diagram of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] As the physical layer medium of the optical transmission system, optical fiber link resources are the foundation of the entire optical communication system. With the development of optical network technology and the expansion of its applications, massive optical fibers have been laid in various environments. Optical fiber links cover all cities and villages, carrying all kinds of information that humans need for daily life and survival.

[0078] Optical fiber links with a wide coverage area also frequently fail due to various construction projects, natural disasters or aging damage, and the safety of optical cables is becoming increasingly fragile. The existing technology for detecting optical fiber failures can only detect optical fiber failure events after the optical fiber is abnormally interrupted or damaged, and cannot perform fault pre-monitoring.

[0079] In view of the above technical problems, this embodiment provides a method for monitoring the state of an optical fiber. Figure 1 , is a flow chart of a method for monitoring optical fiber status provided by an embodiment of the present invention, the method comprising:

[0080] Step S1, performing polarization state detection on signal light transmitted by an optical fiber link, and monitoring polarization state change events;

[0081] Step S2, when a polarization state change event is detected, collecting state data of the optical fiber link at a preset first frequency;

[0082] Step S3, determining the disturbed position in the optical fiber according to the status data.

[0083] Specifically, in order to give full play to the advantages of coherent reception, in the coherent optical communication system, the transmitter will take light wave polarization stabilization measures in advance to maintain the polarization state of the local oscillator light and the signal light within a threshold to ensure that the reception is in the best state.

[0084] In idealized optical fiber transmission, the polarization state (SOP) of the signal light is closely related to the ellipticity of the optical fiber core. If the ellipticity of the optical fiber core end face does not change, the SOP will not change either. However, the external environment will have different degrees of impact on the laid optical cables, such as ground construction on buried optical cables, vibrations caused by passing trains on optical cables laid along railways, waves hitting submarine optical cables, and strong winds on overhead optical cables. These will have a great impact, squeezing the optical fiber in the cable, deforming the optical fiber end face, and causing rapid changes in the polarization state of the transmitted light.

[0085] Because the polarization state of the local oscillator light is fixed, while the polarization state of the signal light will change due to abnormal conditions in the signal during optical fiber transmission, when detecting at the receiving end, the intrusion event during optical fiber transmission can be identified by monitoring the polarization state of the signal light.

[0086] Therefore, in this case, when performing optical fiber status monitoring, the receiving end receives the signal light transmitted by the optical fiber link, detects the polarization state of the signal light, and identifies the change event based on the detected polarization state.

[0087] It should be noted that when identifying this change event, the change in polarization state is used to identify the signal light in the optical fiber link due to external force intrusion. In this process, the specific cause of the intrusion into the optical fiber link and the location of the intrusion cannot be identified. It can only be identified that the impact of ground construction on buried optical cables, vibrations caused by passing trains on optical cables laid along the railway, waves on submarine optical cables, and strong winds on overhead optical fiber links. When external forces intrude, the optical fiber is vibrated or squeezed, resulting in a change in the elliptical degree of the optical fiber end face, which ultimately affects the distribution of the polarization state of the transmitted signal light.

[0088] It should be noted that, in the specific implementation of this case, the polarization state of the transmitted signal light can be detected, combined with the polarization state of the signal light output by the transmitter, and the polarization state of the signal light before and after transmission through the optical fiber link. After detecting that the polarization state change meets the preset event conditions, it is determined that a change event is monitored.

[0089] After detecting the change event, this case also collects the fiber link status through the triggering of the change event, and uses distributed sensing equipment to collect the OTDR curve of the optical fiber to be measured.

[0090] OTDR (Optical Time Domain Reflectometer) is a fiber optic instrument used for characterization, troubleshooting, and maintenance of optical communication networks. It contains a laser diode light source, an avalanche diode, and a highly accurate timing circuit (or time base).

[0091] When collecting OTDR curves, a pulse signal of a specific length is emitted into the optical fiber to be tested through the optical time domain reflectometer transmitter. The pulse signal propagates along the optical fiber and generates Rayleigh scattering. The injected light pulse is scattered in all directions at each point along the length of the optical fiber, and part of the light will return back to the detection unit of the OTDR. The OTDR will collect and measure this backscattered light. The backscattered signal will decrease exponentially as the optical fiber distance increases. By converting the backscattered signal into the dB exponential space, the OTDR sampling curve can be linearly and evenly decreased, so that the backscattered signal can be detected as the OTDR curve.

[0092] In the OTDR curve, when there is a joint, fusion loss or damage on the optical fiber link, the sampling signal curve at the corresponding position on the OTDR curve will show a nonlinear mutation. By identifying the nonlinear change of this signal, the optical fiber event can be automatically identified.

[0093] It should be noted that, in the specific implementation of this case, the OTDR curve can be used as the detected status data to characterize the change in the status of the optical fiber link. In other embodiments, a variety of schemes can be used for status data monitoring.

[0094] The existing optical cable monitoring system uses a variety of technologies, including geographic information system (GIS), global positioning system (GPS), optical time domain reflectometer (OTDR), wavelength division multiplexing (WDM), data mining, etc., to timely grasp the operation status of the optical fiber network.

[0095] The monitoring system is a necessity for the development of optical cable line maintenance in the new era. It incorporates optical cable lines into real-time centralized monitoring and maintenance. No matter how much changes occur on the line, monitoring is carried out at the minute level. Transmission monitoring can detect equipment failures, but it is an after-the-fact behavior.

[0096] Simply relying on the fiber link status monitoring behavior can only achieve post-fault monitoring. Therefore, in this case, the polarization state monitoring change event is used, and after the change event is triggered, the status data is collected at a preset frequency.

[0097] It should be noted that the preset first frequency can be set to the second level, triggering active monitoring of abnormal intrusions, and being able to detect the intrusion location in advance before the optical fiber link is intruded by a fault.

[0098] The existing optical cable line monitoring system not only replaces manual work with automation, it also fundamentally improves the maintenance level, that is, the previous one or two tests a year are increased to several times a year, but the detection and monitoring cycle is still maintained at a low level. If the monitoring cycle is simply increased, a large amount of detection status data business and analysis will be required, which will bring about additional losses and resource usage.

[0099] In this case, by monitoring polarization state change events, actively triggering the status monitoring process and performing intrusion identification, the optical fiber degradation trend can be discovered, status maintenance based on operating conditions can be performed, and the fault can be located quickly and accurately when it occurs. The network operation and maintenance personnel can be informed in advance to adopt corresponding emergency plans and contact the construction unit to suspend construction to avoid the optical cable being dug up, or manual switching can be adopted in advance to transfer the services that may be affected to other optical cables, thereby minimizing the losses caused by the impact on the optical cable or the services.

[0100] In another embodiment provided by the present invention, when the polarization state detection and the identification of the polarization state change event are performed in the above step S1, the following steps are specifically performed:

[0101] See also Figure 2 , is a schematic diagram of the structure of an optical fiber transmission link provided by an embodiment of the present invention. In the figure, data is transmitted between node A and node Z via optical fiber.

[0102] An EDFA (Erbium-doped Optical Fiber Amplifier) ​​is also configured between Node A and Node Z as an optical amplifier station to perform power compensation on the signal light in the transmission link to ensure transmission quality.

[0103] Multiple different optical fibers may be multiplexed in one optical link, so optical modes OM and optical amplifiers OA are configured on nodes A and Z to monitor the polarization states of optical signals of different modes through optical digital signal processors oDSP.

[0104] exist Figure 2 In the embodiment of FIG. 5 , N optical signals of different modes are configured, so both node A and node Z need to be configured with N different optical digital signal processors oDSPTx1 to TxN to perform polarization state monitoring and analysis on optical signals of different modes.

[0105] At present, coherent optical communication technology is widely used in optical transmission systems. At the transmitting end, the signal is modulated onto an optical carrier for transmission using external modulation. When performing polarization state analysis of optical signals, when the signal light reaches the receiving end, it is first coherently coupled with the local oscillator optical signal generated locally.

[0106] The receiver performs coherent detection, which requires that the local oscillator light and the received signal light must have the same polarization direction.

[0107] The change of the polarization directions of the signal light and the local oscillation light is detected, and when the change of the polarization direction meets a preset change event condition, a polarization state change event is identified.

[0108] By associating events such as external force disturbance of the optical cable (ground construction work, geological activities, passage of trains or cars, etc.), deformation of the optical fiber end face, and change of polarization state, the optical digital signal processor in the optical sending and receiving units of the transmission equipment will detect the polarization state change event and realize accurate identification of the polarization state change event.

[0109] In another embodiment of the present invention, when identifying a polarization state change event according to a change in polarization direction, the following steps are specifically performed:

[0110] Detect the direction of the electric vector of the signal light and the local oscillator light. Coherent detection requires that the local oscillator light and the received signal light must have the same polarization direction. In other words, the direction of the electric vector of the signal light and the local oscillator light must be the same to obtain the high sensitivity that coherent reception can provide. Otherwise, the sensitivity of coherent detection will decrease.

[0111] The direction difference between the electric vector direction of the signal light and the electric vector direction of the local oscillation light is taken as the change condition, and when the detected direction difference is not within a preset first range, it is determined that a polarization state change event occurs.

[0112] It should be noted that the setting of the first range can be determined according to the actual detection accuracy. The smaller the first range is, the more likely the polarization state change event is to be falsely triggered due to errors. The larger the first range is, the fewer errors are, but there may be missed reports, that is, the polarization state change event caused by a small intrusion event may be ignored.

[0113] In specific implementation, the ratio of the number of intrusion locations identified to the number of change events identified within a preset period can be counted to determine the identification detection accuracy value and adjust the first range. The closer the accuracy value is to 1, the more reasonable the first range setting is. At this time, the false alarm rate is low and the missed alarm rate is also low. At this time, the first range is maintained. When the accuracy value is less than 1, it indicates that the number of intrusion locations identified at this time is lower than the number of change events. At this time, there are false alarms, and the first range needs to be increased. By detecting whether there is a missed alarm event, that is, whether a fiber fault is detected without triggering a change event, it is determined whether there is a missed alarm. If the number of missed alarms is greater than the preset threshold within a certain period, the first range is reduced.

[0114] By setting the first range, it is possible to prevent misjudgment and missed reporting caused by errors in polarization state detection, thereby improving the detection accuracy of change events.

[0115] In another embodiment provided by the present invention, after the polarization state change event is identified in step S2, when collecting state data, fast state information collection is started, specifically including:

[0116] The sampling frequency of the built-in optical time domain reflectometer is adjusted from the initial second frequency to the first frequency. For example, the optical fiber status information is collected and reported once every 15 minutes, and the optical fiber status information is collected and reported once every 1 second. The shortening of the interval time for collecting and reporting the optical fiber status can capture these intrusion events.

[0117] The built-in optical time domain reflectometer collects the optical fiber status, that is, detects the intensity of the received scattered light, calculates the attenuation of the scattered light according to the intensity of the emitted reference light, and thus determines the attenuation curve of the optical signal intensity over time as the status data.

[0118] By analyzing the attenuation curve, the specific location of the intrusion can be determined.

[0119] It should be noted that the first frequency is greater than the second frequency, that is, before the change event is identified, the state data is collected at the preset second frequency to monitor the optical fiber. The second frequency is relatively small, and fault analysis is generally performed at intervals of ten minutes to reduce the resource usage of fault detection. When intrusion is identified, the detection frequency is increased to the second frequency, generally 1 second each time, and intrusion analysis is performed quickly to determine the intrusion event in the optical fiber link. If no intrusion event is detected within the preset first time length, or after the monitored change event disappears, the second frequency is restored.

[0120] After a change event is identified, the interval between collecting and reporting the fiber status is shortened, which can capture these intrusion events and provide more information for quickly locating the location where the fiber is intruded.

[0121] In another embodiment of the present invention, when determining the disturbed location according to the status data in step S3, the following steps are specifically performed:

[0122] When the optical fiber is in normal condition, the eOTDR will have a normal line attenuation curve. As the distance increases, the signal strength slowly decreases at a certain slope.

[0123] To obtain pre-collected standard status data, see Figure 3 , is a schematic diagram of attenuation curve comparison provided by an embodiment of the present invention, according to which the attenuation curve of the optical signal in the state data is compared with the standard attenuation curve in the preset standard state data, an intrusion event that meets the preset conditions is identified

[0124] When an optical fiber is squeezed by external intrusion, the loss caused by a slight bend in the optical fiber changes suddenly, and there will be a sudden drop in signal strength near the intrusion location.

[0125] Identify the disturbed events that meet the preset abnormality conditions, and determine the disturbed locations according to the distribution locations of the disturbed events.

[0126] After collecting the attenuation performance of the optical fiber link, the information is uploaded to the management and control platform of the transmission system. The management and control platform will retain a normal optical fiber link attenuation performance curve. By comparing it with the attenuation performance curve of the optical fiber link with "burrs", the location of external intrusion can be quickly located.

[0127] In another embodiment of the present invention, when the intrusion event is identified, the following steps are specifically performed:

[0128] Calculating the attenuation rates of the attenuation curve at different positions and the standard attenuation rates of the standard attenuation curve at different positions;

[0129] When there is external disturbance, the optical fiber will produce a slight bend and the loss will suddenly change, so the attenuation rate of the optical fiber will change suddenly, which is reflected as "burrs" on the attenuation curve. Therefore, the attenuation rate at different positions is determined by calculating the attenuation rate of the intensity on the attenuation curve.

[0130] By comparing the attenuation rates of the attenuation curve and the standard attenuation curve at different positions, the errors of the attenuation rates at different positions on the attenuation curve and the standard attenuation curve are calculated, the error rate is calculated based on the error, and the error rate is judged.

[0131] When the error rate between the attenuation curve at a certain position and the corresponding position exceeds a preset fluctuation range, it is identified that an intrusion event occurs at the position.

[0132] It should be noted that the continuous parts whose error rates exceed the fluctuation range are identified as the same intrusion event, and the intrusion position of the same intrusion event is specifically determined by the middle position of the continuous parts.

[0133] It should be noted that the setting of the fluctuation range can be adjusted according to actual conditions and is not specifically limited here. Those skilled in the art can set the fluctuation range to 5%, 10% or 15% according to specific conditions to cope with detection errors at different times.

[0134] By comparing the attenuation rates at different locations on the attenuation curve, the location of abnormal loss in the optical fiber link can be accurately identified.

[0135] In another embodiment provided by the present invention, after the disturbed location and the disturbed event are identified, the present invention is also used to identify the disturbing event, specifically:

[0136] The abnormal state data of the optical fiber link of the preset length at the disturbed position is extracted, that is, after the disturbed position is identified, the 1 / 2 preset length before and after the disturbed position is determined as the abnormal state data, and the corresponding abnormal attenuation curve in the attenuation curve is intercepted.

[0137] The attenuation features in the abnormal attenuation curve are extracted, that is, the features of the extracted abnormal attenuation curve are extracted, specifically the features of the "burr" part of the abnormal attenuation curve are extracted. When specifically identifying, the features of the mutation curve of the same intrusion event are extracted. The extracted features include: the mutation extreme value range, that is, the difference between the maximum and minimum values, the continuous distance, the maximum mutation rate and the minimum mutation rate of the attenuation rate, the number of extreme values, etc.

[0138] The extracted attenuation features are input into a pre-trained vibration recognition model to identify the vibration intensity and vibration frequency of the disturbed location.

[0139] The vibration recognition model adopts a model obtained by pre-training through deep learning, and can recognize different features of the input and determine the vibration intensity and vibration frequency of the disturbed location.

[0140] Through pre-training, the vibration frequency and vibration amplitude of the intrusion location can be identified.

[0141] Because the degree of deformation or damage of the optical fiber core will vary under different vibration amplitudes and vibration frequencies, the corresponding optical signal loss will also be different, which is specifically reflected in the attenuation curve. By analyzing the abnormal characteristics of the attenuation curve, the vibration intensity and vibration frequency of the disturbed location can be identified accordingly.

[0142] In yet another embodiment provided by the present invention, after the vibration intensity and the vibration frequency are identified, the type of intrusion can be determined according to the vibration intensity and the vibration frequency.

[0143] That is, different intrusion types generate different vibration intensities and frequencies on the optical fiber, and different intrusion types are pre-classified according to the differences in vibration intensities and vibration frequencies.

[0144] For example: during ground construction work, when a train or car passes by, there will be differences in the vibration frequency and vibration intensity caused by ground conduction. Corresponding relationships between vibration intensity and vibration frequency and intrusion types are established to build an event type library.

[0145] According to the vibration intensity and the vibration frequency, the corresponding intrusion event type is matched from the corresponding relationship in the event type library corresponding relationship.

[0146] By analyzing the vibration intensity and frequency of the intrusion location, the intrusion type can be identified based on the intrusion event, which facilitates rapid response to the intrusion, corresponding management work, and timely stop of losses to avoid damage to the optical fiber caused by continuous intrusion.

[0147] In another embodiment provided by the present invention, when the vibration recognition model is trained, the following steps are specifically performed:

[0148] Perform training data collection, that is, collect the attenuation curve of the optical signal in the optical fiber link with different vibration intensities and different vibration frequencies under simulation as training state data;

[0149] An abnormal part curve is intercepted from the collected attenuation curve. The abnormal part identification process can adopt the method for identifying the disturbed event in the above-mentioned embodiment, which will not be described in detail here.

[0150] The intercepted curve is subjected to feature extraction. The feature extraction method may adopt the same solution as that in the aforementioned embodiment, which will not be described in detail here.

[0151] Based on the intrusion features of different extracted training data as input, and the corresponding vibration intensity and vibration frequency as labels, the preset deep learning model is trained;

[0152] After the training termination condition is reached, the trained model is used as a vibration recognition model to complete the model training.

[0153] By increasing the amount of training data for model training, the recognition accuracy of the model can be improved.

[0154] See also Figure 4 , is a schematic diagram of the structure of an optical fiber status monitoring device provided by an embodiment of the present invention, the device comprising:

[0155] A polarization state monitoring module is used to detect the polarization state of the signal light transmitted by the optical fiber link and monitor the change event of the polarization state;

[0156] A data acquisition module, used for acquiring state data of the optical fiber link at a preset first frequency when a change event of the polarization state is monitored;

[0157] The position determination module is used to determine the disturbed position in the optical fiber according to the state data.

[0158] The optical fiber status monitoring device provided in this embodiment can execute all the steps and functions of the optical fiber status monitoring method provided in any of the above embodiments, and the specific functions of the device will not be described in detail here.

[0159] See also Figure 5 , is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an optical fiber status monitoring program. When the processor executes the computer program, the steps in each of the above-mentioned optical fiber status monitoring method embodiments are implemented, such as Figure 2 Alternatively, the processor implements the functions of each module in the above-mentioned device embodiments when executing the computer program.

[0160] Exemplarily, the computer program may be divided into one or more modules, and the one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the optical fiber status monitoring device. For example, the computer program may be divided into several modules, and the specific functions of each module have been described in detail in the optical fiber status monitoring method provided in any of the above embodiments, and the specific functions of the device will not be repeated here.

[0161] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor and a memory. A person skilled in the art may understand that the schematic diagram is only an example of a terminal device and does not constitute a limitation on an optical fiber status monitoring device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0162] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the optical fiber status monitoring device, and uses various interfaces and lines to connect various parts of the entire optical fiber status monitoring device.

[0163] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the optical fiber status monitoring device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0164] Wherein, if the module integrated in the optical fiber status monitoring device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0165] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of implementing the method by the functional network element in the above embodiment.

[0166] The computer program product provided in this embodiment can execute all the steps and functions of the optical fiber status monitoring method provided in any of the above embodiments, and the specific functions of the product are not described in detail here.

[0167] It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for monitoring optical fiber status, characterized in that: The method comprises: Perform polarization state detection on the signal light transmitted in the optical fiber link and monitor the change event of polarization state; When a polarization state change event is detected, collecting state data of the optical fiber link at a preset first frequency; The disturbed position in the optical fiber is determined according to the status data.

2. The optical fiber status monitoring method according to claim 1, characterized in that: Perform polarization state detection on the signal light transmitted in the optical fiber link and monitor the polarization state change events, including: Coherently coupling the signal light transmitted by the optical fiber link with the local oscillator light generated locally; Performing coherent detection on the coherently coupled optical signal; Detect changes in the polarization directions of the signal light and the local oscillation light, and identify polarization state change events.

3. The optical fiber status monitoring method according to claim 2, characterized in that: Detecting changes in the polarization directions of the signal light and the local oscillator light, and identifying polarization state change events, includes: detecting directions of electric vectors of the signal light and the local oscillator light, and taking a direction difference between the direction of the electric vector of the signal light and the direction of the electric vector of the local oscillator light as the change; When the direction difference is not within a preset first range, it is determined that a polarization state change event occurs.

4. The optical fiber status monitoring method according to claim 1, characterized in that: Collecting the status data of the optical fiber link at a preset first frequency includes: adjusting the sampling frequency of the built-in optical time domain reflectometer from the initial second frequency to the first frequency, and collecting the attenuation curve of the optical signal intensity over the distance on the optical fiber link as the state data; The first frequency is greater than the second frequency.

5. The optical fiber status monitoring method according to claim 1, characterized in that: Determining the disturbed position in the optical fiber according to the status data includes: According to the comparison between the attenuation curve of the optical signal in the state data and the standard attenuation curve in the preset standard state data, the intrusion event meeting the preset conditions is identified; The disturbed location is determined according to the distribution location of the disturbed events.

6. The optical fiber status monitoring method according to claim 5, characterized in that: Identify intrusion events that meet pre-set conditions, including: Calculating the attenuation rates of the attenuation curve at different positions and the attenuation rates of the standard attenuation curve at different positions; Calculating the error rate of attenuation rates at different positions on the attenuation curve and the standard attenuation curve; When the error rate at a certain location exceeds a preset fluctuation range, the intrusion event is identified.

7. The optical fiber status monitoring method according to claim 1, characterized in that: The method further comprises: Extracting abnormal status data of a fiber optic link of a preset length at the disturbed location; The attenuation characteristics of the abnormal state data are extracted and input into a pre-trained vibration recognition model to identify the vibration intensity and vibration frequency of the disturbed position.

8. The optical fiber status monitoring method according to claim 7, characterized in that: The method further comprises: A corresponding intrusion event type is matched from a preset event type library according to the vibration intensity and the vibration frequency.

9. The optical fiber status monitoring method according to claim 7, characterized in that: The vibration recognition model training process specifically includes: Collecting state data of optical signals in optical fiber links with different vibration intensities and frequencies; Extracting the intrusion features corresponding to the intrusion positions in the different state data as training data; The extracted different training data are used as input, and the corresponding vibration intensity and vibration frequency are used as labels to train the preset deep learning model; The trained model is used as the vibration recognition model.

10. An optical fiber status monitoring device, characterized in that: The device comprises: A polarization state monitoring module is used to detect the polarization state of the signal light transmitted by the optical fiber link and monitor the change event of the polarization state; A data acquisition module, used for acquiring state data of the optical fiber link at a preset first frequency when a change event of the polarization state is monitored; The position determination module is used to determine the disturbed position in the optical fiber according to the state data.

11. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the optical fiber status monitoring method according to any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the optical fiber status monitoring method according to any one of claims 1 to 9.

13. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of any method described in claims 1 to 9 are implemented.

Images