Fault diagnosis method and device of optical fiber link, computer equipment, readable storage medium and program product

Abstract

The invention relates to an optical fiber link fault diagnosis method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a time domain power fluctuation characteristic of the optical fiber link through an intelligent optical module, and acquiring a space domain performance fluctuation characteristic of the optical fiber link through an optical time domain reflectometer; fusing the time domain power fluctuation feature and the space domain performance fluctuation feature to obtain a fused fluctuation feature; and determining a fault diagnosis result of the optical fiber link according to the fusion fluctuation characteristics. By adopting the method, the fault diagnosis efficiency of the optical fiber link can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of optical fiber communication, and in particular to a fault diagnosis method and device for an optical fiber link, a computer device, a computer readable storage medium, and a computer program product. BACKGROUND

[0002] Optical fiber communication is a communication technology that uses optical signals as information carriers and optical fibers as transmission media.

[0003] In the prior art, diagnostic tools (such as OTDR, Optical Time-Domain Reflectometer) are often used to diagnose faults in optical fiber links. However, the operation and data analysis of these diagnostic tools require a high level of professional knowledge and experience from the maintenance personnel, and ordinary maintenance personnel are prone to analysis errors, which is not conducive to improving the efficiency of fault diagnosis for optical fiber links.

[0004] Therefore, the prior art has the problem of low efficiency of fault diagnosis for optical fiber links. SUMMARY

[0005] Therefore, it is necessary to provide a fault diagnosis method, device, computer device, computer readable storage medium, and computer program product for an optical fiber link that can improve the efficiency of fault diagnosis for optical fiber links.

[0006] In a first aspect, the present application provides a fault diagnosis method for an optical fiber link, the method comprising:

[0007] obtaining a time-domain power fluctuation feature of the optical fiber link through an intelligent optical module, and obtaining a spatial-domain performance fluctuation feature of the optical fiber link through an optical time-domain reflectometer;

[0008] fusing the time-domain power fluctuation feature and the spatial-domain performance fluctuation feature to obtain a fused fluctuation feature;

[0009] determining a fault diagnosis result for the optical fiber link according to the fused fluctuation feature.

[0010] In one embodiment, the step of fusing the time-domain power fluctuation feature and the spatial-domain performance fluctuation feature to obtain a fused fluctuation feature comprises:

[0011] aligning the time-domain power fluctuation feature and the spatial-domain performance fluctuation feature to obtain the time-domain power fluctuation feature and the spatial-domain performance fluctuation feature after alignment;

[0012] performing feature extraction on the time-domain power fluctuation feature to obtain a time-domain feature vector, and performing feature extraction on the spatial-domain performance fluctuation feature to obtain a spatial-domain feature vector;

[0013] concatenate the time domain feature vector and the space domain feature vector to obtain the fusion fluctuation feature.

[0014] In one of the embodiments, the feature extraction on the time domain power fluctuation feature to obtain a time domain feature vector comprises:

[0015] constructing an optical power time sequence according to the time domain power fluctuation feature;

[0016] inputting the optical power time sequence into a pre-trained optical fiber time domain fault event detection model; the optical fiber time domain fault event detection model is a Transformer model for detecting whether a time domain fault event exists in the optical fiber link;

[0017] obtaining a feature vector output by an encoder in the optical fiber time domain fault event detection model as the time domain feature vector.

[0018] In one of the embodiments, the feature extraction on the space domain performance fluctuation feature to obtain a space domain feature vector comprises:

[0019] inputting the space domain performance fluctuation feature into a pre-trained optical fiber physical fault event detection model; the optical fiber physical fault event detection model is a convolutional neural network for detecting whether a physical abnormal event exists in the optical fiber link;

[0020] obtaining a feature vector output by a convolution kernel in the optical fiber physical fault event detection model as the space domain feature vector.

[0021] In one of the embodiments, the determination of the fault diagnosis result of the optical fiber link according to the fusion fluctuation feature comprises:

[0022] inputting the fusion fluctuation feature into a pre-trained full connection layer to obtain an optical fiber fault recognition result; the optical fiber fault recognition result comprises that a probability of a preset fault type occurring in the optical fiber link is greater than a preset probability threshold;

[0023] obtaining fault position information of the optical fiber link by the optical time domain reflectometer, and generating the fault diagnosis result of the optical fiber link according to the fault position information and the optical fiber fault recognition result.

[0024] In one of the embodiments, the acquisition of the time domain power fluctuation feature of the optical fiber link by the intelligent optical module comprises:

[0025] collecting, by the intelligent optical module, a power fluctuation parameter corresponding to a preset node of the optical fiber link; the power fluctuation parameter comprises at least one of optical power fluctuation data and bit error rate;

[0026] According to the power fluctuation parameter, a time-domain power fluctuation feature of the optical fiber link is determined.

[0027] In one of the embodiments, the acquisition of the spatial performance fluctuation feature of the optical fiber link by the optical time domain reflectometer comprises:

[0028] The optical time domain reflectometer is used to collect loss spatial position information of the optical fiber link, and the loss spatial position information comprises at least one of joint loss positioning data or an attenuation coefficient distribution curve.

[0029] According to the loss spatial position information, a spatial performance fluctuation feature of the optical fiber link is determined.

[0030] In a second aspect, the application further provides a fault diagnosis device for an optical fiber link, and the device comprises:

[0031] A collection unit is configured to acquire a time-domain power fluctuation feature of the optical fiber link by an intelligent optical module, and to acquire a spatial performance fluctuation feature of the optical fiber link by an optical time domain reflectometer.

[0032] A fusion unit is configured to fuse the time-domain power fluctuation feature and the spatial performance fluctuation feature to obtain a fused fluctuation feature.

[0033] A diagnosis unit is configured to determine a fault diagnosis result of the optical fiber link according to the fused fluctuation feature.

[0034] In a third aspect, the application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0035] In a fourth aspect, the application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0036] In a fifth aspect, the application further provides a computer program product comprising a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0037] The fault diagnosis method, device, computer device, computer readable storage medium and computer program product of the optical fiber link can obtain the time domain power fluctuation feature of the optical fiber link through the intelligent optical module, obtain the spatial performance fluctuation feature of the optical fiber link through the optical time domain reflectometer, fuse the time domain power fluctuation feature and the spatial performance fluctuation feature to obtain a fused fluctuation feature, and determine the fault diagnosis result of the optical fiber link according to the fused fluctuation feature. In this way, the time domain power fluctuation feature of the to-be-tested optical fiber link collected by the intelligent optical module and the spatial performance fluctuation feature of the to-be-tested optical fiber link collected by the optical time domain reflectometer can be effectively aligned to obtain the multi-modal fluctuation feature of the to-be-tested optical fiber link. The multi-modal fluctuation feature is used for fault diagnosis of the optical fiber link, which can effectively capture the nonlinear correlation of composite faults such as fiber bending, automatically enhance the fault sensitive features of the optical fiber link, improve the recognition accuracy of fault events of the optical fiber link, and thus reduce the dependence on the professional ability of personnel for data analysis results of the diagnosis tool, effectively reduce the dependence on the professional ability of personnel, and thus reduce the difficulty of fault diagnosis of the optical fiber link and improve the fault diagnosis efficiency of the optical fiber link. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0039] Figure 1 An application environment diagram of a fault diagnosis method of an optical fiber link in an embodiment;

[0040] Figure 2 A flowchart of a fault diagnosis method of an optical fiber link in an embodiment;

[0041] Figure 3 A schematic diagram of an attenuation coefficient distribution curve in an embodiment;

[0042] Figure 4 An architecture diagram of a fault diagnosis system of an optical fiber link in an embodiment;

[0043] Figure 5 A schematic diagram of a space-time feature hybrid model in an embodiment;

[0044] Figure 6 A structural block diagram of a fault diagnosis device of an optical fiber link in an embodiment;

[0045] Figure 7Fig. 1 is a schematic diagram of an internal structure of a computer device in an embodiment. DETAILED DESCRIPTION

[0046] For the purposes of the present application, the technical solutions and advantages thereof are more clearly apparent, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0047] The optical fiber link fault diagnosis method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 . The fault diagnosis device 102 can be connected with the intelligent optical module 104 and the optical time domain reflectometer 106. The fault diagnosis device 102 obtains the time domain power fluctuation characteristics of the optical fiber link through the intelligent optical module 104, and obtains the spatial performance fluctuation characteristics of the optical fiber link through the optical time domain reflectometer 106; the fault diagnosis device 102 fuses the time domain power fluctuation characteristics and the spatial performance fluctuation characteristics to obtain fused fluctuation characteristics; and the fault diagnosis device 102 determines the fault diagnosis result of the optical fiber link according to the fused fluctuation characteristics.

[0048] The fault diagnosis device 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc.

[0049] In an exemplary embodiment, as shown in Figure 2 , an optical fiber link fault diagnosis method is provided. The method is described below with reference to the fault diagnosis device 102 in Figure 1 . The method includes the following steps S202 to S206. Wherein:

[0050] In step S202, the time domain power fluctuation characteristics of the optical fiber link are obtained through the intelligent optical module, and the spatial performance fluctuation characteristics of the optical fiber link are obtained through the optical time domain reflectometer.

[0051] The intelligent optical module (Intelligent Optical Module) can refer to an optical communication core device that has sensing function, computing function, control function and communication function, etc. on the basis of a traditional optical module.

[0052] In actual application, the intelligent optical module can be deployed on a preset node (i.e. a key node) of the optical fiber link.

[0053] The optical time-domain reflectometer is used for measuring a fiber loss curve of the fiber link, and determines uniformity, defects, breakage, joint coupling and other performances of the fiber link through analysis of the measured fiber loss curve.

[0054] In a specific implementation, when it is necessary to diagnose a fault of the fiber link, the fault diagnosis device can acquire the time-domain power fluctuation feature of the fiber link through the intelligent optical module. Specifically, the fault diagnosis device can collect power fluctuation data of a preset node of the fiber link through the intelligent optical module. The fault diagnosis device can determine the time-domain power fluctuation feature of the fiber link according to the power fluctuation data of the preset node.

[0055] Optionally, in the process of acquiring the time-domain power fluctuation feature of the fiber link through the intelligent optical module, the fault diagnosis device comprises: collecting, through the intelligent optical module, a power fluctuation parameter of the fiber link at a preset node; and determining the time-domain power fluctuation feature of the fiber link according to the power fluctuation parameter.

[0056] The power fluctuation parameter comprises at least one of optical power fluctuation data and a bit error rate.

[0057] Specifically, the fault diagnosis device can perform millisecond-level monitoring on the key node of the fiber link through the intelligent optical module, to collect optical power fluctuation data, a bit error rate and other power fluctuation parameters of the key node of the fiber link in real time. Then, the fault diagnosis device can determine the time-domain power fluctuation feature of the fiber link according to the power fluctuation parameters. In actual application, the fault diagnosis device can take the above-mentioned power fluctuation parameters as the time-domain power fluctuation feature of the fiber link.

[0058] Of course, the fault diagnosis device can also perform preset data processing on the above-mentioned power fluctuation parameters to obtain processed power fluctuation parameters as the time-domain power fluctuation feature of the fiber link. Specifically, the fault diagnosis device can calculate the mean value and the standard deviation of the optical power data in a sliding window statistical manner, determine an abnormal data range according to the mean value and the standard deviation, and then replace the optical power data exceeding the abnormal data range with a median value to eliminate device sampling noise interference.

[0059] In addition, the fault diagnosis device can also acquire the spatial performance fluctuation feature of the fiber link through the optical time-domain reflectometer. Specifically, the optical time-domain reflectometer can monitor the fiber link to obtain OTDR monitoring data of the fiber link, and the fault diagnosis device can determine the spatial performance fluctuation feature of the fiber link according to the OTDR monitoring data of the fiber link.

[0060] Optionally, in the process of acquiring the spatial performance fluctuation feature of the optical fiber link by the optical time domain reflectometer, the fault diagnosis device comprises: collecting loss spatial position information of the optical fiber link by the optical time domain reflectometer; and determining the spatial performance fluctuation feature of the optical fiber link according to the loss spatial position information.

[0061] The loss spatial position information can be position information of a loss point of the optical fiber link in space. Specifically, the loss spatial position information can include at least one of joint loss positioning data or an attenuation coefficient distribution curve.

[0062] In a specific implementation, the test wavelength, pulse width and measurement range of the optical time domain reflectometer can be adjusted according to the type of the optical fiber, and bidirectional testing can be used to eliminate Fresnel reflection interference. At the same time, the optical fiber link can be monitored in two modes, i.e., regular inspection and burst fault triggering detection, to obtain the joint loss positioning data and the attenuation coefficient distribution curve. In order to facilitate the understanding of those skilled in the art, Figure 3 An example of an attenuation coefficient distribution curve is shown. The slope of the attenuation coefficient distribution curve represents the attenuation coefficient of the optical fiber, which can be used to estimate the degree of line degradation. Then, the fault diagnosis device can determine the spatial performance fluctuation feature of the optical fiber link according to the loss spatial position information. In actual application, the fault diagnosis device can use the loss spatial position information as described above to determine the spatial performance fluctuation feature of the optical fiber link.

[0063] Of course, the fault diagnosis device can also perform preset data processing on the loss spatial position information as described above to obtain processed loss spatial position information as the spatial performance fluctuation feature of the optical fiber link. Specifically, in the case where the attenuation coefficient distribution curve has a missing data segment, the fault diagnosis device can reconstruct the attenuation coefficient distribution curve by multiple spline interpolation to make the attenuation coefficient distribution curve complete.

[0064] In step S204, the time domain power fluctuation feature and the spatial performance fluctuation feature are fused to obtain a fused fluctuation feature.

[0065] The fused fluctuation feature can be a multi-modal fluctuation feature.

[0066] In a specific implementation, after the fault diagnosis device obtains the time domain power fluctuation feature and the spatial performance fluctuation feature of the optical fiber link, the fault diagnosis device can fuse the time domain power fluctuation feature and the spatial performance fluctuation feature. Specifically, the fault diagnosis device can align the fused time domain power fluctuation feature and the spatial performance fluctuation feature. Then, the fault diagnosis device can perform feature extraction on the aligned time domain power fluctuation feature and the spatial performance fluctuation feature to obtain a corresponding feature extraction result. Then, the fused fluctuation feature is generated by using the feature extraction result.

[0067] At step S206, the fault diagnosis result of the optical fiber link is determined according to the fused fluctuation feature.

[0068] In a specific implementation, after obtaining the fused fluctuation feature, the fault diagnosis device can input the fused fluctuation feature into the pre-trained fault diagnosis model, perform feature space dimension reduction on the fused fluctuation feature through the pre-trained fault diagnosis model, realize non-linear mapping of the fused fluctuation feature, and obtain the fault prediction information of the optical fiber link. The fault prediction information of the optical fiber link can refer to the fault type that the optical fiber link may have.

[0069] Then, the fault diagnosis device can generate a fault diagnosis result according to the fault location information in the measurement result of the optical time domain reflectometer and the fault prediction information of the optical fiber link. In actual application, the fault diagnosis device can present the fault diagnosis result through a display device, or send the fault diagnosis result to a pre-set electronic device to display the fault diagnosis result of the optical fiber link to an operation and maintenance personnel through the electronic device.

[0070] In the above fault diagnosis method of the optical fiber link, the time domain power fluctuation feature of the optical fiber link is obtained through the intelligent optical module, the spatial domain performance fluctuation feature of the optical fiber link is obtained through the optical time domain reflectometer, the time domain power fluctuation feature and the spatial domain performance fluctuation feature are fused to obtain the fused fluctuation feature, and the fault diagnosis result of the optical fiber link is determined according to the fused fluctuation feature. In this way, the time domain power fluctuation feature of the to-be-tested optical fiber link collected by the intelligent optical module and the spatial domain performance fluctuation feature of the to-be-tested optical fiber link collected by the optical time domain reflectometer can be effectively aligned to obtain the multi-modal fluctuation feature of the to-be-tested optical fiber link. The multi-modal fluctuation feature is used for fault diagnosis of the optical fiber link, which can effectively capture the nonlinear correlation of the composite faults such as fiber bending, automatically enhance the fault sensitive features of the optical fiber link, improve the recognition accuracy of the fault events of the optical fiber link, and thus reduce the dependence on the professional ability of the operation and maintenance personnel for the data analysis result of the diagnosis tool, effectively reduce the dependence on the professional ability of the personnel, and thus reduce the difficulty of fault diagnosis of the optical fiber link and improve the fault diagnosis efficiency of the optical fiber link.

[0071] In one of the embodiments, the time domain power fluctuation feature and the spatial domain performance fluctuation feature are fused to obtain the fused fluctuation feature, including: aligning the time domain power fluctuation feature and the spatial domain performance fluctuation feature to obtain the aligned time domain power fluctuation feature and the spatial domain performance fluctuation feature; performing feature extraction on the time domain power fluctuation feature to obtain a time domain feature vector, and performing feature extraction on the spatial domain performance fluctuation feature to obtain a spatial domain feature vector; and splicing the time domain feature vector and the spatial domain feature vector to obtain the fused fluctuation feature.

[0072] In a specific implementation, the fault diagnosis device can perform spatio-temporal matching on the data in the time-domain power fluctuation feature and the space-domain performance fluctuation feature through a timestamp synchronization mechanism, and implement multi-scale feature extraction by using a sliding window mechanism. For example, the fault diagnosis device can perform spatio-temporal matching on the joint loss positioning data, the attenuation coefficient distribution curve, the loss curve and other spatial positioning data collected by the optical time domain reflectometer, in combination with the time-domain power fluctuation data of the intelligent optical module. For example, a timestamp is marked on each spatial scan of the OTDR (such as “2024-05-20 10:00:00, OTDR scan result: 100 meters away, attenuation 0.2dB, 150 meters away, attenuation 0.5dB”). A timestamp is marked on each time-domain power fluctuation data of the intelligent optical module (such as “2024-05-20 10:00:00, power - 5dBm; 10:00:01, power - 5.1dBm……”). Then, the fault diagnosis device can perform spatio-temporal matching on the joint loss positioning data, the attenuation coefficient distribution curve, the loss curve and other spatial positioning data, and the time-domain power fluctuation data in combination with the timestamps of the data, to obtain the aligned time-domain power fluctuation feature and the space-domain performance fluctuation feature.

[0073] Then, the fault diagnosis device can perform feature extraction on the time-domain power fluctuation feature to obtain a time-domain feature vector, and perform feature extraction on the space-domain performance fluctuation feature to obtain a space-domain feature vector. Specifically, the fault diagnosis device can input the time-domain power fluctuation feature into a pre-trained first feature extraction model to obtain the time-domain feature vector. In addition, the fault diagnosis device can input the space-domain performance fluctuation feature into a pre-trained second feature extraction model to obtain the space-domain feature vector.

[0074] Then, the fault diagnosis device can concatenate the time-domain feature vector and the space-domain feature vector to obtain a fused fluctuation feature. Specifically, the fault diagnosis device concatenates the time-domain feature vector and the space-domain feature vector to obtain a spatio-temporal joint representation matrix. Then, the fault diagnosis device takes the spatio-temporal joint representation matrix as the fused fluctuation feature of the optical fiber link.

[0075] The technical scheme of the embodiment is characterized in that the time-domain power fluctuation feature and the space-domain performance fluctuation feature are aligned, the aligned time-domain power fluctuation feature and the aligned space-domain performance fluctuation feature are obtained, the time-domain power fluctuation feature is extracted to obtain a time-domain feature vector, the space-domain performance fluctuation feature is extracted to obtain a space-domain feature vector, the time-domain feature vector and the space-domain feature vector are spliced to obtain a fusion fluctuation feature, thereby the time-domain power fluctuation feature and the space-domain performance fluctuation feature of two different modalities can be effectively fused, the fusion fluctuation feature obtained by fusion can reasonably and effectively represent the time-domain power fluctuation feature and the space-domain performance fluctuation feature, the automatic enhancement of the fault sensitive feature of the optical fiber link is realized, and the recognition accuracy of the fault event of the optical fiber link is improved.

[0076] In one of the embodiments, the time-domain power fluctuation feature is extracted to obtain the time-domain feature vector, including: constructing an optical power time sequence according to the time-domain power fluctuation feature; inputting the optical power time sequence into a pre-trained optical fiber time-domain fault event detection model; and obtaining a feature vector output by an encoder in the optical fiber time-domain fault event detection model as the time-domain feature vector.

[0077] The optical fiber time-domain fault event detection model is a Transformer model for detecting whether the optical fiber link has a time-domain fault event.

[0078] The time-domain fault event can include laser power-down, attenuation transient, etc. Specifically, the optical fiber time-domain fault event detection model can model the long-term dependence relationship of the optical power time sequence to detect the laser power-down, the attenuation transient, and other time-domain events.

[0079] In the process of extracting the time-domain power fluctuation feature to obtain the time-domain feature vector by the fault diagnosis device, the fault diagnosis device can construct an optical power time sequence according to the time-domain power fluctuation feature; input the optical power time sequence into a pre-trained optical fiber time-domain fault event detection model; and obtain a feature vector output by an encoder (i.e., an encoder of the Transformer model) in the optical fiber time-domain fault event detection model as the time-domain feature vector.

[0080] In the process of performing feature extraction on the time-domain power fluctuation feature to obtain a time-domain feature vector, the technical solution of the embodiment constructs an optical power time sequence according to the time-domain power fluctuation feature; inputs the optical power time sequence into a pre-trained optical fiber time-domain fault event detection model; and obtains a feature vector output by an encoder in the optical fiber time-domain fault event detection model as the time-domain feature vector. This can realize the mapping relationship between the optical power time sequence and the time-domain fault event that is pre-learned by the pre-trained optical fiber time-domain fault event detection model, automatically extract high-level abstract features from the optical power time sequence by using the encoder in the optical fiber time-domain fault event detection model, effectively extract the time-domain feature vector that can represent the optical fiber time-domain fault event, and facilitate subsequent fault diagnosis on the optical fiber link.

[0081] In one of the embodiments, the spatial domain performance fluctuation feature is subjected to feature extraction to obtain a spatial domain feature vector, including: inputting the spatial domain performance fluctuation feature into a pre-trained optical fiber physical fault event detection model; and obtaining a feature vector output by a convolution kernel in the optical fiber physical fault event detection model as the spatial domain feature vector.

[0082] The optical fiber physical fault event detection model is a convolutional neural network used for detecting whether a physical abnormal event exists in the optical fiber link.

[0083] The physical abnormal event can include abnormal events such as fiber bending and breaking. Specifically, the multi-layer convolution kernel in the optical fiber physical fault event detection model can perform local feature extraction on the spatial domain performance fluctuation feature, identify the physical abnormal events such as fiber bending and breaking, and form a feature mapping of the optical fiber physical space state.

[0084] In the process of performing feature extraction on the spatial domain performance fluctuation feature to obtain a spatial domain feature vector by the fault diagnosis device, the fault diagnosis device can input the spatial domain performance fluctuation feature into a pre-trained optical fiber physical fault event detection model, and obtain a feature vector output by a convolution kernel in the optical fiber physical fault event detection model as the spatial domain feature vector.

[0085] In the process of extracting the spatial performance fluctuation features to obtain the spatial feature vector, the spatial performance fluctuation features are input into the pre-trained optical fiber physical fault event detection model; the feature vector output by the convolution kernel in the optical fiber physical fault event detection model is obtained as the spatial feature vector. In this way, the mapping relationship between the spatial performance fluctuation features and the physical abnormal events learned by the pre-trained optical fiber physical fault event detection model can be utilized, the high-level abstract features can be automatically extracted from the spatial performance fluctuation features by the convolution kernel in the optical fiber physical fault event detection model, the spatial feature vector representing the optical fiber physical fault event can be effectively extracted, and the subsequent fault diagnosis of the optical fiber link by using the spatial feature vector is facilitated.

[0086] In one of the embodiments, the fault diagnosis result of the optical fiber link is determined according to the fused fluctuation features, including: inputting the fused fluctuation features into the pre-trained full connection layer to obtain an optical fiber fault recognition result; obtaining the fault position information of the optical fiber link by the optical time domain reflectometer, and generating the fault diagnosis result of the optical fiber link according to the fault position information and the optical fiber fault recognition result.

[0087] The optical fiber fault recognition result includes a probability of the optical fiber link occurring a preset fault type being greater than a preset probability threshold.

[0088] In the specific implementation, in the process of determining the fault diagnosis result of the optical fiber link according to the fused fluctuation features, the fault diagnosis device can input the fused fluctuation features into the pre-trained full connection layer to obtain the optical fiber fault recognition result. The optical fiber fault recognition result includes a probability of the optical fiber link occurring a preset fault type being greater than a preset probability threshold. For example, the optical fiber fault recognition result includes a probability of 0.98 for fault type A and a probability of 0.08 for fault type B.

[0089] Then, the fault diagnosis device can generate the fault diagnosis result of the optical fiber link according to the fault position information and the optical fiber fault recognition result. Specifically, the fault diagnosis device can determine the preset fault type with a probability greater than the preset probability threshold as the fault type of the optical fiber link according to the optical fiber fault recognition result. For example, the optical fiber fault recognition result includes a probability of 0.98 for fault type A and a probability of 0.08 for fault type B, and the fault type of the optical fiber link is fault type A.

[0090] Then, the fault diagnosis device can obtain the fault position information of the optical fiber link by the optical time domain reflectometer (for example, 100 meters of a certain section of the optical fiber link), and generate the positioning recognition report of the optical fiber fault (i.e., the fault diagnosis result) according to the fault position information and the fault type of the optical fiber link.

[0091] The technical scheme of the embodiment is characterized in that the fusion fluctuation feature is input into the pre-trained full connection layer to obtain an optical fiber fault recognition result, the fault position information of the optical fiber link is obtained by using the optical time domain reflectometer, the fault diagnosis result of the optical fiber link is generated according to the fault position information and the optical fiber fault recognition result, the fusion fluctuation feature is processed by using the pre-trained full connection layer, and therefore a fault type prediction result with a relatively high credibility can be effectively output based on probability, and in addition, the fault diagnosis result simultaneously includes the fault position information and the optical fiber fault recognition result, so that the current status of the optical fiber link can be comprehensively understood by the operation and maintenance personnel.

[0092] For the convenience of those skilled in the art, Figure 4 As shown in the accompanying drawings, Figure 4 An architectural diagram of an optical fiber link fault diagnosis system is provided; wherein the optical fiber link fault diagnosis system can include a data acquisition layer, a feature fusion layer, and an intelligent diagnosis layer; wherein the data acquisition layer includes an intelligent optical module and an optical time domain analyzer; the intelligent optical module can be an optical communication core device with functions of perception, calculation, control and communication on the basis of a traditional optical module. In actual application, the intelligent optical module can be deployed at a preset node of the optical fiber link. The intelligent optical module collects power fluctuation parameters of the optical fiber link at the preset node, including at least one of optical power fluctuation data and bit error rate. In addition, the test wavelength, pulse width and measurement range of the optical time domain reflectometer can be adjusted according to the type of optical fiber, and bidirectional testing can be used to eliminate Fresnel reflection interference. At the same time, the optical fiber link can be monitored in two modes of periodic inspection and burst fault triggering detection to obtain joint loss positioning data and an attenuation coefficient distribution curve.

[0093] The feature fusion layer includes a feature alignment module and a data cleaning module. The feature alignment module is used to perform space-time matching on data in the time-domain power fluctuation feature and the space-domain performance fluctuation feature through a timestamp synchronization mechanism, and to realize multi-scale feature extraction by using a sliding window mechanism. For example, the joint loss positioning data, the attenuation coefficient distribution curve, the loss curve and other spatial positioning data collected by the optical time domain reflectometer can be combined with the time-domain power fluctuation data of the intelligent optical module for space-time matching by the fault diagnosis device. The data cleaning module can detect and repair abnormal values and fill in missing data. For example, in the case of a missing data section in the attenuation coefficient distribution curve, the fault diagnosis device can reconstruct the attenuation coefficient distribution curve by using multiple spline interpolation to make the attenuation coefficient distribution curve complete. The fault diagnosis device can also calculate the mean value and the standard deviation of the optical power data by using a sliding window statistical method, determine the abnormal data range according to the mean value and the standard deviation, and then replace the optical power data exceeding the abnormal data range with a median value to eliminate device sampling noise interference.

[0094] The intelligent diagnosis layer includes a fault analysis module and a result generation module. The fault analysis module is constructed by a spatio-temporal feature hybrid model, as shown in Figure 5 The spatio-temporal feature hybrid model includes an input layer, a parallel feature extraction layer, a full connection layer, and an output layer. In the parallel feature extraction layer, the fault diagnosis device extracts the time domain power fluctuation features to obtain a time domain feature vector, and extracts the space domain performance fluctuation features to obtain a space domain feature vector, to realize a parallel feature extraction mechanism. In addition, the fault analysis module can input the fused fluctuation features to the pre-trained full connection layer to obtain an optical fiber fault recognition result. The optical fiber fault recognition result includes a probability of a preset fault type of the optical fiber link being greater than a preset probability threshold. For example, the optical fiber fault recognition result includes a probability of 0.98 for a fault type A and a probability of 0.08 for a fault type B. The fault analysis module outputs the fault type of the optical fiber link. The result generation module is used to generate an optical fiber fault positioning recognition report by combining the fault type given by the fault analysis module with the fault location information in the OTDR measurement result.

[0095] It should be understood that, although each step in the flowchart involved in each embodiment as described above is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise explicitly stated herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiments of the present application also provide an optical fiber link fault diagnosis apparatus for implementing the above-mentioned optical fiber link fault diagnosis method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more optical fiber link fault diagnosis apparatus embodiments provided below can refer to the limitations of the optical fiber link fault diagnosis method described above, which will not be described here again.

[0097] In one exemplary embodiment, as shown in Figure 6 An optical fiber link fault diagnosis apparatus is provided, comprising:

[0098] The collection unit 610 is configured to acquire time-domain power fluctuation characteristics of the optical fiber link by the intelligent optical module, and acquire spatial performance fluctuation characteristics of the optical fiber link by an optical time domain reflectometer.

[0099] The fusion unit 620 is configured to fuse the time-domain power fluctuation characteristics and the spatial performance fluctuation characteristics to obtain fused fluctuation characteristics.

[0100] The diagnosis unit 630 is configured to determine a fault diagnosis result of the optical fiber link according to the fused fluctuation characteristics.

[0101] In one of the embodiments, the fusion unit 620 is specifically configured to align the time-domain power fluctuation characteristics and the spatial performance fluctuation characteristics to obtain the aligned time-domain power fluctuation characteristics and the spatial performance fluctuation characteristics; perform feature extraction on the time-domain power fluctuation characteristics to obtain a time-domain feature vector, and perform feature extraction on the spatial performance fluctuation characteristics to obtain a spatial feature vector; and splice the time-domain feature vector and the spatial feature vector to obtain the fused fluctuation characteristics.

[0102] In one of the embodiments, the fusion unit 620 is specifically configured to construct an optical power time sequence according to the time-domain power fluctuation characteristics; input the optical power time sequence into a pre-trained optical fiber time-domain fault event detection model; the optical fiber time-domain fault event detection model is a Transformer model used for detecting whether a time-domain fault event exists in the optical fiber link; and acquire a feature vector output by an encoder in the optical fiber time-domain fault event detection model as the time-domain feature vector.

[0103] In one of the embodiments, the fusion unit 620 is specifically configured to input the spatial performance fluctuation characteristics into a pre-trained optical fiber physical fault event detection model; the optical fiber physical fault event detection model is a convolutional neural network used for detecting whether a physical abnormal event exists in the optical fiber link; and acquire a feature vector output by a convolution kernel in the optical fiber physical fault event detection model as the spatial feature vector.

[0104] In one of the embodiments, the collection unit 610 is specifically configured to collect, by the intelligent optical module, a power fluctuation parameter corresponding to a preset node of the optical fiber link; the power fluctuation parameter includes at least one of optical power fluctuation data and a bit error rate; and determine the time-domain power fluctuation characteristics of the optical fiber link according to the power fluctuation parameter.

[0105] In one of the embodiments, the collection unit 610 is specifically configured to collect the loss spatial position information of the optical fiber link by the optical time domain reflectometer; the loss spatial position information comprises at least one of joint loss positioning data or an attenuation coefficient distribution curve; and the spatial performance fluctuation feature of the optical fiber link is determined according to the loss spatial position information.

[0106] In one of the embodiments, the diagnosis unit 630 is specifically configured to input the fusion fluctuation feature into a pre-trained full connection layer to obtain an optical fiber fault identification result; the optical fiber fault identification result comprises a probability of a preset fault type occurring in the optical fiber link; the fault position information of the optical fiber link is acquired by the optical time domain reflectometer; and a fault diagnosis result of the optical fiber link is generated according to the fault position information and the optical fiber fault identification result.

[0107] In one of the embodiments, a computer device is provided, which can be a terminal. An internal structure diagram of the computer device can be as shown in Figure 7 The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, near field communication (NFC) or other technologies. The computer program is executed by the processor to implement a fault diagnosis method of an optical fiber link. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, a trackball or a touchpad arranged on the shell of the computer device, or can be an external keyboard, a touchpad or a mouse, etc.

[0108] Those skilled in the art can understand that Figure 7The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0109] In an embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the computer program being executed by the processor to cause the processor to perform the steps of the method for diagnosing faults of an optical fiber link. The steps of the method for diagnosing faults of an optical fiber link can be the steps in the method for diagnosing faults of an optical fiber link in each of the above embodiments.

[0110] In an embodiment, a computer readable storage medium is provided, storing a computer program, the computer program being executed by a processor to cause the processor to perform the steps of the method for diagnosing faults of an optical fiber link. The steps of the method for diagnosing faults of an optical fiber link can be the steps in the method for diagnosing faults of an optical fiber link in each of the above embodiments.

[0111] In an embodiment, a computer program product is provided, comprising a computer program, the computer program being executed by a processor to cause the processor to perform the steps of the method for diagnosing faults of an optical fiber link. The steps of the method for diagnosing faults of an optical fiber link can be the steps in the method for diagnosing faults of an optical fiber link in each of the above embodiments.

[0112] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0113] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magneto resistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0114] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0115] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for fault diagnosis of an optical fiber link, characterized in that, The method includes: The temporal power fluctuation characteristics of the optical fiber link are obtained by using an intelligent optical module, and the spatial performance fluctuation characteristics of the optical fiber link are obtained by using an optical time domain reflectometer. By fusing the time-domain power fluctuation characteristics and the spatial-domain performance fluctuation characteristics, a fused fluctuation characteristic is obtained; Based on the fusion fluctuation characteristics, the fault diagnosis result of the optical fiber link is determined.

2. The method according to claim 1, characterized in that, The fusion of the time-domain power fluctuation characteristics and the spatial-domain performance fluctuation characteristics to obtain the fused fluctuation characteristics includes: Align the time-domain power fluctuation feature and the spatial performance fluctuation feature to obtain the aligned time-domain power fluctuation feature and spatial performance fluctuation feature; Feature extraction is performed on the time-domain power fluctuation characteristics to obtain a time-domain feature vector, and feature extraction is performed on the spatial-domain performance fluctuation characteristics to obtain a spatial-domain feature vector; The fused fluctuation feature is obtained by concatenating the temporal feature vector and the spatial feature vector.

3. The method according to claim 2, characterized in that, The step of extracting features from the time-domain power fluctuation characteristics to obtain a time-domain feature vector includes: Based on the aforementioned time-domain power fluctuation characteristics, an optical power time series is constructed; The optical power time series is input into a pre-trained fiber optic time-domain fault event detection model; the fiber optic time-domain fault event detection model is a Transformer model used to detect whether there are time-domain fault events in the fiber optic link. Obtain the feature vector output by the encoder in the fiber optic time-domain fault event detection model, and use it as the time-domain feature vector.

4. The method according to claim 2, characterized in that, The step of extracting features from the spatial performance fluctuation characteristics to obtain a spatial feature vector includes: The spatial performance fluctuation characteristics are input into a pre-trained optical fiber physical fault event detection model; the optical fiber physical fault event detection model is a convolutional neural network used to detect whether there are physical abnormal events in the optical fiber link. The feature vector output by the convolution kernel in the optical fiber physical fault event detection model is obtained as the spatial domain feature vector.

5. The method according to claim 1, characterized in that, The step of acquiring the time-domain power fluctuation characteristics of the optical fiber link through the intelligent optical module includes: The intelligent optical module collects power fluctuation parameters of the optical fiber link at a preset node; the power fluctuation parameters include at least one of optical power fluctuation data and bit error rate. Based on the power fluctuation parameters, the time-domain power fluctuation characteristics of the optical fiber link are determined.

6. The method according to claim 1, characterized in that, The acquisition of the spatial performance fluctuation characteristics of the optical fiber link using an optical time-domain reflectometer includes: The optical fiber link loss spatial location information is acquired by the optical time domain reflectometer; the loss spatial location information includes at least one of connector loss location data or attenuation coefficient distribution curve; Based on the spatial location information of the loss, the spatial performance fluctuation characteristics of the optical fiber link are determined.

7. The method according to any one of claims 1 to 6, characterized in that, The step of determining the fault diagnosis result of the optical fiber link based on the fused fluctuation characteristics includes: The fused fluctuation features are input into a pre-trained fully connected layer to obtain fiber optic fault identification results; the fiber optic fault identification results include the probability that the fiber optic link will experience a preset fault type. The fault location information of the optical fiber link is obtained by the optical time domain reflectometer, and the fault diagnosis result of the optical fiber link is generated based on the fault location information and the optical fiber fault identification result.

8. A fault diagnosis device for an optical fiber link, characterized in that, The device includes: The acquisition unit is used to acquire the time-domain power fluctuation characteristics of the optical fiber link through an intelligent optical module, and to acquire the spatial performance fluctuation characteristics of the optical fiber link through an optical time-domain reflectometer. A fusion unit is used to fuse the time-domain power fluctuation characteristics and the spatial-domain performance fluctuation characteristics to obtain fused fluctuation characteristics. The diagnostic unit is used to determine the fault diagnosis result of the optical fiber link based on the fusion fluctuation characteristics.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images