Optical cable monitoring method, optical cable monitoring device and optical cable monitoring system

By obtaining the number and distance of optical cable sites, determining the location of distributed optical fiber sensors, analyzing the phase value and identifying abnormal frequency, the problem of low optical cable monitoring efficiency is solved, accurate monitoring and early warning of optical cables is achieved, and timely failure detection is improved.

CN119070898APending Publication Date: 2024-12-03CHINA ENERGY GRP NINGXIA COAL IND CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411194144.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, the low efficiency of optical cable monitoring makes it difficult to ensure comprehensiveness and timeliness in the laying of long-distance optical cables, resulting in delays in fault detection or missed inspections, and economic losses.

Method used

By obtaining the number of sites on the optical cable and the distance between adjacent sites, determining the target position of the distributed optical fiber sensor, obtaining sensing data, analyzing phase values, identifying abnormal vibration frequency, and judging the abnormal type of optical cables, achieving accurate monitoring of optical cables and early warning.

Benefits of technology

It improves the efficiency and accuracy of optical cable monitoring, detects abnormal events in advance, reduces fault detection delays, and reduces economic losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119070898A_ABST
    Figure CN119070898A_ABST
Patent Text Reader

Abstract

The invention provides an optical cable monitoring method, an optical cable monitoring device and an optical cable monitoring system, and the method comprises the steps: obtaining the number of stations on a to-be-detected optical cable and the distance between any two adjacent stations, and determining the target position of a distributed optical fiber sensor according to the number and the distance, and the to-be-detected optical cable comprises a plurality of stations; sensing data are obtained and processed, a plurality of phase values are obtained, the sensing data are data obtained by a distributed optical fiber sensor arranged at a target position, and the phase values are phase values corresponding to light at all moments in the transmission process of the to-be-measured optical cable; according to the multiple phase values, abnormal phase parameters are determined, the abnormal phase parameters at least comprise the vibration frequency corresponding to abnormal phase data, and the abnormal phase data are abnormal values in the multiple phase values; and determining the abnormal type of the optical cable according to the abnormal phase parameter so as to monitor the optical cable. The method solves the technical problem of low optical cable monitoring efficiency in the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of optical cables, and in particular, to an optical cable monitoring method, an optical cable monitoring device, a computer-readable storage medium, and an optical cable monitoring system. Background Art

[0002] At present, communication optical cables are generally laid over long distances, passing through various complex environments along the route, such as cities, villages, and remote areas. Traditional optical cable safety protection still relies on manual labor, and inspection methods are still through manual recording, taking photos, etc. Due to the long mileage of transmission optical cables, which can easily be tens to dozens of kilometers, it is difficult to ensure the comprehensiveness, timeliness, and effectiveness of inspection work by manpower alone, and once a failure occurs, it will cause huge losses.

[0003] Therefore, there is an urgent need for a method to solve the technical problem of low efficiency of optical cable monitoring in the prior art. Summary of the invention

[0004] The main purpose of the present application is to provide an optical cable monitoring method, an optical cable monitoring device, a computer-readable storage medium and an optical cable monitoring system, so as to at least solve the problem of low efficiency of optical cable monitoring in the prior art.

[0005] According to one aspect of the present application, a method for monitoring an optical cable is provided, comprising: obtaining the number of sites on an optical cable to be tested and the distance between any two adjacent sites, and determining a target position of a distributed optical fiber sensor based on the number and distance, wherein the optical cable to be tested includes multiple sites; obtaining sensing data, and processing the sensing data to obtain multiple phase values, wherein the sensing data is data obtained by a distributed optical fiber sensor arranged at the target position, and the phase values ​​are phase values ​​corresponding to light at each moment during the transmission of the optical cable to be tested; determining abnormal phase parameters based on the multiple phase values, wherein the abnormal phase parameters at least include a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the multiple phase values; determining the abnormal type of the optical cable based on the abnormal phase parameters for monitoring the optical cable.

[0006] Optionally, the multiple sites include intermediate sites and edge sites, and the edge sites are located on both sides of the intermediate site. The target position of the distributed optical fiber sensor is determined according to the number and distance, including: determining whether the number is greater than two; when the number is two, obtaining a first distance between the two sites, and determining whether the first distance is less than or equal to a distance threshold, and when the first distance is less than or equal to the distance threshold, determining the position of any one of the two sites as the target position, wherein the distance threshold is the maximum detection range of the distributed optical fiber sensor; when the first distance is greater than the distance threshold, determining the positions of the two sites as the target position; when the number is greater than two, obtaining a second distance between any one of the intermediate sites and a first adjacent site, and determining whether the second distance is less than or equal to the distance threshold. value, when the second distance is greater than the distance threshold, determine the position of the intermediate site and the position of the first adjacent site as the target position, wherein the first adjacent site is adjacent to the intermediate site and has the smallest distance; when the second distance is less than or equal to the distance threshold, obtain the third distance between the intermediate site and the second adjacent site, determine whether the sum of the second distance and the third distance is less than or equal to the distance threshold, and when the sum is less than or equal to the distance threshold, determine any one of the position of the intermediate site, the position of the first adjacent site, and the position of the second adjacent site as the target position, wherein the second adjacent site is adjacent to the intermediate site and the third distance is greater than the second distance; when the sum is greater than the distance threshold, determine the position of the first adjacent site and the position of the second adjacent site as the target position.

[0007] Optionally, determining abnormal phase parameters according to multiple phase values ​​includes: obtaining a mapping relationship, determining that the phase value that does not satisfy the mapping relationship among the multiple phase values ​​is the abnormal phase data, wherein the mapping relationship is used to characterize the correspondence between the phase value and the time during the normal transmission of light in the optical cable to be tested; obtaining historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data, wherein the historical abnormal phase data is the abnormal phase data obtained before the current moment; obtaining a target convolutional neural network, and inputting the multiple abnormal phase data into the target convolutional neural network in sequence to obtain the vibration frequencies corresponding to the multiple abnormal phase data, wherein the target convolutional neural network is trained by machine learning using multiple sets of historical data, and each set of the multiple sets of historical data includes: the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data.

[0008] Optionally, obtaining historical abnormal phase data includes: obtaining abnormal phase data of a faulty optical cable to obtain original abnormal phase data, wherein the faulty optical cable is an optical cable that is not working properly; and normalizing the original abnormal phase data to obtain the historical abnormal phase data.

[0009] Optionally, obtaining a target convolutional neural network includes: an obtaining step of obtaining an initial convolutional neural network model; a first input step of inputting the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data into the initial convolutional neural network model to obtain first output data, so as to respectively perform forward propagation processing on the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data; a first calculation step of calculating a cross entropy loss function of the initial convolutional neural network model according to the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data and the first output data; a second input step of inputting the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data into the initial convolutional neural network model to obtain second output data, so as to respectively perform back propagation processing on the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data, wherein the initial convolutional neural network model comprises: The convolution neural network comprises a plurality of layers; a second calculation step of calculating the gradient of each layer, wherein the gradient is used to characterize the influence of the network parameters of each layer on the cross entropy loss function; an updating step of updating the network parameters of the layer using a stochastic gradient descent algorithm to obtain updated network parameters; repeating the first input step, the first calculation step, the second input step, the second calculation step and the updating step at least once in sequence, and updating the network parameters of the layer of the initial convolution neural network in the first input step to the updated network parameters in the updating step obtained in the last repetition process during the repetition process until a preset condition is met, and determining that the initial convolution neural network model when the preset condition is met is the target convolution neural network model, wherein the preset condition comprises one of the following: the gradient reaches a minimum value, the cross entropy loss function reaches a minimum value and the repetition reaches a predetermined number of times.

[0010] Optionally, the first calculation step includes: according to the formula Calculate the cross entropy loss function H, where N is the total number of categories of vibration frequencies corresponding to the historical abnormal phase data, p(x c ) is the vibration frequency corresponding to the cth category, q(x c ) is the first output data corresponding to the c-th category.

[0011] Optionally, the updating step includes: updating the network parameter A of the layer according to the formula A′=AB×M to obtain the updated network parameter A′, wherein B is the learning rate and M is the gradient.

[0012] According to another aspect of the present application, an optical cable monitoring device is provided, comprising: a first determination unit, used to obtain the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determine the target position of the distributed optical fiber sensor based on the number and distance, wherein the optical cable to be tested includes multiple sites; a processing unit, used to obtain sensing data, and process the sensing data to obtain multiple phase values, wherein the sensing data is data obtained by the distributed optical fiber sensor set at the target position, and the phase value is the phase value corresponding to each moment during the transmission process of the optical cable to be tested; a second determination unit, used to determine an abnormal phase parameter based on the multiple phase values, wherein the abnormal phase parameter at least includes the vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the multiple phase values; a third determination unit, used to determine the abnormal type of the optical cable based on the abnormal phase parameter, so as to monitor the optical cable.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0014] According to another aspect of the present application, an optical cable monitoring system is provided, comprising: one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0015] The technical solution of the present application is applied to provide an optical cable monitoring method. First, the number of sites on the optical cable to be tested and the distance between any two adjacent sites are obtained, and the target position of the distributed optical fiber sensor is determined according to the number and distance, and the optical cable to be tested includes multiple sites; then, the sensing data is obtained, and the sensing data is processed to obtain multiple phase values, the sensing data is the data obtained by the distributed optical fiber sensor set at the target position, and the phase value is the phase value corresponding to each moment of the light in the transmission process of the optical cable to be tested; then, according to the multiple phase values, the abnormal phase parameter is determined, and the abnormal phase parameter at least includes the vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is the abnormal value in the multiple phase values; finally, according to the abnormal phase parameter, the abnormal type of the optical cable is determined for monitoring the optical cable. By setting a distributed optical fiber sensor at a target position along the optical cable, and connecting the existing optical cable through the distributed optical fiber sensor, the characteristics of the signal change in the optical fiber are analyzed and identified, the vibration frequency is obtained, and different types of abnormal events are judged according to the vibration frequency, so as to give an early warning, so that the optical cable can be accurately monitored, the optical cable monitoring efficiency is improved, and the technical problem of low optical cable monitoring efficiency in the prior art is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for executing an optical cable monitoring method provided in an embodiment of the present application is shown;

[0018] Figure 2 A schematic diagram of a process of an optical cable monitoring method provided according to an embodiment of the present application is shown;

[0019] Figure 3 A schematic diagram showing the distribution of two sites provided according to an embodiment of the present application is shown;

[0020] Figure 4 A schematic diagram showing the distribution of multiple sites provided in an embodiment of the present application is shown;

[0021] Figure 5 A structural block diagram of an optical cable monitoring device provided according to an embodiment of the present application is shown.

[0022] The above drawings include the following reference numerals:

[0023] 102, processor; 104, memory; 106, transmission device; 108, input and output device; 300, site; 302, first distance; 304, intermediate site; 306, first adjacent site; 308, second adjacent site; 310, second distance; 312, third distance. DETAILED DESCRIPTION

[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] As introduced in the background technology, the optical cable monitoring efficiency in the prior art is low. To solve the above problem, the embodiments of the present application provide an optical cable monitoring method, an optical cable monitoring device, a computer-readable storage medium and an optical cable monitoring system.

[0028] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of an optical cable monitoring method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the optical cable monitoring method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] In this embodiment, a method for monitoring an optical cable running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 2 FIG. 1 is a flow chart of an optical cable monitoring method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0033] Step S201, obtaining the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determining the target position of the distributed optical fiber sensor according to the number and distance, wherein the optical cable to be tested includes a plurality of sites;

[0034] Specifically, an optical cable is a communication line that uses fiber optic technology to transmit data. Optical fibers are thin, long filaments made of ultra-pure quartz glass that can reflect light signals internally, thereby enabling data transmission. Optical cables are composed of many such optical fibers and are encapsulated in a protective outer sheath. The construction of an optical cable network involves multiple sites that are connected by optical fibers to form a complex communication network to support high-speed data transmission and network services. The above-mentioned sites can be optical fiber access sites, optical fiber switching sites, optical fiber relay sites, and optical fiber terminal sites, among which the optical fiber access site is the location where the user connects to the optical fiber network, which can be a home, business, or public facility; the optical fiber switching site is responsible for transmitting signals from one optical fiber to another to achieve data routing and exchange; the optical fiber relay site is used to amplify or regenerate signals to maintain signal quality; the optical fiber terminal site can be a data center, a large server cluster, or other critical network facilities.

[0035] Step S202, acquiring sensing data, and processing the sensing data to obtain a plurality of phase values, wherein the sensing data is data acquired by a distributed optical fiber sensor disposed at the target position, and the phase values ​​are phase values ​​corresponding to each moment of the light during the transmission of the optical cable to be tested;

[0036] Specifically, the Distributed Fiber Optic Sensor (DFOS) uses optical fiber as a sensing medium and can realize continuous monitoring of environmental physical quantities along the optical fiber. This sensor can measure a variety of physical quantities such as temperature, strain, vibration, magnetic field, etc., and has the advantages of anti-electromagnetic interference and long-distance monitoring. The working principle of the distributed optical fiber sensor is mainly based on the backscattering effect in the optical fiber. By analyzing the scattered light signals at different positions in the optical fiber, the distributed monitoring of the environment along the optical fiber is realized. Among them, Rayleigh scattering, Brillouin scattering and Raman scattering are three commonly used scattering mechanisms, which correspond to different measurement principles and technical applications.

[0037] Step S203, determining an abnormal phase parameter according to the plurality of phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the plurality of phase values;

[0038] Specifically, in the process of determining the abnormal phase parameter, multiple phase values ​​may be analyzed based on the optical phase fusion algorithm.

[0039] Step S204: determining the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable.

[0040] Specifically, the abnormal types of the above-mentioned optical cables include optical fiber breakage, insufficient transmission power, connection failure, environmental factors, external force factors and human factors, among which optical fiber breakage is caused by physical squeezing or excessive bending by external force; insufficient transmission power means that the optical fiber laying distance is too long, which may cause signal loss, and damaged connectors may also cause signal loss. Connection failure means that the use of too many optical fiber joints and connectors may cause signal loss, and optical fiber distribution tray or fusion tray connection failure; environmental factors include dust, fingerprints, scratches, humidity and other factors that damage the connector, or the transmission power is too low, and the connector is wrong in the wiring room; external force factors include construction digging, vehicle disconnection, shooting and other situations; human factors include work obstacles, theft, deliberate destruction and other human factors may also cause optical cable line failure.

[0041] Through this embodiment, a method for monitoring an optical cable is provided. First, the number of sites on the optical cable to be tested and the distance between any two adjacent sites are obtained, and the target position of the distributed optical fiber sensor is determined according to the number and distance, and the optical cable to be tested includes multiple sites; then, the sensing data is obtained, and the sensing data is processed to obtain multiple phase values, the sensing data is the data obtained by the distributed optical fiber sensor set at the target position, and the phase value is the phase value corresponding to each moment of the light in the transmission process of the optical cable to be tested; then, according to the multiple phase values, the abnormal phase parameter is determined, and the abnormal phase parameter at least includes the vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is the abnormal value in the multiple phase values; finally, according to the abnormal phase parameter, the abnormal type of the optical cable is determined for monitoring the optical cable. By setting a distributed optical fiber sensor at a target position along the optical cable, and connecting the existing optical cable through the distributed optical fiber sensor, the characteristics of the signal change in the optical fiber are analyzed and identified, the vibration frequency is obtained, and different types of abnormal events are judged according to the vibration frequency, so as to give an early warning, so that the optical cable can be accurately monitored, the optical cable monitoring efficiency is improved, and the technical problem of low optical cable monitoring efficiency in the prior art is solved.

[0042] The multiple sites include intermediate sites and edge sites, and the edge sites are located on both sides of the intermediate sites. The step S201 can also be implemented in other ways, for example: step S2011, determine whether the number is greater than two; step S2012, when the number is two, obtain the first distance between the two sites, and determine whether the first distance is less than or equal to the distance threshold, and when the first distance is less than or equal to the distance threshold, determine the position of any one of the two sites as the target position, wherein the distance threshold is the maximum detection range of the distributed optical fiber sensor; step S2013, when the first distance is greater than the distance threshold, determine the position of the two sites as the target position; step S2014, when the number is greater than two, obtain the second distance between any one of the intermediate sites and the first adjacent site, and determine whether the second distance is less than or equal to the distance threshold. distance threshold, when the second distance is greater than the distance threshold, determine the position of the intermediate station and the position of the first adjacent station as the target position, wherein the first adjacent station is adjacent to the intermediate station and has the smallest distance; step S2015, when the second distance is less than or equal to the distance threshold, obtain the third distance between the intermediate station and the second adjacent station, determine whether the sum of the second distance and the third distance is less than or equal to the distance threshold, when the sum is less than or equal to the distance threshold, determine any one of the position of the intermediate station, the position of the first adjacent station and the position of the second adjacent station as the target position, wherein the second adjacent station is adjacent to the intermediate station and the third distance is greater than the second distance; step S2016, when the sum is greater than the distance threshold, determine the position of the first adjacent station and the position of the second adjacent station as the target position. This method can further achieve the maximum utilization efficiency of the distributed optical fiber sensor.

[0043] Specifically, the distance threshold may be 50 to 70 km. Figure 3 and Figure 4 As shown, Figure 3 The distribution diagram of the two sites is shown in FIG. Figure 3 As shown, when the number of sites 300 is two, the first distance 302 between the two sites 300 is obtained, and it is determined whether the first distance 302 is less than or equal to the distance threshold. When the first distance 302 is less than or equal to the distance threshold, the position of any one of the two sites 300 is determined to be the target position. When the first distance 302 is greater than the distance threshold, the positions of the two sites 300 are determined to be the target positions. Figure 4A schematic diagram of the distribution of multiple sites is shown, such as Figure 4 As shown, when the number of the above-mentioned sites is greater than two, the second distance 310 between any one of the above-mentioned intermediate sites 304 and the first adjacent site 306 is obtained, and it is determined whether the above-mentioned second distance 310 is less than or equal to the above-mentioned distance threshold. When the above-mentioned second distance 310 is greater than the above-mentioned distance threshold, the position of the above-mentioned intermediate site 304 and the position of the above-mentioned first adjacent site 306 are determined to be the above-mentioned target position; when the above-mentioned second distance 310 is less than or equal to the above-mentioned distance threshold, the third distance 312 between the above-mentioned intermediate site 304 and the second adjacent site 308 is obtained, and it is determined whether the sum of the above-mentioned second distance 310 and the above-mentioned third distance 312 is less than or equal to the above-mentioned distance threshold. When the above-mentioned sum is less than or equal to the above-mentioned distance threshold, it is determined that any one of the position of the above-mentioned intermediate site 304, the position of the above-mentioned first adjacent site 306 and the position of the above-mentioned second adjacent site 308 is the above-mentioned target position; when the above-mentioned sum is greater than the above-mentioned distance threshold, the position of the above-mentioned first adjacent site 306 and the position of the above-mentioned second adjacent site 308 are determined to be the above-mentioned target position.

[0044] In some embodiments, the above step S203 can be specifically implemented by the following steps: step S2031, obtaining a mapping relationship, determining that the phase value that does not satisfy the above mapping relationship among the multiple phase values ​​is the above abnormal phase data, wherein the above mapping relationship is used to characterize the correspondence between the phase value and the time during the normal transmission of light in the above optical cable to be tested; step S2032, obtaining historical abnormal phase data and the vibration frequency corresponding to the above historical abnormal phase data, wherein the above historical abnormal phase data is the above abnormal phase data obtained before the current moment; step S2033, obtaining a target convolutional neural network, inputting the multiple abnormal phase data into the above target convolutional neural network in sequence, and obtaining the vibration frequencies corresponding to the multiple abnormal phase data, wherein the above target convolutional neural network is trained by machine learning using multiple groups of historical data, and each group of the multiple groups of historical data includes: the above historical abnormal phase data and the vibration frequency corresponding to the above historical abnormal phase data. This method can further quickly obtain the above abnormal phase parameters.

[0045] Specifically, the above abnormal phase parameters may also include the time corresponding to the abnormal phase data and the position corresponding to the abnormal phase data. Since the phase value corresponds to the time one by one, the time corresponding to the abnormal phase data can be directly determined according to the abnormal phase protection. The position corresponding to the abnormal phase data can be determined according to the coverage range of the distributed optical fiber sensor.

[0046] In the specific implementation process, the above step S2032 can be implemented by the following steps: step S20321, obtaining the abnormal phase data of the faulty optical cable to obtain the original abnormal phase data, wherein the above faulty optical cable is an optical cable that is not working properly; step S20322, normalizing the above original abnormal phase data to obtain the above historical abnormal phase data. This method can further improve the performance and stability of the above target convolutional neural network.

[0047] Specifically, the above normalization method can adopt linear normalization method, zero mean normalization or standardization method and nonlinear normalization method, wherein the linear normalization method scales the data to the interval [0,1], and the zero mean normalization method converts the data into a distribution with a mean of 0 and a standard deviation of 1. The nonlinear normalization method can adopt logarithmic transformation, square root transformation, exponential transformation, etc., to map the data to a new interval through a nonlinear function to improve the distribution characteristics of the data. For example, logarithmic transformation can compress the range of data and reduce volatility. When selecting a normalization method, it is necessary to comprehensively consider the characteristics of the data and the needs of subsequent algorithms. For example, if there are specific requirements for the range of the output results, normalization can be used; if the data is relatively stable and there are no extreme maximum and minimum values, normalization is also appropriate; and if the data has outliers and more noise, it may be more appropriate to use standardization because it can indirectly avoid the influence of outliers and extreme values ​​through centralization.

[0048] In order to further quickly obtain the above-mentioned target convolutional neural network model, the above-mentioned step S2033 of the present application can be implemented by the following steps: step S20331, an acquisition step, obtaining an initial convolutional neural network model; step S20332, a first input step, inputting the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data into the above-mentioned initial convolutional neural network model, and obtaining first output data, so as to respectively perform forward propagation processing on the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data; step S20333, a first calculation step, calculating the cross entropy loss function of the above-mentioned initial convolutional neural network model according to the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data and the above-mentioned first output data; step S20334, a second input step, inputting the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data into the above-mentioned initial convolutional neural network model, and obtaining second output data, so as to respectively perform forward propagation processing on the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data The frequency is back-propagated, wherein the initial convolutional neural network includes multiple layers; step S20335, a second calculation step, calculating the gradient of each of the above layers, wherein the gradient is used to characterize the degree of influence of the network parameters of each of the above layers on the cross entropy loss function; step S20336, an updating step, using a stochastic gradient descent algorithm to update the network parameters of the above layers to obtain updated network parameters; step S20337, sequentially repeating the first input step, the first calculation step, the second input step, the second calculation step and the updating step at least once, and in the repetition process, updating the network parameters of the above layer of the initial convolutional neural network in the first input step to the updated network parameters in the updating step obtained in the last repetition process, until the preset conditions are met, and determining that the initial convolutional neural network model when the preset conditions are met is the target convolutional neural network model, wherein the preset conditions include one of the following: the gradient reaches a minimum value, the cross entropy loss function reaches a minimum value and the repetition reaches a predetermined number of times.

[0049] In practical applications, the above iterative process for obtaining the target convolutional neural network model is as follows: First, the parameters of the model need to be initialized, and these parameters can be randomly initialized; the input data is forward propagated through the model to calculate the prediction result; the loss function is used to calculate the difference between the model prediction and the true label to obtain the loss value; the gradient of the loss value to each parameter is calculated through the back-propagation algorithm. This process involves calculating the derivatives of the loss function with respect to the model parameters, which indicate the direction in which the loss function grows fastest in the parameter space; the result of back-propagation is the gradient of each parameter, which represents the local rate of change of the loss function at the current parameter position; the calculated gradient and the pre-set learning rate are used to update the parameters of the model. Repeat the above steps until the performance of the model on the validation set no longer improves, or the preset number of iterations is reached.

[0050] The above step S20333 includes: according to the formula Calculate the above cross entropy loss function H, where N is the total number of vibration frequency categories corresponding to the above historical abnormal phase data, p(x c ) is the vibration frequency corresponding to the cth category, q(x c ) is the first output data corresponding to the cth category. This method can further calculate the accurate cross entropy loss function.

[0051] Specifically, the cross entropy loss function is a loss function applied in classification problems. It evaluates the performance of the model by comparing the difference between the probability distribution predicted by the model and the true label distribution. The smaller the value of the cross entropy loss function, the closer the model's prediction result is to the true label, and the better the model's performance. Types of cross entropy loss functions include binary cross entropy loss and multi-category cross entropy loss. The advantage of the cross entropy loss function is that it can converge quickly, and when the predicted probability differs greatly from the true label, the loss value will increase rapidly, forcing the model to adjust parameters faster during training. In practical applications, the cross entropy loss function is used in conjunction with the optimizer in the deep learning framework to update the model parameters by iterating the training data to reduce the difference between the predicted probability and the true label.

[0052] Step S20336 includes: updating the network parameter A of the above layer according to the formula A′=AB×M to obtain the above updated network parameter A′, where B is the learning rate and M is the above gradient. This method can further quickly implement the update of network parameters.

[0053] Specifically, the learning rate is a hyperparameter in the gradient descent algorithm, which determines the step size of the parameter update in each iteration. The choice of learning rate is crucial to the training of the model. If the learning rate is too large, it may cause the model to "jump" around the optimal solution or even diverge and fail to converge. If the learning rate is too small, the model will converge very slowly, resulting in inefficient training.

[0054] The present application embodiment also provides a kind of optical cable monitoring device, it should be noted that the optical cable monitoring device of the present application embodiment can be used to execute the optical cable monitoring method provided by the present application embodiment. The device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description has been made no further. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented with software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0055] The following is an introduction to the optical cable monitoring device provided in an embodiment of the present application.

[0056] Figure 5 Schematic diagram of an optical cable monitoring device according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0057] The first determination unit 10 is used to obtain the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determine the target position of the distributed optical fiber sensor according to the number and distance, wherein the optical cable to be tested includes a plurality of sites;

[0058] Specifically, an optical cable is a communication line that uses fiber optic technology to transmit data. Optical fibers are thin, long filaments made of ultra-pure quartz glass that can reflect light signals internally, thereby enabling data transmission. Optical cables are composed of many such optical fibers and are encapsulated in a protective outer sheath. The construction of an optical cable network involves multiple sites that are connected by optical fibers to form a complex communication network to support high-speed data transmission and network services. The above-mentioned sites can be optical fiber access sites, optical fiber switching sites, optical fiber relay sites, and optical fiber terminal sites, among which the optical fiber access site is the location where the user connects to the optical fiber network, which can be a home, business, or public facility; the optical fiber switching site is responsible for transmitting signals from one optical fiber to another to achieve data routing and exchange; the optical fiber relay site is used to amplify or regenerate signals to maintain signal quality; the optical fiber terminal site can be a data center, a large server cluster, or other critical network facilities.

[0059] The processing unit 20 is used to obtain the sensing data and process the sensing data to obtain a plurality of phase values, wherein the sensing data is the data obtained by the distributed optical fiber sensor arranged at the target position, and the phase value is the phase value corresponding to each moment of the light during the transmission process of the optical cable to be tested;

[0060] Specifically, the Distributed Fiber Optic Sensor (DFOS) uses optical fiber as a sensing medium and can realize continuous monitoring of environmental physical quantities along the optical fiber. This sensor can measure a variety of physical quantities such as temperature, strain, vibration, magnetic field, etc., and has the advantages of anti-electromagnetic interference and long-distance monitoring. The working principle of the distributed optical fiber sensor is mainly based on the backscattering effect in the optical fiber. By analyzing the scattered light signals at different positions in the optical fiber, the distributed monitoring of the environment along the optical fiber is realized. Among them, Rayleigh scattering, Brillouin scattering and Raman scattering are three commonly used scattering mechanisms, which correspond to different measurement principles and technical applications.

[0061] A second processing unit 30 is used to determine an abnormal phase parameter according to the plurality of phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the plurality of phase values;

[0062] Specifically, in the process of determining the abnormal phase parameter, multiple phase values ​​may be analyzed based on the optical phase fusion algorithm.

[0063] The third processing unit 40 is used to determine the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable.

[0064] Specifically, the abnormal types of the above-mentioned optical cables include optical fiber breakage, insufficient transmission power, connection failure, environmental factors, external force factors and human factors, among which optical fiber breakage is caused by physical squeezing or excessive bending by external force; insufficient transmission power means that the optical fiber laying distance is too long, which may cause signal loss, and damaged connectors may also cause signal loss. Connection failure means that the use of too many optical fiber joints and connectors may cause signal loss, and optical fiber distribution tray or fusion tray connection failure; environmental factors include dust, fingerprints, scratches, humidity and other factors that damage the connector, or the transmission power is too low, and the connector is wrong in the wiring room; external force factors include construction digging, vehicle disconnection, shooting and other situations; human factors include work obstacles, theft, deliberate destruction and other human factors may also cause optical cable line failure.

[0065] Through this embodiment, an optical cable monitoring device is provided, wherein the first determination unit obtains the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determines the target position of the distributed optical fiber sensor according to the number and the distance, and the optical cable to be tested includes multiple sites; the processing unit obtains the sensing data, and processes the sensing data to obtain multiple phase values, the sensing data is the data obtained by the distributed optical fiber sensor set at the target position, and the phase value is the phase value corresponding to each moment of the light in the transmission process of the optical cable to be tested; the second determination unit determines the abnormal phase parameter according to the multiple phase values, and the abnormal phase parameter at least includes the vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is the abnormal value among the multiple phase values; the third determination unit determines the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable. By setting a distributed optical fiber sensor at the target position along the optical cable, and connecting the existing optical cable through the distributed optical fiber sensor, the characteristics of the signal change in the optical fiber are analyzed and identified, the vibration frequency is obtained, and different types of abnormal events are judged according to the vibration frequency, so as to give an early warning, so that the optical cable can be accurately monitored, the optical cable monitoring efficiency can be improved, and the technical problem of low optical cable monitoring efficiency in the prior art is solved.

[0066] The multiple sites include intermediate sites and edge sites, and the edge sites are located on both sides of the intermediate sites. The first determination unit includes a first determination module, a second determination module, a third determination module, a fourth determination module, a fifth determination module and a sixth determination module, wherein the first determination module is used to determine whether the number is greater than two; the second determination module is used to obtain the first distance between the two sites when the number is two, and determine whether the first distance is less than or equal to a distance threshold, and when the first distance is less than or equal to the distance threshold, determine the position of any one of the two sites as the target position, wherein the distance threshold is the maximum detection range of the distributed optical fiber sensor; the third determination module is used to determine the positions of the two sites as the target position when the first distance is greater than the distance threshold; the fourth determination module is used to obtain the second distance between any one of the intermediate sites and the first adjacent site when the number is greater than two, and Determine whether the second distance is less than or equal to the distance threshold. If the second distance is greater than the distance threshold, determine the position of the intermediate station and the position of the first adjacent station as the target position, wherein the first adjacent station is adjacent to the intermediate station and has the smallest distance; the fifth determination module is used to obtain the third distance between the intermediate station and the second adjacent station when the second distance is less than or equal to the distance threshold, determine whether the sum of the second distance and the third distance is less than or equal to the distance threshold, and determine any one of the position of the intermediate station, the position of the first adjacent station and the position of the second adjacent station as the target position when the sum is less than or equal to the distance threshold, wherein the second adjacent station is adjacent to the intermediate station and the third distance is greater than the second distance; the sixth determination module is used to determine the position of the first adjacent station and the position of the second adjacent station as the target position when the sum is greater than the distance threshold. The device can further achieve the maximum utilization efficiency of the distributed optical fiber sensor.

[0067] Specifically, the distance threshold may be 50 to 70 km. Figure 3 and Figure 4 As shown, Figure 3 The distribution diagram of the two sites is shown in FIG. Figure 3As shown, when the number of sites 300 is two, the first distance 302 between the two sites 300 is obtained, and it is determined whether the first distance 302 is less than or equal to the distance threshold. When the first distance 302 is less than or equal to the distance threshold, the position of any one of the two sites 300 is determined to be the target position. When the first distance 302 is greater than the distance threshold, the positions of the two sites 300 are determined to be the target positions. Figure 4 A schematic diagram of the distribution of multiple sites is shown, such as Figure 4 As shown, when the number of the above-mentioned sites is greater than two, the second distance 310 between any one of the above-mentioned intermediate sites 304 and the first adjacent site 306 is obtained, and it is determined whether the above-mentioned second distance 310 is less than or equal to the above-mentioned distance threshold. When the above-mentioned second distance 310 is greater than the above-mentioned distance threshold, the position of the above-mentioned intermediate site 304 and the position of the above-mentioned first adjacent site 306 are determined to be the above-mentioned target position; when the above-mentioned second distance 310 is less than or equal to the above-mentioned distance threshold, the third distance 312 between the above-mentioned intermediate site 304 and the second adjacent site 308 is obtained, and it is determined whether the sum of the above-mentioned second distance 310 and the above-mentioned third distance 312 is less than or equal to the above-mentioned distance threshold. When the above-mentioned sum is less than or equal to the above-mentioned distance threshold, it is determined that any one of the position of the above-mentioned intermediate site 304, the position of the above-mentioned first adjacent site 306 and the position of the above-mentioned second adjacent site 308 is the above-mentioned target position; when the above-mentioned sum is greater than the above-mentioned distance threshold, the position of the above-mentioned first adjacent site 306 and the position of the above-mentioned second adjacent site 308 are determined to be the above-mentioned target position.

[0068] In some embodiments, the second determination unit includes a seventh determination module, a first acquisition module, and a second acquisition module, wherein the seventh determination module is used to obtain a mapping relationship, and determine that the phase value that does not satisfy the mapping relationship among the multiple phase values ​​is the abnormal phase data, wherein the mapping relationship is used to characterize the correspondence between the phase value and the time during the normal transmission of light in the optical cable to be tested; the first acquisition module is used to obtain the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data, wherein the historical abnormal phase data is the abnormal phase data obtained before the current moment; the second acquisition module is used to obtain the target convolutional neural network, and the multiple abnormal phase data are sequentially input into the target convolutional neural network to obtain the vibration frequencies corresponding to the multiple abnormal phase data, wherein the target convolutional neural network is trained by machine learning using multiple groups of historical data, and each group of the multiple groups of historical data includes: the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data. The device can further quickly obtain the abnormal phase parameters.

[0069] Specifically, the above abnormal phase parameters may also include the time corresponding to the abnormal phase data and the position corresponding to the abnormal phase data. Since the phase value corresponds to the time one by one, the time corresponding to the abnormal phase data can be directly determined according to the abnormal phase protection. The position corresponding to the abnormal phase data can be determined according to the coverage range of the distributed optical fiber sensor.

[0070] In the specific implementation process, the first acquisition module includes a first acquisition submodule and a processing submodule, wherein the first acquisition submodule is used to acquire the abnormal phase data of the faulty optical cable to obtain the original abnormal phase data, wherein the faulty optical cable is an optical cable that is not working properly; the processing submodule is used to normalize the original abnormal phase data to obtain the historical abnormal phase data. The device can further improve the performance and stability of the target convolutional neural network.

[0071] Specifically, the above normalization method can adopt linear normalization method, zero mean normalization or standardization method and nonlinear normalization method, wherein the linear normalization method scales the data to the interval [0,1], and the zero mean normalization method converts the data into a distribution with a mean of 0 and a standard deviation of 1. The nonlinear normalization method can adopt logarithmic transformation, square root transformation, exponential transformation, etc., to map the data to a new interval through a nonlinear function to improve the distribution characteristics of the data. For example, logarithmic transformation can compress the range of data and reduce volatility. When selecting a normalization method, it is necessary to comprehensively consider the characteristics of the data and the needs of subsequent algorithms. For example, if there are specific requirements for the range of the output results, normalization can be used; if the data is relatively stable and there are no extreme maximum and minimum values, normalization is also appropriate; and if the data has outliers and more noise, it may be more appropriate to use standardization because it can indirectly avoid the influence of outliers and extreme values ​​through centralization.

[0072] In order to further quickly obtain the above-mentioned target convolutional neural network model, the above-mentioned second acquisition module of the present application includes a second acquisition submodule, a first input submodule, a first calculation submodule, a second input submodule, a second calculation submodule, an update submodule and a repetition submodule, wherein the second acquisition submodule is used for the acquisition step to obtain the initial convolutional neural network model; the first input submodule is used for the first input step to input the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data into the above-mentioned initial convolutional neural network model to obtain the first output data, so as to respectively perform forward propagation processing on the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data; the first calculation submodule is used for the first calculation step to calculate the cross entropy loss function of the above-mentioned initial convolutional neural network model according to the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data and the above-mentioned first output data; the second input submodule is used for the second input step to input the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data into the above-mentioned initial convolutional neural network model to obtain the second output data, so as to respectively perform forward propagation processing on the above-mentioned historical abnormal phase data and the vibration frequency corresponding to the above-mentioned historical abnormal phase data The historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data are back-propagated, wherein the initial convolutional neural network includes multiple layers; the second calculation submodule is used for the second calculation step to calculate the gradient of each of the above layers, wherein the gradient is used to characterize the influence of the network parameters of each of the above layers on the cross entropy loss function; the updating submodule is used for the updating step, and the network parameters of the above layers are updated by using the stochastic gradient descent algorithm to obtain updated network parameters; the repetition submodule is used to sequentially repeat the first input step, the first calculation step, the second input step, the second calculation step and the updating step at least once, and in the repetition process, the network parameters of the above layer of the initial convolutional neural network in the first input step are updated to the updated network parameters in the updating step obtained in the last repetition process, until the preset conditions are met, and it is determined that the initial convolutional neural network model when the preset conditions are met is the target convolutional neural network model, wherein the preset conditions include one of the following: the gradient reaches a minimum value, the cross entropy loss function reaches a minimum value, and the repetition reaches a predetermined number of times.

[0073] In practical applications, the above iterative process for obtaining the target convolutional neural network model is as follows: First, the parameters of the model need to be initialized, and these parameters can be randomly initialized; the input data is forward propagated through the model to calculate the prediction result; the loss function is used to calculate the difference between the model prediction and the true label to obtain the loss value; the gradient of the loss value to each parameter is calculated through the back-propagation algorithm. This process involves calculating the derivatives of the loss function with respect to the model parameters, which indicate the direction in which the loss function grows fastest in the parameter space; the result of back-propagation is the gradient of each parameter, which represents the local rate of change of the loss function at the current parameter position; the calculated gradient and the pre-set learning rate are used to update the parameters of the model. Repeat the above steps until the performance of the model on the validation set no longer improves, or the preset number of iterations is reached.

[0074] The first calculation submodule is also used to calculate the Calculate the above cross entropy loss function H, where N is the total number of vibration frequency categories corresponding to the above historical abnormal phase data, p(x c ) is the vibration frequency corresponding to the cth category, q(x c ) is the first output data corresponding to the c-th category. The device can further calculate and obtain an accurate cross entropy loss function.

[0075] Specifically, the cross entropy loss function is a loss function applied in classification problems. It evaluates the performance of the model by comparing the difference between the probability distribution predicted by the model and the true label distribution. The smaller the value of the cross entropy loss function, the closer the model's prediction result is to the true label, and the better the model's performance. Types of cross entropy loss functions include binary cross entropy loss and multi-category cross entropy loss. The advantage of the cross entropy loss function is that it can converge quickly, and when the predicted probability differs greatly from the true label, the loss value will increase rapidly, forcing the model to adjust parameters faster during training. In practical applications, the cross entropy loss function is used in conjunction with the optimizer in the deep learning framework to update the model parameters by iterating the training data to reduce the difference between the predicted probability and the true label.

[0076] The updating submodule is also used to update the network parameter A of the layer according to the formula A'=AB×M to obtain the updated network parameter A', where B is the learning rate and M is the gradient. The device can further quickly update the network parameters.

[0077] Specifically, the learning rate is a hyperparameter in the gradient descent algorithm, which determines the step size of the parameter update in each iteration. The choice of learning rate is crucial to the training of the model. If the learning rate is too large, it may cause the model to "jump" around the optimal solution or even diverge and fail to converge. If the learning rate is too small, the model will converge very slowly, resulting in inefficient training.

[0078] The optical cable monitoring device includes a processor and a memory. The first determination unit, the processing unit, the second determination unit, and the third determination unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0079] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set to monitor the optical cable by adjusting kernel parameters.

[0080] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0081] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the optical cable monitoring method.

[0082] Specifically, the optical cable monitoring method includes:

[0083] Step S201, obtaining the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determining the target position of the distributed optical fiber sensor according to the number and distance, wherein the optical cable to be tested includes a plurality of sites;

[0084] Specifically, an optical cable is a communication line that uses fiber optic technology to transmit data. Optical fibers are thin, long filaments made of ultra-pure quartz glass that can reflect light signals internally, thereby enabling data transmission. Optical cables are composed of many such optical fibers and are encapsulated in a protective outer sheath. The construction of an optical cable network involves multiple sites that are connected by optical fibers to form a complex communication network to support high-speed data transmission and network services. The above-mentioned sites can be optical fiber access sites, optical fiber switching sites, optical fiber relay sites, and optical fiber terminal sites, among which the optical fiber access site is the location where the user connects to the optical fiber network, which can be a home, business, or public facility; the optical fiber switching site is responsible for transmitting signals from one optical fiber to another to achieve data routing and exchange; the optical fiber relay site is used to amplify or regenerate signals to maintain signal quality; the optical fiber terminal site can be a data center, a large server cluster, or other critical network facilities.

[0085] Step S202, acquiring sensing data, and processing the sensing data to obtain a plurality of phase values, wherein the sensing data is data acquired by a distributed optical fiber sensor disposed at the target position, and the phase values ​​are phase values ​​corresponding to each moment of the light during the transmission of the optical cable to be tested;

[0086] Specifically, the Distributed Fiber Optic Sensor (DFOS) uses optical fiber as a sensing medium and can realize continuous monitoring of environmental physical quantities along the optical fiber. This sensor can measure a variety of physical quantities such as temperature, strain, vibration, magnetic field, etc., and has the advantages of anti-electromagnetic interference and long-distance monitoring. The working principle of the distributed optical fiber sensor is mainly based on the backscattering effect in the optical fiber. By analyzing the scattered light signals at different positions in the optical fiber, the distributed monitoring of the environment along the optical fiber is realized. Among them, Rayleigh scattering, Brillouin scattering and Raman scattering are three commonly used scattering mechanisms, which correspond to different measurement principles and technical applications.

[0087] Step S203, determining an abnormal phase parameter according to the plurality of phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the plurality of phase values;

[0088] Specifically, in the process of determining the abnormal phase parameter, multiple phase values ​​may be analyzed based on the optical phase fusion algorithm.

[0089] Step S204: determining the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable.

[0090] Specifically, the abnormal types of the above-mentioned optical cables include optical fiber breakage, insufficient transmission power, connection failure, environmental factors, external force factors and human factors, among which optical fiber breakage is caused by physical squeezing or excessive bending by external force; insufficient transmission power means that the optical fiber laying distance is too long, which may cause signal loss, and damaged connectors may also cause signal loss. Connection failure means that the use of too many optical fiber joints and connectors may cause signal loss, and optical fiber distribution tray or fusion tray connection failure; environmental factors include dust, fingerprints, scratches, humidity and other factors that damage the connector, or the transmission power is too low, and the connector is wrong in the wiring room; external force factors include construction digging, vehicle disconnection, shooting and other situations; human factors include work obstacles, theft, deliberate destruction and other human factors may also cause optical cable line failure.

[0091] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the optical cable monitoring method is executed when the program is run.

[0092] Specifically, the optical cable monitoring method includes:

[0093] Step S201, obtaining the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determining the target position of the distributed optical fiber sensor according to the number and distance, wherein the optical cable to be tested includes a plurality of sites;

[0094] Step S202, acquiring sensing data, and processing the sensing data to obtain a plurality of phase values, wherein the sensing data is data acquired by a distributed optical fiber sensor disposed at the target position, and the phase values ​​are phase values ​​corresponding to each moment of the light during the transmission of the optical cable to be tested;

[0095] Step S203, determining an abnormal phase parameter according to the plurality of phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the plurality of phase values;

[0096] Step S204: determining the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable.

[0097] An embodiment of the present invention provides a device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0098] Step S201, obtaining the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determining the target position of the distributed optical fiber sensor according to the number and distance, wherein the optical cable to be tested includes a plurality of sites;

[0099] Step S202, acquiring sensing data, and processing the sensing data to obtain a plurality of phase values, wherein the sensing data is data acquired by a distributed optical fiber sensor disposed at the target position, and the phase values ​​are phase values ​​corresponding to each moment of the light during the transmission of the optical cable to be tested;

[0100] Step S203, determining an abnormal phase parameter according to the plurality of phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the plurality of phase values;

[0101] Step S204: determining the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable.

[0102] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0103] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0104] Step S201, obtaining the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determining the target position of the distributed optical fiber sensor according to the number and distance, wherein the optical cable to be tested includes a plurality of sites;

[0105] Step S202, acquiring sensing data, and processing the sensing data to obtain a plurality of phase values, wherein the sensing data is data acquired by a distributed optical fiber sensor disposed at the target position, and the phase values ​​are phase values ​​corresponding to each moment of the light during the transmission of the optical cable to be tested;

[0106] Step S203, determining an abnormal phase parameter according to the plurality of phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the plurality of phase values;

[0107] Step S204: determining the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable.

[0108] The present application also provides an optical cable protection monitoring system, including: an acquisition layer, a data layer, a model layer, a service layer, and an application layer; the acquisition layer is used to collect vibration data along the optical cable collected by distributed optical fiber sensors; the data layer is used to classify and store the collected data in various formats and establish a corresponding database, including map data to form a spatial database, real-time collection of vibration data to form a real-time database, and combining the vibration source identification results to form a vibration source type database; the model layer is used to establish a data model supporting the system based on the database data established by the data layer; the data model includes: a map model, a real-time data processing model, and a vibration source type model. The service layer is used for map services, alarm statistics, alarm reminders, alarm processing, and system model optimization; the application layer is used to build a corresponding application system based on the vibration data along the optical cable collected by the system and the vibration source model that has been established and continuously optimized.

[0109] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0111] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0116] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0118] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0119] 1) The optical cable monitoring method of the present application first obtains the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determines the target position of the distributed optical fiber sensor according to the number and distance, and the optical cable to be tested includes multiple sites; then obtains the sensing data, and processes the sensing data to obtain multiple phase values, the sensing data is the data obtained by the distributed optical fiber sensor set at the target position, and the phase value is the phase value corresponding to each moment of the light during the transmission process of the optical cable to be tested; then, according to the multiple phase values, the abnormal phase parameters are determined, and the abnormal phase parameters at least include the vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is the abnormal value in the multiple phase values; finally, according to the abnormal phase parameters, the abnormal type of the optical cable is determined for monitoring the optical cable. By setting a distributed optical fiber sensor at the target position along the optical cable, and connecting the existing optical cable through the distributed optical fiber sensor, the characteristics of the signal change in the optical fiber are analyzed and identified, the vibration frequency is obtained, and different types of abnormal events are judged according to the vibration frequency, so as to give early warning, therefore, accurate monitoring of the optical cable can be achieved, the efficiency of optical cable monitoring is improved, and the technical problem of low efficiency of optical cable monitoring in the prior art is solved.

[0120] 2) The optical cable monitoring device of the present application, the first determination unit obtains the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determines the target position of the distributed optical fiber sensor according to the number and distance, and the optical cable to be tested includes multiple sites; the processing unit obtains the sensing data, and processes the sensing data to obtain multiple phase values, the sensing data is the data obtained by the distributed optical fiber sensor set at the target position, and the phase value is the phase value corresponding to each moment of the light in the transmission process of the optical cable to be tested; the second determination unit determines the abnormal phase parameter according to the multiple phase values, and the abnormal phase parameter at least includes the vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is the abnormal value among the multiple phase values; the third determination unit determines the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable. By setting a distributed optical fiber sensor at the target position along the optical cable, and connecting the existing optical cable through the distributed optical fiber sensor, the characteristics of the signal change in the optical fiber are analyzed and identified, the vibration frequency is obtained, and different types of abnormal events are judged according to the vibration frequency, so as to give early warning, therefore, accurate monitoring of the optical cable can be achieved, the efficiency of optical cable monitoring can be improved, and the technical problem of low efficiency of optical cable monitoring in the prior art is solved.

[0121] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for monitoring an optical cable, characterized in that: include: Acquire the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determine the target position of the distributed optical fiber sensor according to the number and the distance, wherein the optical cable to be tested includes a plurality of sites; Acquire sensing data, and process the sensing data to obtain a plurality of phase values, wherein the sensing data is data acquired by a distributed optical fiber sensor disposed at the target position, and the phase value is a phase value corresponding to each moment during the transmission of light in the optical cable to be tested; Determine an abnormal phase parameter according to the multiple phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the multiple phase values; The abnormal type of the optical cable is determined according to the abnormal phase parameter, so as to monitor the optical cable.

2. The method according to claim 1, characterized in that The plurality of sites include an intermediate site and an edge site, the edge site is located on both sides of the intermediate site, and the target position of the distributed optical fiber sensor is determined according to the number and the distance, including: determining whether the number is greater than two; When the number is two, a first distance between the two sites is obtained, and whether the first distance is less than or equal to a distance threshold is determined, and when the first distance is less than or equal to the distance threshold, the position of any one of the two sites is determined to be the target position, wherein the distance threshold is the maximum detection range of the distributed optical fiber sensor; When the first distance is greater than the distance threshold, determining the positions of the two sites as the target positions; When the number is greater than two, obtain a second distance between any one of the intermediate sites and the first adjacent site, and determine whether the second distance is less than or equal to the distance threshold; when the second distance is greater than the distance threshold, determine the position of the intermediate site and the position of the first adjacent site as the target position, wherein the first adjacent site is adjacent to the intermediate site and has the smallest distance; When the second distance is less than or equal to the distance threshold, obtaining a third distance between the intermediate site and the second adjacent site, determining whether the sum of the second distance and the third distance is less than or equal to the distance threshold, and when the sum is less than or equal to the distance threshold, determining that any one of the position of the intermediate site, the position of the first adjacent site, and the position of the second adjacent site is the target position, wherein the second adjacent site is adjacent to the intermediate site, and the third distance is greater than the second distance; When the sum is greater than the distance threshold, the position of the first neighboring site and the position of the second neighboring site are determined as the target position.

3. The method according to claim 1, characterized in that Determining an abnormal phase parameter according to the plurality of phase values ​​includes: Acquire a mapping relationship, and determine that a phase value that does not satisfy the mapping relationship among the multiple phase values ​​is the abnormal phase data, wherein the mapping relationship is used to characterize the correspondence between the phase value and the time during the normal transmission of light in the optical cable to be tested; Acquire historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data, wherein the historical abnormal phase data is the abnormal phase data acquired before the current moment; Obtain a target convolutional neural network, input the multiple abnormal phase data into the target convolutional neural network in sequence, and obtain the vibration frequencies corresponding to the multiple abnormal phase data, wherein the target convolutional neural network is trained by machine learning using multiple groups of historical data, and each group of the multiple groups of historical data includes: the historical abnormal phase data and the vibration frequencies corresponding to the historical abnormal phase data.

4. The method according to claim 3, characterized in that Obtain historical abnormal phase data, including: Acquire abnormal phase data of a faulty optical cable to obtain original abnormal phase data, wherein the faulty optical cable is an optical cable that does not work normally; The original abnormal phase data is normalized to obtain the historical abnormal phase data.

5. The method according to claim 3, characterized in that: Get the target convolutional neural network, including: Acquisition step, obtaining the initial convolutional neural network model; A first input step, inputting the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data into the initial convolutional neural network model to obtain first output data, so as to perform forward propagation processing on the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data respectively; A first calculation step is to calculate a cross entropy loss function of the initial convolutional neural network model according to the historical abnormal phase data, the vibration frequency corresponding to the historical abnormal phase data, and the first output data; A second input step, inputting the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data into the initial convolutional neural network model to obtain second output data, so as to perform back propagation processing on the historical abnormal phase data and the vibration frequency corresponding to the historical abnormal phase data, respectively, wherein the initial convolutional neural network includes a plurality of layers; The second calculation step is to calculate the gradient of each layer, wherein the gradient is used to characterize the influence of the network parameters of each layer on the cross entropy loss function; An updating step, using a stochastic gradient descent algorithm to update the network parameters of the layer to obtain updated network parameters; Repeat the first input step, the first calculation step, the second input step, the second calculation step and the updating step in sequence at least once, and update the network parameters of the layer of the initial convolutional neural network in the first input step to the updated network parameters in the updating step obtained in the previous repetition process during the repetition process until a preset condition is met, and determine that the initial convolutional neural network model when the preset condition is met is the target convolutional neural network model, wherein the preset condition includes one of the following: the gradient reaches a minimum value, the cross entropy loss function reaches a minimum value, and the repetition reaches a predetermined number of times.

6. The method according to claim 5, characterized in that The first calculation step comprises: According to the formula Calculate the cross entropy loss function H, where N is the total number of vibration frequency categories corresponding to the historical abnormal phase data, p(x c ) is the vibration frequency corresponding to the cth category, q(x c ) is the first output data corresponding to the c-th category.

7. The method according to claim 5, characterized in that The updating step comprises: According to the formula A′=AB×M, the network parameter A of the layer is updated to obtain the updated network parameter A′, where B is the learning rate and M is the gradient.

8. An optical cable monitoring device, characterized in that: include: A first determining unit is used to obtain the number of sites on the optical cable to be tested and the distance between any two adjacent sites, and determine the target position of the distributed optical fiber sensor according to the number and the distance, wherein the optical cable to be tested includes a plurality of sites; A processing unit, used to acquire sensing data and process the sensing data to obtain a plurality of phase values, wherein the sensing data is data acquired by a distributed optical fiber sensor arranged at the target position, and the phase value is a phase value corresponding to each moment during the transmission of light in the optical cable to be tested; A second determining unit is used to determine an abnormal phase parameter according to the multiple phase values, wherein the abnormal phase parameter at least includes a vibration frequency corresponding to the abnormal phase data, and the abnormal phase data is an abnormal value among the multiple phase values; The third determining unit is used to determine the abnormal type of the optical cable according to the abnormal phase parameter, so as to monitor the optical cable.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. An optical cable monitoring system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Citation Information

Cited By

  • Optical cable online monitoring method and system based on time sequence big data analysis

    CN119814135A

  • Optical cable fault detection method based on industrial data processing

    CN120320837A