An optical fiber aging state evaluation system and an evaluation method thereof

Abstract

The application discloses a kind of optical fiber aging state evaluation systems, including optical fiber temperature measurement module, for collecting optical fiber temperature data;Optical fiber dispersion measurement module, for collecting the dispersion coefficient of optical fiber;Optical fiber attenuation measurement module, for collecting the attenuation coefficient of optical fiber;Optical fiber polarization measurement module, for collecting the polarization state data of optical fiber;Data preprocessing module is respectively connected with optical fiber temperature measurement module, optical fiber dispersion measurement module, optical fiber attenuation measurement module and optical fiber polarization measurement module communication, for the optical fiber parameter data collected is preprocessed;State evaluation module, for according to the data of data preprocessing module after processing the aging state of optical fiber is evaluated.The present application can improve the deficiency of prior art, improve the accuracy of optical fiber aging state evaluation.

Description

Technical Field

[0001] This invention relates to the field of optical fiber condition detection technology, and in particular to an optical fiber aging condition assessment system and assessment method. Background Technology

[0002] With the development of fiber optic communication technology, data transmission via fiber optics is becoming increasingly common. During use, fiber optic cables gradually develop potential problems such as aging. If the aging condition of the fiber optic cable is not assessed in a timely manner, communication interruptions and other failures can significantly impact and damage the entire communication system. Existing methods for assessing fiber optic aging conditions typically rely on algorithms such as neural networks or decision trees to calculate fiber optic parameters. However, due to inherent limitations in these algorithms (e.g., the computational burden of neural network models and the susceptibility to overfitting in decision trees), the accuracy of assessing fiber optic aging conditions can be poor under certain operating conditions. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an optical fiber aging condition assessment system and method, which can overcome the shortcomings of the prior art and improve the accuracy of optical fiber aging condition assessment.

[0004] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows.

[0005] A fiber optic aging condition assessment system, comprising:

[0006] Fiber optic temperature measurement module, used to collect fiber optic temperature data;

[0007] Fiber dispersion measurement module, used to acquire the dispersion coefficient of optical fiber;

[0008] Fiber optic attenuation measurement module, used to collect the attenuation coefficient of fiber optic cable;

[0009] Fiber polarization measurement module, used to acquire polarization state data of optical fibers;

[0010] The data preprocessing module is connected to the fiber temperature measurement module, fiber dispersion measurement module, fiber attenuation measurement module and fiber polarization measurement module respectively, and is used to preprocess the collected fiber parameter data.

[0011] The condition assessment module is used to assess the aging status of optical fibers based on the data processed by the data preprocessing module.

[0012] Preferably, the fiber optic temperature measurement module, fiber optic dispersion measurement module, fiber optic attenuation measurement module, and fiber optic polarization measurement module communicate with the data preprocessing module using a frequency division multiplexing method.

[0013] Preferably, a data storage module is provided between the data preprocessing module and the status evaluation module.

[0014] An evaluation method for the above-mentioned optical fiber aging status assessment system includes the following steps:

[0015] A. The fiber temperature measurement module collects fiber temperature data, the fiber dispersion measurement module collects fiber dispersion coefficient, the fiber attenuation measurement module collects fiber attenuation coefficient, and the fiber polarization measurement module collects fiber polarization state data. Then, the fiber temperature measurement module, fiber dispersion measurement module, fiber attenuation measurement module, and fiber polarization measurement module send the collected fiber parameter data to the data preprocessing module.

[0016] B. The data preprocessing module preprocesses the fiber optic parameter data;

[0017] C. The status assessment module assesses the aging status of the optical fiber based on the data processed by the data preprocessing module.

[0018] As a preferred option, step B, the preprocessing of the fiber optic parameter data includes the following steps: B1, fitting each type of data separately, and deleting noisy data based on the fitting results;

[0019] B2. Perform difference processing on the fitted data;

[0020] B3. Normalize the data after difference processing.

[0021] Preferably, in step B1, fitting data for each type of data and removing noisy data based on the fitting results includes the following steps:

[0022] B11. Perform surface fitting according to the two dimensions of time axis and space axis;

[0023] B12. Delineate a circular range with the data point to be processed as the center and a preset radius. Compare the average distance between other data points within the circular range and the fitted surface with the distance between the data point to be processed and the fitted surface. If the distance difference exceeds the set threshold, delete the data point to be processed; otherwise, retain the data point to be processed.

[0024] Preferably, the difference processing of the fitted data in step B2 includes the following steps: B21, perform difference processing on the fitted data twice along the time axis and the spatial axis respectively;

[0025] B22. Take a weighted average of the results of the two difference processing steps. The weighting coefficient is inversely proportional to the difference between the maximum and minimum values ​​of the difference processing results.

[0026] Preferably, step C, which assesses the aging condition of the optical fiber, includes the following steps:

[0027] C1. Establish a random forest evaluation model and use a neural network module to replace the decision trees in the random forest one-to-one.

[0028] C2. Calculate the constraints of the neural network modules according to the requirements of the random forest evaluation model;

[0029] C3. Train the neural network modules under constraints;

[0030] C4. Add a data integration module to the random forest evaluation model, and then train the random forest evaluation model.

[0031] C5. Input the data into the trained random forest evaluation model, and the random forest evaluation model outputs the fiber optic aging status evaluation results.

[0032] Preferably, in step C1, the neural network modules are divided into a use group and a spare group. The neural network modules in the use group are used to replace the decision tree, and the neural network modules in the use group and the spare group are interchanged according to the needs of the random forest evaluation model.

[0033] Preferably, in step C4, the data integration module is a set of functions. The data integration module is set between the output of the neural network module and the output of the random forest evaluation model. The data integration module is used to correct the output of the neural network module to meet the output requirements of the random forest evaluation model. When training the random forest evaluation model, the functions in the data integration module are iteratively updated.

[0034] The beneficial effects of adopting the above technical solution are as follows: This invention abandons the existing method of directly using neural networks and other algorithms for state evaluation. It innovatively integrates neural network algorithms into a random forest model, replacing decision trees and avoiding overfitting. Furthermore, a data preprocessing process is specifically designed for the characteristics of neural network algorithms, effectively reducing the amount of data computation required for the neural network model. This invention effectively overcomes the shortcomings of existing algorithms and provides highly accurate assessment of fiber optic aging conditions. Attached Figure Description

[0035] Figure 1 This is a structural diagram of a specific embodiment of the present invention.

[0036] In the diagram: 1. Fiber optic temperature measurement module; 2. Fiber optic dispersion measurement module; 3. Fiber optic attenuation measurement module; 4. Fiber optic polarization measurement module; 5. Data preprocessing module; 6. Condition assessment module; 7. Data temporary storage module. Detailed Implementation

[0037] In the following description of the embodiments, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0038] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0039] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0040] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0041] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0042] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0043] A fiber optic aging condition assessment system, comprising:

[0044] Fiber optic temperature measurement module 1 is used to collect fiber optic temperature data;

[0045] Fiber dispersion measurement module 2 is used to collect the dispersion coefficient of the fiber;

[0046] Fiber optic attenuation measurement module 3 is used to collect the attenuation coefficient of the fiber optic cable;

[0047] Fiber polarization measurement module 4 is used to acquire polarization state data of the fiber;

[0048] The data preprocessing module 5 is communicatively connected to the fiber temperature measurement module 1, the fiber dispersion measurement module 2, the fiber attenuation measurement module 3, and the fiber polarization measurement module 4, respectively, and is used to preprocess the collected fiber parameter data.

[0049] The status assessment module 6 is used to assess the aging status of optical fibers based on the data processed by the data preprocessing module 5.

[0050] The fiber optic temperature measurement module 1, fiber optic dispersion measurement module 2, fiber optic attenuation measurement module 3, and fiber optic polarization measurement module 4 communicate with the data preprocessing module 5 using a frequency division multiplexing method.

[0051] A data storage module 7 is provided between the data preprocessing module 5 and the status evaluation module 6.

[0052] An evaluation method for the above-mentioned optical fiber aging status assessment system includes the following steps:

[0053] A. Fiber temperature measurement module 1 collects fiber temperature data, fiber dispersion measurement module 2 collects fiber dispersion coefficient, fiber attenuation measurement module 3 collects fiber attenuation coefficient, and fiber polarization measurement module 4 collects fiber polarization state data. Then, fiber temperature measurement module 1, fiber dispersion measurement module 2, fiber attenuation measurement module 3, and fiber polarization measurement module 4 send the collected fiber parameter data to data preprocessing module 5.

[0054] B. Data preprocessing module 5 preprocesses the fiber optic parameter data;

[0055] C. The status assessment module 6 assesses the aging status of the optical fiber based on the data processed by the data preprocessing module 5.

[0056] Step B involves preprocessing the fiber optic parameter data, including the following steps:

[0057] B1. Fit the data for each category separately, and remove noisy data based on the fitting results;

[0058] B2. Perform difference processing on the fitted data;

[0059] B3. Normalize the data after difference processing.

[0060] In step B1, fitting data to each category and removing noisy data based on the fitting results includes the following steps:

[0061] B11. Perform surface fitting according to the two dimensions of time axis and space axis;

[0062] B12. Delineate a circular range with the data point to be processed as the center and a preset radius. Compare the average distance between other data points within the circular range and the fitted surface with the distance between the data point to be processed and the fitted surface. If the distance difference exceeds the set threshold, delete the data point to be processed; otherwise, retain the data point to be processed.

[0063] Step B2, which involves differencing the fitted data, includes the following steps:

[0064] B21. Perform two differencing operations on the fitted data along the time axis and the spatial axis, respectively.

[0065] B22. Take a weighted average of the results of the two difference processing steps. The weighting coefficient is inversely proportional to the difference between the maximum and minimum values ​​of the difference processing results.

[0066] Step C, assessing the aging condition of the optical fiber, includes the following steps:

[0067] C1. Establish a random forest evaluation model and use a neural network module to replace the decision trees in the random forest one-to-one.

[0068] C2. Calculate the constraints of the neural network modules according to the requirements of the random forest evaluation model;

[0069] C3. Train the neural network modules under constraints;

[0070] C4. Add a data integration module to the random forest evaluation model, and then train the random forest evaluation model.

[0071] C5. Input the data into the trained random forest evaluation model, and the random forest evaluation model outputs the fiber optic aging status evaluation results.

[0072] In step C1, the neural network modules are divided into a use group and a standby group. The neural network modules in the use group are used to replace the decision tree. The neural network modules in the use group and the standby group are interchanged according to the needs of the random forest evaluation model.

[0073] In step C4, the data integration module is a set of functions. The data integration module is set between the output of the neural network module and the output of the random forest evaluation model. The data integration module is used to correct the output of the neural network module to meet the output requirements of the random forest evaluation model. When training the random forest evaluation model, the functions in the data integration module are iteratively updated.

[0074] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this invention, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0075] In this embodiment, the hardware implementation of the technology can directly utilize existing smart devices, including but not limited to industrial control computers, PCs, smartphones, handheld devices, and floor-standing devices. The input device is preferably an on-screen keyboard, the data storage and computing modules utilize existing memory, calculators, and controllers, the internal communication module utilizes existing communication ports and protocols, and the remote communication utilizes existing GPRS networks, the World Wide Web, etc.

[0076] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0077] In the various embodiments of this invention, the functional units can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units can be implemented in hardware or as software functional units. If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in computer-readable media may be appropriately added to or subtracted from the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, computer-readable media may not include electrical carrier signals and telecommunication signals, in accordance with legislation and patent practice.

[0078] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. An evaluation method for an optical fiber aging condition assessment system, the optical fiber aging condition assessment system comprising: Fiber optic temperature measurement module (1) is used to collect fiber optic temperature data; Fiber dispersion measurement module (2) is used to collect the dispersion coefficient of the fiber; The fiber optic attenuation measurement module (3) is used to collect the attenuation coefficient of the fiber optic cable; Fiber polarization measurement module (4) is used to collect polarization state data of fiber; The data preprocessing module (5) is connected to the fiber temperature measurement module (1), fiber dispersion measurement module (2), fiber attenuation measurement module (3) and fiber polarization measurement module (4) respectively, and is used to preprocess the collected fiber parameter data. The status assessment module (6) is used to assess the aging status of optical fibers based on the data processed by the data preprocessing module (5). Its characteristics include the following steps: A. The fiber temperature measurement module (1) collects fiber temperature data, the fiber dispersion measurement module (2) collects the fiber dispersion coefficient, the fiber attenuation measurement module (3) collects the fiber attenuation coefficient, and the fiber polarization measurement module (4) collects fiber polarization state data. Then, the fiber temperature measurement module (1), the fiber dispersion measurement module (2), the fiber attenuation measurement module (3), and the fiber polarization measurement module (4) send the collected fiber parameter data to the data preprocessing module (5). B. Data preprocessing module (5) preprocesses the fiber optic parameter data; C. The status assessment module (6) assesses the aging status of the optical fiber based on the data processed by the data preprocessing module (5); the assessment of the aging status of the optical fiber includes the following steps. C1. Establish a random forest evaluation model and use a neural network module to replace the decision trees in the random forest one-to-one. C2. Calculate the constraints of the neural network modules according to the requirements of the random forest evaluation model; C3. Train the neural network modules under constraints; C4. Add a data integration module to the random forest evaluation model, and then train the random forest evaluation model. C5. Input the data into the trained random forest evaluation model, and the random forest evaluation model outputs the fiber optic aging status evaluation results.

2. The evaluation method of the optical fiber aging status evaluation system according to claim 1, characterized in that: The fiber temperature measurement module (1), fiber dispersion measurement module (2), fiber attenuation measurement module (3), and fiber polarization measurement module (4) communicate with the data preprocessing module (5) using a frequency division multiplexing method.

3. The evaluation method of the optical fiber aging status evaluation system according to claim 1, characterized in that: A data storage module (7) is provided between the data preprocessing module (5) and the status evaluation module (6).

4. The evaluation method of the optical fiber aging status evaluation system according to claim 1, characterized in that: Step B involves preprocessing the fiber optic parameter data, including the following steps: B1. Fit the data for each category separately, and remove noisy data based on the fitting results; B2. Perform difference processing on the fitted data; B3. Normalize the data after difference processing.

5. The evaluation method of the optical fiber aging status evaluation system according to claim 4, characterized in that: In step B1, fitting data to each category and removing noisy data based on the fitting results includes the following steps: B11. Perform surface fitting according to the two dimensions of time axis and space axis; B12. Delineate a circular range with the data point to be processed as the center and a preset radius. Compare the average distance between other data points within the circular range and the fitted surface with the distance between the data point to be processed and the fitted surface. If the distance difference exceeds the set threshold, delete the data point to be processed; otherwise, retain the data point to be processed.

6. The evaluation method of the optical fiber aging status evaluation system according to claim 5, characterized in that: Step B2, which involves differencing the fitted data, includes the following steps: B21. Perform two differencing operations on the fitted data along the time axis and the spatial axis, respectively. B22. Take a weighted average of the results of the two difference processing steps. The weighting coefficient is inversely proportional to the difference between the maximum and minimum values ​​of the difference processing results.

7. The evaluation method of the optical fiber aging status evaluation system according to claim 1, characterized in that: In step C1, the neural network modules are divided into a use group and a standby group. The neural network modules in the use group are used to replace the decision tree. The neural network modules in the use group and the standby group are interchanged according to the needs of the random forest evaluation model.

8. The evaluation method of the optical fiber aging status evaluation system according to claim 7, characterized in that: In step C4, the data integration module is a set of functions. The data integration module is set between the output of the neural network module and the output of the random forest evaluation model. The data integration module is used to correct the output of the neural network module to meet the output requirements of the random forest evaluation model. When training the random forest evaluation model, the functions in the data integration module are iteratively updated.

Images