Optical fiber performance evaluation method and system based on environmental conditions and storage medium

Abstract

The invention discloses an optical fiber performance evaluation method and system based on environmental conditions and a storage medium. The method comprises the following steps: acquiring environmental factors; inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; when the optical fiber performance score is lower than a preset score threshold value, generating an optical fiber performance evaluation report which indicates that the optical fiber cannot be used in an environment corresponding to the environmental factor; the training process of the optical fiber performance evaluation model comprises the following steps: acquiring historical environmental factors and historical optical fiber performance, and carrying out data preprocessing and principal component analysis dimension reduction operation to obtain dimension reduction data; and on the basis of taking the dimension reduction data and preset standard optical fiber data as input data, constructing an initial optical fiber performance evaluation model based on a particle swarm algorithm, and training the initial optical fiber performance evaluation model according to a membership matrix and a possibility division matrix to obtain an optical fiber performance evaluation model. The method can improve the accuracy of optical fiber performance evaluation.

Description

Technical Field

[0001] The present invention relates to the field of optical fiber testing technology, and in particular to an optical fiber performance evaluation method, system and storage medium based on environmental conditions. Background Art

[0002] At present, optical fiber is a widely used transmission medium in communication systems, and its performance directly affects the quality and reliability of communication. For example, in the exploration, drilling and production of oil and gas, it is necessary to monitor the underground environment. Optical fiber can be used to transmit parameters such as temperature, pressure, strain, etc. Due to its small size, light weight, good corrosion resistance and ability to work under extreme conditions, it is very suitable for such harsh working environments. However, with the rapid development of communication technology and the continuous upgrading of networks, the requirements for optical fiber performance are becoming higher and higher, and different optical fibers have different adaptability to high temperature and high pressure environments. Therefore, how to accurately evaluate optical fiber performance has become an important research topic in the field of communication. The main goal of optical fiber performance evaluation is to determine the performance indicators of optical fiber in various aspects, such as transmission loss, dispersion, nonlinear effects, etc., and to comprehensively evaluate the performance of optical fiber based on these indicators. Through optical fiber performance evaluation, the type of optical fiber suitable for specific application scenarios can be selected to ensure the performance and reliability of the communication system. At the same time, it is also possible to diagnose and repair defects and problems of optical fibers to improve the maintenance efficiency of optical fiber networks.

[0003] In the prior art, a neural network model is constructed and modified in combination with actual measurement data to achieve prediction and evaluation of optical fiber performance. However, this method is only applicable to optical fibers under specific environmental conditions and cannot meet general needs. Furthermore, the influence of temperature and humidity on optical fiber performance is comprehensively considered, and a multivariate linear regression model is constructed to predict optical fiber loss and dispersion coefficient. However, this method ignores the generalization ability of the model, resulting in large errors in the prediction results. In short, when the prior art is combined with machine learning, since optical fiber performance is affected by a combination of multiple factors, it is difficult for a single algorithm to accurately evaluate and predict optical fiber performance, resulting in low efficiency in optical fiber performance evaluation and large deviations between the evaluation results and the actual results. Summary of the invention

[0004] The present invention provides an optical fiber performance evaluation method, system and storage medium based on environmental conditions, so as to improve the evaluation efficiency of optical fiber performance and the accuracy of evaluation results.

[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a method for evaluating optical fiber performance based on environmental conditions, comprising: Acquiring environmental factors, the environmental factors including: environmental temperature data, environmental humidity data and environmental pressure data; Inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; When the optical fiber performance score is lower than a preset score threshold, a optical fiber performance evaluation report is generated, indicating that the optical fiber cannot be used in the environment corresponding to the environmental factor; The training process of the optical fiber performance evaluation model includes: Obtain historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data; Performing data preprocessing and principal component analysis dimensionality reduction operations on the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain reduced-dimensionality data; Based on the dimension reduction data and preset standard optical fiber data as input data, an initial optical fiber performance evaluation model is constructed based on a particle swarm algorithm, and the initial optical fiber performance evaluation model is trained according to a membership matrix and a possibility partition matrix to obtain an optical fiber performance evaluation model.

[0006] In an optional implementation, the historical ambient temperature data, the historical ambient humidity data, the historical ambient pressure data, the historical optical fiber dispersion data, and the historical optical fiber transmission performance data are subjected to data preprocessing and principal component analysis dimensionality reduction operations to obtain dimensionality reduction data, including: Standardizing the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain standardized data; The correlation covariance matrix is ​​calculated based on the standardized data using the following formula: ; in, A normalized matrix representing normalized data; represents the transpose of a normalized matrix; represents the degrees of freedom of the sample covariance; represents the correlation covariance matrix; Performing eigenvalue decomposition according to the correlation covariance matrix to obtain eigenvalues ​​and eigenvectors; According to the eigenvalues ​​and the eigenvectors, a preset number of the eigenvectors are selected in descending order of the eigenvalues ​​to obtain an eigenvector matrix; According to the standardized data and the eigenvector matrix, the standardized data is projected onto the eigenvector matrix to obtain dimension-reduced data.

[0007] In an optional implementation, the dimension reduction data and preset standard optical fiber data are used as input data, an initial optical fiber performance evaluation model is constructed based on a particle swarm algorithm, and the initial optical fiber performance evaluation model is trained according to a membership matrix and a possibility partition matrix to obtain an optical fiber performance evaluation model, including: Initializing the cluster center and the number of clusters of the optical fiber performance evaluation model; Initializing a particle swarm according to the cluster center and the cluster number, and obtaining an optimal initial cluster center and an optimal initial cluster number through a full gradient inertial particle swarm optimization algorithm; Initializing the parameters, the membership matrix and the possibility partition matrix of the initial optical fiber performance evaluation model according to the optimal initial cluster center and the optimal initial cluster number; According to the current membership matrix and the possibility partition matrix, cluster centers are updated and trained; When the number of training times is greater than or equal to the preset maximum number of training times, the training is determined to be completed and the optical fiber performance evaluation model is obtained.

[0008] In an optional implementation, the initializing the particle swarm according to the cluster center and the cluster number, and obtaining the optimal initial cluster center and the optimal initial cluster number by a full gradient inertial particle swarm optimization algorithm, comprises: Initializing a particle swarm according to the cluster center and the number of clusters to obtain an initial particle swarm; Calculating the particle inertia weight according to the initial particle group to obtain the inertia weight value of each particle; Calculating the fitness of particles according to the initial particle group to obtain the fitness of each particle; According to the fitness and the inertia weight value of each particle, the particle velocity and the particle position are iterated based on full gradient descent, and when the number of iterations is greater than or equal to the preset maximum number of iterations, the iteration is determined to be completed, and the optimal initial cluster center and the optimal initial cluster number are obtained; The particle position represents the cluster center and the number of clusters of the initial optical fiber performance evaluation model, and the particle speed represents the update step length of the cluster center and the number of clusters.

[0009] In an optional implementation, the updating and training of cluster centers according to the current membership matrix and the possibility partition matrix includes: Obtaining the membership matrix and the possibility partition matrix; Perform distance calculation based on the membership matrix and the possibility partition matrix to obtain the distance from each data point to all cluster centers; For each cluster center, a contribution value is calculated according to the membership matrix to obtain a position contribution value of each data point to each cluster center; According to the position contribution value, weighted sum of the position contribution values ​​of all data points is performed to obtain a second cluster center; Recalculate the membership of all data points according to the second cluster center to obtain a second membership matrix and a second possibility partition matrix; The cluster center, the membership matrix and the possibility partition matrix are replaced by the second cluster center, the second membership matrix and the second possibility partition matrix respectively.

[0010] In an optional implementation, recalculating the membership of all data points according to the second cluster center to obtain a second membership matrix and a second possibility partition matrix includes: The membership is updated by calculating the following formula: ; in, For the The data points belong to The class membership, For the The data points belong to The class membership, For the The data points belong to The likelihood of the class split, For the The data points belong to The likelihood of the class split, is the number of clusters; The possibility partition matrix is ​​updated by calculating through the following formula: ; in, For the The data points belong to The likelihood of the class split, For data points and The Euclidean distance between cluster centers, For the data points, For the Cluster centers, For the The scale parameter of the class, is the likelihood weighted index.

[0011] In an optional implementation, the optical fiber performance score is calculated by the following formula: in, Score the fiber performance. is the fiber dispersion performance weight, is the fiber transmission performance weight, To standardize the dispersion performance of optical fibers, To standardize fiber optic transmission performance.

[0012] In a second aspect, the present invention provides an optical fiber performance evaluation system based on environmental conditions, comprising: A data acquisition module is used to acquire environmental factors, wherein the environmental factors include: environmental temperature data, environmental humidity data and environmental pressure data; A score prediction module, used for inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; A historical data acquisition module is used to acquire historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data; A data dimension reduction module, for performing data preprocessing and principal component analysis dimension reduction operations on the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain dimension reduction data; A model training module, used to construct an initial optical fiber performance evaluation model based on a particle swarm algorithm based on the dimension reduction data and preset standard optical fiber data as input data, and train the initial optical fiber performance evaluation model according to a membership matrix and a possibility partition matrix to obtain an optical fiber performance evaluation model; The result output module is used to generate a fiber performance evaluation report when the fiber performance score is lower than a preset score threshold, indicating that the fiber cannot be used in the environment corresponding to the environmental factor.

[0013] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the optical fiber performance evaluation method based on environmental conditions as described above is implemented.

[0014] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for evaluating optical fiber performance based on environmental conditions.

[0015] Compared with the prior art, the present invention has the following beneficial effects: the present invention discloses a method, system and storage medium for evaluating optical fiber performance based on environmental conditions, the method comprising: obtaining environmental factors, the environmental factors comprising: environmental temperature data, environmental humidity data and environmental pressure data; inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; when the optical fiber performance score is lower than a preset score threshold, generating an optical fiber performance evaluation report, indicating that the optical fiber cannot be used in the environment corresponding to the environmental factors; wherein the training process of the optical fiber performance evaluation model comprises: obtaining historical environmental temperature data, historical environmental humidity data, historical environmental pressure data, historical optical fiber dispersion data and historical optical fiber transmission performance data; performing data preprocessing and principal component analysis dimensionality reduction operations on the historical environmental temperature data, historical environmental humidity data, historical environmental pressure data, historical optical fiber dispersion data and historical optical fiber transmission performance data to obtain reduced dimensionality data; based on the reduced dimensionality data and preset standard optical fiber data as input data, constructing an initial optical fiber performance evaluation model based on a particle swarm algorithm, training the initial optical fiber performance evaluation model according to a membership matrix and a possibility partitioning matrix to obtain an optical fiber performance evaluation model. By utilizing historical environmental factors and historical fiber performance, a fiber performance evaluation model is obtained through particle swarm algorithm training, which has good generalization ability. It takes into account the influence of multiple environmental factors on fiber transmission performance and fiber dispersion performance, and improves the efficiency and accuracy of fiber performance evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flow chart of a method for evaluating optical fiber performance based on environmental conditions provided by a first embodiment of the present invention; Figure 2 is a schematic diagram of optical fiber performance model training provided by the first embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an optical fiber performance evaluation system based on environmental conditions provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] At present, optical fiber is a widely used transmission medium in communication systems, and its performance directly affects the quality and reliability of communication. For example, in the exploration, drilling and production of oil and gas, it is necessary to monitor the underground environment. Optical fiber can be used to transmit parameters such as temperature, pressure, strain, etc. Due to its small size, light weight, good corrosion resistance and ability to work under extreme conditions, it is very suitable for such harsh working environments. However, with the rapid development of communication technology and the continuous upgrading of networks, the requirements for optical fiber performance are becoming higher and higher, and different optical fibers have different adaptability to high temperature and high pressure environments. Therefore, how to accurately evaluate optical fiber performance has become an important research topic in the field of communication. The main goal of optical fiber performance evaluation is to determine the performance indicators of optical fiber in various aspects, such as transmission loss, dispersion, nonlinear effects, etc., and to comprehensively evaluate the performance of optical fiber based on these indicators. Through optical fiber performance evaluation, the type of optical fiber suitable for specific application scenarios can be selected to ensure the performance and reliability of the communication system. At the same time, it is also possible to diagnose and repair defects and problems of optical fibers to improve the maintenance efficiency of optical fiber networks.

[0019] In the prior art, a neural network model is constructed and modified in combination with actual measurement data to achieve prediction and evaluation of optical fiber performance. However, this method is only applicable to optical fibers under specific environmental conditions and cannot meet general needs. Furthermore, the influence of temperature and humidity on optical fiber performance is comprehensively considered, and a multivariate linear regression model is constructed to predict optical fiber loss and dispersion coefficient. However, this method ignores the generalization ability of the model, resulting in large errors in the prediction results. In short, when the prior art is combined with machine learning, since optical fiber performance is affected by a combination of multiple factors, it is difficult for a single algorithm to accurately evaluate and predict optical fiber performance, resulting in low efficiency in optical fiber performance evaluation and large deviations between the evaluation results and the actual results.

[0020] To solve the above problems, refer to Figure 1 The first embodiment of the present invention provides a method for evaluating optical fiber performance based on environmental conditions, comprising the following steps: S1, obtaining environmental factors, wherein the environmental factors include: environmental temperature data, environmental humidity data and environmental pressure data; S2, inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; S3, when the optical fiber performance score is lower than a preset score threshold, generating an optical fiber performance evaluation report, indicating that the optical fiber cannot be used in the environment corresponding to the environmental factor.

[0021] In step S1, environmental factors are acquired, and the environmental factors include: environmental temperature data, environmental humidity data, and environmental pressure data.

[0022] It is worth noting that the refractive index of optical fiber materials changes with temperature, which will directly affect the propagation speed and loss of optical signals in the optical fiber. Rising temperature will cause the optical fiber to expand, thereby changing its geometry, which in turn affects the mode distribution, dispersion, and microbend loss. In addition, temperature changes will cause changes in mechanical stress at connectors and joints, resulting in additional insertion loss or reflection. Ambient temperature data is obtained through temperature sensors installed near the optical fiber deployment location. These sensors can be contact or non-contact and can provide real-time temperature readings. In a high humidity environment, moisture will penetrate into the optical fiber coating or cable, resulting in water peak absorption, especially significantly increasing attenuation at wavelengths around 1383nm. Long-term exposure to a humid environment will also accelerate the aging process of the outer protective material of the optical fiber and reduce its protective ability. Ambient humidity data is measured by a hygrometer. For optical fiber systems used outdoors, special humidity detection equipment will be set up at the monitoring point. Although environmental pressure has less impact on most terrestrial optical fiber communication systems than temperature and humidity, it becomes particularly important in special application scenarios such as deep-sea optical cables. The compression under high pressure will also produce deformation effect on the optical fiber, thus affecting the quality of the signal. The environmental pressure data can be collected by pressure sensors. For applications such as submarine cables, special instruments with strong pressure resistance and high precision are required to carry out long-term and stable pressure monitoring.

[0023] like Figure 2 As shown, the step S2 of inputting the environmental factors into the pre-trained optical fiber performance evaluation model to obtain the optical fiber performance score includes: S21, obtaining historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data; S22, performing data preprocessing and principal component analysis dimensionality reduction operations on the historical ambient temperature data, the historical ambient humidity data, the historical ambient pressure data, the historical optical fiber dispersion data, and the historical optical fiber transmission performance data to obtain dimensionality reduction data; S23, based on the dimension reduction data and the preset standard optical fiber data as input data, construct an initial optical fiber performance evaluation model based on the particle swarm algorithm, train the initial optical fiber performance evaluation model according to the membership matrix and the possibility partition matrix, and obtain the optical fiber performance evaluation model.

[0024] In step S21, historical environmental temperature data, historical environmental humidity data, historical environmental pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data are obtained.

[0025] It is worth noting that historical ambient temperature data, historical ambient humidity data, and historical ambient pressure data are also measured using temperature and humidity sensors and pressure sensors and stored in the database. Historical optical fiber dispersion data is tested on optical fibers under certain environmental factors using a dispersion tester, OTDR (optical time domain reflectometer), and network analyzer to obtain the dispersion characteristics in the optical fiber. Through continuous monitoring of the optical fiber network, such as regular checks on indicators such as signal strength, signal-to-noise ratio, and bit error rate, the overall transmission quality of the optical fiber can be evaluated. These data are automatically collected by the monitoring function built into the network equipment, or obtained through special testing activities, and are also stored in the database. This method directly calls the historical data stored in the database through the API interface.

[0026] In step S22, data preprocessing and principal component analysis dimensionality reduction operations are performed on the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain reduced dimensionality data.

[0027] In one implementation, the historical environmental temperature data, the historical environmental humidity data, the historical environmental pressure data, the historical optical fiber dispersion data, and the historical optical fiber transmission performance data are standardized to obtain standardized data; The correlation covariance matrix is ​​calculated based on the standardized data using the following formula: ; in, A normalized matrix representing normalized data; represents the transpose of a normalized matrix; represents the degrees of freedom of the sample covariance; represents the correlation covariance matrix; According to the correlation covariance matrix, eigenvalue decomposition is performed to obtain eigenvalues ​​and eigenvectors; according to the eigenvalues ​​and the eigenvectors, a preset number of the eigenvectors are selected in descending order of eigenvalues ​​to obtain an eigenvector matrix; according to the standardized data and the eigenvector matrix, the standardized data is projected onto the eigenvector matrix to obtain reduced-dimensional data.

[0028] It is worth noting that, in the embodiment of the present invention, the calculation formula for the normalization process is: ; in, represents the original data point; Represents the mean of the data set; Represents the standard deviation of the data set; Represents the standardized data point. Since different variables may have different scales, directly performing principal component analysis will cause some variables to dominate due to their large numerical range. Therefore, before performing principal component analysis, the data needs to be standardized, that is, the data of each variable is converted into a standard normal distribution with a mean of 0 and a standard deviation of 1. This step ensures that all variables are on the same scale, so there is no bias towards any particular variable.

[0029] It is worth noting that principal component analysis is a commonly used statistical method for converting raw data into a new coordinate system through linear transformation so that the variance of the data in the new coordinate system is maximized. The purpose of this is to reduce the dimension of the data set while retaining the variation information in the raw data as much as possible. The covariance matrix is ​​a square matrix, which is calculated using standardized data and reflects the correlation between various parameters. Eigenvalue decomposition is the process of decomposing the covariance matrix into eigenvalues ​​and eigenvectors. The eigenvalue represents the variance of each principal component, and the eigenvector represents the direction of the principal component. The purpose of selecting eigenvectors is to retain the most important principal components, and a preset number of eigenvectors are selected in order from large to small eigenvalues, and eigenvectors that can explain most of the variation are usually selected. In this embodiment, the preset number of eigenvectors is 3. Depending on the application scenario and user needs, the preset number of eigenvectors can also be set to 5, 10, etc., which is not limited by the present invention. Data projection is to use the selected eigenvector matrix to perform linear transformation on the standardized data to obtain a new data set, and the dimension of this data set is usually much smaller than the original data. Through this series of data preprocessing and principal component analysis dimensionality reduction operations, the dimension of the data can be effectively reduced while retaining the most important information. The reduced-dimensional data is easier to process and analyze, which helps improve the efficiency and accuracy of subsequent model training.

[0030] In step S23, based on the reduced dimension data and preset standard optical fiber data as input data, an initial optical fiber performance evaluation model is constructed based on a particle swarm algorithm, and the initial optical fiber performance evaluation model is trained according to a membership matrix and a possibility partitioning matrix to obtain an optical fiber performance evaluation model.

[0031] In one implementation, the cluster center and the number of clusters of the optical fiber performance evaluation model are initialized; a particle swarm is initialized according to the cluster center and the number of clusters, and an optimal initial cluster center and an optimal initial number of clusters are obtained through a full gradient inertial particle swarm optimization algorithm; parameters, a membership matrix and a possibility partitioning matrix of the initial optical fiber performance evaluation model are initialized according to the optimal initial cluster center and the optimal initial number of clusters; the cluster center is updated and trained according to the current membership matrix and the possibility partitioning matrix; when the number of training times is greater than or equal to a preset maximum number of training times, the training is determined to be completed, and the optical fiber performance evaluation model is obtained.

[0032] It is worth noting that the optical fiber performance evaluation model can predict the optical fiber performance according to the input environmental factors, and the optical fiber performance includes the optical fiber dispersion performance and the optical fiber transmission performance.

[0033] It is worth noting that in fiber performance evaluation, cluster centers can help identify different performance modes or types, such as fiber performance characteristics under high temperature conditions. In fiber performance prediction, the particle swarm optimization algorithm can be used to find the best cluster centers and number of clusters to improve the accuracy of the model. The full gradient inertia particle swarm optimization algorithm is an improvement on the particle swarm optimization algorithm, adding full gradient information and inertia weight adjustment strategy to speed up convergence and avoid local optimality.

[0034] In one embodiment, a particle swarm is initialized according to the cluster center and the cluster number to obtain an initial particle swarm; based on the initial particle swarm, particle inertia weight is calculated to obtain the inertia weight value of each particle; based on the initial particle swarm, particle fitness is calculated to obtain the fitness of each particle; based on the fitness and inertia weight value of each particle, particle velocity and particle position are iterated based on full gradient descent, and when the number of iterations is greater than or equal to a preset maximum number of iterations, it is determined that the iteration is completed to obtain an optimal initial cluster center and an optimal initial cluster number; wherein the particle position represents the cluster center and the cluster number of the initial optical fiber performance evaluation model, and the particle velocity represents the update step of the cluster center and the cluster number.

[0035] In one implementation manner, in an embodiment of the present invention, the calculation formula for calculating the inertia weight is as follows: ; in, is the new inertia weight; is the detection function value of the current iteration.

[0036] In the embodiment of the present invention, the detection function is as follows: ; in, represents the individual optimal solution; represents the global optimal solution; Indicates The particle in The position at the iteration; represents the Euclidean distance between the two; Indicates The detection function value of iteration.

[0037] In the embodiment of the present invention, the updating formula for updating the speed and position of the particle is as follows: ; ; in, represents the inertia weight; Indicates the number of iterations; Indicates The current velocity of a particle at the kth iteration; Indicates The current velocity of a particle at the k+1th iteration; Indicates The current position of a particle at the kth iteration; Indicates The current position of a particle at the k+1th iteration; The value is 2, indicating the self-learning factor; The value is 2, indicating the social learning factor; The value range is [0, 1], indicating a random factor; The value range is [0, 1], indicating a random factor; represents the individual optimal solution; It represents the global optimal solution, which embodies the idea of ​​full gradient descent method.

[0038] It is worth noting that the preset maximum number of iterations is a key parameter that determines the convergence speed of the algorithm and the quality of the final solution. If it is set too small, the algorithm may converge too early and fail to find the global optimal solution; if it is set too large, although a better solution may be found, it will increase the computational difficulty and time consumption. In this embodiment, the maximum number of iterations is set to 100. Depending on the application scenario and user needs, the maximum number of iterations can also be set to 50, 200, etc., which is not limited by the present invention.

[0039] In one implementation, the membership matrix and the possibility partition matrix are obtained; distance calculation is performed based on the membership matrix and the possibility partition matrix to obtain the distance from each data point to all cluster centers; for each cluster center, contribution value calculation is performed based on the membership matrix to obtain the position contribution value of each data point to each cluster center; based on the position contribution value, the position contribution values ​​of all data points are weightedly summed to obtain a second cluster center; based on the second cluster center, the membership of all data points is recalculated to obtain a second membership matrix and a second possibility partition matrix; the cluster center, the membership matrix and the possibility partition matrix are replaced with the second cluster center, the second membership matrix and the second possibility partition matrix respectively.

[0040] In one implementation, the membership degree is calculated and updated by the following formula: ; in, For the The data points belong to The class membership, For the The data points belong to The class membership, For the The data points belong to The likelihood of the class split, For the The data points belong to The likelihood of the class split, is the number of clusters; The possibility partition matrix is ​​updated by calculating through the following formula: ; in, For the The data points belong to The likelihood of the class split, For data points and The Euclidean distance between cluster centers, For the data points, For the Cluster centers, For the The scale parameter of the class, is the likelihood weighted index.

[0041] It is worth noting that data points are the basic units in cluster analysis, and they represent individuals that need to be classified or grouped. In this embodiment, the fiber performance data under each historical environmental factor constitutes a data point. These data points are clustered and analyzed to identify abnormal points or outliers in the data, thereby determining whether the fiber performance is abnormal. The membership matrix allows data points to belong to multiple clusters at the same time, which is particularly useful when processing data with unclear boundaries and can provide more detailed data classification results. The possibility partition matrix is ​​also used to describe the relationship between data points and each cluster, but it focuses more on probability distribution, which helps to process data with higher uncertainty.

[0042] In step S3, when the optical fiber performance score is lower than a preset score threshold, an optical fiber performance evaluation report is generated, indicating that the optical fiber cannot be used in the environment corresponding to the environmental factor.

[0043] In one implementation, the optical fiber performance score is calculated using the following formula: in, Score the fiber performance. is the fiber dispersion performance weight, is the fiber transmission performance weight, To standardize the dispersion performance of optical fibers, To standardize fiber optic transmission performance.

[0044] It is worth mentioning that the fiber performance score is a comprehensive evaluation score that combines two key fiber performance indicators: dispersion performance and transmission performance, and reflects the importance of each performance indicator through weights. The weight setting adjusts the importance of each performance indicator according to the needs of the specific application scenario. For example, when long-distance transmission is required, more attention is paid to transmission quality; and when attention is paid to transmission bandwidth, better control of dispersion is required. If the fiber performance score is close to 1, it means that the fiber performs very well in both performances. If the fiber performance score is close to -1, it means that the fiber performance is poor. Both the standardized fiber dispersion performance and the standardized fiber transmission performance are predicted by the fiber performance evaluation model. The preset score threshold can be set to 0, or it can be set to 0.5 according to the high requirements of the use environment.

[0045] In summary, the present invention proposes a fiber performance evaluation method, system and storage medium based on environmental conditions, aiming to improve the accuracy and efficiency of fiber performance evaluation. The method collects data such as ambient temperature, humidity and pressure, and inputs them into a pre-trained evaluation model to obtain a fiber performance score. If the score is lower than the set threshold, an evaluation report is generated, indicating that the fiber may not be used in the current environment. The training of the model involves preprocessing of historical environment and fiber performance data, principal component analysis dimensionality reduction, and model construction and training based on particle swarm algorithm. In the present invention, particle swarm algorithm is used to build and train a fiber performance evaluation model. Specifically, each particle in the algorithm represents a potential solution, that is, a set of cluster centers and the number of clusters. The particle swarm algorithm works by initializing a particle swarm, evaluating particle fitness, updating particle speed and position, and iteratively searching for the optimal solution. The position and speed update of the particle not only depends on the individual historical best position and the global best position, but also introduces full gradient information and inertia weight adjustment strategy to speed up convergence and avoid local optimality. In the training process of the fiber performance evaluation model, the particle swarm algorithm improves the accuracy of the model by optimizing the cluster center and the number of clusters. The cluster centers help identify different fiber performance modes or types, while the number of clusters determines the number of performance modes that the model can identify. In this way, the fiber performance evaluation model can more accurately predict the performance of the fiber under different environmental conditions. This invention comprehensively considers the impact of multiple environmental factors on fiber performance and uses particle swarm optimization to improve the generalization ability and accuracy of the evaluation. Ultimately, it improves the efficiency and accuracy of fiber performance evaluation.

[0046] Reference Figure 3 The second embodiment of the present invention provides an optical fiber performance evaluation system based on environmental conditions, comprising: A data acquisition module is used to acquire environmental factors, wherein the environmental factors include: environmental temperature data, environmental humidity data and environmental pressure data; A score prediction module, used for inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; A historical data acquisition module is used to acquire historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data; A data dimension reduction module, for performing data preprocessing and principal component analysis dimension reduction operations on the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain dimension reduction data; A model training module, used to construct an initial optical fiber performance evaluation model based on a particle swarm algorithm based on the dimension reduction data and preset standard optical fiber data as input data, and train the initial optical fiber performance evaluation model according to a membership matrix and a possibility partition matrix to obtain an optical fiber performance evaluation model; The result output module is used to generate a fiber performance evaluation report when the fiber performance score is lower than a preset score threshold, indicating that the fiber cannot be used in the environment corresponding to the environmental factor.

[0047] It should be noted that the optical fiber performance evaluation system based on environmental conditions provided in an embodiment of the present invention is used to execute all the process steps of the optical fiber performance evaluation method based on environmental conditions in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0048] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, the steps in the above-mentioned embodiments of the optical fiber performance evaluation method based on environmental conditions are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0049] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0050] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0051] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0052] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0053] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0054] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0055] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for evaluating optical fiber performance based on environmental conditions, characterized in that: include: Acquiring environmental factors, the environmental factors including: environmental temperature data, environmental humidity data and environmental pressure data; Inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; When the optical fiber performance score is lower than a preset score threshold, a optical fiber performance evaluation report is generated, indicating that the optical fiber cannot be used in the environment corresponding to the environmental factor; The training process of the optical fiber performance evaluation model includes: Obtain historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data; Performing data preprocessing and principal component analysis dimensionality reduction operations on the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain reduced-dimensionality data; Based on the dimension reduction data and preset standard optical fiber data as input data, an initial optical fiber performance evaluation model is constructed based on a particle swarm algorithm, and the initial optical fiber performance evaluation model is trained according to a membership matrix and a possibility partition matrix to obtain an optical fiber performance evaluation model.

2. The optical fiber performance evaluation method based on environmental conditions according to claim 1, characterized in that: The historical ambient temperature data, the historical ambient humidity data, the historical ambient pressure data, the historical optical fiber dispersion data and the historical optical fiber transmission performance data are subjected to data preprocessing and principal component analysis dimensionality reduction operations to obtain dimensionality reduction data, including: Standardizing the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain standardized data; The correlation covariance matrix is ​​calculated based on the standardized data using the following formula: ； in, A normalized matrix representing normalized data; represents the transpose of a normalized matrix; represents the degrees of freedom of the sample covariance; represents the correlation covariance matrix; Performing eigenvalue decomposition according to the correlation covariance matrix to obtain eigenvalues ​​and eigenvectors; According to the eigenvalues ​​and the eigenvectors, a preset number of the eigenvectors are selected in descending order of the eigenvalues ​​to obtain an eigenvector matrix; According to the standardized data and the eigenvector matrix, the standardized data is projected onto the eigenvector matrix to obtain dimension-reduced data.

3. The optical fiber performance evaluation method based on environmental conditions according to claim 1, characterized in that: The method uses the dimension reduction data and the preset standard optical fiber data as input data, constructs an initial optical fiber performance evaluation model based on a particle swarm algorithm, and trains the initial optical fiber performance evaluation model according to a membership matrix and a possibility partition matrix to obtain an optical fiber performance evaluation model, including: Initializing the cluster center and the number of clusters of the optical fiber performance evaluation model; Initializing a particle swarm according to the cluster center and the cluster number, and obtaining an optimal initial cluster center and an optimal initial cluster number through a full gradient inertial particle swarm optimization algorithm; Initializing the parameters, the membership matrix and the possibility partition matrix of the initial optical fiber performance evaluation model according to the optimal initial cluster center and the optimal initial cluster number; According to the current membership matrix and the possibility partition matrix, cluster centers are updated and trained; When the number of training times is greater than or equal to the preset maximum number of training times, the training is determined to be completed and the optical fiber performance evaluation model is obtained.

4. The optical fiber performance evaluation method based on environmental conditions according to claim 3, characterized in that: Initializing the particle swarm according to the cluster center and the cluster number, and obtaining the optimal initial cluster center and the optimal initial cluster number through the full gradient inertial particle swarm optimization algorithm, includes: Initializing a particle swarm according to the cluster center and the number of clusters to obtain an initial particle swarm; Calculating the particle inertia weight according to the initial particle group to obtain the inertia weight value of each particle; Calculating the fitness of particles according to the initial particle group to obtain the fitness of each particle; According to the fitness and the inertia weight value of each particle, the particle velocity and the particle position are iterated based on full gradient descent, and when the number of iterations is greater than or equal to the preset maximum number of iterations, the iteration is determined to be completed, and the optimal initial cluster center and the optimal initial cluster number are obtained; The particle position represents the cluster center and the number of clusters of the initial optical fiber performance evaluation model, and the particle speed represents the update step length of the cluster center and the number of clusters.

5. The optical fiber performance evaluation method based on environmental conditions according to claim 3, characterized in that: The updating and training of cluster centers according to the current membership matrix and the possibility partition matrix includes: Obtaining the membership matrix and the possibility partition matrix; Perform distance calculation based on the membership matrix and the possibility partition matrix to obtain the distance from each data point to all cluster centers; For each cluster center, a contribution value is calculated according to the membership matrix to obtain a position contribution value of each data point to each cluster center; According to the position contribution value, weighted sum of the position contribution values ​​of all data points is performed to obtain a second cluster center; Recalculate the membership of all data points according to the second cluster center to obtain a second membership matrix and a second possibility partition matrix; The cluster center, the membership matrix and the possibility partition matrix are replaced by the second cluster center, the second membership matrix and the second possibility partition matrix respectively.

6. The optical fiber performance evaluation method based on environmental conditions according to claim 5, characterized in that: The step of recalculating the membership of all data points according to the second cluster center to obtain a second membership matrix and a second possibility partition matrix includes: The membership is updated by calculating the following formula: ； in, For the The data points belong to The class membership, For the The data points belong to The class membership, For the The data points belong to The likelihood of the class split, For the The data points belong to The likelihood of the class split, is the number of clusters; The possibility partition matrix is ​​updated by calculating through the following formula: ； in, For the The data points belong to The likelihood of the class split, For data points and The Euclidean distance between cluster centers, For the data points, For the Cluster centers, For the The scale parameter of the class, is the likelihood weighted index.

7. The optical fiber performance evaluation method based on environmental conditions according to claim 1, characterized in that: The fiber performance score is calculated by the following formula: in, Score the fiber performance. is the fiber dispersion performance weight, is the fiber transmission performance weight, To standardize the dispersion performance of optical fibers, To standardize fiber optic transmission performance.

8. An optical fiber performance evaluation system based on environmental conditions, characterized in that: include: A data acquisition module is used to acquire environmental factors, wherein the environmental factors include: environmental temperature data, environmental humidity data and environmental pressure data; A score prediction module, used for inputting the environmental factors into a pre-trained optical fiber performance evaluation model to obtain an optical fiber performance score; A historical data acquisition module is used to acquire historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data; A data dimension reduction module, for performing data preprocessing and principal component analysis dimension reduction operations on the historical ambient temperature data, historical ambient humidity data, historical ambient pressure data, historical optical fiber dispersion data, and historical optical fiber transmission performance data to obtain dimension reduction data; A model training module, used to construct an initial optical fiber performance evaluation model based on a particle swarm algorithm based on the dimension reduction data and preset standard optical fiber data as input data, and train the initial optical fiber performance evaluation model according to a membership matrix and a possibility partition matrix to obtain an optical fiber performance evaluation model; The result output module is used to generate a fiber performance evaluation report when the fiber performance score is lower than a preset score threshold, indicating that the fiber cannot be used in the environment corresponding to the environmental factor.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for evaluating optical fiber performance based on environmental conditions as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the optical fiber performance evaluation method based on environmental conditions according to any one of claims 1 to 7.

Images