A core on-line rapid testing method and system

Abstract

The application discloses a kind of fiber core online quick test method and system, it is related to communication technical field, including optical signal data acquisition, edge computing preliminary processing, data reception and integration, principal component analysis dimension reduction, establish optical signal attenuation prediction model, fault point positioning and decision support.System is composed of online OTDR test unit, cloud platform, resource visualization system, and each part cooperates to complete test procedure.Compared with prior art, fiber core state real-time online monitoring can be realized, and monitoring timeliness is improved;Data processing speed is fast, and the period of obtaining test results is shortened;Multi-dimensional data processing is more accurate to grasp fiber core state;Fault positioning precision is high, and repair time is saved;Resource visualization system provides comprehensive visual display and decision support, and improves the scientificity and effectiveness of optical fiber communication network operation and maintenance.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, in particular to a fiber core online rapid testing method and system. BACKGROUND

[0002] As the second entity network of the power system, the power communication network undertakes the important responsibility of guaranteeing the safe and stable operation of the power grid, realizing efficient dispatching and management. As the core physical transmission medium of the power communication network, the power communication optical cable carries important services such as power grid relay protection, stability control, automation and video monitoring, and is the basis of power grid dispatching, operation and management informationization, and also an important means to ensure the safe and stable operation of the power grid. Therefore, its stability and reliability are directly related to the safety and efficiency of the entire power system, and play an important role in promoting the green and low-carbon transformation of the supply side and demand side of the power system.

[0003] The huge optical cable network of the power system brings huge operation and maintenance pressure. At present, there are more than 200,000 optical cables in the State Grid, and more than 7,000 optical cables in the Shandong power system, with about 210,000 cores. The power communication optical cable network is increasingly large and complex. For example, Dongying Power Supply Company has more than 5,000 kilometers of total length of power communication optical cables, with more than 650 optical cables and a total number of cores of more than 15,000. According to the specification requirements, the communication professional should detect all the spare cores every year in order to master the available, electrocorrosion, joint box and attenuation of the optical cable cores. The conventional detection method is that the patrol personnel carry heavy test equipment to the station to detect the optical cable single core with handheld test equipment. The time for optical cable core testing in a single station is 1.5-2 hours. Therefore, for such a huge optical cable network, the traditional manual inspection and test method has been difficult to meet the operation and maintenance needs, resulting in huge operation and maintenance pressure, low operation and maintenance efficiency, and the urgent need for a rapid detection system to solve the pressure of optical cable network operation and maintenance.

[0004] Traditional manual operation and maintenance mode is difficult to guarantee the reliability of optical cable operation and maintenance data. The traditional optical cable test process relies on manual operation and input of test results, and there are problems such as low test efficiency, human factor influence and low accuracy. The increasingly complex optical cable network topology further increases the difficulty of operation and maintenance. With the development of smart grid, the network topology of optical cable is becoming more and more complex, and higher requirements are put forward for the operation and maintenance management of power communication optical cable. Especially in the event of extreme weather, natural disasters and other emergencies, the fault risk of optical cable is significantly increased, the monitoring demand of high-risk sites is increasing, and the demand for optical cable network topology and optical fiber health prediction is more urgent. The traditional operation and maintenance mode lacks visual resources of optical cable network topology, and it is difficult to timely locate, respond and handle faults. At the same time, the intelligent operation and maintenance level is low, and the optical fiber state cannot be monitored in real time, which leads to the fault discovery and positioning not timely, and seriously affects the safe and stable operation of power grid. Therefore, it is urgent to improve the intelligent level of optical cable operation and maintenance and realize the reliable operation and maintenance of optical cable core monitoring. SUMMARY

[0005] The purpose of the present application is to provide a kind of core online rapid test method and system, by online OTDR test unit acquisition optical signal data, by edge computing, cloud platform processing, principal component analysis, attenuation prediction model is established and so on Step, combined with the analysis of transmission characteristics of optical propagation theory to locate fault point, is completed by the overall architecture of the whole including test unit, cloud platform, resource visualization system. The above problems have been solved.

[0006] To achieve the above purpose, the present application provides the following technical scheme:

[0007] A kind of core online rapid test method, characterized in that, it includes the following steps:

[0008] S1: optical signal data acquisition;

[0009] S2: edge computing carries out preliminary processing;

[0010] S3: data reception and integration;

[0011] S4: principal component analysis and data dimension reduction;

[0012] S5: establish optical signal attenuation prediction model;

[0013] S6: fault point positioning and decision support.

[0014] Step S1 optical signal data acquisition specifically: using online OTDR test unit in time interval In acquisition optical signal data sequence , its sequence list is:

[0015]

[0016] wherein denotes time, denotes the acquisition time interval, is the total duration of the acquisition, is the data point number in the sequence of optical signal data acquired in the time interval .

[0017] The preliminary processing by the edge computing in step S2 specifically includes data filtering and feature extraction;

[0018] The data filtering specifically is: a finite impulse response (FIR) filter is adopted, the filter coefficient sequence of which is , the length of which is , and the filtered optical signal data sequence is obtained through convolution operation:

[0019]

[0020] wherein is the data point number in the sequence of filtered optical signal data, the filter coefficient sequence of which is , is the length of the filter coefficient sequence , and is the data point number in the original acquired optical signal data sequence that is relevant to the current filtered data point to be calculated.

[0021] The preliminary processing by the edge computing in step S2 specifically includes data filtering and feature extraction;

[0022] The feature extraction specifically is: the filtered optical signal data is subjected to feature extraction, and the average intensity and the intensity variance of the optical signal are calculated, the formula of which is:

[0023]

[0024] wherein is the average intensity of the optical signal, which is obtained by summing and averaging the filtered optical signal data from the data point number to the last data point, i.e. the data point number , and it can roughly reflect the overall intensity level of the optical signal in this time period; ​is the variance of the light signal intensity, used to measure the dispersion degree of the light signal intensity relative to the average intensity within a certain time range, by calculating the square sum of the difference between each filtered data point and the average intensity , and performing corresponding average processing, the stability and other characteristics of the light signal can be further analyzed; is the number of data points involved in calculating the average intensity and variance, and its value is , is the total duration of the collection, the collection time interval, is the length of the filter coefficient sequence.

[0025] Step S3 data reception and integration is: using the cloud platform to receive the characteristic value data sequence from the online OTDR test unit, including the average intensity and the intensity variance , arranging these data in time sequence to form time series data, which can be expressed in vector form:

[0026]

[0027] wherein is the specific value of the average intensity of the light signal received by the cloud platform from the online OTDR test unit at time , which forms a time series data about the average intensity as time goes by; is the specific value of the intensity variance of the light signal received by the cloud platform from the online OTDR test unit at time , which forms a time series data about the intensity variance as time goes by; is a two-dimensional data matrix formed by arranging the characteristic value data of the average intensity and the intensity variance of the light signal received by the cloud platform at different times in time sequence, is the length of the received data time series, that is, the number of groups of characteristic value data received by the cloud platform at different times, which determines the number of rows of the data matrix .

[0028] Step S4 principal component analysis and data dimension reduction is: through principal component analysis for data dimension reduction:

[0029]

[0030] wherein, is the covariance matrix of the data matrix , which is an important basis for principal component analysis and other data processing operations, is the vector mean, is the length of the received data time series, that is, the number of groups of characteristic value data received by the cloud platform at different times, which determines the number of rows of the data matrix number of rows;

[0031] Principal component analysis was performed on the two dimensions of received average intensity and intensity variance to calculate the data matrix. ;in yes Given the mean vector, solve for the covariance matrix. eigenvalues and the corresponding feature vector The projection matrix is ​​formed by selecting the eigenvectors corresponding to the main eigenvalues. The original data is dimensionality reduced to obtain the dimensionality-reduced data. :

[0032]

[0033] in The data after dimensionality reduction processing using principal component analysis is obtained by using the original data matrix. The projection matrix consisting of eigenvectors corresponding to the main features Multiplying by the transposes yields, The projection matrix consists of eigenvectors corresponding to the selected principal eigenvalues, which are obtained by adjusting the covariance matrix. Solve for eigenvalues ​​and eigenvectors.

[0034] Step S5, establishing the optical signal attenuation prediction model, specifically involves using a nonlinear regression model to establish the prediction model based on optical signal attenuation.

[0035]

[0036] in The attenuation of the optical signal is a function of time. The regression coefficients in the optical signal attenuation prediction model are determined by fitting the data using the least squares method, thereby defining the specific optical signal attenuation prediction model. In the optical signal attenuation prediction model, it is a vector composed of other factors affecting optical signal attenuation. The relevant regression coefficients, A vector composed of other factors affecting optical signal attenuation. The first in A function of factors changing over time;

[0037] Based on the observed optical signal attenuation data sequence The corresponding predicted value is Let the sum of squared errors function be defined as:

[0038]

[0039] wherein is a sum of square error function, is the i-th data point in the actual observed optical signal attenuation data sequence, is the corresponding predicted value, is the length of the actual observed optical signal attenuation data sequence, i.e. the number of measured attenuation data points at different time instants;

[0040] By solving the partial derivative equations that minimize , the optimal regression coefficients are obtained, thereby determining the optical signal attenuation prediction model.

[0041]

[0042]

[0043] Step S6 fault point positioning and decision support is specifically: the established prediction model and the real-time received optical signal data, analyzing the transmission characteristics of the optical signal in the optical cable, according to the propagation theory of light, the following relationship is established:

[0044]

[0045] wherein is a function of the change of the optical signal intensity with the transmission distance, wherein is the transmission distance of the optical signal in the optical cable, is the initial intensity of the optical signal, i.e. the intensity value of the optical signal when it enters the optical cable to start transmission, is the attenuation coefficient of the optical signal in the optical cable, is the reflected signal intensity function of the optical signal in the transmission process;

[0046] By fitting the collected optical signal data, the specific forms of the attenuation coefficient and the reflected signal intensity function are determined, thereby analyzing the transmission characteristics of the optical signal in the optical cable;

[0047] When the optical cable fails, the transmission characteristics of the optical signal will change significantly, at this time the optical signal intensity will sharply decrease, the reflected signal intensity will suddenly increase, by monitoring the changes of the optical signal intensity and the reflected signal intensity, combined with the above analysis of the transmission characteristics of the optical signal, when the fault determination condition is met, the fault point position can be determined as:

[0048]

[0049] is the position of the fault point from the starting point, is the initial intensity of the optical signal,​​ is a threshold value for light signal intensity drop, is a reference value for reflected signal intensity under normal circumstances, is a threshold value for reflected signal increase;

[0050] According to the location of the fault point and the analysis result of the light signal transmission characteristics, decision support is provided for troubleshooting and repair.

[0051] A fiber core online rapid testing system, comprising an online OTDR testing unit, a cloud platform and a resource visualization system, the online OTDR testing unit and the cloud platform are used to execute the steps of the fiber core online rapid testing method.

[0052] The resource visualization system provides optical fiber state visualization and optical cable resource visualization, specifically including optical fiber route, connection point, occupation of each port, connection state of optical fiber, fault information, and based on GIS map and optical cable quality dyeing function, the quality state of the optical cable is distinguished.

[0053] First, the online OTDR testing unit collects a light signal data sequence in a set time interval to complete the light signal data collection step. Then the collected data is preliminarily processed by edge computing, including data filtering using a finite impulse response (FIR) filter, and extracting average intensity and intensity variance and other characteristics from the filtered data. Then the cloud platform receives the characteristic value data sequence from the testing unit and arranges it in time sequence to form time series data, and then performs dimension reduction processing on the received data in two dimensions of average intensity and intensity variance through principal component analysis. Subsequently, a prediction model is established based on light signal attenuation using a nonlinear regression model, and the optimal regression coefficient is determined by solving the partial derivative equation set that minimizes the error sum of squares function. Finally, combining the established prediction model and the real-time received light signal data, the transmission characteristics of the light signal in the optical cable are analyzed according to the propagation theory of light, when the optical cable fails, the location of the fault point is determined by monitoring the changes of light signal intensity and reflected signal intensity according to the fault determination condition, and decision support is provided for troubleshooting and repair based on this. The entire process is completed by the online OTDR testing unit, the cloud platform and the resource visualization system which provides functions such as optical fiber and optical cable resource visualization, and each part performs the corresponding steps to realize the work flow of the entire fiber core online rapid testing.

[0054] Compared with the prior art, the beneficial effects of the present application are:

[0055] The present technology can continuously collect light signal data through the online OTDR testing unit, realize real-time online monitoring of the fiber core state. Without interrupting the normal operation of the optical fiber, the actual working condition of the optical fiber can be grasped at any time, greatly improving the timeliness of the monitoring, and potential problems can be found at the first time.

[0056] The preliminary processing by edge computing and the data receiving and integration of the cloud platform can quickly process data. The conversion from optical signal collection to effective data for analysis can be completed in a short time, which greatly shortens the cycle of obtaining test results compared with the traditional method, so that the operation and maintenance personnel can respond more quickly.

[0057] Not only the optical signal data is collected, but also the average intensity, intensity variance and other multi-dimensional data are processed and reduced by principal component analysis, so that the data characteristics are more comprehensively and deeply mined. Compared with the traditional single-dimensional or simple data processing test method, the real state of the core can be more accurately grasped, and the misjudgment situation is reduced.

[0058] In the fault point positioning link, according to the established optical signal attenuation prediction model and the detailed analysis of the optical signal transmission characteristics, combined with the propagation theory of light, the position of the fault point can be accurately determined. Compared with the traditional fault positioning method relying on experience or rough investigation, the accuracy is significantly improved, the investigation range can be effectively reduced, and the fault repair time is saved.

[0059] The matching resource visualization system provides comprehensive visualization display of the optical fiber state and the optical cable resource, including the optical fiber trend, the connection point, the port occupation condition and many other details. The operation and maintenance personnel can intuitively understand the overall situation, which provides a strong basis for formulating reasonable operation and maintenance strategies and fault troubleshooting schemes, which is the intuitive decision-making function that the traditional technology lacks.

[0060] Through the integration of the collected and analyzed data, scientific and accurate decision support can be provided for fault troubleshooting and repair. Instead of relying on experience, the operation and maintenance decision is based on actual data and accurate analysis results, so that the operation and maintenance decision is more reasonable and efficient, and the scientificity and effectiveness of the whole optical fiber communication network operation and maintenance are improved. BRIEF DESCRIPTION OF DRAWINGS

[0061] Fig. 1 A fiber core online rapid test system of the present application;

[0062] Fig. 2 A working flowchart of a fiber core online rapid test system of the present application;

[0063] Fig. 3 A fiber core online rapid test method flowchart of the present application; DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application.

[0065] As shown in Figs. 1-3 A fiber core online rapid test method, characterized in that it comprises the following steps:

[0066] S1: light signal data collection;

[0067] S2: edge computing for preliminary processing;

[0068] S3: data receiving and integration;

[0069] S4: principal component analysis and data dimension reduction;

[0070] S5: establishment of light signal attenuation prediction model;

[0071] S6: fault point positioning and decision support.

[0072] Step S1: light signal data collection, specifically, using an online OTDR test unit to collect a light signal data sequence within a time interval , the sequence of which is represented as:

[0073]

[0074] wherein represents time, represents the collection time interval, is the total duration of collection, is the th data point in the light signal data sequence collected within the time interval according to the collection time interval .

[0075] Step S2: edge computing for preliminary processing, specifically including data filtering and feature extraction;

[0076] The data filtering specifically is: using a finite impulse response (FIR) filter, the filter coefficient sequence of which is , the length of which is , and the filtered light signal data sequence is obtained through convolution operation as:

[0077]

[0078] wherein is the th data point in the filtered light signal data sequence, the filter coefficient sequence of which is , is the length of the filter coefficient sequence , and is the th data point in the originally collected light signal data sequence related to the filtered data point to be calculated. ​

[0079] The step S2 edge computing performs preliminary processing, specifically including data filtering and feature extraction;

[0080] The feature extraction is specifically: performing feature extraction on the filtered optical signal data, calculating the average intensity and intensity variance of the optical signal , the formula is:

[0081]

[0082] wherein is the average intensity of the optical signal, is the intensity variance of the optical signal, is the number of data points involved in calculating the average intensity and variance, and its value is , is the total duration of collection, is the collection time interval, is the length of the filter coefficient sequence.

[0083] The step S3 data receiving and integration is specifically: using a cloud platform to receive the feature value data sequence from the online OTDR test unit, including the average intensity and intensity variance , arranging these data in time sequence to form time series data, which can be expressed in vector form:

[0084]

[0085] wherein is the specific value of the average intensity of the optical signal received by the cloud platform from the online OTDR test unit at time , is the specific value of the intensity variance of the optical signal received by the cloud platform from the online OTDR test unit at time , is the two-dimensional data matrix formed by arranging the feature value data of the average intensity and intensity variance of the optical signal received by the cloud platform in time sequence at different times, is the length of the received data time sequence.

[0086] The step S4 principal component analysis and data dimension reduction is specifically: using principal component analysis for data dimension reduction:

[0087]

[0088] wherein, is the covariance matrix of the data matrix , which is an important basis for performing principal component analysis and other data processing operations, is the vector mean, The length of the received data time series, which is the data matrix. number of rows;

[0089] Principal component analysis was performed on the two dimensions of received average intensity and intensity variance to calculate the data matrix. ;in yes Given the mean vector, solve for the covariance matrix. eigenvalues and the corresponding feature vector The projection matrix is ​​formed by selecting the eigenvectors corresponding to the main eigenvalues. The original data is dimensionality reduced to obtain the dimensionality-reduced data. :

[0090]

[0091] in The data after dimensionality reduction processing using principal component analysis is obtained by using the original data matrix. The projection matrix consisting of eigenvectors corresponding to the main features Multiplying by the transposes yields, The projection matrix consists of eigenvectors corresponding to the selected principal eigenvalues, which are obtained by adjusting the covariance matrix. Solve for eigenvalues ​​and eigenvectors.

[0092] Step S5, establishing the optical signal attenuation prediction model, specifically involves using a nonlinear regression model to establish the prediction model based on optical signal attenuation.

[0093]

[0094] in The attenuation of the optical signal is a function of time. The regression coefficients in the optical signal attenuation prediction model are determined by fitting the data using the least squares method, thereby defining the specific optical signal attenuation prediction model. In the optical signal attenuation prediction model, it is a vector composed of other factors affecting optical signal attenuation. The relevant regression coefficients, A vector composed of other factors affecting optical signal attenuation. The first in A function of factors changing over time;

[0095] Based on the observed optical signal attenuation data sequence The corresponding predicted value is Let the sum of squared errors function be defined as:

[0096]

[0097] wherein is the sum of squared error function, is the i-th data point in the actual observed optical signal attenuation data sequence, is the corresponding predicted value, is the length of the actual observed optical signal attenuation data sequence, i.e. the number of measured attenuation data points at different time instants;

[0098] by solving the partial derivative equations that minimize

[0099]

[0100] the optimal regression coefficients are obtained, thereby determining the optical signal attenuation prediction model.

[0101] Step S6 fault point positioning and decision support is specifically: the prediction model established and the optical signal data received in real time, analyzing the transmission characteristics of the optical signal in the optical cable, according to the propagation theory of light, the following relationship is established:

[0102]

[0103] wherein is the function of the change of the optical signal intensity with the transmission distance, wherein is the transmission distance of the optical signal in the optical cable, is the initial intensity of the optical signal, i.e. the intensity value of the optical signal when it enters the optical cable to start transmission, is the attenuation coefficient of the optical signal in the optical cable, is the reflected signal intensity function of the optical signal in the transmission process;

[0104] by fitting the collected optical signal data, the specific form of the attenuation coefficient and the reflected signal intensity function is determined, thereby analyzing the transmission characteristics of the optical signal in the optical cable;

[0105] When the optical cable fails, the transmission characteristics of the optical signal will change significantly, at this time the intensity of the optical signal will sharply decrease, the intensity of the reflected signal will suddenly increase, by monitoring the change of the intensity of the optical signal and the intensity of the reflected signal, combined with the above analysis of the transmission characteristics of the optical signal, when the fault determination condition is met, the fault point position can be determined:

[0106]

[0107] ​​is the location of the fault point from the start point, is the initial intensity of the optical signal, is the threshold of the optical signal intensity drop, is the reference value of the reflected signal intensity under normal circumstances, is the threshold of the reflected signal increase;

[0108] According to the location of the fault point and the analysis result of the optical signal transmission characteristics, decision support is provided for fault troubleshooting and repair.

[0109] A fiber core online rapid test system, characterized in that it comprises an online OTDR test unit, a cloud platform and a resource visualization system, wherein the online OTDR test unit and the cloud platform are used to execute the steps of the fiber core online rapid test method.

[0110] The resource visualization system provides optical fiber state visualization and optical cable resource visualization, specifically including fiber routing, connection points, occupation of each port, connection state of optical fibers, fault information discovery, and distinguishing optical cable quality states based on GIS maps and optical cable quality coloring functions.

[0111] The specific steps are as follows:

[0112] S1: Optical signal data acquisition; specifically, using the online OTDR test unit to collect optical signal data sequences within a time interval The sequence representation is:

[0113]

[0114] wherein represents time, represents the collection time interval, is the total duration of collection, is the th data point in the optical signal data sequence collected within the time interval according to the collection time interval

[0115] S2: Edge computing for preliminary processing; specifically including data filtering and feature extraction;

[0116] The data filtering specifically uses a finite impulse response (FIR) filter with a filter coefficient sequence with a length of The filtered optical signal data sequence is obtained through convolution operation:

[0117]

[0118] ​​wherein is the i-th data point in the filtered optical signal data sequence, whose filter coefficient sequence is , is the length of the filter coefficient sequence , is the i-th data point in the original collected optical signal data sequence related to the current filtered data point to be calculated.

[0119] The feature extraction is specifically: performing feature extraction on the filtered optical signal data, calculating the average intensity and intensity variance of the optical signal, whose formula is:

[0120]

[0121] wherein is the average intensity of the optical signal, which is obtained by summing and averaging the filtered optical signal data from the i-th data point to the last data point, i.e. , and can roughly reflect the overall intensity level of the optical signal in this time period; is the intensity variance of the optical signal, which is used to measure the dispersion degree of the optical signal intensity relative to the average intensity within a certain time range, and is obtained by calculating the sum of squares of the difference between each filtered data point and the average intensity , and performing corresponding average processing, which can further analyze the stability and other characteristics of the optical signal; is the number of data points involved in calculating the average intensity and variance, whose value is , is the total duration of collection, is the collection time interval, is the length of the filter coefficient sequence.

[0122] S3: Data reception and integration; specifically: using a cloud platform to receive the feature value data sequence from the online OTDR test unit, including the average intensity and intensity variance , arranging these data in time sequence to form time series data, which can be expressed in vector form:

[0123]

[0124] wherein is the average intensity of the optical signal received by the cloud platform from the online OTDR test unit at time ​​​a specific numerical value, which forms a time series data of average intensity over time; a specific numerical value, which forms a time series data of intensity variance over time; a specific numerical value, which forms a time series data of intensity variance over time; a two-dimensional data matrix formed by arranging the received characteristic value data of average intensity and intensity variance at different time points in time sequence, a time series length of the received data, i.e., the number of groups of characteristic value data at different time points received by the cloud platform, which determines the number of rows of the data matrix .

[0125] S4: Principal component analysis and data dimension reduction; the principal component analysis is used for data dimension reduction:

[0126]

[0127] wherein, the covariance matrix of the data matrix , is an important basis for performing principal component analysis and other data processing operations, the vector mean, the time series length of the received data, i.e., the number of rows of the data matrix , the total duration of collection;

[0128] The principal component analysis is performed on the received average intensity and intensity variance in two dimensions, and the data matrix is calculated; wherein is the mean vector of , the eigenvalues and the corresponding eigenvectors of the covariance matrix are solved, the projection matrix is composed of the eigenvectors corresponding to the main eigenvalues, and the original data is processed by dimension reduction to obtain the dimension-reduced data :

[0129]

[0130] wherein is the data processed by the principal component analysis and dimension reduction, which is obtained by multiplying the original data matrix by the transpose of the projection matrix composed of the eigenvectors corresponding to the main eigenvalues, the projection matrix composed of the eigenvectors corresponding to the selected main eigenvalues, which are obtained by solving the covariance matrix Solving eigenvalues and eigenvectors.

[0131] S5: Establishing the optical signal attenuation prediction model; specifically, using a nonlinear regression model to establish the prediction model:

[0132]

[0133] wherein is a function of the optical signal attenuation amount over time, is a regression coefficient in the optical signal attenuation prediction model, and the values of these coefficients are determined by fitting the data using the least squares method, thereby determining the specific optical signal attenuation prediction model, is a vector in the optical signal attenuation prediction model composed of other factors affecting the optical signal attenuation related regression coefficients, is a vector composed of other factors affecting the optical signal attenuation the first factor in the vector changes over time;

[0134] The actual observed optical signal attenuation data sequence and the corresponding predicted value is , and the error sum of squares function is set as:

[0135]

[0136] wherein is the error sum of squares function, is the first data point in the actual observed optical signal attenuation data sequence, is the corresponding predicted value, is the length of the actual observed optical signal attenuation data sequence, i.e., the number of attenuation data points measured at different times;

[0137] By solving the partial derivative equation set that minimizes :

[0138]

[0139] the optimal regression coefficient is obtained, thereby determining the optical signal attenuation prediction model.

[0140] S6: Fault point positioning and decision support. Specifically, the prediction model established and the real-time received optical signal data are used to analyze the transmission characteristics of the optical signal in the optical cable, and according to the theory of light propagation, the following relationship is established:

[0141]

[0142] wherein is a function of the transmission distance of the optical signal in the optical cable, is a function of the transmission distance of the optical signal in the optical cable, is the initial intensity of the optical signal, i.e., the intensity value of the optical signal when it enters the optical cable to start transmission, is the attenuation coefficient of the optical signal in the optical cable, is a function of the reflected signal intensity of the optical signal in the transmission process;

[0143] By fitting the collected optical signal data, the specific forms of the attenuation coefficient and the reflected signal intensity function are determined, so as to analyze the transmission characteristics of the optical signal in the optical cable;

[0144] When the optical cable fails, the transmission characteristics of the optical signal will change significantly, at this time the intensity of the optical signal will sharply decrease, and the intensity of the reflected signal will suddenly increase, by monitoring the changes of the intensity of the optical signal and the intensity of the reflected signal, combined with the above analysis of the transmission characteristics of the optical signal, when the fault determination condition is met, the position of the fault point can be determined:

[0145]

[0146] is the position of the fault point from the starting point, is the initial intensity of the optical signal, is the threshold value of the decrease of the intensity of the optical signal, is the reference value of the intensity of the reflected signal under normal circumstances, is the threshold value of the increase of the reflected signal;

[0147] According to the position of the fault point and the analysis results of the transmission characteristics of the optical signal, decision support is provided for fault troubleshooting and repair.

[0148] A fiber core online rapid test system, characterized in that it comprises an online OTDR test unit, a cloud platform and a resource visualization system, wherein the online OTDR test unit and the cloud platform are used to execute the steps of the fiber core online rapid test method.

[0149] The resource visualization system provides optical fiber state visualization and optical cable resource visualization, specifically including optical fiber route, connection point, occupation of each port, connection state of optical fiber, fault information, and based on GIS map and optical cable quality dyeing function, the quality state of the optical cable is distinguished.

Claims

1. A rapid online testing method for fiber cores, characterized in that, Includes the following steps: S1: Optical signal data acquisition; S2: Edge computing performs preliminary processing; S3: Data reception and integration; S4: Principal component analysis and dimensionality reduction of the data; S5: Establish an optical signal attenuation prediction model; S6: Fault location and decision support; Step S2 edge computing performs preliminary processing, specifically including data filtering and feature extraction; The data filtering specifically involves using a Finite Impulse Response (FIR) filter, whose filter coefficient sequence is as follows: , length is Filtered optical signal data sequence The result obtained through convolution operation is: ， in The first element in the filtered optical signal data sequence The filter coefficient sequence for each data point is as follows: , For the filter coefficient sequence Length, The original acquired optical signal data sequence and the filtered data points to be calculated. The relevant first One data point; The feature extraction specifically involves: performing feature extraction on the filtered optical signal data and calculating the average intensity of the optical signal. With intensity variance Its formula is: ， in The average intensity of the light signal. The variance of the optical signal intensity. The number of data points involved in calculating the mean intensity and variance is denoted by _____. , For the total collection time, Data collection time interval The length of the filter coefficient sequence; Step S3, data reception and integration, specifically involves using a cloud platform to receive the eigenvalue data sequence from the online OTDR test unit, including the average intensity. With intensity variance Arranging these data in chronological order to form time series data can be represented in vector form: ， in The average intensity of the optical signal received by the cloud platform from the online OTDR test unit at time [time missing]. The specific value, The variance of the optical signal intensity received by the cloud platform from the online OTDR test unit at time [time value missing]. The specific value, This is a two-dimensional data matrix formed by arranging the characteristic values ​​such as the average intensity and intensity variance of optical signals received by the cloud platform at different times in chronological order. The length of the received data time series; Step S4, principal component analysis and dimensionality reduction, specifically involves using principal component analysis for dimensionality reduction. ， in, For data matrix The covariance matrix is ​​an important foundation for data processing operations such as principal component analysis. The vector mean, The length of the received data time series, which is the data matrix. number of rows; Principal component analysis was performed on the two dimensions of received average intensity and intensity variance to calculate the data matrix. ;in yes Given the mean vector, solve for the covariance matrix. eigenvalues and the corresponding feature vector The projection matrix is ​​formed by selecting the eigenvectors corresponding to the main eigenvalues. The original data is dimensionality reduced to obtain the dimensionality-reduced data. : ， in The data after dimensionality reduction processing using principal component analysis is obtained by using the original data matrix. The projection matrix consisting of eigenvectors corresponding to the main features Multiplying by the transposes yields, The projection matrix consists of eigenvectors corresponding to the selected principal eigenvalues, which are obtained by adjusting the covariance matrix. Find the eigenvalues ​​and eigenvectors; Step S5, establishing the optical signal attenuation prediction model, specifically involves using a nonlinear regression model to establish the prediction model based on optical signal attenuation. ， in The attenuation of the optical signal is a function of time. The regression coefficients in the optical signal attenuation prediction model are determined by fitting the data using the least squares method, thereby defining the specific optical signal attenuation prediction model. In the optical signal attenuation prediction model, it is a vector composed of other factors affecting optical signal attenuation. The relevant regression coefficients, A vector composed of other factors affecting optical signal attenuation. The first in A function of factors changing over time; Based on the observed optical signal attenuation data sequence The corresponding predicted value is Let the sum of squared errors function be defined as: ， in Let be the sum of squared errors function. The first data in the actual observed optical signal attenuation data sequence Data points, For the corresponding predicted value, The length of the observed optical signal attenuation data sequence, i.e., the number of attenuation data points measured at different times; By solving Minimize the system of partial derivative equations: ， The optimal regression coefficients are obtained, thereby determining the optical signal attenuation prediction model; Step S6, Fault Location and Decision Support, specifically involves: analyzing the transmission characteristics of the optical signal in the optical cable based on the established prediction model and the real-time received optical signal data, and establishing the following relationship based on the theory of light propagation: ， in Let be the function of optical signal intensity as a function of transmission distance, where This refers to the transmission distance of the optical signal in the optical cable. This represents the initial intensity of the optical signal, that is, the intensity value of the optical signal when it enters the optical cable and begins transmission. This is the attenuation coefficient of the optical signal in the optical cable. This is a function of the intensity of the reflected signal during the transmission of the optical signal; The attenuation coefficient is determined by fitting the collected optical signal data. and reflected signal intensity function The specific form of the optical signal is then analyzed to determine its transmission characteristics in the optical cable. When a fiber optic cable malfunctions, the transmission characteristics of the optical signal change significantly. The optical signal strength drops sharply, while the reflected signal strength suddenly increases. By monitoring the changes in optical and reflected signal strengths, and combining this with the analysis of the aforementioned optical signal transmission characteristics, a fault determination can be made when the conditions are met. Then the location of the fault can be determined: ， The fault point is located at a distance from the starting point. The initial intensity of the optical signal. The threshold for the decrease in optical signal intensity. This is a reference value for the intensity of the reflected signal under normal conditions. A threshold added to the reflected signal; Based on the analysis results of the fault location and optical signal transmission characteristics, decision support is provided for fault diagnosis and repair.

2. The online rapid testing method for fiber cores according to claim 1, characterized in that, Step S1, optical signal data acquisition, specifically involves using an online OTDR test unit to perform data acquisition within a specific time interval. Internal acquisition optical signal data sequence Its sequence is represented as: ， in Indicates time, Indicates the time interval for data collection. The total duration of data collection. In the time interval According to the collection time interval The first of the acquired optical signal data sequence Data points.

3. A fiber core online rapid testing system, characterized in that, The system includes an online OTDR testing unit, a cloud platform, and a resource visualization system, characterized in that the online OTDR testing unit and the cloud platform implement the steps of the method described in any one of claims 1 to 2.

4. The fiber core online rapid testing system according to claim 3, characterized in that, The resource visualization system is used to provide clients with visualization of fiber optic status and optical cable resources. The functions of the resource visualization system include: displaying fiber optic routes, connection points, occupancy status of each port, fiber optic connection status and fault information; and distinguishing the quality status of optical cables based on GIS maps and optical cable quality coloring functions.

Images