Optical cable intelligent monitoring method and system based on digital twin

Abstract

The present invention discloses an optical cable intelligent monitoring method and system based on digital twins, and specifically relates to the field of optical cable monitoring technology, including: step one: collecting real-time optical cable performance data of N optical cable segments, and screening out I optical cable segments with suspected transmission fault marks based on the real-time optical cable performance data; the suspected transmission fault marks include suspected burst transmission fault marks and suspected minor transmission fault marks; step two: analyzing the optical cable segments corresponding to the suspected transmission fault marks to obtain the transmission fault levels of the corresponding optical cable segments; step three: using a pre-built transmission fault analysis digital twin model to simulate and analyze the real-time optical cable performance data to generate simulation prediction data; the present invention can effectively improve the accuracy of the transmission fault prediction model by combining real-time data with the simulation data of the digital twin model, and the prediction results are more reliable compared with OTDR monitoring.

Description

Technical Field

[0001] The present invention relates to the field of optical cable monitoring technology, and more specifically, to an optical cable intelligent monitoring method and system based on digital twins. Background Art

[0002] With the rapid development of communication networks, the health status of optical cables, as the core medium for information transmission, directly affects the quality of communication. Traditional optical cable monitoring methods mostly rely on manual inspections or monitoring systems based on simple sensors. For example, in traditional methods, optical cable inspections often require a lot of manpower and it is difficult to detect problems in real time. Although conventional sensors can monitor key parameters of optical cables, such as temperature, vibration, and fiber loss, they have limited positioning accuracy when transmission failures occur, especially for early warning of potential problems. The existing method is based on OTDR remote detection technology. By analyzing the influence of optical fiber loss rate on data transmission bit error rate, the degree of optical fiber wear is predicted in advance, and early warning of optical fiber transmission failure is achieved; managers can monitor data transmission efficiency and optical cable wear in real time through the platform, which is convenient for managers to check optical fiber transmission fault sections and improve work efficiency; by recording equipment abnormalities and equipment maintenance conditions, managers can check the optical fiber management conditions of each section at any time, which improves the management efficiency of multiple optical fiber communication sections. For example, the Chinese patent application with publication number CN117353807A discloses an optical cable remote monitoring system and method based on artificial intelligence. Although the above method can realize intelligent monitoring of optical cables, timely warn of transmission failures, and facilitate management of managers to improve the efficiency of optical fiber communication transmission, the inventor has studied and applied the above method and the existing technology and found that the above method and the existing technology have at least the following defects:

[0003] OTDR monitoring is highly dependent on the strength of the optical fiber transmission signal. Slight changes in the optical cable and environmental changes may affect the detection results. Especially in the case of slight damage to the optical cable or minor transmission faults, environmental changes will mask the actual transmission fault signal and lead to inaccurate monitoring.

[0004] To this end, the present invention provides an optical cable intelligent monitoring method and system based on digital twins. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides an optical cable intelligent monitoring method and system based on digital twins to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above objectives, in a first aspect, the present invention provides the following technical solutions: an optical cable intelligent monitoring method based on digital twins, comprising:

[0007] Step 1: collecting real-time optical cable performance data of N optical cable segments, and screening out I optical cable segments with suspected transmission fault marks based on the real-time optical cable performance data; the suspected transmission fault marks include suspected burst transmission fault marks and suspected minor transmission fault marks;

[0008] Step 2: Analyze the optical cable segment corresponding to the suspected transmission fault mark to obtain the transmission fault level of the corresponding optical cable segment;

[0009] Step 3: Using the pre-built transmission fault analysis digital twin model, simulate and analyze the real-time optical cable performance data to generate simulation prediction data;

[0010] Step 4: taking the real-time optical cable performance data and the transmission fault level as a real-time sample set, and taking the real-time optical cable performance data and the simulation prediction data as a simulation sample set; constructing and training a transmission fault prediction model based on the real-time sample set and the simulation sample set;

[0011] Step 5: Use the trained transmission fault prediction model to perform prediction analysis on the optical cable line to obtain a transmission fault prediction result; the transmission fault prediction result includes whether a transmission fault occurs during the prediction period and whether a transmission fault does not occur during the prediction period.

[0012] Furthermore, the real-time optical cable performance data includes real-time optical cable basic data and real-time comprehensive environmental data; the real-time optical cable basic data includes real-time value of attenuation coefficient, real-time value of dispersion and real-time value of microbending loss; the real-time comprehensive environmental data includes predicted value of rainfall, predicted value of rainfall duration and predicted value of electromagnetic interference;

[0013] The method for screening out the optical cable line segments suspected of burst transmission fault marks and suspected of slight transmission fault marks based on the real-time optical cable performance data comprises:

[0014] a1: Obtaining the experimental optical cable standard data of the nth optical cable segment; n=1, 2, ..., N; N is the number of optical cable segments; the experimental optical cable standard data includes optical cable quality standard data and comprehensive environmental standard data; the optical cable quality standard data includes attenuation coefficient standard value, dispersion standard value and microbending loss standard value; the comprehensive environmental standard data includes rainfall standard value, rainfall duration standard value and electromagnetic interference standard value;

[0015] a2: performing optical cable analysis and processing based on the real-time optical cable basic data and optical cable quality standard data to obtain a performance evaluation coefficient;

[0016] a3: Performing environmental analysis based on the real-time comprehensive environmental data and the comprehensive environmental standard data to obtain a comprehensive environmental assessment coefficient;

[0017] a4: Perform a comprehensive analysis of transmission faults based on the performance evaluation coefficient and the comprehensive environment evaluation coefficient to obtain I optical cable segments marked with suspected transmission faults.

[0018] Furthermore, the method for performing optical cable analysis and processing based on the real-time optical cable basic data and optical cable quality standard data includes:

[0019] The attenuation coefficient real-time value and the attenuation coefficient standard value are calculated by formulating to calculate the attenuation evaluation coefficient ;

[0020] The dispersion real-time value and the dispersion standard value are calculated by formulating to calculate the dispersion evaluation coefficient ;

[0021] The real-time value of the microbending loss and the standard value of the microbending loss are calculated by formulating to calculate the microbending loss evaluation coefficient. ;

[0022] Based on the attenuation evaluation coefficient , dispersion evaluation coefficient and microbending loss evaluation coefficient Calculate the performance evaluation coefficient.

[0023] Furthermore, the method for performing environmental analysis based on the real-time integrated environmental data and the integrated environmental standard data includes:

[0024] The rainfall prediction value and the rainfall standard value are calculated by formulating to calculate the rainfall assessment coefficient ;

[0025] The rainfall duration prediction value and the rainfall duration standard value are calculated by formulating to calculate the rainfall duration evaluation coefficient. ;

[0026] The electromagnetic interference prediction value and the electromagnetic interference standard value are calculated by formulating to calculate the interference assessment coefficient ;

[0027] Based on the rainfall assessment factor , Rainfall duration assessment coefficient and interference assessment coefficient Calculate the comprehensive environmental assessment coefficient;

[0028] The method for comprehensive analysis of transmission failures based on the performance evaluation coefficient and the comprehensive environment evaluation coefficient includes:

[0029] Calculating an optical cable evaluation coefficient based on the performance evaluation coefficient and the comprehensive environmental evaluation coefficient;

[0030] A first evaluation threshold is preset, and the optical cable evaluation coefficient is compared with the preset first evaluation threshold to obtain a transmission fault evaluation result; the transmission fault evaluation result obtained includes a suspected burst transmission fault mark, a suspected minor transmission fault mark, and a no transmission fault mark, and the number of optical cable segments with suspected burst transmission fault marks and suspected minor transmission fault marks is counted, and I optical cable segments are screened out.

[0031] Furthermore, a first evaluation threshold is preset, and a method for comparing the optical cable evaluation coefficient with the preset first evaluation threshold includes:

[0032] Preset the first evaluation threshold and , comparing the optical cable evaluation coefficient with a preset first evaluation threshold; wherein < ;

[0033] If the optical cable evaluation coefficient is greater than or equal to a preset first evaluation threshold , then the corresponding optical cable segment is marked as a suspected burst transmission fault mark;

[0034] If the optical cable evaluation coefficient is less than a preset first evaluation threshold , and is greater than the preset first evaluation threshold , then the corresponding optical cable segment is marked as a suspected minor transmission fault mark;

[0035] If the optical cable evaluation coefficient is less than or equal to a preset first evaluation threshold , the corresponding optical cable segment is marked as having no transmission fault mark.

[0036] Furthermore, the method for obtaining the transmission fault level of the corresponding optical cable segment includes:

[0037] b1: respectively obtaining the real-time transmission characteristic data of the optical cable segments corresponding to the suspected burst transmission fault mark and the suspected minor transmission fault mark; the real-time transmission characteristic data includes the real-time value of the optical cable temperature, the real-time value of the optical power and the real-time value of the bit error rate;

[0038] b2: Input the real-time transmission feature data into the trained speed prediction model to predict the corresponding transmission speed;

[0039] b3: Divide the predicted transmission speed into M transmission fault levels in sequence to obtain the transmission fault level of the corresponding optical cable segment, wherein the transmission fault level includes a first burst fault level, a second burst fault level, a first slight transmission fault level, and a second slight transmission fault level, and the first burst fault level>the second burst fault level>the first slight transmission fault level>the second slight transmission fault level.

[0040] Furthermore, the specific training process of the speed prediction model includes:

[0041] Pre-collecting Q groups of transmission speeds corresponding to real-time transmission characteristic data, and converting the real-time transmission characteristic data and the corresponding transmission speeds into a corresponding set of characteristic vectors;

[0042] Each set of feature vectors is used as the input of the speed prediction model. The speed prediction model uses a set of predicted transmission speeds corresponding to each set of real-time transmission feature data as output, and uses the actual transmission speed corresponding to each set of real-time transmission feature data as the prediction target. The actual transmission speed is the transmission speed corresponding to the real-time transmission feature data collected in advance. The training target is to minimize the sum of the prediction errors of all real-time transmission feature data. The calculation formula of the prediction error is: ,in is the prediction error, The group number of the feature vector corresponding to the real-time transmission feature data, For the The predicted transmission speed corresponding to the real-time transmission characteristic data of the group, For the The actual transmission speed corresponding to the real-time transmission feature data of the group is obtained; the speed prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped; the speed prediction model is a deep neural network model.

[0043] Furthermore, the predicted transmission speed is divided into M transmission fault levels in sequence, and the method for obtaining the transmission fault level of the corresponding optical cable segment includes:

[0044] c1: Get the transmission speed of the i-th optical cable segment; i=1, 2, ..., I;

[0045] c2: setting F transmission speed intervals and setting M transmission fault levels corresponding to the F transmission speed intervals;

[0046] Each of the transmission speed intervals has and only has one transmission failure level associated and bound thereto;

[0047] c3: Compare the transmission speed of the i-th optical cable segment with each transmission speed interval to obtain the transmission speed interval into which the transmission speed of the i-th optical cable segment falls;

[0048] c4: classify the i-th optical cable segment into a corresponding transmission fault level according to the transmission speed interval into which the transmission speed of the i-th optical cable segment falls; and set i=i+1, and jump back to step c1;

[0049] c5: Repeat the above steps c1 to c4 until the loop ends when i=I, so that each of the optical cable segments is divided into M transmission fault levels in turn, where I is the total number of optical cable segments.

[0050] Furthermore, the method of simulating and analyzing the real-time optical cable performance data using the pre-built transmission fault analysis digital twin model includes:

[0051] Inputting the real-time optical cable performance data into the transmission fault analysis digital twin model for simulation to obtain an optical cable simulation image;

[0052] The optical cable simulation image is processed, and the pre-built convolutional neural network (CNN) is used to extract features from the processed optical cable simulation image to generate simulation prediction data.

[0053] Furthermore, the method for constructing and training a transmission fault prediction model based on the real-time sample set and the simulation sample set includes:

[0054] The real-time sample set and the simulated sample set are divided into a 70% transmission fault training set and a 30% transmission fault test set;

[0055] Constructing a recurrent neural model, inputting the transmission fault training set as input data into the recurrent neural model for training, and optimizing the model using a cross entropy loss function;

[0056] The trained recurrent neural model is verified using the transmission fault test set to output a recurrent neural model that meets a preset accuracy as a transmission fault prediction model, wherein the recurrent neural model is an RNN.

[0057] Furthermore, the method of using the trained transmission fault prediction model to perform prediction analysis on the optical cable line includes:

[0058] directly inputting the real-time optical cable performance data of the nth optical cable segment into the transmission fault prediction model to obtain a transmission fault prediction result;

[0059] Or analyze and simulate the real-time optical cable performance data of the nth optical cable segment to obtain the transmission fault level and simulation prediction data of the optical cable line;

[0060] The transmission fault level or simulation prediction data is input into the transmission fault prediction model to obtain a transmission fault prediction result.

[0061] In a second aspect, the present invention provides an optical cable intelligent monitoring system based on digital twins, which is used to implement the above-mentioned optical cable intelligent monitoring method based on digital twins, including:

[0062] An optical cable marking module is used to collect real-time optical cable performance data of N optical cable segments, and screen out I optical cable segments with suspected transmission fault marks based on the real-time optical cable performance data; the suspected transmission fault marks include suspected burst transmission fault marks and suspected minor transmission fault marks;

[0063] An optical cable analysis module, used to analyze the optical cable segment corresponding to the suspected transmission fault mark to obtain the transmission fault level of the corresponding optical cable segment;

[0064] The optical cable simulation module uses a pre-built transmission fault analysis digital twin model to simulate and analyze the real-time optical cable performance data to generate simulation prediction data;

[0065] A model training module is used to use the real-time optical cable performance data and the transmission fault level as a real-time sample set, and use the real-time optical cable performance data and the simulation prediction data as a simulation sample set; and to construct and train a transmission fault prediction model based on the real-time sample set and the simulation sample set;

[0066] The model prediction module uses the trained transmission fault prediction model to perform prediction analysis on the optical cable line to obtain a transmission fault prediction result; the transmission fault prediction result includes the occurrence of transmission faults in the prediction period and the non-occurrence of transmission faults in the prediction period.

[0067] Technical effects and advantages of the present invention:

[0068] 1. The present invention collects real-time optical cable performance data of N optical cable segments, and screens out I optical cable segments with suspected transmission fault marks based on the real-time optical cable performance data; the suspected transmission fault marks include suspected burst transmission fault marks and suspected minor transmission fault marks; the optical cable segments corresponding to the suspected transmission fault marks are analyzed to obtain the transmission fault levels of the corresponding optical cable segments; the real-time optical cable performance data are simulated and analyzed by using a pre-built transmission fault analysis digital twin model to generate simulation prediction data; the real-time optical cable performance data and the transmission fault level are used as a real-time sample set, and the real-time optical cable performance data and the simulation prediction data are used as a simulation sample set; a transmission fault prediction model is constructed and trained based on the real-time sample set and the simulation sample set; the optical cable line is predicted and analyzed by using the trained transmission fault prediction model to obtain a transmission fault prediction result; the present invention can effectively improve the accuracy of the transmission fault prediction model by combining real-time data with the simulation data of the digital twin model, and the prediction result is more reliable compared with OTDR monitoring; by accurately predicting transmission faults, measures can be taken in advance to reduce or avoid serious consequences caused by faults, thereby improving the operational reliability and stability of the optical cable line.

[0069] 2. The present invention can effectively concentrate maintenance resources in the required areas, optimize resource allocation, and reduce maintenance costs by identifying the optical cable segments that may fail in advance. The transmission fault prediction results generated by this solution provide important decision-making support for staff and help formulate more reasonable maintenance plans and emergency plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a flow chart of the optical cable intelligent monitoring method based on digital twins in Example 1;

[0071] Figure 2 This is a structural diagram of an optical cable intelligent monitoring system based on digital twins according to Example 3;

[0072] Figure 3 This is a schematic diagram of an electronic device according to Embodiment 4;

[0073] Figure 4 This is a schematic diagram of a computer-readable storage medium of Example 5. DETAILED DESCRIPTION

[0074] 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.

[0075] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0076] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0077] Example 1

[0078] See also Figure 1 As shown, this embodiment discloses an optical cable intelligent monitoring method based on digital twins, including:

[0079] Step 1: Collect real-time optical cable performance data of N optical cable segments, and screen out I optical cable segments with suspected transmission fault marks based on the real-time optical cable performance data; the suspected transmission fault marks include suspected burst transmission fault marks and suspected minor transmission fault marks.

[0080] Specifically, the N optical cable segments are obtained based on the optical cable distribution topology map pre-stored in the system database; it should be further explained that the generation process of the N optical cable segments is: first, the optical cable distribution topology map is obtained from the pre-built system database; then, the optical cable distribution topology map is divided according to the connection points between the optical cable segments to generate multiple optical cable topology grids; finally, each optical cable topology grid is divided into N independent optical cable segments according to the connection path, and the length of each optical cable segment can be determined artificially, and the present invention does not make too many restrictions on this.

[0081] The real-time optical cable performance data includes real-time optical cable basic data and real-time comprehensive environmental data; the real-time optical cable basic data includes real-time value of attenuation coefficient, real-time value of dispersion and real-time value of microbending loss; the real-time comprehensive environmental data includes rainfall prediction value, rainfall duration prediction value and electromagnetic interference prediction value; it should be noted that the real-time comprehensive environmental data is the comprehensive environmental data of the prediction period, and the prediction period can be minutes, hours and days.

[0082] It should be noted that the real-time value of the attenuation coefficient is obtained by measuring the degree of loss of the optical signal during transmission in the optical cable through an optical time domain reflectometer. The smaller the real-time value of the attenuation coefficient, the less the loss of the optical signal during transmission. The attenuation coefficient is an important indicator for measuring the performance of optical fiber transmission and directly affects the signal transmission distance and quality.

[0083] The real-time dispersion value indicates that when an optical signal propagates in an optical cable, light of different wavelengths propagates at different speeds, resulting in signal broadening and distortion. The real-time dispersion value is obtained by analyzing and calculating the broadening of an optical signal at a specific wavelength using a dispersion tester. The calculation formula is: ; In the formula, Indicates the real-time value of dispersion, It indicates the amount of time that the fiber signal pulse is broadened. Indicates the bandwidth of the optical fiber signal. Indicates the length of the optical cable.

[0084] The real-time value of microbend loss refers to the optical signal loss caused by tiny bends or unevenness in the optical fiber; microbends are caused by external forces, improper installation or temperature changes. Although the bending amplitude is small, it still causes light scattering and loss, thereby increasing the overall attenuation of the optical fiber.

[0085] Specifically, the method for obtaining the real-time value of microbending loss includes:

[0086] Measure the optical cable through OTDR to obtain the reflection curve;

[0087] Find the microbend on the reflection curve and read the loss value ;

[0088] Compare the loss values ​​in the normal position without microbends in the curve ;

[0089] The calculation formula of the real-time value of microbending loss is as follows: ;

[0090] In the formula, Indicates the real-time value of microbending loss, is the loss value at the microbend, is the loss value at the normal position. It should be supplemented that: there are a variety of methods in the prior art that can be used to measure microbending losses. Under appropriate conditions, the results obtained by these methods can be used as real-time values ​​of microbending losses.

[0091] The rainfall forecast value is the rainfall expected in a certain period of time in the future. Rainfall may affect the physical structure of the optical cable (such as water accumulation, increased humidity) and the electromagnetic environment around the optical cable, thereby interfering with signal transmission;

[0092] The rainfall duration prediction value refers to the predicted duration of rainfall in a specific time period in the future. The rainfall duration is directly related to the humidity, water accumulation and potential environmental damage to the optical cable, which will cause problems such as optical cable aging and optical cable sheath moisture;

[0093] The electromagnetic interference prediction value is to predict the intensity of electromagnetic interference in the environment where the optical cable is located. Electromagnetic interference mainly comes from power lines, lightning, radio transmission equipment, etc., which will affect the stability and quality of the optical signal; the electromagnetic interference prediction value is obtained by measuring with a spectrum analyzer.

[0094] It should be noted that the predicted rainfall amount and rainfall duration are obtained through predictions from weather stations, radars and meteorological models.

[0095] In implementation, the method of screening out I optical cable segments marked with suspected transmission faults based on the real-time optical cable performance data includes:

[0096] a1: obtaining the experimental optical cable standard data of the nth optical cable segment; n=1, 2, ..., N; N is the number of optical cable segments;

[0097] Specifically, the experimental optical cable standard data includes optical cable quality standard data and comprehensive environment standard data; the optical cable quality standard data includes attenuation coefficient standard value, dispersion standard value and microbending loss standard value; the comprehensive environment standard data includes rainfall standard value, rainfall duration standard value and electromagnetic interference standard value, and the experimental optical cable standard data is pre-stored in the system database.

[0098] It should be noted that the experimental optical cable standard data is obtained by artificially setting after preliminary experimental simulation, and is the best ideal value for monitoring sudden transmission failures and minor transmission failures of the optical cable.

[0099] a2: performing optical cable analysis and processing based on the real-time optical cable basic data and optical cable quality standard data to obtain a performance evaluation coefficient;

[0100] Specifically, the method for performing optical cable analysis and processing based on the real-time optical cable basic data and optical cable quality standard data includes:

[0101] The attenuation coefficient real-time value and the attenuation coefficient standard value are calculated by formulating to calculate the attenuation evaluation coefficient , and its calculation formula is: ; Where: Indicates the standard value of the attenuation coefficient, Indicates the real-time value of the attenuation coefficient;

[0102] The dispersion real-time value and the dispersion standard value are calculated by formulating to calculate the dispersion evaluation coefficient , and its calculation formula is: ; Where: represents the standard value of dispersion, Indicates the real-time value of dispersion; Indicates Logarithmic function with base ;

[0103] The real-time value of the microbending loss and the standard value of the microbending loss are calculated by formulating to calculate the microbending loss evaluation coefficient. , and its calculation formula is: ; Where: represents the standard value of microbending loss, Indicates the real-time value of microbending loss, Expressed as a natural constant;

[0104] Based on the attenuation evaluation coefficient , dispersion evaluation coefficient and microbending loss evaluation coefficient Calculate the performance evaluation coefficient, the calculation formula is: ; Where: represents the performance evaluation coefficient;

[0105] It should be noted that: the larger the performance evaluation coefficient is, the greater the possibility of transmission failure in the corresponding optical cable segment is, and the lower the reliability of optical fiber signal transmission is.

[0106] a3: Performing environmental analysis based on the real-time comprehensive environmental data and the comprehensive environmental standard data to obtain a comprehensive environmental assessment coefficient;

[0107] Specifically, the method for performing environmental analysis based on the real-time integrated environmental data and the integrated environmental standard data includes:

[0108] The rainfall prediction value and the rainfall standard value are calculated by formulating to calculate the rainfall assessment coefficient , and its calculation formula is: ; Where: represents the standard value of rainfall, represents the rainfall forecast value;

[0109] The rainfall duration prediction value and the rainfall duration standard value are calculated by formulating to calculate the rainfall duration evaluation coefficient. , and its calculation formula is: ; Where: Indicates the standard value of rainfall duration. represents the predicted value of rainfall duration, Indicates Logarithmic function with base ;

[0110] The electromagnetic interference prediction value and the electromagnetic interference standard value are calculated by formulating to calculate the interference assessment coefficient , and its calculation formula is: ; Where: Indicates the standard value of electromagnetic interference, Indicates the predicted value of electromagnetic interference;

[0111] Based on the rainfall assessment factor , Rainfall duration assessment coefficient and interference assessment coefficient Calculate the comprehensive environmental assessment coefficient, the calculation formula is: ; Where: represents the comprehensive environmental assessment coefficient;

[0112] a4: Performing a comprehensive analysis of transmission faults based on the performance evaluation coefficient and the comprehensive environment evaluation coefficient to obtain optical cable segments with suspected burst transmission fault marks and suspected minor transmission fault marks;

[0113] Specifically, the method for comprehensive analysis of transmission failures based on the performance evaluation coefficient and the comprehensive environment evaluation coefficient includes:

[0114] The optical cable evaluation coefficient is calculated based on the performance evaluation coefficient and the comprehensive environmental evaluation coefficient, and the calculation formula is: ; Where: represents the optical cable evaluation coefficient, and represents the evaluation correction factor, .

[0115] It should be noted that the larger the value of the performance evaluation coefficient and the larger the value of the comprehensive environmental evaluation coefficient, the greater the possibility of transmission failure in the optical fiber signal transmission in the optical cable.

[0116] A first evaluation threshold is preset, and the optical cable evaluation coefficient is compared with the preset first evaluation threshold to obtain a transmission fault evaluation result; the transmission fault evaluation result includes a suspected burst transmission fault mark, a suspected minor transmission fault mark and a no transmission fault mark.

[0117] Specifically, a method for presetting a first evaluation threshold and comparing the optical cable evaluation coefficient with the preset first evaluation threshold includes:

[0118] Preset the first evaluation threshold and , comparing the optical cable evaluation coefficient with a preset first evaluation threshold; wherein < ;

[0119] If the optical cable evaluation coefficient is greater than or equal to a preset first evaluation threshold , then the corresponding optical cable segment is marked as a suspected burst transmission fault mark;

[0120] If the optical cable evaluation coefficient is less than a preset first evaluation threshold , and is greater than the preset first evaluation threshold , then the corresponding optical cable segment is marked as a suspected minor transmission fault mark;

[0121] If the optical cable evaluation coefficient is less than or equal to a preset first evaluation threshold , then the corresponding optical cable segment is marked as having no transmission fault mark;

[0122] The number of optical cable segments with suspected burst transmission fault marks and suspected minor transmission fault marks is counted, and a total of I optical cable segments are screened out.

[0123] It should be noted that the suspected sudden transmission fault mark indicates a serious transmission fault that may suddenly occur during the operation of the optical cable, which usually leads to a complete interruption of optical signal transmission or serious signal loss. This type of transmission fault is often sudden and unpredictable, and has a wide range of impact. Common causes of sudden transmission failures include but are not limited to construction excavation, traffic accidents, natural disasters (such as earthquakes, mudslides, etc.) that cause the optical cable to be cut or severely damaged, and excessive bending, compression or stretching of the optical cable, resulting in optical fiber breakage.

[0124] The suspected minor transmission fault mark indicates a small-scale transmission fault that may occur during the operation of the optical cable, which is usually manifested as a slight signal loss, an increase in bit error rate or unstable transmission. If the attenuation coefficient, microbend loss or dispersion increases slightly when the predicted value of rainfall or electromagnetic interference increases, but does not cause obvious communication interruption or major transmission failure, this usually indicates that the optical cable has a minor transmission fault. This type of transmission fault is usually manifested as a slight change in performance indicators and is highly correlated with fluctuations in environmental factors.

[0125] This step analyzes the collected real-time optical cable performance data and experimental optical cable standard data. This step is helpful in screening out optical cable segments with suspected sudden transmission fault marks and suspected minor transmission fault marks, thereby facilitating the determination of transmission fault areas, so as to provide a basis for the next step of targeted analysis, thereby helping to improve the accuracy of optical cable line transmission fault prediction.

[0126] Step 2: Analyze the optical cable segment corresponding to the suspected transmission fault mark to obtain the transmission fault level of the corresponding optical cable segment;

[0127] Specifically, the method for obtaining the transmission fault level of the corresponding optical cable segment includes:

[0128] b1: respectively obtaining the real-time transmission characteristic data of the optical cable segments corresponding to the suspected burst transmission fault mark and the suspected minor transmission fault mark;

[0129] It should be noted that the real-time transmission characteristic data includes the real-time value of optical cable temperature, the real-time value of optical power and the real-time value of bit error rate; wherein the real-time value of optical cable temperature refers to the actual temperature of the optical cable section during the signal transmission process; excessively high or low temperature will affect the performance of the optical cable material, thereby causing changes in the signal transmission characteristics of the optical fiber, such as increased loss or increased attenuation; it is measured and obtained through a temperature sensor or a distributed optical fiber temperature sensing system (DTS); the DTS system is based on the principle of Raman scattering and continuously monitors temperature changes along the optical fiber.

[0130] The real-time value of optical power indicates the intensity or power of the optical signal in the optical cable. Changes in optical power will directly affect the quality and stability of signal transmission. Too low power means excessive signal attenuation or problems with joints or connectors. The real-time value of optical power is measured by an optical power meter or an optical time domain reflectometer.

[0131] The real-time value of the bit error rate represents the ratio of the number of bits received erroneously to the total number of bits during signal transmission; an increase in the bit error rate generally indicates a decrease in signal transmission quality, which may be caused by optical fiber loss, interference, temperature changes, etc.; the real-time value of the bit error rate is obtained by measuring with a bit error rate tester.

[0132] b2: Input the real-time transmission feature data into the trained speed prediction model to predict the corresponding transmission speed;

[0133] b3: Divide the predicted transmission speed into M transmission fault levels in sequence to obtain the transmission fault level of the corresponding optical cable segment, wherein the transmission fault level includes a first burst fault level, a second burst fault level, a first slight transmission fault level, and a second slight transmission fault level, and the first burst fault level>the second burst fault level>the first slight transmission fault level>the second slight transmission fault level.

[0134] It should be noted that: the first sudden fault level represents the most serious fault level, which may indicate that the optical cable transmission speed has dropped sharply, there is a major failure risk, and immediate maintenance is required; the second sudden fault level indicates a slightly lighter fault than the first sudden fault level, but still indicates a more serious fault; the first minor transmission fault level indicates a minor fault, which may cause a slight drop in transmission speed, but will not immediately cause optical cable failure; the second minor transmission fault level indicates the slightest fault, the change in transmission speed may be very small, the optical cable can still operate normally, but attention is required.

[0135] Specifically, the specific training process of the speed prediction model includes:

[0136] Pre-collecting Q groups of transmission speeds corresponding to real-time transmission characteristic data, and converting the real-time transmission characteristic data and the corresponding transmission speeds into a corresponding set of characteristic vectors;

[0137] Each set of feature vectors is used as the input of the speed prediction model. The speed prediction model uses a set of predicted transmission speeds corresponding to each set of real-time transmission feature data as output, and uses the actual transmission speed corresponding to each set of real-time transmission feature data as the prediction target. The actual transmission speed is the transmission speed corresponding to the real-time transmission feature data collected in advance. The training target is to minimize the sum of the prediction errors of all real-time transmission feature data. The calculation formula of the prediction error is: ,in is the prediction error, The group number of the feature vector corresponding to the real-time transmission feature data, For the The predicted transmission speed corresponding to the real-time transmission characteristic data of the group, For the The actual transmission speed corresponding to the real-time transmission feature data of the group is obtained; the speed prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped; the speed prediction model is a deep neural network model.

[0138] It should be noted that the transmission speed corresponding to the real-time transmission characteristic data is obtained by technical personnel in this field by collecting multiple groups of different real-time transmission characteristic data during the optical fiber signal transmission process, monitoring the optical cable segment corresponding to each group of real-time transmission characteristic data multiple times, collecting the transmission speeds corresponding to the multiple monitorings, and taking the average of the multiple transmission speeds as the transmission speed corresponding to the group of real-time transmission characteristic data, and so on to obtain the transmission speeds corresponding to multiple groups of different real-time transmission characteristic data.

[0139] Specifically, the method of sequentially dividing the predicted transmission speed into M transmission fault levels includes:

[0140] c1: Get the transmission speed of the i-th optical cable segment; i=1, 2, ..., I;

[0141] c2: setting F transmission speed intervals and setting M transmission fault levels corresponding to the F transmission speed intervals;

[0142] It should be understood that: each transmission speed interval has one and only one transmission fault level associated with it;

[0143] c3: Compare the transmission speed of the i-th optical cable segment with each transmission speed interval to obtain the transmission speed interval into which the transmission speed of the i-th optical cable segment falls;

[0144] c4: classify the i-th optical cable segment into a corresponding transmission fault level according to the transmission speed interval into which the transmission speed of the i-th optical cable segment falls; and set i=i+1, and jump back to step c1;

[0145] c5: Repeat the above steps c1 to c4 until the loop ends when i=I, so that each of the optical cable segments is divided into M transmission fault levels in turn, where I is the total number of optical cable segments.

[0146] By conducting further targeted analysis on optical cable segments with suspected burst transmission fault marks and suspected minor transmission fault marks, and introducing multiple related factors, this embodiment can provide an implementation plan for the prediction of transmission faults in existing optical cable lines, thereby facilitating timely warnings and facilitating staff to repair optical cables in a timely manner according to the transmission fault level.

[0147] Example 2

[0148] See also Figure 1 As shown, based on the above embodiment 1, in order to further improve the accuracy of optical cable intelligent monitoring, reduce the error of optical cable transmission fault prediction, and solve the singleness of existing model training data, this embodiment will perform digital twin model analysis on the optical cable segment according to the real-time optical cable performance data, and combine the model analysis results with the output data of the above embodiment 1 for fusion learning to achieve high-precision optical cable transmission fault prediction. This embodiment discloses an optical cable intelligent monitoring method based on digital twins, and the method also includes:

[0149] Step 3: Use the pre-built transmission fault analysis digital twin model to simulate and analyze the real-time optical cable performance data to generate simulation prediction data;

[0150] It should also be noted that: the transmission fault analysis digital twin model is a virtual digital simulation of the physical optical cable line;

[0151] In implementation, the method for constructing the transmission fault analysis digital twin model includes:

[0152] First, various data related to the optical cable line are collected, including optical cable physical property data, environmental data and optical fiber transmission characteristics, etc.; these data can come from various sources such as optical cable manufacturers, sensor networks, field monitoring, etc.; then the collected data are preprocessed and cleaned, including removing outliers, processing missing data, performing data interpolation and other operations to ensure the accuracy and completeness of the data; then the data from different sources and different types are integrated; finally, a simulation model is established using the collected data to simulate the changes in optical cable performance parameters such as attenuation, dispersion, and microbend loss; the established simulation model is compared and verified with the actual monitoring data to evaluate the accuracy and reliability of the model, and the model is adjusted and improved as needed to improve the accuracy of the simulation results, and finally a virtual digital simulation body for optical cable monitoring is constructed using the verified model and the integrated data; the algorithm of the simulation model includes but is not limited to finite element method, finite difference method, deep learning algorithm and principal component analysis, etc.;

[0153] For example, suppose that in a river area near an optical cable line, the water level rises rapidly due to recent heavy rainfall. The latest hydrological data is obtained through satellite remote sensing and drone monitoring, and these data are input into the digital twin model. The model first simulates the impact of rising water levels on soil moisture around the optical cable through physical modeling, and then predicts the increase in microbending loss and attenuation of the optical cable caused by high humidity through a data-driven model. The model simulation results show that a certain section of optical cable may experience increased attenuation in the next 24 hours. Based on these predictions, the maintenance team can conduct on-site inspections and preventive maintenance in a timely manner to avoid major transmission failures.

[0154] Specifically, the method of simulating and analyzing the real-time optical cable performance data using the pre-built transmission fault analysis digital twin model includes:

[0155] Inputting the real-time optical cable performance data into the transmission fault analysis digital twin model for simulation to obtain an optical cable simulation image;

[0156] The optical cable simulation image is processed, and the pre-built convolutional neural network (CNN) is used to extract features from the processed optical cable simulation image to generate simulation prediction data.

[0157] It should be noted that: the image processing includes but is not limited to image enhancement, image denoising and image normalization, etc.; it should also be noted that: the simulation prediction data is an image feature vector;

[0158] Step 4: taking the real-time optical cable performance data and the transmission fault level as a real-time sample set, and taking the real-time optical cable performance data and the simulation prediction data as a simulation sample set; and constructing a transmission fault prediction model based on the real-time sample set and the simulation sample set;

[0159] By constructing a real-time sample set and a simulation sample set, and using them as training parameters of a transmission fault prediction model, since the training parameters are derived from evaluation analysis processing and simulation analysis processing respectively, it is helpful to solve the problem of small amount of existing optical cable training data, and it is helpful to avoid the problem of singleness of training data; by fusing multi-source data, the present invention can further improve the accuracy of optical cable transmission fault prediction;

[0160] Specifically, the method for constructing and training a transmission fault prediction model based on the real-time sample set and the simulation sample set includes:

[0161] The real-time sample set and the simulated sample set are divided into a 70% transmission fault training set and a 30% transmission fault test set;

[0162] Constructing a recurrent neural model, inputting the transmission fault training set as input data into the recurrent neural model for training, and optimizing the model using a cross entropy loss function;

[0163] The trained recurrent neural model is verified using the transmission fault test set to output a recurrent neural model that meets a preset accuracy as a transmission fault prediction model, wherein the recurrent neural model is an RNN.

[0164] Step 5: Use the trained transmission fault prediction model to perform prediction analysis on the optical cable line to obtain a transmission fault prediction result; the transmission fault prediction result includes whether a transmission fault occurs during the prediction period and whether a transmission fault does not occur during the prediction period.

[0165] Specifically, the method for predicting and analyzing the optical cable line using the transmission fault prediction model includes:

[0166] Collect real-time optical cable performance data of the N optical cable segments in the current cycle; the daily interval between the prediction cycle and the current cycle is K, K is an integer greater than or equal to 1; the units of the current cycle and the prediction cycle are the same, which can be minutes, hours and days.

[0167] The method for performing model analysis on the real-time optical cable performance data of the nth optical cable segment includes:

[0168] directly inputting the real-time optical cable performance data of the nth optical cable segment into the transmission fault prediction model to obtain a transmission fault prediction result;

[0169] Or analyze and simulate the real-time optical cable performance data of the nth optical cable segment to obtain the transmission fault level and simulation prediction data of the optical cable line;

[0170] Inputting the transmission fault level or simulation prediction data into the transmission fault prediction model to obtain a transmission fault prediction result;

[0171] This step uses the real-time optical cable performance data and the transmission fault level as a real-time sample set, and the real-time optical cable performance data and the simulation prediction data as a simulation sample set, and builds a transmission fault prediction model based on them. This embodiment is beneficial to reducing the error of optical cable line transmission fault prediction, solving the problem of the singleness of existing model training data, and further improving the accuracy and credibility of optical cable line transmission fault prediction.

[0172] Example 3

[0173] See also Figure 2 As shown, this embodiment provides an optical cable intelligent monitoring system based on digital twins, including: an optical cable marking module, an optical cable analysis module, an optical cable simulation module, a model training module and a model prediction module, and each module is connected by wired and / or wireless means to realize data transmission between modules;

[0174] An optical cable marking module is used to collect real-time optical cable performance data of N optical cable segments, and screen out I optical cable segments with suspected transmission fault marks based on the real-time optical cable performance data; the suspected transmission fault marks include suspected burst transmission fault marks and suspected minor transmission fault marks;

[0175] An optical cable analysis module, used to analyze the optical cable segment corresponding to the suspected transmission fault mark to obtain the transmission fault level of the corresponding optical cable segment;

[0176] The optical cable simulation module uses a pre-built transmission fault analysis digital twin model to simulate and analyze the real-time optical cable performance data to generate simulation prediction data;

[0177] A model training module is used to use the real-time optical cable performance data and the transmission fault level as a real-time sample set, and use the real-time optical cable performance data and the simulation prediction data as a simulation sample set; and to construct and train a transmission fault prediction model based on the real-time sample set and the simulation sample set;

[0178] The model prediction module uses the trained transmission fault prediction model to perform prediction analysis on the optical cable line to obtain a transmission fault prediction result; the transmission fault prediction result includes the occurrence of transmission faults in the prediction period and the non-occurrence of transmission faults in the prediction period.

[0179] Example 4

[0180] See also Figure 3 As shown, this embodiment provides an electronic device 500. The electronic device 500 may include one or more processors and one or more memories. The memory stores a computer-readable code, and when the computer-readable code is run by one or more processors, the optical cable intelligent monitoring method based on digital twins as described above can be executed.

[0181] The system according to the embodiment of the present application can also be used Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store the optical cable intelligent monitoring method based on digital twins provided in the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0182] Example 5

[0183] See also Figure 4 As shown, this embodiment provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes the optical cable intelligent monitoring method based on digital twins of Example 1.

[0184] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0185] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0186] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An optical cable intelligent monitoring method based on digital twins, characterized in that: include: Step 1: collecting real-time optical cable performance data of N optical cable segments, and screening out I optical cable segment with suspected transmission fault mark based on the real-time optical cable performance data; The suspected transmission fault mark includes a suspected burst transmission fault mark and a suspected minor transmission fault mark; The real-time optical cable performance data includes real-time optical cable basic data and real-time comprehensive environmental data; the real-time optical cable basic data includes real-time value of attenuation coefficient, real-time value of dispersion and real-time value of microbending loss; the real-time comprehensive environmental data includes predicted value of rainfall, predicted value of rainfall duration and predicted value of electromagnetic interference; The method for screening out the optical cable line segments suspected of burst transmission fault marks and suspected of slight transmission fault marks based on the real-time optical cable performance data comprises: a1: Obtaining the experimental optical cable standard data of the nth optical cable segment; n=1, 2, ..., N; N is the number of optical cable segments; the experimental optical cable standard data includes optical cable quality standard data and comprehensive environmental standard data; the optical cable quality standard data includes attenuation coefficient standard value, dispersion standard value and microbending loss standard value; the comprehensive environmental standard data includes rainfall standard value, rainfall duration standard value and electromagnetic interference standard value; a2: performing optical cable analysis and processing based on the real-time optical cable basic data and optical cable quality standard data to obtain a performance evaluation coefficient; a3: Performing environmental analysis based on the real-time comprehensive environmental data and the comprehensive environmental standard data to obtain a comprehensive environmental assessment coefficient; a4: performing a comprehensive analysis of transmission faults based on the performance evaluation coefficient and the comprehensive environment evaluation coefficient to obtain I optical cable segments marked with suspected transmission faults; Step 2: Analyze the optical cable segment corresponding to the suspected transmission fault mark to obtain the transmission fault level of the corresponding optical cable segment; The method for obtaining the transmission fault level of the corresponding optical cable segment includes: b1: respectively obtaining the real-time transmission characteristic data of the optical cable segments corresponding to the suspected burst transmission fault mark and the suspected minor transmission fault mark; the real-time transmission characteristic data includes the real-time value of the optical cable temperature, the real-time value of the optical power and the real-time value of the bit error rate; b2: Input the real-time transmission feature data into the trained speed prediction model to predict the corresponding transmission speed; b3: Divide the predicted transmission speed into M transmission fault levels in sequence to obtain the transmission fault level of the corresponding optical cable segment, wherein the transmission fault level includes a first burst fault level, a second burst fault level, a first slight transmission fault level, and a second slight transmission fault level, wherein the first burst fault level>the second burst fault level>the first slight transmission fault level>the second slight transmission fault level; The specific training process of the speed prediction model includes: Pre-collecting Q groups of transmission speeds corresponding to real-time transmission characteristic data, and converting the real-time transmission characteristic data and the corresponding transmission speeds into a corresponding set of characteristic vectors; Each set of feature vectors is used as the input of the speed prediction model. The speed prediction model uses a set of predicted transmission speeds corresponding to each set of real-time transmission feature data as output, and uses the actual transmission speed corresponding to each set of real-time transmission feature data as the prediction target. The actual transmission speed is the transmission speed corresponding to the real-time transmission feature data collected in advance. The training target is to minimize the sum of the prediction errors of all real-time transmission feature data. The calculation formula of the prediction error is: ,in is the prediction error, The group number of the feature vector corresponding to the real-time transmission feature data, For the The predicted transmission speed corresponding to the real-time transmission characteristic data of the group, For the The actual transmission speed corresponding to the real-time transmission characteristic data of the group is obtained; the speed prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped; the speed prediction model is a deep neural network model; Step 3: Using the pre-built transmission fault analysis digital twin model, simulate and analyze the real-time optical cable performance data to generate simulation prediction data; The method of simulating and analyzing the real-time optical cable performance data using the pre-built transmission fault analysis digital twin model includes: Inputting the real-time optical cable performance data into the transmission fault analysis digital twin model for simulation to obtain an optical cable simulation image; Perform image processing on the optical cable simulation image, and use the pre-built convolutional neural network (CNN) to extract features from the processed optical cable simulation image to generate simulation prediction data; Step 4: taking the real-time optical cable performance data and the transmission fault level as a real-time sample set, and taking the real-time optical cable performance data and the simulation prediction data as a simulation sample set; constructing and training a transmission fault prediction model based on the real-time sample set and the simulation sample set; Step 5: Use the trained transmission fault prediction model to perform prediction analysis on the optical cable line to obtain a transmission fault prediction result; the transmission fault prediction result includes whether a transmission fault occurs during the prediction period and whether a transmission fault does not occur during the prediction period.

2. The optical cable intelligent monitoring method based on digital twin according to claim 1 is characterized in that: The method for performing optical cable analysis and processing based on the real-time optical cable basic data and optical cable quality standard data comprises: The attenuation coefficient real-time value and the attenuation coefficient standard value are calculated by formulating to calculate the attenuation evaluation coefficient ; The dispersion real-time value and the dispersion standard value are calculated by formulating to calculate the dispersion evaluation coefficient ; The real-time value of the microbending loss and the standard value of the microbending loss are calculated by formulating to calculate the microbending loss evaluation coefficient. ; Based on the attenuation evaluation coefficient , dispersion evaluation coefficient and microbending loss evaluation coefficient Calculate the performance evaluation coefficient.

3. The optical cable intelligent monitoring method based on digital twin according to claim 2 is characterized in that: The method for performing environmental analysis based on the real-time integrated environmental data and the integrated environmental standard data includes: The rainfall prediction value and the rainfall standard value are calculated by formulating to calculate the rainfall assessment coefficient ; The rainfall duration prediction value and the rainfall duration standard value are calculated by formulating to calculate the rainfall duration evaluation coefficient. ; The electromagnetic interference prediction value and the electromagnetic interference standard value are calculated by formulating to calculate the interference assessment coefficient ; Based on the rainfall assessment factor , Rainfall duration assessment coefficient and interference assessment coefficient Calculate the comprehensive environmental assessment coefficient; The method for comprehensive analysis of transmission failures based on the performance evaluation coefficient and the comprehensive environment evaluation coefficient includes: Calculating an optical cable evaluation coefficient based on the performance evaluation coefficient and the comprehensive environmental evaluation coefficient; A first evaluation threshold is preset, and the optical cable evaluation coefficient is compared with the preset first evaluation threshold to obtain a transmission fault evaluation result; the transmission fault evaluation result obtained includes a suspected burst transmission fault mark, a suspected minor transmission fault mark, and a no transmission fault mark, and the number of optical cable segments with suspected burst transmission fault marks and suspected minor transmission fault marks is counted, and I optical cable segments are screened out.

4. The optical cable intelligent monitoring method based on digital twin according to claim 3 is characterized in that: A method for presetting a first evaluation threshold and comparing the optical cable evaluation coefficient with the preset first evaluation threshold comprises: Preset the first evaluation threshold and , comparing the optical cable evaluation coefficient with a preset first evaluation threshold; wherein < ; If the optical cable evaluation coefficient is greater than or equal to a preset first evaluation threshold , then the corresponding optical cable segment is marked as a suspected burst transmission fault mark; If the optical cable evaluation coefficient is less than a preset first evaluation threshold , and is greater than the preset first evaluation threshold , then the corresponding optical cable segment is marked as a suspected minor transmission fault mark; If the optical cable evaluation coefficient is less than or equal to a preset first evaluation threshold , the corresponding optical cable segment is marked as having no transmission fault mark.

5. The optical cable intelligent monitoring method based on digital twin according to claim 4 is characterized in that: The method of dividing the predicted transmission speed into M transmission fault levels in sequence and obtaining the transmission fault level of the corresponding optical cable segment includes: c1: Get the transmission speed of the i-th optical cable segment; i=1, 2, ..., I; c2: setting F transmission speed intervals and setting M transmission fault levels corresponding to the F transmission speed intervals; Each of the transmission speed intervals has and only has one transmission failure level associated and bound thereto; c3: Compare the transmission speed of the i-th optical cable segment with each transmission speed interval to obtain the transmission speed interval into which the transmission speed of the i-th optical cable segment falls; c4: classify the i-th optical cable segment into a corresponding transmission fault level according to the transmission speed interval into which the transmission speed of the i-th optical cable segment falls; and set i=i+1, and jump back to step c1; c5: Repeat the above steps c1 to c4 until the loop ends when i=I, so that each of the optical cable segments is divided into M transmission fault levels in turn, where I is the total number of optical cable segments.

6. The optical cable intelligent monitoring method based on digital twin according to claim 5 is characterized in that: The method for constructing and training a transmission fault prediction model based on the real-time sample set and the simulation sample set includes: The real-time sample set and the simulated sample set are divided into a 70% transmission fault training set and a 30% transmission fault test set; Constructing a recurrent neural model, inputting the transmission fault training set as input data into the recurrent neural model for training, and optimizing the model using a cross entropy loss function; The trained recurrent neural model is verified using the transmission fault test set to output a recurrent neural model that meets a preset accuracy as a transmission fault prediction model, wherein the recurrent neural model is an RNN.

7. The optical cable intelligent monitoring method based on digital twin according to claim 6 is characterized in that: The method of using the trained transmission fault prediction model to perform predictive analysis on the optical cable line includes: directly inputting the real-time optical cable performance data of the nth optical cable segment into the transmission fault prediction model to obtain a transmission fault prediction result; Or analyze and simulate the real-time optical cable performance data of the nth optical cable segment to obtain the transmission fault level and simulation prediction data of the optical cable line; The transmission fault level or simulation prediction data is input into the transmission fault prediction model to obtain a transmission fault prediction result.

8. An optical cable intelligent monitoring system based on digital twin, used to implement the optical cable intelligent monitoring method based on digital twin according to any one of claims 1 to 7, characterized in that: include: An optical cable marking module, used to collect real-time optical cable performance data of N optical cable segments, and screen out I optical cable segment with suspected transmission fault mark based on the real-time optical cable performance data; The suspected transmission fault mark includes a suspected burst transmission fault mark and a suspected minor transmission fault mark; The real-time optical cable performance data includes real-time optical cable basic data and real-time comprehensive environmental data; the real-time optical cable basic data includes real-time value of attenuation coefficient, real-time value of dispersion and real-time value of microbending loss; the real-time comprehensive environmental data includes predicted value of rainfall, predicted value of rainfall duration and predicted value of electromagnetic interference; The method for screening out the optical cable line segments suspected of burst transmission fault marks and suspected of slight transmission fault marks based on the real-time optical cable performance data comprises: a1: Obtaining the experimental optical cable standard data of the nth optical cable segment; n=1, 2, ..., N; N is the number of optical cable segments; the experimental optical cable standard data includes optical cable quality standard data and comprehensive environmental standard data; the optical cable quality standard data includes attenuation coefficient standard value, dispersion standard value and microbending loss standard value; the comprehensive environmental standard data includes rainfall standard value, rainfall duration standard value and electromagnetic interference standard value; a2: performing optical cable analysis and processing based on the real-time optical cable basic data and optical cable quality standard data to obtain a performance evaluation coefficient; a3: Performing environmental analysis based on the real-time comprehensive environmental data and the comprehensive environmental standard data to obtain a comprehensive environmental assessment coefficient; a4: performing a comprehensive analysis of transmission faults based on the performance evaluation coefficient and the comprehensive environment evaluation coefficient to obtain I optical cable segments marked with suspected transmission faults; An optical cable analysis module, used to analyze the optical cable segment corresponding to the suspected transmission fault mark to obtain the transmission fault level of the corresponding optical cable segment; The method for obtaining the transmission fault level of the corresponding optical cable segment includes: b1: respectively obtaining the real-time transmission characteristic data of the optical cable segments corresponding to the suspected burst transmission fault mark and the suspected minor transmission fault mark; the real-time transmission characteristic data includes the real-time value of the optical cable temperature, the real-time value of the optical power and the real-time value of the bit error rate; b2: Input the real-time transmission feature data into the trained speed prediction model to predict the corresponding transmission speed; b3: Divide the predicted transmission speed into M transmission fault levels in sequence to obtain the transmission fault level of the corresponding optical cable segment, wherein the transmission fault level includes a first burst fault level, a second burst fault level, a first slight transmission fault level, and a second slight transmission fault level, wherein the first burst fault level>the second burst fault level>the first slight transmission fault level>the second slight transmission fault level; The specific training process of the speed prediction model includes: Pre-collecting Q groups of transmission speeds corresponding to real-time transmission characteristic data, and converting the real-time transmission characteristic data and the corresponding transmission speeds into a corresponding set of characteristic vectors; Each set of feature vectors is used as the input of the speed prediction model. The speed prediction model uses a set of predicted transmission speeds corresponding to each set of real-time transmission feature data as output, and uses the actual transmission speed corresponding to each set of real-time transmission feature data as the prediction target. The actual transmission speed is the transmission speed corresponding to the real-time transmission feature data collected in advance. The training target is to minimize the sum of the prediction errors of all real-time transmission feature data. The calculation formula of the prediction error is: ,in is the prediction error, The group number of the feature vector corresponding to the real-time transmission feature data, For the The predicted transmission speed corresponding to the real-time transmission characteristic data of the group, For the The actual transmission speed corresponding to the real-time transmission characteristic data of the group is obtained; the speed prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped; the speed prediction model is a deep neural network model; The optical cable simulation module uses a pre-built transmission fault analysis digital twin model to simulate and analyze the real-time optical cable performance data to generate simulation prediction data; The method of simulating and analyzing the real-time optical cable performance data using the pre-built transmission fault analysis digital twin model includes: Inputting the real-time optical cable performance data into the transmission fault analysis digital twin model for simulation to obtain an optical cable simulation image; Perform image processing on the optical cable simulation image, and use the pre-built convolutional neural network (CNN) to extract features from the processed optical cable simulation image to generate simulation prediction data; A model training module is used to use the real-time optical cable performance data and the transmission fault level as a real-time sample set, and use the real-time optical cable performance data and the simulation prediction data as a simulation sample set; and to construct and train a transmission fault prediction model based on the real-time sample set and the simulation sample set; The model prediction module uses the trained transmission fault prediction model to perform prediction analysis on the optical cable line to obtain a transmission fault prediction result; the transmission fault prediction result includes the occurrence of transmission faults in the prediction period and the non-occurrence of transmission faults in the prediction period.

Images