Optical fiber longitudinal power anomaly detection method and device, equipment and storage medium

Abstract

The invention relates to an optical fiber longitudinal power anomaly detection method and device, equipment and a storage medium. The method comprises the following steps: acquiring input optical power data of an input end of an optical fiber and actual output optical power data of an output end of the optical fiber; inputting the input optical power data into an optical power evolution physical model, and obtaining predicted output optical power data through optical power attenuation parameters of different positions of an optical fiber in the optical power evolution physical model; based on the difference between the actual output optical power data and the predicted output optical power data, using an artificial intelligence optimizer to optimize each optical power attenuation parameter until the difference satisfies a first preset condition; and obtaining a longitudinal power anomaly detection result of the optical fiber according to each optimized optical power attenuation parameter. By adopting the method, the efficiency and precision of optical fiber longitudinal power anomaly detection can be improved, and the detection cost is saved.

Description

Technical Field

[0001] This application relates to the field of communication network technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for detecting longitudinal power anomalies in optical fibers. Background Technology

[0002] With the development of network communication technology, fiber optic lines are becoming increasingly widespread. Fiber optic lines have long signal transmission distances, and due to environmental changes, construction, and other factors, longitudinal power anomalies may occur at certain locations along the fiber optic line. Therefore, accurately identifying and locating such anomalies is a crucial aspect of fiber optic line operation and maintenance.

[0003] In related technologies, physical devices (such as optical time domain reflectometers) are used to detect the location of optical power anomalies in optical fibers. However, this method relies on additional physical equipment, which is not only costly, slow in response, and low in accuracy, but also affects the normally transmitted optical signal because it requires intervention in the optical fiber for detection. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, equipment, and storage medium for detecting longitudinal power anomalies in optical fibers that can improve the detection efficiency and save detection costs, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for detecting longitudinal power anomalies in optical fibers, including:

[0006] Obtain the input optical power data at the input end of the optical fiber and the actual output optical power data at the output end of the optical fiber;

[0007] The input optical power data is input into the optical power evolution physical model, and the predicted output optical power data is obtained through the optical power attenuation parameters at different positions of the optical fiber in the optical power evolution physical model.

[0008] Based on the difference between the actual output optical power data and the predicted output optical power data, an artificial intelligence optimizer is used to optimize each of the optical power attenuation parameters until the difference meets the first preset condition.

[0009] Based on the optimized optical power attenuation parameters, the longitudinal power anomaly detection results of the optical fiber are obtained.

[0010] In one embodiment, optimizing each of the optical power attenuation parameters using an artificial intelligence optimizer until the difference meets a first preset condition includes:

[0011] If the difference does not meet the first preset condition, the artificial intelligence optimizer is used to optimize each of the optical power attenuation parameters to obtain a new physical model of optical power evolution.

[0012] Return to the step of inputting the input optical power data into the optical power evolution physical model until the difference meets the first preset condition, and use each optical power attenuation parameter in the optical power evolution physical model as the optimized optical power attenuation parameter.

[0013] In one embodiment, when the difference does not meet the first preset condition, optimizing each of the optical power attenuation parameters using the artificial intelligence optimizer includes:

[0014] Based on the aforementioned differences, an optical power difference index value is constructed;

[0015] Using the artificial intelligence optimizer, with the goal of minimizing the optical power difference index value, each of the optical power attenuation parameters is optimized.

[0016] In one embodiment, the optical power evolution physical model characterizes the derivative relationship between the optical power of the optical fiber and different positions. The step of inputting the input optical power data into the optical power evolution physical model and obtaining predicted output optical power data through the optical power attenuation parameters at different positions of the optical fiber in the optical power evolution physical model includes:

[0017] Obtain the Raman gain coefficient and effective area of ​​the optical fiber;

[0018] The input optical power data is used as the initial input to the optical power evolution physical model, and the derivative relationship is iteratively solved using the Raman gain coefficient, the effective area of ​​the optical fiber, and the optical power attenuation parameters at different positions of the optical fiber until the predicted output optical power data is obtained.

[0019] In one embodiment, the method further includes:

[0020] When the optical power attenuation parameters at different locations of the optical fiber do not have initial values, the attribute information of the optical fiber is obtained, and the initial values ​​of the optical power attenuation parameters at different locations of the optical fiber are determined based on the attribute information.

[0021] In one embodiment, obtaining the longitudinal power anomaly detection result of the optical fiber based on the optimized optical power attenuation parameters includes:

[0022] Based on the optimized optical power attenuation parameters, the target optical power data of the optical fiber at different locations are determined.

[0023] If any of the target optical power data does not meet the second preset condition, obtain the location information of the position corresponding to the target optical power data, and the optical power abnormal loss information corresponding to the target optical power data;

[0024] Based on the location information and the optical power anomaly loss information, the longitudinal power anomaly detection result is output.

[0025] Secondly, this application also provides an optical fiber longitudinal power anomaly detection device, comprising:

[0026] The optical power acquisition module is used to acquire the input optical power data at the input end of the optical fiber and the actual output optical power data at the output end of the optical fiber.

[0027] The optical power prediction module is used to input the input optical power data into the optical power evolution physical model, and obtain the predicted output optical power data through the optical power attenuation parameters at different positions of the optical fiber in the optical power evolution physical model.

[0028] The optical power attenuation parameter optimization module is used to optimize each of the optical power attenuation parameters using an artificial intelligence optimizer based on the difference between the actual output optical power data and the predicted output optical power data, until the difference meets a first preset condition.

[0029] The longitudinal power anomaly detection result output module is used to obtain the longitudinal power anomaly detection result of the optical fiber based on the optimized optical power attenuation parameters.

[0030] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described fiber longitudinal power anomaly detection method.

[0031] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described fiber longitudinal power anomaly detection method.

[0032] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described fiber longitudinal power anomaly detection method.

[0033] The aforementioned fiber longitudinal power anomaly detection method, apparatus, device, and storage medium simulate the evolution of optical power during optical signal transmission by inputting input optical power data into an optical power evolution physical model and using optical power attenuation parameters at different locations in the optical fiber within the model. This yields predicted output optical power data, providing a reliable foundation for fiber longitudinal power anomaly detection without the need for additional physical equipment, thus saving detection costs. Furthermore, based on the difference between the actual output optical power data and the predicted output optical power data, the high processing speed and computational accuracy of an artificial intelligence optimizer are utilized to optimize each optical power attenuation parameter. This not only improves the efficiency of anomaly detection but also ensures that the optimized optical power attenuation parameters accurately reflect the optical power attenuation at each location. Consequently, high-precision and high-reliability longitudinal power anomaly detection results are obtained based on the optimized optical power attenuation parameters. Moreover, fiber longitudinal power anomaly detection can be completed using only the input optical power data at the fiber input end and the actual output optical power data at the output end, without requiring intervention in the optical fiber. This does not affect the normally transmitted optical signal, thereby ensuring the stability of optical fiber transmission. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating the steps of an optical fiber longitudinal power anomaly detection method according to an embodiment of this application;

[0036] Figure 2 This is a schematic diagram of the optical power data processing process;

[0037] Figure 3 A schematic diagram illustrating the process of optimizing optical power attenuation parameters;

[0038] Figure 4 This is a flowchart illustrating the operation of an optical fiber longitudinal power anomaly detection system according to an embodiment of this application.

[0039] Figure 5 This is a structural block diagram of an optical fiber longitudinal power anomaly detection device provided in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0042] It should be noted that the terms "comprising" and "having," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusion. The term "multiple" as used in this application refers to two or more. The term "and / or" as used in this application refers to one of the solutions, or any combination of multiple solutions.

[0043] Currently, optical networks are growing in scale and their interweaving with urban, highway, and railway networks is becoming increasingly dense. Due to factors such as environmental changes, construction, natural disasters, and fiber optic aging, faults such as abnormal fiber attenuation, degraded transmission performance, and even service interruptions occur frequently. Accurately analyzing fiber power evolution and locating the location of anomalies is one of the most important components of an intelligent optical network operation and maintenance system.

[0044] In one related technology, the method of locating fiber optic anomalies based on an optical time-domain reflectometer (OTDR) introduces additional hardware costs, and as the network scales up, the response time becomes longer and the accuracy decreases. Furthermore, the OTDR detection signal can also affect the normally transmitted optical signal, causing a temporary degradation in optical transmission performance. Therefore, this method of detecting fiber power anomalies faces limitations such as high cost, slow response, low accuracy, and interference with normal transmission signals, making it difficult to meet the operation and maintenance requirements of next-generation intelligent optical network systems.

[0045] Based on the optical power evolution physical model and artificial intelligence technology, this application proposes a method, device, equipment, and storage medium for detecting longitudinal power anomalies in optical fibers. By analyzing and identifying longitudinal power anomalies in optical fibers through the optical power evolution physical model, and by using an artificial intelligence optimizer to accelerate the search for the global optimal solution of the optical power attenuation parameter in the optical power evolution physical model, this application achieves low-cost, interpretable, high-precision, high-efficiency, and highly available detection of longitudinal power anomalies in optical fibers without the need for additional hardware equipment or without affecting normal signal transmission.

[0046] In one embodiment, such as Figure 1 As shown, a method for detecting longitudinal power anomalies in optical fibers is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0047] Step 101: Obtain the input optical power data at the input end of the optical fiber and the actual output optical power data at the output end of the optical fiber;

[0048] In practice, the input optical power data and the actual output optical power data can be obtained through direct measurement, for example, by acquiring them through an optical channel monitor; or they can be obtained through indirect calculation.

[0049] In some examples, optical power data can specifically be optical power spectrum data, that is, the optical power of the optical fiber in different channels. Here, different channels of the optical fiber correspond to different frequencies.

[0050] Step 102: Input the input optical power data into the optical power evolution physical model, and obtain the predicted output optical power data through the optical power attenuation parameters at different positions of the optical fiber in the optical power evolution physical model;

[0051] An optical power evolution physical model is a model that reflects the physical laws governing the change in optical power during optical signal transmission in an optical fiber. It simulates the attenuation of optical power as transmission distance increases, thereby pinpointing the location of abnormal attenuation. The optical power attenuation parameters at different locations within the optical power evolution physical model reflect the attenuation situation at those locations.

[0052] In practical implementation, the input end of the optical fiber is the starting position for transmitting optical signals, and the output end is the ending position. By inputting the input optical power data into the optical power evolution physical model, the physical change in optical power from the starting position to the ending position is simulated using the optical power attenuation parameters at various positions of the optical fiber, thus obtaining the predicted output optical power data. The more accurate the values ​​of the optical power attenuation parameters at each position, the closer the predicted output optical power data is to the actual situation. Therefore, it is necessary to optimize the optical power attenuation parameters.

[0053] In some examples, such as Figure 2 As shown, the position of the optical fiber at different transmission distances is zi, and the optical power attenuation parameter at each position is a(zi). The input optical power spectrum and the actual output optical power spectrum were collected at the input and output ends of the optical fiber, respectively. By comparing the graphs of the input optical power spectrum and the actual output optical power spectrum, it can be seen that the L-band and C-band of the output end of the optical fiber have significant optical power attenuation. This is due to the abnormal optical power loss of 2dB at the position of 40km.

[0054] Furthermore, the input optical power spectrum, i.e., the input optical power data, is input into the optical power evolution physical model. Using the optical power attenuation parameters at different locations in the optical fiber within the model, the predicted output optical power spectrum, i.e., the predicted output optical power data, is obtained. Comparing the predicted and actual output optical power spectra reveals a discrepancy between the prediction and the actual situation. Therefore, subsequent optimization of the optical power attenuation parameters is needed based on this discrepancy to more accurately pinpoint the actual longitudinal power anomaly occurring at 40km.

[0055] In practical applications, the initial value of the optical power attenuation parameter can be a predefined value, such as a preset value calibrated through experiments.

[0056] In some embodiments, the method further includes:

[0057] When the optical power attenuation parameters at different locations of the optical fiber do not have initial values, the attribute information of the optical fiber is obtained, and the initial values ​​of the optical power attenuation parameters at different locations of the optical fiber are determined based on the attribute information.

[0058] In practical implementation, different types of optical fibers may exhibit varying degrees of optical power attenuation at the same distance. Therefore, when initial values ​​for each optical power attenuation parameter are not available, their initial values ​​can be determined using attribute information. This simulates the optical power attenuation under normal conditions and serves as the starting point for optimizing each parameter. Specifically, attribute information can include the fiber's type, material, and geometric dimensions. By obtaining this attribute information, pre-stored initial values ​​for the optical power attenuation parameters at various locations within the fiber can be obtained. For example, typical attenuation values ​​measured or calibrated for the same type of optical fiber can be obtained through experiments.

[0059] In this embodiment, the initial values ​​of optical power attenuation parameters at different locations of the optical fiber are determined by the attribute information of the optical fiber, providing a more accurate and realistic starting point for optimizing each optical power attenuation parameter. This can shorten the optimization process of the optical power attenuation parameters and thus improve the overall detection efficiency of optical fiber longitudinal power anomaly detection.

[0060] Step 103: Based on the difference between the actual output optical power data and the predicted output optical power data, optimize each of the optical power attenuation parameters using an artificial intelligence optimizer until the difference meets the first preset condition.

[0061] An AI optimizer is an optimization tool that uses artificial intelligence technologies such as machine learning and deep learning to improve model performance by adjusting model parameters. Examples of AI optimizers include backpropagation and gradient descent algorithms.

[0062] In practical implementation, comparing the difference between the actual output optical power data and the predicted output optical power data provides guidance for the optimization of the AI ​​optimizer. The AI ​​optimizer then optimizes various optical power attenuation parameters, making their values ​​more accurate, and further optimizes the optical power evolution model until the difference meets a first preset condition. Specifically, the difference can be in the form of numerical values, graphs, etc., such as numerical index differences or graphical comparison differences. When the difference is a numerical index difference, the first preset condition can be that the numerical index difference meets a certain preset range, or that the numerical index difference is less than or equal to a preset difference threshold. When the difference is a graphical comparison difference, the first preset condition can be that the graphical comparison difference meets a preset graphical similarity.

[0063] In some embodiments, optimizing each of the optical power attenuation parameters using an artificial intelligence optimizer until the difference meets a first preset condition includes:

[0064] If the difference does not meet the first preset condition, the artificial intelligence optimizer is used to optimize each of the optical power attenuation parameters to obtain a new physical model of optical power evolution.

[0065] Return to the step of inputting the input optical power data into the optical power evolution physical model until the difference meets the first preset condition, and use each optical power attenuation parameter in the optical power evolution physical model as the optimized optical power attenuation parameter.

[0066] In practical implementation, if the difference does not meet the first preset condition, an artificial intelligence optimizer can be used to iteratively optimize each optical power attenuation parameter multiple times to update the optical power evolution physical model multiple times. After each iteration update of the optical power evolution physical model, the input optical power data is used to input the new optical power evolution physical model again to obtain new predicted output optical power data. The new predicted output optical power data is compared with the actual output optical power data to obtain new differences. If the new differences still do not meet the first preset condition, the above process is repeated until the differences meet the first preset condition, indicating that the optical power evolution physical model has been iteratively updated. Then, each optical power attenuation parameter in the updated optical power evolution physical model is used as the optimized optical power attenuation parameter to obtain the target value of each optical power attenuation parameter.

[0067] In some examples, such as Figure 3 As shown, through multiple iterations and optimizations of the physical model of optical power evolution, it can be seen that the optical power attenuation parameters optimized from step 1 to step n-1 gradually approach [the desired level]. Figure 2 The actual optical power attenuation at each location shown, and the predicted output optical power spectrum obtained using the updated optical power evolution physical model, gradually approach the actual optical power attenuation. Figure 2 The actual output optical power spectrum is shown.

[0068] After the nth optimization, the difference between the actual output optical power data and the predicted output optical power data meets the first preset condition, and the optical power evolution physical model is optimized. The optical power attenuation parameters in the optical power evolution physical model are then used as the optimized optical power attenuation parameters. The fitted output optical power spectrum output by the optimized optical power evolution physical model is closer to the actual output optical power spectrum, and the accuracy meets expectations.

[0069] In this embodiment, by updating and optimizing the optical power evolution physical model when the difference does not meet the first preset condition, the optimized optical power attenuation parameters in the optical power evolution physical model can accurately reflect the changes in the longitudinal power of the optical fiber, thereby achieving precise location of the longitudinal power anomaly and obtaining more accurate longitudinal power anomaly detection results.

[0070] In some embodiments, when the difference does not meet the first preset condition, optimizing each of the optical power attenuation parameters using the artificial intelligence optimizer includes:

[0071] Based on the aforementioned differences, an optical power difference index value is constructed;

[0072] Using the artificial intelligence optimizer, with the goal of minimizing the optical power difference index value, each of the optical power attenuation parameters is optimized.

[0073] In the specific implementation, during each round of iterative optimization of each optical power attenuation parameter, the overall index values ​​of the actual output optical power data and the predicted output optical power data, such as the average optical power, can be determined separately. Then, the difference between the overall index values ​​of the actual output optical power data and the predicted output optical power data is determined to obtain the difference between the two, and the optical power difference index value is constructed through this difference.

[0074] Furthermore, an artificial intelligence optimizer is used to optimize each optical power attenuation parameter with the goal of minimizing the optical power difference index. For example, a loss function is constructed using the optical power difference index, and the optimization objective is to minimize the function value of the loss function. The artificial intelligence optimizer is then used to optimize each optical power attenuation parameter until a preset convergence condition is met, thus completing a single round of optimization iteration for each optical power attenuation parameter.

[0075] After completing the iterative optimization of each optical power attenuation parameter in this round, new predicted output optical power data is obtained through the new optical power evolution physical model. The difference between the actual output optical power data and the predicted output optical power data is re-determined. If the difference does not meet the first preset condition, the next round of iterative optimization of each optical power attenuation parameter is entered.

[0076] In this embodiment, by constructing an optical power difference index value, the difference between predicted optical power data and actual optical power data can be accurately quantified, providing optimization direction for the artificial intelligence optimizer, shortening the optimization process for each optical power attenuation parameter, and further improving the detection efficiency of optical fiber longitudinal power anomaly detection.

[0077] In some embodiments, the optical power evolution physical model characterizes the derivative relationship between the optical power of the optical fiber and different positions. The step of inputting the input optical power data into the optical power evolution physical model and obtaining the predicted output optical power data through the optical power attenuation parameters at different positions of the optical fiber in the optical power evolution physical model includes:

[0078] Obtain the Raman gain coefficient and effective area of ​​the optical fiber;

[0079] The input optical power data is used as the initial input to the optical power evolution physical model, and the derivative relationship is iteratively solved using the Raman gain coefficient, the effective area of ​​the optical fiber, and the optical power attenuation parameters at different positions of the optical fiber until the predicted output optical power data is obtained.

[0080] Raman gain coefficient is a physical parameter describing the strength of stimulated Raman scattering in optical fiber, and is usually related to the properties of the optical fiber itself (such as material); the effective area of ​​an optical fiber refers to the cross-sectional area of ​​the optical fiber actually occupied when the optical signal propagates in the optical fiber.

[0081] In practical applications, the Raman gain coefficient of the optical fiber can be pre-calibrated and stored, and can be directly obtained when needed; the effective area of ​​the optical fiber can be obtained by combining the wavelength of the optical signal transmitted by the optical fiber with the total cross-sectional area of ​​the optical fiber.

[0082] In practical implementation, the physical model of optical power evolution characterizes the relationship between the optical power of the optical fiber and the derivative at different locations as shown in the following equation (1):

[0083] (1)

[0084] in, For the i-th position Optical power attenuation parameters, For the nth channel of the optical fiber optical power, For the m-th channel of the optical fiber optical power, This represents the Raman gain coefficient corresponding to the frequency difference between the m-th and n-th channels in the optical fiber. This represents the effective area of ​​the optical fiber.

[0085] Let the fiber optic input end be the starting position. The input optical power data at the fiber input end is used as the initial input to the optical power evolution physical model. The input optical power data can include the fiber's position... The optical power corresponding to different channels is substituted into equation (1) for solution; based on the next position of the input end Optical power attenuation parameters The Raman gain coefficient and effective area of ​​the optical fiber are used to determine the optical fiber's position using the derived derivative relationship. Optical power data; then use Substitute the optical power data back into equation (1) to solve for the next position. Using the derivative relationship obtained after solving, the next position can be calculated. The optical power data. Similarly, Equation (1) is iteratively solved until the end position is obtained, that is, the predicted optical power data at the output end of the optical fiber.

[0086] In this embodiment, the nonlinear effect of the optical fiber is reflected by the Raman gain coefficient and the effective area of ​​the optical fiber. The nonlinear effect is actively used in combination with the optical power attenuation parameter to iteratively solve the derivative relationship characterized by the physical model of optical power evolution, so as to simulate the optical power evolution of the optical fiber until the predicted output optical power data is obtained. This realizes the full utilization of the physical characteristics of the optical fiber and reduces the resource cost of anomaly detection.

[0087] Step 104: Based on the optimized optical power attenuation parameters, obtain the longitudinal power anomaly detection result of the optical fiber.

[0088] In practical implementation, based on the optimized optical power attenuation parameters, the optical power attenuation at each location of the optical fiber can be determined, thereby determining whether there is an optical power anomaly at each location. If an optical power anomaly is found at a location, a longitudinal power anomaly detection result indicating an abnormality in the longitudinal power of the optical fiber can be output; if no optical power anomaly is found at a location, a longitudinal power anomaly detection result indicating that the longitudinal power of the optical fiber is normal can be output.

[0089] In practical applications, if the longitudinal power anomaly detection result of the optical fiber indicates that the optical fiber has an anomaly, corresponding operation and maintenance strategies and operation and maintenance work orders can be generated for the anomaly, and operation and maintenance personnel can be reminded to handle the anomaly in a timely manner.

[0090] In some embodiments, obtaining the longitudinal power anomaly detection result of the optical fiber based on the optimized optical power attenuation parameters includes:

[0091] Based on the optimized optical power attenuation parameters, the target optical power data of the optical fiber at different locations are determined.

[0092] If any of the target optical power data does not meet the second preset condition, obtain the location information of the position corresponding to the target optical power data, and the optical power abnormal loss information corresponding to the target optical power data;

[0093] Based on the location information and the optical power anomaly loss information, the longitudinal power anomaly detection result is output.

[0094] In the specific implementation, the input optical power data is used as the initial input to the optical power evolution physical model. Based on the optimized optical power attenuation parameters in the optical power evolution physical model, the evolution of the optical fiber during optical signal transmission is simulated to determine the target optical power data at each location. Because the optical power attenuation parameters are optimized by an artificial intelligence optimizer, the obtained target optical power data is more accurate and closer to the actual situation.

[0095] The second preset condition can be a logical judgment condition based on the target optical power data to determine whether an optical power anomaly has occurred at the corresponding location. For example, it can determine whether the target optical power data conforms to a preset optical power range.

[0096] If any target optical power data fails to meet the second preset condition, it indicates that the corresponding location is an abnormal location where optical power anomalies have occurred. The location information of the abnormal location and the optical power anomaly loss information corresponding to the target optical power data are then acquired. Based on the location information and the optical power anomaly loss information, a longitudinal power anomaly detection result is output, incorporating both location information and optical power anomaly loss information into the longitudinal power anomaly detection result. Location information can be coordinate information, distance information, etc., such as the geographical coordinates of the abnormal location, the distance between the abnormal location and the fiber optic input end, etc. This location information allows for accurate localization of the abnormal location. Optical power anomaly loss information can include various specific information related to optical power anomaly loss. For example, when the target optical power data is optical power spectrum data, the optical power anomaly loss information can include the optical power and optical power loss values ​​of each channel of the optical fiber at the abnormal location. This optical power anomaly loss information reflects the specific circumstances of the optical power anomaly occurring at the abnormal location.

[0097] In practical applications, corresponding operation and maintenance strategies and work orders can be generated based on location information and abnormal optical power loss information, and operation and maintenance personnel can be reminded to handle anomalies in a timely manner, so as to facilitate the operation and maintenance personnel to follow up and maintain the fiber optic anomalies.

[0098] In this embodiment, the longitudinal power anomaly detection result is output by using location information and optical power anomaly loss information. This allows maintenance personnel to quickly locate the abnormal position of the optical fiber and the specific details of the abnormal position, providing reliable support for optical fiber maintenance work.

[0099] In some embodiments, such as Figure 4 As shown, a fiber longitudinal power anomaly detection system is also provided. The process of performing the fiber longitudinal power anomaly detection method through this system is as follows:

[0100] S1: In the data acquisition module, optical power spectrum data of the optical fiber input and output ends are acquired through the optical channel monitor and stored in the database.

[0101] S2: In the model calculation module, the collected input optical power spectrum is substituted into the optical power evolution physical model. The optical power attenuation parameters at each location in the optical power evolution physical model, i.e., the loss at each location, are preset to the typical loss values ​​of the optical fiber used. The output optical power spectrum of the optical fiber under normal conditions is calculated using numerical methods to obtain the predicted output optical power spectrum. Specifically, the optical power evolution physical model can be the channel power evolution physical model of a wavelength division multiplexing system.

[0102] S3: In the loss optimization module, the predicted output optical power spectrum is compared with the actual optical power spectrum, and a loss function is constructed based on the difference. Using an AI optimizer, the optical power attenuation parameters in the optical power evolution physical model are optimized and adjusted, and the predicted output optical power spectrum of the fiber under loss conditions is recalculated using the optical power evolution physical model.

[0103] S4: In the loss optimization module, repeat S3 multiple times until the error between the predicted output optical power spectrum and the actual optical power spectrum is less than a preset error threshold. At this point, the loss at each location obtained after multiple optimizations can accurately reflect the evolution of the longitudinal power of the optical fiber.

[0104] S5: In the analysis and processing module, further analyze the final loss values ​​at each location and obtain the optical power evolution of the optical fiber. Then, analyze the location of the longitudinal power anomaly and the magnitude of the abnormal loss value to obtain the longitudinal power anomaly information of the optical fiber.

[0105] S6: In the analysis and processing module, based on the fiber longitudinal power anomaly information determined in S5, corresponding operation and maintenance strategies and operation and maintenance work orders are generated, and operation and maintenance personnel are reminded to handle the anomalies in a timely manner.

[0106] In this embodiment, compared with the fiber longitudinal power anomaly detection method of related technologies, it has the following advantages:

[0107] 1. Low cost. A related fiber optic power anomaly localization method requires additional hardware such as an optical time-domain reflectometer for measurement, resulting in additional hardware procurement costs. In contrast, this embodiment only requires the optical channel monitor integrated into the optical module, eliminating the need for additional hardware for data acquisition and reducing anomaly detection costs.

[0108] 2. Explainability. One related technology is a "black box" fiber optic anomaly detection scheme based on deep learning, which establishes a mapping from input features to anomaly information by fitting data. In contrast, this embodiment is based on a physical model of optical power evolution, which is physically explainable. The anomaly detection process is completely transparent, and the physical meaning of each step can be clearly understood.

[0109] 3. High accuracy. Related technologies based on optical time-domain reflectometers for fiber optic power anomaly localization experience decreased accuracy as network scale increases. This embodiment follows the mathematical evolution laws in the optical power physical evolution model and optimizes model parameters using an artificial intelligence optimizer, enabling accurate fiber optic anomaly localization and determination of anomaly loss levels.

[0110] 4. High efficiency. Existing fiber optic power anomaly localization methods have long response times for longer fiber optic links. This embodiment employs an artificial intelligence optimizer, which can be hardware-accelerated using a Graphics Processing Unit (GPU), and requires less data, enabling second-level anomaly power detection.

[0111] 5. High availability. In this embodiment, it can be applied to the detection of longitudinal power anomalies in optical fibers of different manufacturers, models, and lengths.

[0112] Furthermore, the advantages of this embodiment can also be seen in the following aspects:

[0113] In terms of detection efficiency, related technologies are often designed from a single technical perspective. This embodiment combines physical models and artificial intelligence, making full use of the advantages of each and overcoming their shortcomings to achieve low-cost, interpretable, high-precision, high-efficiency, and highly available fiber longitudinal power anomaly detection.

[0114] Regarding standardized procedures, due to differences in manufacturers, models, and identification tools, there is no clearly standardized procedure for detecting longitudinal power anomalies in optical fibers. This embodiment aims to provide standardized definitions for various aspects, including the functions of each module and the overall system process.

[0115] Regarding the utilization of optical fiber physical properties, in most optical fiber communication systems, the nonlinear effects of optical fibers typically affect signal transmission quality, requiring suppression and compensation. In contrast to this passive suppression and compensation, this embodiment, based on a wavelength division multiplexing (WDM) system channel power evolution physical model, actively utilizes the nonlinear effects of stimulated Raman scattering present in wideband systems. By analyzing the correlation between the power transfer phenomenon caused by this effect and optical fiber loss, the design effectively utilizes the nonlinear effects of optical fibers.

[0116] In terms of operation and maintenance, the existing technologies for fiber optic network maintenance often require manual anomaly analysis, strategy formulation, work order generation, and anomaly handling. This embodiment can automate abnormal power analysis, operation and maintenance strategy and work order generation, and provide anomaly handling alerts, greatly improving the automation capabilities of existing network operation and maintenance.

[0117] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0118] Based on the same inventive concept, this application also provides an optical fiber longitudinal power anomaly detection device for implementing the optical fiber longitudinal power anomaly detection method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the optical fiber longitudinal power anomaly detection device provided below can be found in the limitations of the optical fiber longitudinal power anomaly detection method described above, and will not be repeated here.

[0119] In one exemplary embodiment, such as Figure 5 As shown, a fiber longitudinal power anomaly detection device is provided, comprising:

[0120] The optical power acquisition module 501 is used to acquire the input optical power data at the input end of the optical fiber and the actual output optical power data at the output end of the optical fiber.

[0121] The optical power prediction module 502 is used to input the input optical power data into the optical power evolution physical model, and obtain the predicted output optical power data through the optical power attenuation parameters at different positions of the optical fiber in the optical power evolution physical model.

[0122] The optical power attenuation parameter optimization module 503 is used to optimize each of the optical power attenuation parameters using an artificial intelligence optimizer based on the difference between the actual output optical power data and the predicted output optical power data, until the difference meets a first preset condition.

[0123] The longitudinal power anomaly detection result output module 504 is used to obtain the longitudinal power anomaly detection result of the optical fiber based on the optimized optical power attenuation parameters.

[0124] In some embodiments, the optical power attenuation parameter optimization module 503 includes:

[0125] The model optimization submodule is used to optimize each of the optical power attenuation parameters using the artificial intelligence optimizer when the difference does not meet the first preset condition, so as to obtain a new physical model of optical power evolution.

[0126] The iterative execution submodule is used to return to the step of inputting the input optical power data into the optical power evolution physical model until the difference meets the first preset condition, and then use each optical power attenuation parameter in the optical power evolution physical model as the optimized optical power attenuation parameter.

[0127] In some embodiments, the model optimization submodule includes:

[0128] A difference index value construction unit is used to construct an optical power difference index value based on the difference.

[0129] The parameter optimization unit is used to optimize each of the optical power attenuation parameters by using the artificial intelligence optimizer with the goal of minimizing the optical power difference index value.

[0130] In some embodiments, the optical power evolution physical model characterizes the derivative relationship between the optical power of the optical fiber and different locations, and the optical power prediction module 502 includes:

[0131] The fiber optic information acquisition submodule is used to acquire the Raman gain coefficient and the effective area of ​​the fiber optic cable.

[0132] The optical power prediction submodule is used to take the input optical power data as the initial input of the optical power evolution physical model, and iteratively solve the derivative relationship through the Raman gain coefficient, the effective area of ​​the optical fiber and the optical power attenuation parameters at different positions of the optical fiber until the predicted output optical power data is obtained.

[0133] In some embodiments, the apparatus further includes:

[0134] The parameter initial value determination module is used to obtain the attribute information of the optical fiber when the optical power attenuation parameter at different locations of the optical fiber does not have an initial value, and to determine the initial value of the optical power attenuation parameter at different locations of the optical fiber based on the attribute information.

[0135] In some embodiments, the longitudinal power anomaly detection result output module 504 includes:

[0136] The target optical power data determination submodule is used to determine the target optical power data of the optical fiber at different locations based on the optimized optical power attenuation parameters.

[0137] The loss information determination submodule is used to obtain the location information of the position corresponding to the target optical power data and the optical power abnormal loss information corresponding to the target optical power data when any of the target optical power data does not meet the second preset condition.

[0138] The longitudinal power anomaly detection result output submodule is used to output the longitudinal power anomaly detection result based on the location information and the optical power anomaly loss information.

[0139] Each module in the aforementioned fiber optic longitudinal power anomaly detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0140] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data including, but not limited to, input optical power data and output optical power data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for detecting longitudinal power anomalies in optical fibers.

[0141] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for detecting longitudinal power anomalies in optical fibers. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0142] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0143] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the fiber longitudinal power anomaly detection method described above.

[0144] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the fiber longitudinal power anomaly detection method described above.

[0145] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the fiber longitudinal power anomaly detection method as described above.

[0146] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0147] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0148] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting longitudinal power anomalies in an optical fiber, the method comprising: The method comprises: obtaining input optical power data of an input end of an optical fiber and actual output optical power data of an output end of the optical fiber; inputting the input optical power data into an optical power evolution physical model, and obtaining predicted output optical power data through optical power attenuation parameters of different positions of the optical fiber in the optical power evolution physical model; optimizing each of the optical power attenuation parameters by using an artificial intelligence optimizer based on a difference between the actual output optical power data and the predicted output optical power data until the difference meets a first preset condition; obtaining a longitudinal power anomaly detection result of the optical fiber according to the optimized optical power attenuation parameters.

2. The method of claim 1, wherein, The optimization of each of the optical power attenuation parameters by using the artificial intelligence optimizer until the difference meets the first preset condition comprises: in the case that the difference does not meet the first preset condition, optimizing each of the optical power attenuation parameters by using the artificial intelligence optimizer to obtain a new optical power evolution physical model; returning to the step of inputting the input optical power data into the optical power evolution physical model until the difference meets the first preset condition, and taking each of the optical power attenuation parameters in the optical power evolution physical model as the optimized optical power attenuation parameters.

3. The method of claim 2, wherein, The optimization of each of the optical power attenuation parameters by using the artificial intelligence optimizer in the case that the difference does not meet the first preset condition comprises: constructing an optical power difference index value according to the difference; optimizing each of the optical power attenuation parameters by using the artificial intelligence optimizer with the minimization of the optical power difference index value as an optimization target.

4. The method according to any one of claims 1 to 3, characterized in that, The optical power evolution physical model represents a derivative relationship between optical power and different positions of the optical fiber, and the inputting of the input optical power data into the optical power evolution physical model to obtain predicted output optical power data through the optical power attenuation parameters of different positions of the optical fiber in the optical power evolution physical model comprises: obtaining a Raman gain coefficient and an effective area of the optical fiber corresponding to the optical fiber; taking the input optical power data as initial input of the optical power evolution physical model, and iteratively solving the derivative relationship through the Raman gain coefficient, the effective area of the optical fiber and the optical power attenuation parameters of different positions of the optical fiber until the predicted output optical power data is obtained.

5. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: in the case that the optical power attenuation parameters of different positions of the optical fiber do not have initial values, obtaining attribute information of the optical fiber, and determining initial values of the optical power attenuation parameters of different positions of the optical fiber according to the attribute information.

6. The method according to any one of claims 1 to 3, characterized in that, The obtaining of the longitudinal power anomaly detection result of the optical fiber according to the optimized optical power attenuation parameters comprises: determining target optical power data of the optical fiber at different positions according to the optimized optical power attenuation parameters; in the case that any of the target optical power data does not meet a second preset condition, obtaining position information of a position corresponding to the target optical power data and optical power anomaly loss information corresponding to the target optical power data; According to the position information and the optical power abnormal loss information, the longitudinal power abnormality detection result is output.

7. An optical fiber longitudinal power anomaly detection apparatus, characterized by, The device comprises: An optical power acquisition module is configured to acquire input optical power data of an input end of an optical fiber and actual output optical power data of an output end of the optical fiber; An optical power prediction module is configured to input the input optical power data into an optical power evolution physical model, and obtain predicted output optical power data through optical power attenuation parameters of different positions of the optical fiber in the optical power evolution physical model; An optical power attenuation parameter optimization module is configured to optimize each of the optical power attenuation parameters by using an artificial intelligence optimizer based on a difference between the actual output optical power data and the predicted output optical power data until the difference meets a first preset condition; A longitudinal power abnormality detection result output module is configured to obtain a longitudinal power abnormality detection result of the optical fiber according to each of the optimized optical power attenuation parameters.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images