Optical fiber communication fault diagnosis method and system based on machine learning, and medium
Through machine learning-based fiber communication fault diagnosis method, fiber communication information is extracted and processed, and the fiber communication fault index is calculated, which solves the problem of incomplete fault diagnosis in the existing technology, and realizes efficient and accurate fault detection and rapid troubleshooting. .
Patent Information
- Application Number
- CN202410967012.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing fiber optic communication fault diagnosis technology is too single and lacks a comprehensive fault diagnosis method, which cannot effectively identify the potential relationship between faults, resulting in long troubleshooting and repair time, low accuracy and efficiency.
Using machine learning-based fiber communication fault diagnosis method, by obtaining fiber communication information within the preset time period, extracting optical cable line detection information and transmitting signal monitoring information, and obtaining overtemperature fault data, refractive index deviation data, and attenuation exceeding standard after processing. Data and penetration distortion data are further processed to obtain corresponding indexes. Combined with the optical fiber communication diagnostic model, the optical fiber communication fault index is calculated, and compared with the historical fault index of the same type to determine whether the fault meets the requirements.
It realizes automatic learning and identification of fault patterns from a large amount of data, timely discovering and reporting faults, significantly improving the accuracy and efficiency of fault detection, reducing troubleshooting and repair time, and no need to manually write complex rules or perform cumbersome manual analysis.
Smart Images

Figure CN118921111A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of optical fiber fault diagnosis and big data technology, and more specifically, to an optical fiber communication fault diagnosis method, system and medium based on machine learning. Background Art
[0002] With the rapid development of information technology, fiber-optic communication has become the mainstream technology in the field of modern communications. Its high speed, high bandwidth, low loss, and low interference make fiber-optic communication widely used in data transmission, network communication, and other fields. However, the complexity and scale of fiber-optic communication systems also bring difficulties to fault diagnosis. Any failure in the fiber-optic communication system may have a significant impact on the communication network. Therefore, it is of great significance to perform efficient and accurate fault diagnosis on the fiber-optic communication system.
[0003] The current optical fiber communication fault diagnosis technology uses various professional instruments to conduct targeted detection of the optical fiber's electrical signal, optical signal and optical cable. For example, it can diagnose the optical signal phase, wavelength and intensity in optical fiber communication, and then reflect whether the optical fiber transmission is normal. However, this detection method is too single and lacks a comprehensive fault diagnosis technology and the potential relationship between various faults.
[0004] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention
[0005] The purpose of this application is to provide a method, system and medium for optical fiber communication fault diagnosis based on machine learning. It can obtain optical fiber communication information within a preset time period, extract optical cable line detection information and transmission signal monitoring information, and obtain over-temperature fault data, refractive index deviation data, attenuation excess data and penetration distortion data after processing. After further processing, the over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index can be obtained. Finally, the optical fiber communication diagnosis model is used to process and obtain the optical fiber communication fault index, which is then compared with the historical optical fiber communication fault index of the same type to determine whether the optical fiber communication fault index meets the requirements. This application monitors the temperature, refractive index, attenuation and penetration data that have an important impact on the performance of optical fiber communication, and analyzes the degree of influence of each data on the performance of optical fiber communication.
[0006] The present application provides a method for optical fiber communication fault diagnosis based on machine learning, comprising the following steps:
[0007] Obtaining optical fiber communication information within a preset time period, and extracting optical cable line detection information and transmission signal monitoring information according to the optical fiber communication information;
[0008] Extracting optical cable temperature data and optical fiber refractive index data according to the optical cable line detection information, and extracting optical signal attenuation data and optical signal penetration data according to the transmission signal monitoring information;
[0009] Processing the optical cable temperature data to obtain over-temperature fault data;
[0010] Processing the optical fiber refractive index data to obtain refractive index deviation data;
[0011] Processing the optical signal attenuation data to obtain attenuation exceeding standard data;
[0012] Processing the optical signal transmittance data to obtain transmittance distortion data;
[0013] Extracting over-temperature frequency data and over-temperature degree data according to the over-temperature fault data, extracting refractive index deviation frequency data and refractive index deviation degree data according to the refractive index deviation data, extracting attenuation degree exceeding frequency data and attenuation degree exceeding degree data according to the attenuation degree exceeding data, and extracting penetration distortion frequency data and penetration distortion degree data according to the penetration distortion data;
[0014] Processing the over-temperature frequency data and the over-temperature degree data to obtain an over-temperature fault index, processing the refractive index deviation frequency data and the refractive index deviation degree data to obtain a refractive index deviation index, processing the attenuation exceeding standard frequency data and the attenuation exceeding standard degree data to obtain an attenuation exceeding standard index, and processing the penetration distortion frequency data and the penetration distortion degree data to obtain a penetration distortion index;
[0015] Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model;
[0016] The optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate and the preset fault deviation rate threshold are determined.
[0017] Among them, in the optical fiber communication fault diagnosis method based on machine learning described in the present application, it is characterized in that the processing is performed according to the optical cable temperature data to obtain the over-temperature fault data, specifically:
[0018] Comparing the optical cable temperature data with a preset temperature threshold to obtain a temperature deviation rate;
[0019] Determining whether the temperature deviation rate is greater than a preset temperature deviation rate threshold;
[0020] If the temperature deviation rate is less than the preset temperature deviation rate threshold, the optical cable temperature is normal;
[0021] If the temperature deviation rate is greater than or equal to a preset temperature deviation rate threshold, over-temperature fault data is obtained.
[0022] Among them, in the optical fiber communication fault diagnosis method based on machine learning described in the present application, it is characterized in that the processing is performed according to the optical fiber refractive index data to obtain the refractive index deviation data, specifically:
[0023] Comparing the optical fiber refractive index data with a preset refractive index threshold to obtain a refractive deviation rate;
[0024] Determining whether the refractive deviation rate is greater than a preset refractive deviation rate threshold;
[0025] If the refractive index deviation is less than the preset refractive index deviation threshold, the optical fiber refractive index is normal;
[0026] If the refractive index deviation is greater than or equal to a preset refractive index deviation threshold, refractive index deviation data is obtained.
[0027] Among them, in the optical fiber communication fault diagnosis method based on machine learning described in the present application, it is characterized in that the processing is performed according to the optical signal attenuation data to obtain the attenuation exceeding standard data, specifically:
[0028] Comparing the optical signal attenuation data with a preset first attenuation threshold and a second attenuation threshold respectively;
[0029] The first attenuation threshold is less than the second attenuation threshold;
[0030] If the optical signal attenuation data is less than the first attenuation threshold, the optical fiber transmission is normal;
[0031] If the optical signal attenuation data is greater than or equal to the first attenuation threshold and less than or equal to the second attenuation threshold, the optical signal transmission is in a low performance state;
[0032] If the optical signal attenuation data is greater than the second attenuation threshold, attenuation exceeding threshold data is obtained.
[0033] Among them, in the optical fiber communication fault diagnosis method based on machine learning described in the present application, it is characterized in that the processing is performed according to the optical signal transmittance data to obtain the transmittance distortion data, specifically:
[0034] Comparing the optical signal penetration data with a preset penetration threshold to obtain a penetration deviation rate;
[0035] Determining whether the penetration deviation rate is greater than a preset penetration deviation rate threshold;
[0036] If the penetration deviation rate is less than the preset penetration deviation rate threshold, the optical signal penetration rate is normal;
[0037] If the penetration deviation rate is greater than or equal to a preset penetration deviation rate threshold, penetration distortion data is obtained.
[0038] Among them, in the optical fiber communication fault diagnosis method based on machine learning described in the present application, it is characterized in that the over-temperature fault index is obtained by processing according to the over-temperature frequency data and the over-temperature degree data, the refractive index deviation index is obtained by processing according to the refractive index deviation frequency data and the refractive index deviation degree data, the attenuation exceeding frequency data and the attenuation exceeding degree data are processed to obtain the attenuation exceeding index, and the penetration distortion frequency data and the penetration distortion degree data are processed to obtain the penetration distortion index, which is specifically:
[0039] The over-temperature frequency data and the over-temperature degree data are processed by a preset over-temperature evaluation model to obtain an over-temperature fault index;
[0040] Processing the refractive index deviation frequency data and the refractive index deviation degree data through a preset refractive index evaluation model to obtain a refractive index deviation index;
[0041] The attenuation exceeding standard frequency data and the attenuation exceeding standard degree data are processed by a preset attenuation evaluation model to obtain an attenuation exceeding standard index;
[0042] The penetration distortion frequency data and the penetration distortion degree data are processed by a preset penetration evaluation model to obtain a penetration distortion index.
[0043] Among them, in the optical fiber communication fault diagnosis method based on machine learning described in the present application, it is characterized in that the optical fiber communication fault index is obtained by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnosis model, specifically:
[0044] Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model;
[0045] The calculation formula of the optical fiber communication diagnostic model is:
[0046]
[0047] Among them, G ψ is the optical fiber communication fault index, T e is the over-temperature fault index, Z pis the refractive index deviation index, S c is the attenuation excess index, C b is the penetration distortion index, and α, β, γ1, and γ2 are preset characteristic coefficients.
[0048] Among them, in the optical fiber communication fault diagnosis method based on machine learning described in the present application, it is characterized in that the optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate is judged to be different from the preset fault deviation rate threshold, specifically:
[0049] Comparing the optical fiber communication failure index with the historical optical fiber communication failure index of the same type to obtain the optical fiber communication failure deviation rate;
[0050] Determining whether the optical fiber communication fault deviation rate is greater than a preset fault deviation rate threshold;
[0051] If the optical fiber communication fault deviation rate is less than the preset fault deviation rate threshold, the optical fiber communication fault is within the controllable range;
[0052] If the optical fiber communication fault deviation rate is greater than or equal to a preset fault deviation rate threshold, the optical fiber communication fault rate exceeds the standard.
[0053] In a second aspect, the present application provides an optical fiber communication fault diagnosis system based on machine learning, the system comprising: a memory and a processor, the memory comprising a program of an optical fiber communication fault diagnosis method based on machine learning, the program of the optical fiber communication fault diagnosis method based on machine learning being executed by the processor to implement the following steps:
[0054] Obtaining optical fiber communication information within a preset time period, and extracting optical cable line detection information and transmission signal monitoring information according to the optical fiber communication information;
[0055] Extracting optical cable temperature data and optical fiber refractive index data according to the optical cable line detection information, and extracting optical signal attenuation data and optical signal penetration data according to the transmission signal monitoring information;
[0056] Processing the optical cable temperature data to obtain over-temperature fault data;
[0057] Processing the optical fiber refractive index data to obtain refractive index deviation data;
[0058] Processing the optical signal attenuation data to obtain attenuation exceeding standard data;
[0059] Processing the optical signal transmittance data to obtain transmittance distortion data;
[0060] Extracting over-temperature frequency data and over-temperature degree data according to the over-temperature fault data, extracting refractive index deviation frequency data and refractive index deviation degree data according to the refractive index deviation data, extracting attenuation degree exceeding frequency data and attenuation degree exceeding degree data according to the attenuation degree exceeding data, and extracting penetration distortion frequency data and penetration distortion degree data according to the penetration distortion data;
[0061] Processing the over-temperature frequency data and the over-temperature degree data to obtain an over-temperature fault index, processing the refractive index deviation frequency data and the refractive index deviation degree data to obtain a refractive index deviation index, processing the attenuation exceeding standard frequency data and the attenuation exceeding standard degree data to obtain an attenuation exceeding standard index, and processing the penetration distortion frequency data and the penetration distortion degree data to obtain a penetration distortion index;
[0062] Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model;
[0063] The optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate and the preset fault deviation rate threshold are determined.
[0064] In a third aspect, the present application also provides a readable storage medium, which includes a fiber optic communication fault diagnosis method program based on machine learning. When the fiber optic communication fault diagnosis method program based on machine learning is executed by a processor, the steps of the fiber optic communication fault diagnosis method based on machine learning as described in any one of the above items are implemented.
[0065] As can be seen from the above, the present application provides a method, system and medium for optical fiber communication fault diagnosis based on machine learning. By acquiring optical fiber communication information within a preset time period, extracting optical cable line detection information and transmission signal monitoring information, and processing, over-temperature fault data, refractive index deviation data, attenuation excess data and penetration distortion data can be obtained respectively. After further processing, over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index can be obtained. Finally, the optical fiber communication diagnosis model is used to process and obtain the optical fiber communication fault index, which is then compared with the historical optical fiber communication fault index of the same type to determine whether the optical fiber communication fault index meets the requirements. The present application monitors the temperature, refractive index, attenuation and penetration data that have an important impact on the performance of optical fiber communication, and analyzes the degree of influence of each data on the performance of optical fiber communication. It can automatically learn and identify fault modes from a large amount of data, discover and report faults in a timely manner, reduce the time for troubleshooting and repair, and does not require manual writing of complex rules or tedious manual analysis, thereby significantly improving the accuracy and efficiency of fault detection.
[0066] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0068] Figure 1 A flowchart of a method for diagnosing optical fiber communication faults based on machine learning provided in an embodiment of the present application;
[0069] Figure 2 A flowchart of obtaining over-temperature fault data of a method for diagnosing optical fiber communication faults based on machine learning provided in an embodiment of the present application;
[0070] Figure 3 A flowchart of obtaining refractive index deviation data in a method for optical fiber communication fault diagnosis based on machine learning provided in an embodiment of the present application;
[0071] Figure 4 A flowchart of obtaining attenuation exceeding standard data in a method for diagnosing optical fiber communication faults based on machine learning provided in an embodiment of the present application;
[0072] Figure 5 A flowchart of obtaining penetration distortion data in a method for optical fiber communication fault diagnosis based on machine learning provided in an embodiment of the present application. DETAILED DESCRIPTION
[0073] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0074] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. 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, stored data, displayed data, 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 relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.
[0075] Please refer to Figure 1 , Figure 1 The present invention is a flowchart of a method for diagnosing optical fiber communication faults based on machine learning in some embodiments of the present invention. The method for diagnosing optical fiber communication faults based on machine learning is used in terminal devices, such as computers, mobile phone terminals, etc. The method for diagnosing optical fiber communication faults based on machine learning includes the following steps:
[0076] S101, acquiring optical fiber communication information within a preset time period, and extracting optical cable line detection information and transmission signal monitoring information according to the optical fiber communication information;
[0077] S102, extracting optical cable temperature data and optical fiber refractive index data according to the optical cable line detection information, and extracting optical signal attenuation data and optical signal penetration data according to the transmission signal monitoring information;
[0078] S103, processing the optical cable temperature data to obtain over-temperature fault data;
[0079] S104, processing the optical fiber refractive index data to obtain refractive index deviation data;
[0080] S105, processing the optical signal attenuation data to obtain attenuation exceeding standard data;
[0081] S106, processing the optical signal transmittance data to obtain transmittance distortion data;
[0082] S107, extracting over-temperature frequency data and over-temperature degree data according to the over-temperature fault data, extracting refractive index deviation frequency data and refractive index deviation degree data according to the refractive index deviation data, extracting attenuation degree exceeding frequency data and attenuation degree exceeding degree data according to the attenuation degree exceeding data, and extracting penetration distortion frequency data and penetration distortion degree data according to the penetration distortion data;
[0083] S108, processing the over-temperature frequency data and the over-temperature degree data to obtain an over-temperature fault index, processing the refractive index deviation frequency data and the refractive index deviation degree data to obtain a refractive index deviation index, processing the attenuation exceeding standard frequency data and the attenuation exceeding standard degree data to obtain an attenuation exceeding standard index, and processing the penetration distortion frequency data and the penetration distortion degree data to obtain a penetration distortion index;
[0084] S109, obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnosis model;
[0085] S1010, comparing the optical fiber communication fault index with the historical optical fiber communication fault index of the same type to obtain an optical fiber communication fault deviation rate, and determining whether the optical fiber communication fault deviation rate is equal to a preset fault deviation rate threshold.
[0086] Among them, this application obtains the optical fiber communication information within a preset time period, extracts the optical cable line detection information and the transmission signal monitoring information, and after processing, it can obtain the over-temperature fault data, refractive index deviation data, attenuation excess data and penetration distortion data respectively, and further processing can obtain the over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index, and finally processes it through the optical fiber communication diagnosis model to obtain the optical fiber communication fault index, and then compares it with the historical optical fiber communication fault index of the same type to determine whether the optical fiber communication fault index meets the requirements. This application monitors the temperature, refractive index, attenuation and penetration data that have an important impact on the performance of optical fiber communication, and analyzes the degree of influence of each data on the performance of optical fiber communication.
[0087] Please refer to Figure 2 , Figure 2 The present invention is a flowchart of obtaining over-temperature fault data of a method for diagnosing optical fiber communication faults based on machine learning in some embodiments of the present invention. According to an embodiment of the present invention, the processing according to the optical cable temperature data to obtain the over-temperature fault data is specifically as follows:
[0088] S201, comparing the optical cable temperature data with a preset temperature threshold to obtain a temperature deviation rate;
[0089] S202, determining whether the temperature deviation rate is greater than a preset temperature deviation rate threshold;
[0090] S203: If the temperature deviation rate is less than a preset temperature deviation rate threshold, the temperature of the optical cable is normal;
[0091] S204: If the temperature deviation rate is greater than or equal to a preset temperature deviation rate threshold, over-temperature fault data is obtained.
[0092] Among them, in order to understand the over-temperature situation of the optical cable when the optical fiber is working, the temperature data of the optical cable is compared with the preset temperature threshold to obtain the temperature deviation rate, and judge whether the temperature deviation rate is greater than the preset temperature deviation rate threshold. If the temperature deviation rate is less than the preset temperature deviation rate threshold, the temperature of the optical cable is normal. For example, the temperature deviation rate is 8%, and the preset temperature deviation rate threshold is 10%. If the temperature deviation rate is greater than or equal to the preset temperature deviation rate threshold, over-temperature fault data is obtained. For example, the temperature deviation rate is 13%, and the preset temperature deviation rate threshold is 10%.
[0093] Please refer to Figure 3 , Figure 3 The present invention is a flowchart of a method for diagnosing optical fiber communication faults based on machine learning in some embodiments of the present invention for obtaining refractive index deviation data. According to an embodiment of the present invention, the processing according to the optical fiber refractive index data to obtain the refractive index deviation data is specifically as follows:
[0094] S301, comparing the optical fiber refractive index data with a preset refractive index threshold to obtain a refractive deviation rate;
[0095] S302, determining whether the refractive deviation rate is greater than a preset refractive deviation rate threshold;
[0096] S303, if the refractive index deviation is less than the preset refractive index deviation threshold, the optical fiber refractive index is normal;
[0097] S304: If the refractive index deviation rate is greater than or equal to a preset refractive index deviation rate threshold, obtaining refractive index deviation data.
[0098] Among them, in order to determine whether the refractive index of the optical fiber meets the communication requirements, the optical fiber refractive index data is compared with the preset refractive index threshold to obtain the refractive deviation rate, and determine whether the refractive deviation rate is greater than the preset refractive deviation rate threshold. If the refractive deviation rate is less than the preset refractive deviation rate threshold, the optical fiber refractive index is normal, for example, the refractive deviation rate is 2%, and the preset refractive deviation rate threshold is 3%. If the refractive deviation rate is greater than or equal to the preset refractive deviation rate threshold, the refractive index deviation data is obtained, for example, the refractive deviation rate is 3%, and the preset refractive deviation rate threshold is 3%.
[0099] Please refer to Figure 4 , Figure 4 The present invention is a flowchart of a method for diagnosing optical fiber communication faults based on machine learning in some embodiments of the present invention for obtaining attenuation exceeding standard data. According to an embodiment of the present invention, the processing according to the optical signal attenuation data to obtain attenuation exceeding standard data is specifically as follows:
[0100] S401, comparing the optical signal attenuation data with a preset first attenuation threshold and a second attenuation threshold respectively;
[0101] S402: The first attenuation threshold is less than the second attenuation threshold;
[0102] S403: If the optical signal attenuation data is less than the first attenuation threshold, the optical fiber transmission is normal;
[0103] S404: If the optical signal attenuation data is greater than or equal to the first attenuation threshold and less than or equal to the second attenuation threshold, the optical signal transmission is in a low performance state;
[0104] S405: If the optical signal attenuation data is greater than a second attenuation threshold, obtain attenuation exceeding threshold data.
[0105] Among them, in order to reduce the attenuation of the optical signal when the optical fiber is working, the optical signal attenuation data is compared with the preset first attenuation threshold and the second attenuation threshold respectively, the first attenuation threshold is less than the second attenuation threshold, for example, the first attenuation threshold is 25dB / km, and the second attenuation threshold is 50dB / km. If the optical signal attenuation data is less than the first attenuation threshold, the optical fiber transmission is normal, for example, the optical signal attenuation data is 21dB / km, if the optical signal attenuation data is greater than or equal to the first attenuation threshold and less than or equal to the second attenuation threshold, the optical signal transmission is in a low performance state, for example, the optical signal attenuation data is 32dB / km, if the optical signal attenuation data is greater than the second attenuation threshold, the attenuation exceeds the standard data is obtained, for example, the optical signal attenuation data is 55dB / km.
[0106] Please refer to Figure 5 , Figure 5The present invention is a flowchart of obtaining the penetration distortion data of a method for optical fiber communication fault diagnosis based on machine learning in some embodiments of the present application. According to an embodiment of the present invention, the optical signal penetration data is processed to obtain the penetration distortion data, specifically:
[0107] S501, comparing the optical signal transmittance data with a preset transmittance threshold to obtain a transmittance deviation rate;
[0108] S502, determining whether the penetration deviation rate is greater than a preset penetration deviation rate threshold;
[0109] S503: If the penetration deviation rate is less than the preset penetration deviation rate threshold, the optical signal penetration rate is normal;
[0110] S504: If the penetration deviation rate is greater than or equal to a preset penetration deviation rate threshold, then obtaining penetration distortion data.
[0111] Among them, in order to reduce the distortion of the optical signal transmittance, the optical signal transmittance data is compared with the preset transmittance threshold to obtain the penetration deviation rate, and it is determined whether the penetration deviation rate is greater than the preset penetration deviation rate threshold. If the penetration deviation rate is less than the preset penetration deviation rate threshold, the optical signal transmittance is normal. For example, the penetration deviation rate is 1.2%, and the penetration deviation rate threshold is 2%. If the penetration deviation rate is greater than or equal to the preset penetration deviation rate threshold, the penetration distortion data is obtained, for example, the penetration deviation rate is 2.3%, and the penetration deviation rate threshold is 2%.
[0112] According to an embodiment of the present invention, the over-temperature frequency data and the over-temperature degree data are processed to obtain an over-temperature fault index, the refractive index deviation index is obtained by processing the refractive index deviation frequency data and the refractive index deviation degree data, the attenuation exceeding frequency data and the attenuation exceeding degree data are processed to obtain an attenuation exceeding index, and the penetration distortion frequency data and the penetration distortion degree data are processed to obtain a penetration distortion index, which is specifically:
[0113] The over-temperature frequency data and the over-temperature degree data are processed by a preset over-temperature evaluation model to obtain an over-temperature fault index;
[0114] Processing the refractive index deviation frequency data and the refractive index deviation degree data through a preset refractive index evaluation model to obtain a refractive index deviation index;
[0115] The attenuation exceeding standard frequency data and the attenuation exceeding standard degree data are processed by a preset attenuation evaluation model to obtain an attenuation exceeding standard index;
[0116] The penetration distortion frequency data and the penetration distortion degree data are processed by a preset penetration evaluation model to obtain a penetration distortion index.
[0117] Among them, in order to reflect and reduce the impact of various types of faults in optical fiber communication, the optical fiber communication situation is first detected through multi-dimensional parameters and their faults, and then the various types of communication fault data are respectively evaluated and processed by the corresponding fault evaluation model for fault frequency and fault degree. The over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index can be obtained respectively, which accurately reflects the frequency and degree of various types of optical fiber faults;
[0118] The calculation formulas of the over-temperature evaluation model, the refractive index evaluation model, the attenuation evaluation model and the transmittance evaluation model are respectively:
[0119] T e =∈1t f 2 ×∈2t c 2 ;
[0120]
[0121]
[0122]
[0123] Among them, T e is the over-temperature fault index, Z p is the refractive index deviation index, S c is the attenuation excess index, C b is the transmittance distortion index, t f ,t c are respectively the over-temperature frequency data and over-temperature degree data, z p 、z k are the refractive index deviation frequency data and the refractive index deviation degree data, respectively. h 、a d are the frequency data of attenuation exceeding the standard and the degree data of attenuation exceeding the standard, b y , b x are the penetration distortion frequency data and the penetration distortion degree data respectively, and ∈1, ∈2, κ1, κ2, π1, π2, μ1, μ2, and μ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset optical fiber communication monitoring database platform).
[0124] According to an embodiment of the present invention, the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index are processed by a preset optical fiber communication diagnostic model to obtain an optical fiber communication fault index, specifically:
[0125] Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model;
[0126] The calculation formula of the optical fiber communication diagnostic model is:
[0127]
[0128] Among them, G ψ is the optical fiber communication fault index, T e is the over-temperature fault index, Z p is the refractive index deviation index, S c is the attenuation excess index, C b is the penetration distortion index, and α, β, γ1, and γ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset optical fiber communication monitoring database platform).
[0129] Among them, in order to comprehensively reflect the fault conditions existing in optical fiber communication, the over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index are processed through a preset optical fiber communication diagnostic model to obtain the optical fiber communication fault index. The optical fiber communication fault index comprehensively reflects the number of fault events, the severity of the faults and the performance of optical fiber communication.
[0130] According to an embodiment of the present invention, the optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate is judged to be different from the preset fault deviation rate threshold, specifically:
[0131] Comparing the optical fiber communication failure index with the historical optical fiber communication failure index of the same type to obtain the optical fiber communication failure deviation rate;
[0132] Determining whether the optical fiber communication fault deviation rate is greater than a preset fault deviation rate threshold;
[0133] If the optical fiber communication fault deviation rate is less than the preset fault deviation rate threshold, the optical fiber communication fault is within the controllable range;
[0134] If the optical fiber communication fault deviation rate is greater than or equal to a preset fault deviation rate threshold, the optical fiber communication fault rate exceeds the standard.
[0135] Among them, in order to reduce optical fiber communication failures, the optical fiber communication failure index is compared with the historical optical fiber communication failure index of the same type to obtain the optical fiber communication failure deviation rate, and it is determined whether the optical fiber communication failure deviation rate is greater than the preset failure deviation rate threshold. If the optical fiber communication failure deviation rate is less than the preset failure deviation rate threshold, the optical fiber communication failure is within a controllable range. For example, the optical fiber communication failure deviation rate is 1%, and the failure deviation rate threshold is 2.5%. If the optical fiber communication failure deviation rate is greater than or equal to the preset failure deviation rate threshold, the optical fiber communication failure rate exceeds the standard. For example, the optical fiber communication failure deviation rate is 3%, and the failure deviation rate threshold is 2.5%.
[0136] The present invention also discloses a machine learning-based optical fiber communication fault diagnosis system, comprising a memory and a processor, wherein the memory comprises a machine learning-based optical fiber communication fault diagnosis method program, and when the machine learning-based optical fiber communication fault diagnosis method program is executed by the processor, the following steps are implemented:
[0137] Obtaining optical fiber communication information within a preset time period, and extracting optical cable line detection information and transmission signal monitoring information according to the optical fiber communication information;
[0138] Extracting optical cable temperature data and optical fiber refractive index data according to the optical cable line detection information, and extracting optical signal attenuation data and optical signal penetration data according to the transmission signal monitoring information;
[0139] Processing the optical cable temperature data to obtain over-temperature fault data;
[0140] Processing the optical fiber refractive index data to obtain refractive index deviation data;
[0141] Processing the optical signal attenuation data to obtain attenuation exceeding standard data;
[0142] Processing the optical signal transmittance data to obtain transmittance distortion data;
[0143] Extracting over-temperature frequency data and over-temperature degree data according to the over-temperature fault data, extracting refractive index deviation frequency data and refractive index deviation degree data according to the refractive index deviation data, extracting attenuation degree exceeding frequency data and attenuation degree exceeding degree data according to the attenuation degree exceeding data, and extracting penetration distortion frequency data and penetration distortion degree data according to the penetration distortion data;
[0144] Processing the over-temperature frequency data and the over-temperature degree data to obtain an over-temperature fault index, processing the refractive index deviation frequency data and the refractive index deviation degree data to obtain a refractive index deviation index, processing the attenuation exceeding standard frequency data and the attenuation exceeding standard degree data to obtain an attenuation exceeding standard index, and processing the penetration distortion frequency data and the penetration distortion degree data to obtain a penetration distortion index;
[0145] Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model;
[0146] The optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate and the preset fault deviation rate threshold are determined.
[0147] Among them, this application obtains the optical fiber communication information within a preset time period, extracts the optical cable line detection information and the transmission signal monitoring information, and after processing, it can obtain the over-temperature fault data, refractive index deviation data, attenuation excess data and penetration distortion data respectively, and further processing can obtain the over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index, and finally processes it through the optical fiber communication diagnosis model to obtain the optical fiber communication fault index, and then compares it with the historical optical fiber communication fault index of the same type to determine whether the optical fiber communication fault index meets the requirements. This application monitors the temperature, refractive index, attenuation and penetration data that have an important impact on the performance of optical fiber communication, and analyzes the degree of influence of each data on the performance of optical fiber communication.
[0148] According to an embodiment of the present invention, the processing according to the optical cable temperature data to obtain the over-temperature fault data is specifically:
[0149] Comparing the optical cable temperature data with a preset temperature threshold to obtain a temperature deviation rate;
[0150] Determining whether the temperature deviation rate is greater than a preset temperature deviation rate threshold;
[0151] If the temperature deviation rate is less than the preset temperature deviation rate threshold, the optical cable temperature is normal;
[0152] If the temperature deviation rate is greater than or equal to a preset temperature deviation rate threshold, over-temperature fault data is obtained.
[0153] Among them, in order to understand the over-temperature situation of the optical cable when the optical fiber is working, the temperature data of the optical cable is compared with the preset temperature threshold to obtain the temperature deviation rate, and judge whether the temperature deviation rate is greater than the preset temperature deviation rate threshold. If the temperature deviation rate is less than the preset temperature deviation rate threshold, the temperature of the optical cable is normal. For example, the temperature deviation rate is 8%, and the preset temperature deviation rate threshold is 10%. If the temperature deviation rate is greater than or equal to the preset temperature deviation rate threshold, over-temperature fault data is obtained. For example, the temperature deviation rate is 13%, and the preset temperature deviation rate threshold is 10%.
[0154] Please refer to Figure 3 , Figure 3 The present invention is a flowchart of a method for diagnosing optical fiber communication faults based on machine learning in some embodiments of the present invention for obtaining refractive index deviation data. According to an embodiment of the present invention, the processing according to the optical fiber refractive index data to obtain the refractive index deviation data is specifically as follows:
[0155] Comparing the optical fiber refractive index data with a preset refractive index threshold to obtain a refractive deviation rate;
[0156] Determining whether the refractive deviation rate is greater than a preset refractive deviation rate threshold;
[0157] If the refractive index deviation is less than the preset refractive index deviation threshold, the optical fiber refractive index is normal;
[0158] If the refractive index deviation is greater than or equal to a preset refractive index deviation threshold, refractive index deviation data is obtained.
[0159] Among them, in order to determine whether the refractive index of the optical fiber meets the communication requirements, the optical fiber refractive index data is compared with the preset refractive index threshold to obtain the refractive deviation rate, and determine whether the refractive deviation rate is greater than the preset refractive deviation rate threshold. If the refractive deviation rate is less than the preset refractive deviation rate threshold, the optical fiber refractive index is normal, for example, the refractive deviation rate is 2%, and the preset refractive deviation rate threshold is 3%. If the refractive deviation rate is greater than or equal to the preset refractive deviation rate threshold, the refractive index deviation data is obtained, for example, the refractive deviation rate is 3%, and the preset refractive deviation rate threshold is 3%.
[0160] According to an embodiment of the present invention, the processing according to the optical signal attenuation data to obtain the attenuation exceeding standard data is specifically:
[0161] Comparing the optical signal attenuation data with a preset first attenuation threshold and a second attenuation threshold respectively;
[0162] The first attenuation threshold is less than the second attenuation threshold;
[0163] If the optical signal attenuation data is less than the first attenuation threshold, the optical fiber transmission is normal;
[0164] If the optical signal attenuation data is greater than or equal to the first attenuation threshold and less than or equal to the second attenuation threshold, the optical signal transmission is in a low performance state;
[0165] If the optical signal attenuation data is greater than the second attenuation threshold, attenuation exceeding threshold data is obtained.
[0166] Among them, in order to reduce the attenuation of the optical signal when the optical fiber is working, the optical signal attenuation data is compared with the preset first attenuation threshold and the second attenuation threshold respectively, the first attenuation threshold is less than the second attenuation threshold, for example, the first attenuation threshold is 25dB / km, and the second attenuation threshold is 50dB / km. If the optical signal attenuation data is less than the first attenuation threshold, the optical fiber transmission is normal, for example, the optical signal attenuation data is 21dB / km, if the optical signal attenuation data is greater than or equal to the first attenuation threshold and less than or equal to the second attenuation threshold, the optical signal transmission is in a low performance state, for example, the optical signal attenuation data is 32dB / km, if the optical signal attenuation data is greater than the second attenuation threshold, the attenuation exceeds the standard data is obtained, for example, the optical signal attenuation data is 55dB / km.
[0167] According to an embodiment of the present invention, the processing is performed according to the optical signal transmittance data to obtain transmittance distortion data, specifically:
[0168] Comparing the optical signal penetration data with a preset penetration threshold to obtain a penetration deviation rate;
[0169] Determining whether the penetration deviation rate is greater than a preset penetration deviation rate threshold;
[0170] If the penetration deviation rate is less than the preset penetration deviation rate threshold, the optical signal penetration rate is normal;
[0171] If the penetration deviation rate is greater than or equal to a preset penetration deviation rate threshold, penetration distortion data is obtained.
[0172] Among them, in order to reduce the distortion of the optical signal transmittance, the optical signal transmittance data is compared with the preset transmittance threshold to obtain the penetration deviation rate, and it is determined whether the penetration deviation rate is greater than the preset penetration deviation rate threshold. If the penetration deviation rate is less than the preset penetration deviation rate threshold, the optical signal transmittance is normal. For example, the penetration deviation rate is 1.2%, and the penetration deviation rate threshold is 2%. If the penetration deviation rate is greater than or equal to the preset penetration deviation rate threshold, the penetration distortion data is obtained, for example, the penetration deviation rate is 2.3%, and the penetration deviation rate threshold is 2%.
[0173] According to an embodiment of the present invention, the over-temperature frequency data and the over-temperature degree data are processed to obtain an over-temperature fault index, the refractive index deviation index is obtained by processing the refractive index deviation frequency data and the refractive index deviation degree data, the attenuation exceeding frequency data and the attenuation exceeding degree data are processed to obtain an attenuation exceeding index, and the penetration distortion frequency data and the penetration distortion degree data are processed to obtain a penetration distortion index, which is specifically:
[0174] The over-temperature frequency data and the over-temperature degree data are processed by a preset over-temperature evaluation model to obtain an over-temperature fault index;
[0175] Processing the refractive index deviation frequency data and the refractive index deviation degree data through a preset refractive index evaluation model to obtain a refractive index deviation index;
[0176] The attenuation exceeding standard frequency data and the attenuation exceeding standard degree data are processed by a preset attenuation evaluation model to obtain an attenuation exceeding standard index;
[0177] The penetration distortion frequency data and the penetration distortion degree data are processed by a preset penetration evaluation model to obtain a penetration distortion index.
[0178] Among them, in order to reflect and reduce the impact of various types of faults in optical fiber communication, the optical fiber communication situation is first detected through multi-dimensional parameters and their faults, and then the various types of communication fault data are respectively evaluated and processed by the corresponding fault evaluation model for fault frequency and fault degree. The over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index can be obtained respectively, which accurately reflects the frequency and degree of various types of optical fiber faults;
[0179] The calculation formulas of the over-temperature evaluation model, the refractive index evaluation model, the attenuation evaluation model and the transmittance evaluation model are respectively:
[0180] T e =∈1t f 2 ×∈2t c 2 ;
[0181]
[0182]
[0183]
[0184] Among them, T e is the over-temperature fault index, Z p is the refractive index deviation index, Sc is the attenuation excess index, C b is the transmittance distortion index, t f ,t c are respectively the over-temperature frequency data and over-temperature degree data, z p 、z k are the refractive index deviation frequency data and the refractive index deviation degree data, respectively. h 、a d are the frequency data of attenuation exceeding the standard and the degree data of attenuation exceeding the standard, b y , b x are the penetration distortion frequency data and the penetration distortion degree data respectively, and ∈1, ∈2, κ1, κ2, π1, π2, μ1, μ2, and μ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset optical fiber communication monitoring database platform).
[0185] According to an embodiment of the present invention, the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index are processed by a preset optical fiber communication diagnostic model to obtain an optical fiber communication fault index, specifically:
[0186] Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model;
[0187] The calculation formula of the optical fiber communication diagnostic model is:
[0188]
[0189] Among them, G ψ is the optical fiber communication fault index, T e is the over-temperature fault index, Z p is the refractive index deviation index, S c is the attenuation excess index, C b is the penetration distortion index, and α, β, γ1, and γ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset optical fiber communication monitoring database platform).
[0190] Among them, in order to comprehensively reflect the fault conditions existing in optical fiber communication, the over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index are processed through a preset optical fiber communication diagnostic model to obtain the optical fiber communication fault index. The optical fiber communication fault index comprehensively reflects the number of fault events, the severity of the faults and the performance of optical fiber communication.
[0191] According to an embodiment of the present invention, the optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate is judged to be different from the preset fault deviation rate threshold, specifically:
[0192] Comparing the optical fiber communication failure index with the historical optical fiber communication failure index of the same type to obtain the optical fiber communication failure deviation rate;
[0193] Determining whether the optical fiber communication fault deviation rate is greater than a preset fault deviation rate threshold;
[0194] If the optical fiber communication fault deviation rate is less than the preset fault deviation rate threshold, the optical fiber communication fault is within the controllable range;
[0195] If the optical fiber communication fault deviation rate is greater than or equal to a preset fault deviation rate threshold, the optical fiber communication fault rate exceeds the standard.
[0196] Among them, in order to reduce optical fiber communication failures, the optical fiber communication failure index is compared with the historical optical fiber communication failure index of the same type to obtain the optical fiber communication failure deviation rate, and it is determined whether the optical fiber communication failure deviation rate is greater than the preset failure deviation rate threshold. If the optical fiber communication failure deviation rate is less than the preset failure deviation rate threshold, the optical fiber communication failure is within a controllable range. For example, the optical fiber communication failure deviation rate is 1%, and the failure deviation rate threshold is 2.5%. If the optical fiber communication failure deviation rate is greater than or equal to the preset failure deviation rate threshold, the optical fiber communication failure rate exceeds the standard. For example, the optical fiber communication failure deviation rate is 3%, and the failure deviation rate threshold is 2.5%.
[0197] The third aspect of the present invention also provides a readable storage medium, which includes a fiber optic communication fault diagnosis method program based on machine learning. When the fiber optic communication fault diagnosis method program based on machine learning is executed by a processor, the steps of the fiber optic communication fault diagnosis method based on machine learning as described in any one of the above items are implemented.
[0198] The present invention discloses a method, system and medium for diagnosing optical fiber communication faults based on machine learning. By acquiring optical fiber communication information within a preset time period, extracting optical cable line detection information and transmission signal monitoring information, over-temperature fault data, refractive index deviation data, attenuation excess data and penetration distortion data can be obtained after processing, and over-temperature fault index, refractive index deviation index, attenuation excess index and penetration distortion index can be obtained after further processing. Finally, the optical fiber communication diagnosis model is used to process the optical fiber communication fault index, and the optical fiber communication fault index is obtained. The optical fiber communication fault index is then compared with the historical optical fiber communication fault index of the same type to determine whether the optical fiber communication fault index meets the requirements. The present application monitors the temperature, refractive index, attenuation and penetration data that have an important impact on the performance of optical fiber communication, and analyzes the degree of influence of each data on the performance of optical fiber communication. It can automatically learn and identify fault modes from a large amount of data, discover and report faults in a timely manner, reduce the time for troubleshooting and repair, and does not require manual writing of complex rules or tedious manual analysis, thereby significantly improving the accuracy and efficiency of fault detection.
[0199] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0200] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0201] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0202] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories, random access memories, magnetic disks or optical disks, and other media that can store program codes.
[0203] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
Claims
1. A method for optical fiber communication fault diagnosis based on machine learning, characterized in that: The following steps are involved: Obtaining optical fiber communication information within a preset time period, and extracting optical cable line detection information and transmission signal monitoring information according to the optical fiber communication information; Extracting optical cable temperature data and optical fiber refractive index data according to the optical cable line detection information, and extracting optical signal attenuation data and optical signal penetration data according to the transmission signal monitoring information; Processing the optical cable temperature data to obtain over-temperature fault data; Processing the optical fiber refractive index data to obtain refractive index deviation data; Processing the optical signal attenuation data to obtain attenuation exceeding standard data; Processing the optical signal transmittance data to obtain transmittance distortion data; Extracting over-temperature frequency data and over-temperature degree data according to the over-temperature fault data, extracting refractive index deviation frequency data and refractive index deviation degree data according to the refractive index deviation data, extracting attenuation degree exceeding frequency data and attenuation degree exceeding degree data according to the attenuation degree exceeding data, and extracting penetration distortion frequency data and penetration distortion degree data according to the penetration distortion data; Processing the over-temperature frequency data and the over-temperature degree data to obtain an over-temperature fault index, processing the refractive index deviation frequency data and the refractive index deviation degree data to obtain a refractive index deviation index, processing the attenuation exceeding standard frequency data and the attenuation exceeding standard degree data to obtain an attenuation exceeding standard index, and processing the penetration distortion frequency data and the penetration distortion degree data to obtain a penetration distortion index; Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model; The optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate and the preset fault deviation rate threshold are determined.
2. The optical fiber communication fault diagnosis method based on machine learning according to claim 1, characterized in that: The processing according to the optical cable temperature data to obtain over-temperature fault data is specifically: Comparing the optical cable temperature data with a preset temperature threshold to obtain a temperature deviation rate; Determining whether the temperature deviation rate is greater than a preset temperature deviation rate threshold; If the temperature deviation rate is less than the preset temperature deviation rate threshold, the optical cable temperature is normal; If the temperature deviation rate is greater than or equal to a preset temperature deviation rate threshold, over-temperature fault data is obtained.
3. The optical fiber communication fault diagnosis method based on machine learning according to claim 2, characterized in that: The processing according to the optical fiber refractive index data to obtain the refractive index deviation data is specifically: Comparing the optical fiber refractive index data with a preset refractive index threshold to obtain a refractive deviation rate; Determining whether the refractive deviation rate is greater than a preset refractive deviation rate threshold; If the refractive index deviation is less than the preset refractive index deviation threshold, the optical fiber refractive index is normal; If the refractive index deviation is greater than or equal to a preset refractive index deviation threshold, refractive index deviation data is obtained.
4. The optical fiber communication fault diagnosis method based on machine learning according to claim 3 is characterized in that: The processing according to the optical signal attenuation data to obtain attenuation exceeding standard data is specifically: Comparing the optical signal attenuation data with a preset first attenuation threshold and a second attenuation threshold respectively; The first attenuation threshold is less than the second attenuation threshold; If the optical signal attenuation data is less than the first attenuation threshold, the optical fiber transmission is normal; If the optical signal attenuation data is greater than or equal to the first attenuation threshold and less than or equal to the second attenuation threshold, the optical signal transmission is in a low performance state; If the optical signal attenuation data is greater than the second attenuation threshold, attenuation exceeding threshold data is obtained.
5. The optical fiber communication fault diagnosis method based on machine learning according to claim 4, characterized in that: The processing is performed according to the optical signal transmittance data to obtain transmittance distortion data, specifically: Comparing the optical signal penetration data with a preset penetration threshold to obtain a penetration deviation rate; Determining whether the penetration deviation rate is greater than a preset penetration deviation rate threshold; If the penetration deviation rate is less than the preset penetration deviation rate threshold, the optical signal penetration rate is normal; If the penetration deviation rate is greater than or equal to a preset penetration deviation rate threshold, penetration distortion data is obtained.
6. The optical fiber communication fault diagnosis method based on machine learning according to claim 5, characterized in that: The over-temperature fault index is obtained by processing the over-temperature frequency data and the over-temperature degree data, the refractive index deviation index is obtained by processing the refractive index deviation frequency data and the refractive index deviation degree data, the attenuation exceeding frequency data and the attenuation exceeding degree data are processed to obtain the attenuation exceeding index, and the penetration distortion frequency data and the penetration distortion degree data are processed to obtain the penetration distortion index, which is specifically: The over-temperature frequency data and the over-temperature degree data are processed by a preset over-temperature evaluation model to obtain an over-temperature fault index; Processing the refractive index deviation frequency data and the refractive index deviation degree data through a preset refractive index evaluation model to obtain a refractive index deviation index; The attenuation exceeding standard frequency data and the attenuation exceeding standard degree data are processed by a preset attenuation evaluation model to obtain an attenuation exceeding standard index; The penetration distortion frequency data and the penetration distortion degree data are processed by a preset penetration evaluation model to obtain a penetration distortion index.
7. The optical fiber communication fault diagnosis method based on machine learning according to claim 6, characterized in that: The optical fiber communication fault index is obtained by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnosis model, specifically: Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model; The calculation formula of the optical fiber communication diagnostic model is: Among them, G ψ is the optical fiber communication fault index, T e is the over-temperature fault index, Z p is the refractive index deviation index, S c is the attenuation excess index, C b is the penetration distortion index, and α, β, γ1, and γ2 are preset characteristic coefficients.
8. The optical fiber communication fault diagnosis method based on machine learning according to claim 7, characterized in that: The optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate is judged to be different from the preset fault deviation rate threshold value, specifically: Comparing the optical fiber communication failure index with the historical optical fiber communication failure index of the same type to obtain the optical fiber communication failure deviation rate; Determining whether the optical fiber communication fault deviation rate is greater than a preset fault deviation rate threshold; If the optical fiber communication fault deviation rate is less than the preset fault deviation rate threshold, the optical fiber communication fault is within the controllable range; If the optical fiber communication fault deviation rate is greater than or equal to a preset fault deviation rate threshold, the optical fiber communication fault rate exceeds the standard.
9. A fiber optic communication fault diagnosis system based on machine learning, characterized in that: The invention comprises a memory and a processor, wherein the memory comprises a method program for diagnosing optical fiber communication faults based on machine learning, and when the method program for diagnosing optical fiber communication faults based on machine learning is executed by the processor, the following steps are implemented: Obtaining optical fiber communication information within a preset time period, and extracting optical cable line detection information and transmission signal monitoring information according to the optical fiber communication information; Extracting optical cable temperature data and optical fiber refractive index data according to the optical cable line detection information, and extracting optical signal attenuation data and optical signal penetration data according to the transmission signal monitoring information; Processing the optical cable temperature data to obtain over-temperature fault data; Processing the optical fiber refractive index data to obtain refractive index deviation data; Processing the optical signal attenuation data to obtain attenuation exceeding standard data; Processing the optical signal transmittance data to obtain transmittance distortion data; Extracting over-temperature frequency data and over-temperature degree data according to the over-temperature fault data, extracting refractive index deviation frequency data and refractive index deviation degree data according to the refractive index deviation data, extracting attenuation degree exceeding frequency data and attenuation degree exceeding degree data according to the attenuation degree exceeding data, and extracting penetration distortion frequency data and penetration distortion degree data according to the penetration distortion data; Processing the over-temperature frequency data and the over-temperature degree data to obtain an over-temperature fault index, processing the refractive index deviation frequency data and the refractive index deviation degree data to obtain a refractive index deviation index, processing the attenuation exceeding standard frequency data and the attenuation exceeding standard degree data to obtain an attenuation exceeding standard index, and processing the penetration distortion frequency data and the penetration distortion degree data to obtain a penetration distortion index; Obtaining an optical fiber communication fault index by processing the over-temperature fault index, the refractive index deviation index, the attenuation excess index and the penetration distortion index through a preset optical fiber communication diagnostic model; The optical fiber communication fault index is compared with the historical optical fiber communication fault index of the same type to obtain the optical fiber communication fault deviation rate, and the optical fiber communication fault deviation rate and the preset fault deviation rate threshold are determined.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a fiber optic communication fault diagnosis method, system and medium program based on machine learning. When the fiber optic communication fault diagnosis method, system and medium program based on machine learning are executed by a processor, the steps of the fiber optic communication fault diagnosis method based on machine learning as described in any one of claims 1 to 8 are implemented.
Citation Information
Patent Citations
Optical fiber eavesdropping monitoring method based on machine learning and related equipment
CN110518973A
Optical fiber performance monitoring method and device based on passive optical fiber network technology
CN113067633A
Fault monitoring method, device and equipment of optical fiber link and storage medium
CN113691310A
Remote control method and system for industrial power supply and medium
CN118100443A
Motor fault detection method and system and medium
CN118131043A
Cited By
Distributed solar photovoltaic support system fault diagnosis method and system
CN121919727A
A distributed solar photovoltaic support system fault diagnosis method and system
CN121919727B
