Intelligent optical cable monitoring system and method

Abstract

The invention discloses an intelligent optical cable monitoring system and method, and belongs to the technical field of optical cable fault monitoring, and the method specifically comprises the steps: collecting optical cable related data in real time, including temperature and humidity, pressure and vibration, carrying out the preprocessing of the collected optical cable related data, extracting the features of the preprocessed optical cable related data, including frequency domain features and instantaneous frequency, combining the health assessment result of the optical cable power transmission line and the external environment factors to establish an optical cable fault identification model, judging the abnormal condition and the abnormal type of the optical cable, and predicting the fault condition of the optical cable in the preset time; through real-time analysis of various parameters such as transmission data, environmental changes and health states of the optical cable, abnormal conditions in the operation process of the optical cable are found in time, early warning is given out, state changes of the optical cable can be quickly responded, potential fault hidden dangers can be recognized in advance, and the safety of the optical cable is improved. And in the face of complex environment change, load fluctuation and health state change, the evaluation capability can be adaptively adjusted in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of optical cable fault monitoring, and specifically relates to an intelligent optical cable monitoring system and method. Background Art

[0002] With the rapid development of information technology, optical cable communication, as an efficient and stable data transmission method, has been widely used in various fields, especially in industries such as telecommunications, the Internet, and data centers. Optical cables carry a large amount of information flow and data flow, and their quality and stability are crucial for the normal operation of information communication networks. However, with the increasingly complex usage environment of optical cables, optical cable lines may be affected by various factors during long-term operation and face many problems.

[0003] Deficiency 1: Especially during the operation of optical cables, factors such as external environmental changes, equipment aging, and accidental damage may cause faults or performance degradation of optical cables, affecting communication quality.

[0004] Traditional optical cable monitoring methods mainly rely on manual inspections, regular detections, and traditional sensor technologies. In recent years, artificial intelligence technology has been widely applied to the field of optical cable monitoring, but there are still deficiencies. Limitations of a single data source: Most existing monitoring methods only rely on a single data source (such as current, voltage, temperature, etc.) for judgment, ignoring the diversity and complexity of system operation; Static threshold determination: Many traditional systems judge whether a line has a fault based on a fixed threshold, but the state of an optical cable transmission line is affected by multiple factors, and this simple threshold judgment method is prone to false positives or false negatives; Difficulty in adapting to dynamic changes: In the face of complex environmental changes, load fluctuations, and health state changes, there is a lack of real-time and adaptive adjustment capabilities, resulting in the inability to effectively predict potential faults.

[0005] Deficiency 2: Optical cable lines may be affected by various external factors during long-term operation, including temperature fluctuations, mechanical bending, external collisions, damage, corrosion, etc. These factors may cause a decline in the performance of optical cable lines or even faults. Therefore, real-time monitoring and status monitoring of optical cable transmission lines are particularly important.

[0006] Currently, the monitoring methods for optical fiber lines mainly rely on analyzing the transmission signals of optical fibers. Common technologies include time-domain reflectometry (OTDR), optical power monitoring, and real-time data acquisition methods based on sensors. These traditional methods can detect some faults in the line (such as fiber breaks, connector mismatches, etc.), but there are some limitations, such as insufficient ability to identify subtle damages, inability to comprehensively reflect the actual operating state of the line, and difficulty in achieving large-scale online monitoring.

[0007] Shortcoming 3: The optical cable transmission channel is a crucial part of the fiber optic network. Any minor damage or change may affect the signal transmission quality. When dealing with a huge amount of data, it may even lead to the paralysis of the entire network. Optimizing the load of the optical cable power transmission line is the key to ensuring stable transmission of the optical cable under high-load environments. With the continuous growth of data transmission volume, the optimized management of the optical cable load becomes particularly important. Optical cable repair is a complex and costly process, especially when a fault occurs. It is crucial to quickly and accurately repair it.

[0008] However, during the long-term use of optical cables, due to factors such as external environmental changes, natural disasters, and equipment aging, they are prone to damage, resulting in problems such as signal attenuation and transmission interruption. Traditional optical cable monitoring and maintenance methods mostly rely on manual inspections, regular checks, and sensors at fixed positions, suffering from problems such as unreasonable resource allocation, inaccurate load prediction, difficulty in effectively modeling and predicting variable environmental factors, and high labor costs. Summary of the Invention

[0009] Aiming at the deficiencies of the prior art, the present invention proposes an intelligent optical cable monitoring system and method, which uses big data analysis and artificial intelligence algorithms, combines relevant data, historical data, and health status data of the optical cable to predict faults in the optical cable line in real time.

[0010] To achieve the above object, the present invention provides the following technical solutions:

[0011] An intelligent optical cable monitoring method, including:

[0012] Real-time collection of optical cable-related data, including temperature and humidity, pressure, and vibration;

[0013] Preprocessing the collected optical cable-related data;

[0014] Extracting the features of the preprocessed optical cable-related data, including: frequency domain features, instantaneous frequency, combining the health assessment results of the optical cable power transmission line and external environmental factors, establishing an optical cable fault identification model, judging the abnormal conditions and abnormal types of the optical cable, and predicting the fault conditions of the optical cable within a preset time.

[0015] Specifically, the extracting the features of the preprocessed optical cable-related data, including: frequency domain features, instantaneous frequency, combining the health assessment results of the optical cable power transmission line and external environmental factors, establishing an optical cable fault identification model, judging the abnormal conditions and abnormal types of the optical cable, and predicting the fault conditions of the optical cable within a preset time, includes:

[0016] Extracting the features of the preprocessed optical cable-related data;

[0017] Based on the historical dataset of deep learning and optical cables, an optical cable fault identification model is established and the optical cable fault identification model is trained;

[0018] Using the trained optical cable fault identification model, combined with the health assessment results of the optical cable transmission line, the faults during optical cable transmission are detected in real time;

[0019] On the basis of fault detection, the fault conditions of the optical cable within a preset time are predicted.

[0020] Specifically, the extraction of the features of the preprocessed optical cable-related data includes:

[0021] Extracting the time-domain features of the preprocessed optical cable-related data, including: the change rate ΔA(t) of the optical cable transmission loss, the maximum value V max (t) and the minimum value V min (t);

[0022] Extracting the frequency-domain features of the preprocessed optical cable-related data, including: the spectral features of the optical signal and the frequency response and resonance features of the optical signal;

[0023] Extracting the frequency features of the preprocessed optical cable-related data, including: the instantaneous frequency f(t), and the calculation method of the instantaneous frequency is: transforming the original optical signal into a complex signal, the complex signal includes the real part of the original optical signal and the imaginary part generated by the transformation, calculating the phase angle of the complex signal, taking the derivative of the phase angle of the complex signal with respect to time t to obtain the phase angle change rate, and dividing the phase angle change rate by 2π to obtain the instantaneous frequency f(t) of the optical signal at time t;

[0024] Fusing the extracted features to obtain the feature vector F(t) of the fused optical cable-related data.

[0025] Specifically, the establishment of the optical cable fault identification model based on deep learning and the historical dataset of optical cables and the training of the optical cable fault identification model include:

[0026] Selecting a deep learning algorithm to construct an optical cable fault identification model, using the historical dataset of optical cables to train the optical cable fault identification model, and setting the training target of the model to minimize the loss function. The formula of the loss function is:

[0027]

[0028] Among them, Γ represents the loss function, y a represents the annotation of the ath data in the historical dataset of the optical cable with annotations, that is, whether a fault occurs at the corresponding time of this data, represents the prediction result of the optical cable fault identification model for the ath data, xl represents the number of data in the historical dataset of the optical cable with annotations, ωya Represents the class weight of the a-th data;

[0029] Train the optical cable fault identification model until the minimum loss function of the training objective of the model converges and remains unchanged, then stop the training to obtain the trained optical cable fault identification model.

[0030] Specifically, the historical data set of the optical cable is a labeled historical data set of the optical cable, which is processed by artificial or artificial intelligence models.

[0031] Specifically, using the trained optical cable fault identification model, combined with the health assessment results of the optical cable transmission line, real-time detection of faults during optical cable transmission is carried out, including:

[0032] Input the feature vector F(t) of the fused optical cable-related data into the trained optical cable fault identification model, and calculate the preliminary fault identification probability during optical cable transmission. The specific formula is:

[0033]

[0034] Where, P flaut (t, y = c|F(t)) represents the probability of the c-th type of fault occurring at time t given the feature vector F(t), W c Represents the weight related to class c, b c Represents the bias term related to class c, m1 represents the total number of fault classes, exp(·) represents the exponential function, W e1 Represents the weight related to class e1, b e1 Represents the bias term related to class e1, y represents the fault class;

[0035] Taking into account the health assessment results of the optical cable transmission line and the influence of external environmental factors, according to the probability of the c-th type of fault occurring at time t given the feature vector F(t) and the health status evaluation value of the optical cable transmission line at time t, calculate the fault identification probability during optical cable transmission. The specific formula is:

[0036]

[0037] Where, P flaut (t) represents the fault identification probability during optical cable transmission at time t, β1, β2, and β3 represent weight coefficients used to control the influence degree of each factor in the comprehensive decision-making, φ(t) represents the environmental influence factor at time t, which is used to describe the influence of environmental factors (such as temperature, humidity, pressure, etc.) on the probability of fault occurrence, Represents the health status evaluation value of the optical cable transmission line at time t;

[0038] Select P flautThe fault category corresponding to the maximum value of (t) is used as the fault category of the optical cable.

[0039] Specifically, the preprocessing includes: data cleaning, duplicate removal, and standardization.

[0040] The data cleaning eliminates invalid, duplicate, incorrect, or incomplete data records.

[0041] The duplicate data removal identifies and removes duplicate records or redundant information.

[0042] The standardization converts the original data from one format to another format suitable for analysis and processing.

[0043] An intelligent optical cable monitoring system for implementing the intelligent optical cable monitoring method described above, includes: a data acquisition module, a data preprocessing module, and a fault detection module.

[0044] The data acquisition module is used to collect optical cable related data in real time, including temperature and humidity, pressure, and vibration.

[0045] The data preprocessing module is used to preprocess the collected optical cable related data.

[0046] The fault detection module is used to extract the characteristics of the preprocessed optical cable related data, including: frequency domain characteristics, instantaneous frequency, combine the health assessment results of the optical cable transmission line and external environmental factors, establish an optical cable fault identification model, judge the abnormal conditions and abnormal types of the optical cable, and predict the fault conditions of the optical cable within a preset time.

[0047] Specifically, the fault detection module includes a feature extraction unit, a model training unit, a fault detection unit, and a prediction unit.

[0048] The feature extraction unit is used to extract the characteristics of the preprocessed optical cable related data.

[0049] The model training unit is used to establish an optical cable fault identification model based on deep learning and the historical data set of the optical cable, and train the optical cable fault identification model.

[0050] The fault detection unit is used to use the trained optical cable fault identification model, combine the health assessment results of the optical cable transmission line, and perform real-time detection of the faults during the optical cable transmission.

[0051] The prediction unit is used to predict the fault conditions of the optical cable within a preset time based on the fault detection.

[0052] Specifically, the fault detection unit includes: a preliminary fault identification subunit and a fault identification subunit.

[0053] The preliminary fault identification subunit is used to calculate the preliminary fault identification probability during the optical cable transmission by using the trained optical cable fault identification model.

[0054] The fault identification subunit is used to calculate the fault identification probability during the optical cable transmission by comprehensively considering the health assessment results of the optical cable power transmission line and the influence of external environmental factors.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0056] 1. The present invention proposes an intelligent optical cable monitoring method. By real-time analyzing various parameters such as the transmission data, environmental changes, and health status of the optical cable, and combining the analysis of artificial intelligence algorithms, it can timely detect abnormal situations during the operation of the optical cable and issue early warnings, being able to quickly respond to the state changes of the optical cable and identify potential fault hazards in advance.

[0057] 2. The present invention proposes an intelligent optical cable monitoring method. Through automated analysis and diagnosis, it reduces the dependence on manual inspections, thereby reducing labor costs and the time cost of inspections.

[0058] 3. The present invention proposes an intelligent optical cable monitoring method. When facing complex environmental changes, load fluctuations, and health status changes, it can adjust the evaluation ability in real-time and adaptively, effectively improving the stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is the flowchart of the intelligent optical cable status monitoring method provided by the present invention;

[0060] Figure 2 is the time-domain reflectogram provided by the present invention;

[0061] Figure 3 is the flowchart of the intelligent optical cable monitoring method provided by the present invention;

[0062] Figure 4 is the flowchart of the optical cable monitoring and data analysis method provided by the present invention;

[0063] Figure 5 is the architecture diagram of the intelligent optical cable status monitoring system provided by the present invention;

[0064] Figure 6 is the architecture diagram of the intelligent optical cable monitoring system provided by the present invention;

[0065] Figure 7 is the architecture diagram of the optical cable monitoring and data analysis system provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] The present application will be described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that those of ordinary skill in the art can make several modifications and improvements without departing from the concept of the present application. These all fall within the protection scope of the present application.

[0067] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] It should be noted that if there is no conflict, the various features in the embodiments of the present application can be combined with each other, and all are within the protection scope of the present application. In addition, although functional module division is carried out in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the flowchart. In addition, the terms "first", "second", "third", etc. used in the present application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0069] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs. The terms used in this specification in the description of the present application are only for the purpose of describing specific embodiments and are not used to limit the present application. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0070] Embodiment 1

[0071] Please refer to Figures 1 - 2 , an embodiment provided by the present invention: an intelligent monitoring method for the state of an optical cable, including the following specific steps:

[0072] Step S1: Real-time collect optical cable-related data, including the structural parameters of the optical cable, optical signals, temperature and humidity, pressure, vibration, acceleration, etc.;

[0073] The structural data of the optical cable includes: the geometric shape, material properties of the optical cable, the laying environment of the optical cable, the type of the optical cable, the attenuation rate of the optical cable, etc.; the optical cable-related data also includes: vibration monitoring, the laying state of the optical cable, the load condition, etc.;

[0074] The geometric form of the optical cable includes: obtaining the length, diameter of the optical cable, outer diameter of a single optical fiber, wiring method of each optical fiber, distance between the optical fiber and the protective layer, etc.; material characteristics include: refractive index of different optical fibers, types of optical fibers (such as single-mode optical fibers, multi-mode optical fibers), and optical transmission characteristics of the optical fibers (such as transmission loss, transmission rate of the optical fiber, etc.); parameters of the installation environment include: environmental factors such as climatic conditions, temperature, humidity, geographical location, and possible mechanical stress during the installation of the optical cable; optical cable attenuation rate: the attenuation coefficient of the optical fiber provided by the manufacturer, or it can be obtained by testing the loss of the optical fiber at different wavelengths.

[0075] Specifically collecting optical signals includes: signal acquisition device selection: using a high-precision fiber optic sensor (such as an optical time domain reflectometer (OTDR)) to obtain the optical signals propagating along the optical cable. Optical signals usually include information such as wavelength, optical intensity, time delay, and phase; signal acquisition timing: regularly collecting data or sampling when specific events are triggered (such as sudden increase in load, abnormal temperature, etc.) to obtain accurate line state information; data acquisition method: using a synchronous acquisition system to perform multi-channel acquisition of optical signals of different wavelengths to ensure that signals in different dimensions can be comprehensively analyzed. The acquisition process is as follows: 1) Use the OTDR device to send optical pulses and monitor the reflected signals; 2) Record the reflected intensity and time delay at different positions to generate a time domain reflectogram; 3) Collect the optical signal intensities at different points according to different distances of the transmission path.

[0076] Types of optical signals include: optical reflection signals, optical attenuation signals, and transmission time delays.

[0077] Step S2: Preprocess the collected data related to the optical cable;

[0078] The preprocessing includes data cleaning, duplicate removal, and standardization, etc.;

[0079] The data cleaning is the first step of data preprocessing, which eliminates invalid, duplicate, incorrect, or incomplete data records. The cleaning process can be completed through methods such as setting rules, algorithms, and manual intervention. The purpose is to improve data quality and ensure the accuracy of subsequent analysis;

[0080] The data duplicate removal may occur that the same information is stored repeatedly in different data sources during the data preprocessing process. Data duplicate removal is to identify and remove duplicate records or redundant information to ensure that each piece of data appears only once, thereby reducing redundant storage and computational burden;

[0081] The standardization converts the original data from one format to another more suitable for analysis and processing. For example, it converts text data into structured data (such as JSON, XML, etc.), or converts unstructured data (such as logs, pictures, videos) into structured or semi-structured data. Through these conversion operations, the data becomes more easily analyzable and storable.

[0082] Step S3: Calculate the status of the optical cable power transmission line based on the preprocessed optical cable-related data, and evaluate the status of the optical cable power transmission line.

[0083] The specific steps of step S3 are as follows:

[0084] Step S31: Calculate the optical signal attenuation loss of the optical cable power transmission line based on the preprocessed optical cable-related data.

[0085] The specific steps of step S31 are as follows:

[0086] Step S311: The basic attenuation of the optical cable is determined by the material of the optical cable (such as glass or plastic) and the structure of the optical cable (such as the refractive index difference between the core and the cladding of the optical cable). Calculate the basic attenuation of the optical cable. The specific formula is:

[0087] A basic (d) = α0 × d,

[0088] where A basic (d) represents the basic attenuation of the optical cable, α0 represents the basic attenuation coefficient of the optical cable, and d represents the length of the optical cable.

[0089] The basic attenuation coefficient α0 is usually a constant, which can be obtained through the technical data provided by the optical cable manufacturer or experiments.

[0090] Step S312: When the optical cable is bent, the refractive index distribution of the optical cable will change, resulting in partial leakage of the optical signal and increased attenuation. The bending loss formula of the optical cable is:

[0091]

[0092] where A bend (d,R) represents the bending loss of the optical cable, α bend represents the bending loss coefficient of the optical cable, which is related to the material of the optical cable and the bending angle. R represents the bending radius of the optical cable. When the optical cable is bent excessively, the loss will increase significantly.

[0093] Step S313: Calculate the optical signal attenuation loss of the optical cable power transmission line. The specific formula is:

[0094]

[0095] where Atatal (d, R, T) represents the optical signal attenuation loss of the optical cable power transmission line, and α temp represents the attenuation coefficient of the optical cable with respect to temperature change, which is usually a constant and can be obtained through experiments. T represents the current ambient temperature of the optical cable, and T0 represents the reference temperature, usually 25 degrees Celsius.

[0096] Step S32: Generate a time-domain reflectogram based on the optical signal of the optical cable, and determine the damage location and severity of the optical cable;

[0097] The specific steps of Step S32 are as follows:

[0098] Step S321: Calculate the intensity of the reflected optical signal of the optical cable. The specific formula is:

[0099]

[0100] where S reflect represents the intensity of the reflected optical signal of the optical cable, log(·) represents the logarithmic function, P send represents the power of the transmitted optical signal, P recv represents the power of the received reflected signal, e represents the natural constant, ΔS reflect (T) represents the change in the intensity of the reflected signal caused by temperature, S da represents the change in the intensity of the reflected signal caused by the damage of the optical cable power transmission line, A joint represents the reflection loss at joints and connection points;

[0101] The principle of the above formula: The power P of the transmitted optical signal send is usually provided by a light source or a laser and is directly related to the intensity of the light source of the system. Due to factors such as optical cable damage, joints, or bending, the optical signal will be reflected, and part of the optical signal is reflected and returned to the monitoring device. The power P of the received reflected signal recv is an important basis for judging the state of the optical fiber. Generally, the greater the reflection intensity, the more serious the damage or other problems. Considering the influence of multiple factors on the optical signal comprehensively can more accurately reflect the state of the optical cable power transmission line. Through the comprehensive calculation of these factors, it can more carefully evaluate whether there are problems with the optical cable (such as damage, joint problems, excessive bending, etc.).

[0102] Step S322: Construct a time-domain reflectogram with the propagation distance of the optical signal as the horizontal axis and the intensity of the reflected optical signal of the optical cable as the vertical axis;

[0103] The time-domain reflectogram (OTDRTrace) is a map of the optical signal reflection data collected by an optical time-domain reflectometer (OTDR). The OTDR technology can help locate problems such as damage points, bends, and joint losses in the optical cable by sending short pulses of optical signals and measuring the time and intensity of the signals reflected from various positions of the optical cable;

[0104] Reference Figure 2 Among them, Damage Point: a severely damaged reflection point, Bend: reflection caused by a slight bend, Joint Loss: loss reflection of the joint, Start Point: the left side of the figure is the starting position where the OTDR starts testing, usually the point where the OTDR device is connected to the optical cable; Signal Attenuation Region: most of the middle part of the optical cable shows asymptotic attenuation, reflecting the propagation loss of the signal in the optical cable. This attenuation can be caused by factors such as the material, length, and loss of the optical cable; Reflection Spike: If there are joints, breakpoints, or damages in the optical cable, the OTDR will display reflection spikes at the corresponding positions. The height of the spike is proportional to the severity of the damage. Large Reflection Spike: usually indicates relatively serious problems such as fiber breakage and joint failure. Small Reflection Spike: may indicate minor damages such as slight bends or minor losses of joints; End Reflection: There is usually a large reflection spike at the end of the optical cable, indicating that the optical signal reaches the end of the fiber and is reflected back to the OTDR. There is a quantitative threshold for large and small reflection spikes, which can be set according to the actual situation.

[0105] Step S323: Calculate the position of the optical cable damage point according to the reflection time delay of the reflected optical signal of the optical cable. The specific formula is:

[0106]

[0107] Among them, x da represents the position of the optical cable damage point, c1 represents the speed of light, Δt represents the time delay of the reflected optical signal, usually recorded by the OTDR device, and n1 represents the refractive index of the optical cable;

[0108] Step S324: Establish an optical cable damage assessment model to evaluate the severity of the optical cable damage. The specific formula is:

[0109]

[0110] Among them, represents the evaluation value of the severity of the optical cable damage, d da represents the distance from the optical cable damage point to the monitoring device. Considering the influence of distance on signal attenuation, η type represents the coefficient of the optical cable damage type, which describes the influence of the damage type on the severity. ΔT represents the temperature change amount, which affects the evaluation accuracy of the damage. α reflect 、α dis 、α type and αt em represent the weight coefficients, which describe the proportion of each factor in the evaluation of the severity of the optical cable loss and can be obtained through experiments;

[0111] In this embodiment, the coefficient η of the optical cable damage type type , is set according to the specific type of damage, and the following classification criteria can be adopted: η type = 1 indicates fracture and severe joint defects. When η type = 0.5, it indicates slight joint mismatch. When η type = 0.1, it indicates microbending and slight damage. Different types of damage will have different effects on the reflection signal intensity. For example, a fiber break generates a relatively large reflection signal intensity, while joint mismatch or slight bending generates a relatively small reflection signal.

[0112] Step S325: Define the severity of the optical cable damage according to the evaluation value of the optical cable damage severity. When is less than 10, it is a slight damage, usually manifested as slight joint loss or bending. When is greater than or equal to 10 and less than or equal to 30, it is a moderate damage. When is greater than 30, it is a severe damage.

[0113] Step S33: Establish an overall state evaluation model of the optical cable by comprehensively considering the optical signal attenuation loss, the location of the optical cable damage, and the evaluation value of the damage severity.

[0114] The specific steps of Step S33 are as follows:

[0115] Step S331: Establish an overall state evaluation model of the optical cable according to the optical signal attenuation loss, the location of the optical cable damage, and the evaluation value of the damage severity. The specific formula is:

[0116]

[0117] where, represents the evaluation value of the health state of the optical cable transmission line, n represents the number of sampling points of the optical cable transmission line, A total (d i , R i , T i ) represents the optical signal attenuation loss of the optical cable transmission line at the i-th sampling point, P recv (d i ) represents the power of the reflected signal received by the optical cable transmission line at the i-th sampling point, m represents the number of damage points, represents the evaluation value of the damage severity at the j-th damage point of the optical cable transmission line, and (x da , j) represents the location of the j-th damage point;

[0118] Principle of the above formula: The health status of the optical cable power transmission line is calculated by weighted average based on the influence of various physical phenomena (such as bending loss, temperature change, damage reflection, etc.) on the optical signal. The optical cable length d is used to normalize the entire optical cable line to eliminate the influence of line length differences on the state calculation. The longer the optical cable length, the greater the cumulative loss and reflection. Therefore, the total length d enables the comprehensive state parameter to be comparable under different line lengths. To obtain an accurate assessment of the optical fiber state, measurements are usually taken at multiple points, and information such as loss, temperature, and bending radius at different points is recorded, and then the influence of the state at this point on the overall optical fiber is calculated.

[0119] The formula calculates the health status assessment value of the optical cable power transmission line by comprehensively considering the transmission distance, temperature change, bending loss, basic attenuation, and damage reflection signal of the optical cable, and combining the information of the sampling points. Each factor has different weights on the final result, and the overall assessment value of the optical fiber state is obtained by weighted summation.

[0120] Step S332: Set the optical cable health threshold as If is greater than the optical cable health threshold it is determined that there is a fault or damage in the optical cable power transmission line.

[0121] Embodiment 2

[0122] Please refer to Figure 3 One embodiment provided by the present invention: An intelligent optical cable monitoring method includes the following specific steps:

[0123] Step 1: Real-time collect optical cable-related data, including the structural parameters of the optical cable, optical signal, temperature and humidity, pressure, vibration, and acceleration, etc.;

[0124] The structural data of the optical cable includes: the geometric shape, material properties of the optical cable, the laying environment of the optical cable, the type of optical fiber, and the attenuation rate of the optical cable, etc.; The optical cable-related data also includes: vibration monitoring, optical cable laying status, load conditions, etc.;

[0125] The geometric shape of the optical cable includes: obtaining the length, diameter of the optical cable, the outer diameter of a single optical fiber, the wiring method of each optical fiber, the distance between the optical fiber and the protective layer, etc.; The material properties include: the refractive index of different optical fibers, the type of optical fiber (such as single-mode optical fiber, multi-mode optical fiber), and the optical transmission characteristics of the optical fiber (such as transmission loss, transmission rate of the optical fiber, etc.); The parameters of the laying environment include: environmental factors such as the climate conditions, temperature, humidity, geographical location, and possible mechanical stress where the optical cable is installed; The optical cable attenuation rate: the attenuation coefficient of the optical fiber provided by the manufacturer, or it can also be obtained by testing the loss of the optical fiber at different wavelengths.

[0126] The specific process of collecting optical signals includes: signal collection device selection: using high-precision fiber optical sensors (such as optical time domain reflectometer (OTDR)) to obtain optical signals propagating along the optical cable. Optical signals usually include information such as wavelength, light intensity, delay, phase, etc.; signal collection timing: collecting data regularly or sampling when triggered by specific events (such as sudden load increase, temperature abnormality, etc.) to obtain accurate line status information; data collection method: using a synchronous collection system to collect optical signals of different wavelengths in multiple channels to ensure that signals of different dimensions can be comprehensively analyzed. The collection process is: 1) Use OTDR equipment to send optical pulses and monitor reflected signals; 2) Record the reflection intensity and delay at different locations to generate a time domain reflection diagram; 3) Collect the optical signal intensity at different points according to the different distances of the transmission path.

[0127] Optical signal types include: optical reflection signal, optical attenuation signal and transmission delay.

[0128] Step 2: Preprocess the collected optical cable related data;

[0129] The preprocessing includes data cleaning, deduplication and standardization, etc.;

[0130] Data cleaning is the first step in data preprocessing, which removes invalid, duplicate, erroneous or incomplete data records. The cleaning process can be completed by setting rules, algorithms, manual intervention, etc., in order to improve data quality and ensure the accuracy of subsequent analysis.

[0131] In the data preprocessing process, the same information may be stored repeatedly in different data sources. Data deduplication is to identify and remove duplicate records or redundant information to ensure that each piece of data appears only once, thereby reducing redundant storage and computing burden;

[0132] The standardization converts the raw data from one format into another format that is more suitable for analysis and processing. For example, text data is converted into structured data (such as JSON, XML, etc.), or unstructured data (such as logs, pictures, videos) is converted into structured or semi-structured data. Through these conversion operations, the data is easier to analyze and store.

[0133] Step 3: Extract the features of the pre-processed optical cable related data, including frequency domain features and instantaneous frequency. Combined with the health assessment results of the optical cable transmission line and external environmental factors, establish an optical cable fault identification model to determine the abnormal conditions and abnormal types of the optical cable, and predict the fault conditions of the optical cable within a preset time.

[0134] The specific steps of step 3 are:

[0135] Step 31: extracting features of the pre-processed optical cable related data;

[0136] The specific steps of step 31 are as follows:

[0137] Step 311: Extract the time-domain characteristics of the preprocessed optical cable-related data, including: the change rate ΔA(t) of the optical cable transmission loss, the maximum value V max (t) and the minimum value V min (t);

[0138] Specifically, the specific formula for the change rate ΔA(t) of the optical cable transmission loss is: ΔA(t) = A total (d, R, T, t) - A total (d, R, T, t - 1), where A tatal (d, R, T, t) represents the optical signal attenuation loss of the optical cable power transmission line at time t, and A tatal (d, R, T, t - 1) represents the optical signal attenuation loss of the optical cable power transmission line at time t - 1. The maximum value V max (t) and the minimum value V min (t) are specifically formulated as: V max (t) = max(P signal (t) - pj(P signal )) and V min (t) = min(P signal (t) - pj(P signal ))), where max(·) represents the maximum value function, min(·) represents the minimum value function, P signal (t) represents the optical signal intensity at time t, and pj(P signal ) represents the average value of the optical signal intensity over a period of time.

[0139] Step 312: Extract the frequency-domain characteristics of the preprocessed optical cable-related data, including: the spectral characteristics of the optical signal and the frequency response and resonance characteristics of the optical signal;

[0140] The signal frequency components in optical cable transmission can be analyzed through Fourier transform. The characteristic frequency points (such as fundamental frequency, harmonic frequency) in the spectrum can provide valuable information, such as signal distortion, nonlinear effects, or other physical damages. If abnormal frequency components appear in the spectrum, it may indicate a fault in the optical fiber or equipment; the optical cable may cause changes in physical properties due to environmental factors (such as temperature and humidity changes), resulting in changes in the frequency response of the optical signal. By comparing the spectral differences between the input and output signals, the attenuation characteristics, transmission loss, and whether there are abnormal frequency responses of the signal can be analyzed, which is very effective for detecting possible damages or the influence of environmental factors in the optical cable.

[0141] Step 313: Extract the frequency characteristics of the preprocessed optical cable-related data, including: the instantaneous frequency f(t);

[0142] The instantaneous frequency of the optical signal is extracted by Hilbert transform, which can reflect the frequency change of the optical signal over time. It is applicable to the non-linear distortion caused by vibration or external interference during the optical cable transmission. The instantaneous frequency f(t) is the frequency component of the optical signal at time t, and the specific formula is: represents the complex signal after Hilbert transform, which contains the real part of the original optical signal P sign (t) and the imaginary part generated by Hilbert transform. represents the complex signal of the phase angle. represents the phase angle change rate, which is the derivative of the phase angle with respect to time t.

[0143] Instantaneous frequency principle: The instantaneous frequency is defined by solving the phase angle change rate of the signal. Specifically, the rate at which the phase angle changes over time is the instantaneous frequency. Since the optical fiber signal may be affected by factors such as environmental changes, damage, and noise during the propagation process, these factors will cause fluctuations in the instantaneous frequency. Therefore, by analyzing the instantaneous frequency, signal abnormalities or potential faults can be detected. By calculating the instantaneous frequency of the complex signal, problems such as non-linear distortion, frequency drift caused by vibration, and external interference during optical fiber transmission can be identified.

[0144] Step 314: Fuse the extracted features to obtain the feature vector F(t) of the fused optical cable-related data.

[0145] Step 32: Based on deep learning and the historical dataset of the optical cable, establish an optical cable fault identification model and train the optical cable fault identification model.

[0146] It should be noted that the historical dataset of the optical cable here has been processed, that is, each piece of data is labeled with the corresponding label.

[0147] Step 321: Select a deep learning algorithm to construct an optical cable fault identification model, use the historical dataset of the optical cable to train the optical cable fault identification model, and set the training goal of the model to minimize the loss function. The formula of the loss function is:

[0148]

[0149] where Γ represents the loss function, and y a represents the annotation of the a-th data in the historical dataset of the optical cable with annotation, that is, whether a fault occurs at the corresponding time of this data. represents the prediction result of the optical cable fault identification model for the a-th data, and xl represents the number of data in the historical dataset of the optical cable with annotation. Represents the class weight of the a-th data, which is used to handle class imbalance. For example, if the number of samples in a certain class is small, a higher weight can be given to it;

[0150] Cross-entropy loss is a commonly used method to measure the difference between two probability distributions. In classification problems, it evaluates the distance between the predicted distribution output by the model and the true distribution. At the same time, weights are introduced to balance the impact brought by class imbalance. In many practical applications, the number of samples in some classes may be significantly less than that in other classes, resulting in the model's bias towards the major classes. By giving higher weights to the samples of the minority classes, the model can pay more attention to these samples during training, thereby improving its prediction performance. The minimization objective of this loss function is to adjust the model parameters through iterative optimization (such as gradient descent) to make the prediction results closer to the true labels. This method can not only improve the accuracy of the model but also enhance the ability to identify minority class faults.

[0151] Step 322: Train the optical cable fault identification model until the minimum loss function of the training objective of the model converges and remains unchanged, then stop training to obtain the trained optical cable fault identification model.

[0152] Among them, the historical dataset of the optical cable includes normal data and fault data.

[0153] Step 33: Use the trained optical cable fault identification model, combined with the health assessment results of the optical cable transmission line, to detect faults during optical cable transmission in real time;

[0154] The specific steps of Step 33 are as follows:

[0155] Step 331: Input the feature vector F(t) of the fused optical cable-related data into the trained optical cable fault identification model, and calculate the preliminary fault identification probability during optical cable transmission. The specific formula is:

[0156]

[0157] Among them, P flaut (t, y = c|F(t)) represents the probability of the c-th type of fault occurring at time t under the given feature vector F(t). W c represents the weight related to class c, b c represents the bias term related to class c, m1 represents the total number of fault classes, exp(·) represents the exponential function, W e1 represents the weight related to class e1, b e1 represents the bias term related to class e1, y represents the fault class;

[0158] Step 332: Considering the health assessment results of the optical cable transmission line and the influence of external environmental factors comprehensively, calculate the fault identification probability during optical cable transmission. The specific formula is:

[0159]

[0160] Among them, P flaut (t) represents the fault recognition probability during the optical cable transmission at time t. β1, β2, and β3 represent weight coefficients used to control the influence degree of each factor in the comprehensive decision-making. φ(t) represents the environmental impact factor at time t, which is used to describe the influence of environmental factors (such as temperature, humidity, pressure, etc.) on the fault occurrence probability. represents the health status evaluation value of the optical cable power transmission line at time t;

[0161] Explanation and principle of the above formula: The specific formula of the environmental impact factor φ(t) at time t is: Among them, δ represents the adjustment factor of environmental impact, which is used to adjust the influence degree of environmental factors in the comprehensive decision-making. H represents the number of environmental impact factors, and Hj h represents the influence function of the change of the h-th environmental impact factor on the occurrence of optical cable faults. For example, the specific formula of the temperature influence function is: Among them, Hj wd represents the temperature influence function, and α T represents the temperature sensitivity parameter, which controls the influence intensity of temperature on the fault occurrence probability. T(t) represents the temperature of the environment where the optical cable is located at time t, and T threshold represents the temperature threshold, which is a reference temperature. The influence process of temperature on the optical cable is non-linear, and too high or too low temperature may cause faults in the optical cable; the specific formula of the humidity influence function is: Among them, Hj sd represents the humidity influence function, and α Hs represents the humidity sensitivity parameter, which controls the influence intensity of humidity on the fault occurrence probability. Hs env (t) represents the humidity of the environment where the optical cable is located at time t, and Hs threshold represents the humidity threshold, which is a reference humidity. Humidity is one of the important factors affecting optical cable materials and equipment. Too high humidity will cause problems such as corrosion of optical cable connection points and deterioration of the insulation layer, indirectly leading to optical cable faults.

[0162] Through the external environmental impact factor, the response strategy can be automatically adjusted to identify and adapt to the influence of environmental factors on the fault occurrence probability. Combining the health status evaluation and the fault recognition model, through multi-dimensional data fusion (such as sensor data, historical fault data, environmental factors, etc.), the state of the optical cable can be more comprehensively reflected, rather than simply relying on a single fault recognition technology.

[0163] Step 333: Select the fault category corresponding to the maximum value of P flaut (t) as the fault category of the optical cable.

[0164] Step 34: On the basis of fault detection, predict the fault situation of the optical cable within a preset time.

[0165] Embodiment 3

[0166] Please refer to Figure 4 , an embodiment provided by the present invention: A method for optical cable monitoring and data analysis includes the following specific steps:

[0167] Step A1: Collect optical cable related data in real time, including the structural parameters of the optical cable, optical signals, temperature and humidity, pressure, vibration, acceleration, transmission data, load data, etc.;

[0168] The structural data of the optical cable includes: the geometric shape of the optical cable, material properties, the laying environment of the optical cable, the type of optical fiber, and the attenuation rate of the optical cable, etc.; The optical cable related data also includes: vibration monitoring, optical cable laying status, load conditions, etc.;

[0169] The geometric shape of the optical cable includes: obtaining the length, diameter of the optical cable, the outer diameter of a single optical fiber, the wiring method of each optical fiber, the distance between the optical fiber and the protective layer, etc.; Material properties include: the refractive index of different optical fibers, the type of optical fiber (such as single-mode optical fiber, multi-mode optical fiber), and the optical transmission characteristics of the optical fiber (such as transmission loss, transmission rate of the optical fiber, etc.); The parameters of the laying environment include: environmental factors such as the climate conditions, temperature, humidity, geographical location, and possible mechanical stress where the optical cable is installed; Optical cable attenuation rate: the attenuation coefficient of the optical fiber provided by the manufacturer, or it can be obtained by testing the loss of the optical fiber at different wavelengths.

[0170] Specifically collecting optical signals includes: Signal collection device selection: Use a high-precision fiber optic sensor (such as an optical time domain reflectometer (OTDR)) to obtain the optical signals propagating along the optical cable. Optical signals usually include information such as wavelength, optical intensity, time delay, and phase; Signal collection timing: Regularly collect data or sample when a specific event is triggered (such as a sudden increase in load, abnormal temperature, etc.) to obtain accurate line status information; Data collection method: Use a synchronous collection system to perform multi-channel collection of optical signals of different wavelengths to ensure that signals in different dimensions can be comprehensively analyzed. The collection process is: 1) Use the OTDR device to send optical pulses and monitor the reflected signals; 2) Record the reflected intensity and time delay at different positions to generate a time domain reflectogram; 3) Collect the optical signal intensity at different points according to different distances of the transmission path.

[0171] The types of optical signals include: optical reflection signals, optical attenuation signals, and transmission time delays.

[0172] Step A2: Preprocess the collected optical cable related data;

[0173] The preprocessing includes data cleaning, duplicate removal, and standardization, etc.;

[0174] The data cleaning, which is the first step of data preprocessing, eliminates invalid, duplicate, incorrect, or incomplete data records. The cleaning process can be completed by setting rules, algorithms, manual intervention, etc. The purpose is to improve data quality and ensure the accuracy of subsequent analysis;

[0175] The data deduplication may occur that the same information is stored repeatedly in different data sources during the data preprocessing. Data deduplication is to identify and remove duplicate records or redundant information to ensure that each piece of data appears only once, thereby reducing redundant storage and computational burden;

[0176] The standardization converts the original data from one format to another more suitable for analysis and processing. For example, converting text data into structured data (such as JSON, XML, etc.), or converting unstructured data (such as logs, pictures, videos) into structured or semi-structured data. Through these conversion operations, the data becomes more easily analyzable and storable.

[0177] Step A3: Analyze the preprocessed optical cable-related data, combine the fault prediction results and optical cable fault detection results of the optical cable power transmission line, allocate the transmitted optical signal data to the optical cable, and optimize the decision on the operating state of the optical cable power transmission line.

[0178] The specific steps of Step A3 are as follows:

[0179] Step A31: Allocate the transmitted optical signal data to the optical cable and select the optimal optical cable transmission channel;

[0180] The specific steps of Step A31 are as follows:

[0181] Step A311: Set the set of transmission channels for optical signal data transmission in the optical cable as L, L = {l1, l2, ……, l o}, l o represents the o-th transmission channel for optical signal data transmission in the optical cable;

[0182] Step A312: Calculate the priority of the o-th transmission channel. The calculation formula is:

[0183]

[0184] Among them, YX o represents the priority of the o-th transmission channel, eff represents the signal quality indicator. The better the signal quality, the higher the channel priority. α rl represents the capacity adjustment factor, reflecting the influence of channel capacity on the priority. r represents the historical transmission rate. The higher the rate, the higher the priority. e represents the natural constant, sjl represents the data volume of the optical signal data, Z fsRepresents the period of the optical signal data to the target receiving device. Reflects the impact of data volume and transmission period on priority. The larger the data volume and the shorter the period, the higher the priority. κ represents the penalty factor, fzo represents the load of the o-th transmission channel, fz o_max Represents the maximum load of the o-th transmission channel, and max(·) represents the maximum value function. Represents the penalty part. When the channel load is too high, its priority is reduced. Considering these factors to evaluate the channel priority and achieve the optimal channel selection.

[0185] The principle of the above formula: The better the signal quality of the transmission channel, the higher the priority. The channel quality can be measured by the transmission rate ratio, transmission time, and penalty. By evaluating the priority of each channel, the transmission channels and computing resources can be reasonably allocated among multiple communication channels to ensure that critical tasks are given priority, improve the overall transmission quality of the system, and reduce packet loss and latency.

[0186] Step A313: Select the transmission channel corresponding to max(YX o ) as the optimal optical cable transmission channel for sending optical signal data to the target receiving device.

[0187] Step A32: Monitor the load of the optical cable power transmission line in real time.

[0188] Based on the voltage of the optical cable power transmission line at time t, the current of the optical cable power transmission line at time t, the phase difference between the voltage and current of the optical cable power transmission line at time t, the temperature difference of the optical cable power transmission line at time t, and the health status evaluation value of the optical cable power transmission line at time t, calculate the load of the optical cable power transmission line at time t. The calculation formula for the load of the optical cable power transmission line is:

[0189]

[0190] Among them, U realtime (t) represents the load of the optical cable power transmission line at time t, V(t) represents the voltage of the optical cable power transmission line at time t, I(t) represents the current of the optical cable power transmission line at time t, ι(t) represents the phase difference between the voltage and current of the optical cable power transmission line at time t, γ dz Represents the resistance temperature coefficient, T1(t) represents the temperature of the optical cable power transmission line at time t, T0 represents the reference temperature. Represents the health status evaluation value of the optical cable power transmission line at time t.

[0191] Principle of the above formula: Through this comprehensive formula, the real-time load of the optical cable power transmission line under different environmental conditions and health states can be accurately calculated. This formula not only considers electrical parameters but also incorporates the influences of temperature and health state into the calculation, thereby improving the accuracy and reliability of load calculation. Here, the load of the optical cable power transmission line and the load of the transmission channel are not the same concept. One is the data transmission load, and the other is the electrical-related load.

[0192] Step A33: Intelligently optimize the load distribution of the optical cable power transmission line according to the health state evaluation value, fault prediction result, and real-time load of the optical cable power transmission line.

[0193] The specific steps of Step A33 are as follows:

[0194] Step A331: Set the load of the u-th optical cable power transmission line as U realtime,u (t), and the maximum bearing capacity is The health state evaluation value is Construct the overall efficiency model of the optical cable power transmission line.

[0195] Step A332: Set the objective function of the overall efficiency model of the optical cable power transmission line. The specific formula is:

[0196]

[0197] Among them, Ψ load (t) represents the objective function of the overall efficiency model of the optical cable power transmission line. The goal is to minimize this value, indicating the degree of load optimization, that is, the overall efficiency of the optical cable power transmission line. represents the healthy load of the u-th optical cable power transmission line at time t. The safe load is dynamically adjusted according to the health state of each optical cable power transmission line to avoid safety problems caused by line failures. It is a function based on health assessment and reflects the influence of health status on the maximum bearing load. us represents the number of optical cable power transmission lines, and θ represents the adjustment factor, which determines the influence degree of load safety on the objective function. The introduction of this factor makes load safety an important weight in the optimization goal.

[0198] Principle and parameter analysis of the above formula: 1) Load balance It reflects the balance of load distribution. Specifically, this term represents the ratio of the actual load of the u-th optical cable power transmission line to the maximum bearing capacity. The smaller this ratio, the less the optical cable power transmission line is overloaded and the more uniform the load. The larger this ratio, the closer the load of the optical cable power transmission line is to the maximum bearing capacity and the more unbalanced the load distribution. The optimization goal is to adjust the load distribution so that the load of each optical cable power transmission line is as close as possible to the maximum bearing capacity but does not exceed its bearing limit. 2) Safe load limit To measure the security of load distribution. Specifically, is the dynamically adjusted upper limit of the safe load based on the health status of the optical cable power transmission line and environmental factors. When the health status of the optical cable power transmission line deteriorates, this value will decrease, reflecting the reduced load-bearing capacity of the optical cable power transmission line; the purpose of this item is to avoid overloading on lines with poor health status, thereby preventing faults or damages to the optical cable power transmission line; 3) The adjustment factor θ is used to balance between load balance and security. Specifically, when θ is small (e.g., close to zero), the objective function mainly focuses on load balance, that is, to make the load ratios of all optical cable power transmission lines as close to the maximum value as possible, ignoring security. When θ is large, the objective function pays more attention to security, that is, to avoid allocating too much load to optical cable power transmission lines with poor health status, even if this may lead to uneven load distribution. Therefore, by adjusting the value of θ, the optimization objective of the system can be flexibly controlled, and the relationship between load balance and security can be balanced;

[0199] Generally speaking, through this item, the load of each optical cable power transmission line is made as close as possible to the maximum bearing capacity, thereby achieving load balance of the system; through this item, the load distribution is dynamically adjusted to avoid overloading lines with poor health status and ensure the safe operation of the system; through the θ adjustment factor, the balance between load balance and security can be flexibly adjusted to achieve the optimization objective for different application scenarios.

[0200] Step A333: Set the constraint conditions, and the specific formula is:

[0201]

[0202] where U total (t) represents the total load demand. The total load distribution should meet the power supply demand of the system, that is, the sum of the loads of all optical cable power transmission lines is equal to the total demand;

[0203] Step A334: Solve the overall efficiency model of the optical cable power transmission line through the objective function and constraint conditions to obtain the optimal load distribution and the highest overall efficiency of the optical cable power transmission line.

[0204] Step A34: Perform intelligent scheduling for maintenance and repair work.

[0205] Performing intelligent scheduling for maintenance and repair work aims to intelligently schedule maintenance and repair work according to the fault prediction results and the health status of the optical cable power transmission line, minimize the outage time and operation and maintenance costs, and the optimization objective is to balance the maintenance cost and the normal operation time of the system to ensure efficient and low-risk maintenance.

[0206] In this embodiment, load balancing and maintenance scheduling optimization are two core functions of the intelligent decision-making and optimization layer. The two complement each other and jointly improve the overall performance of the system. In practical applications, these two optimization processes can be synergistically optimized through an integrated approach, that is, during the load balancing process, combined with the information of maintenance scheduling, to avoid frequent outages of overloaded lines for maintenance, thereby reducing the operation and maintenance costs and the risk of faults.

[0207] Embodiment 4

[0208] Please refer to Figures 5 - 7 , another embodiment provided by the present invention: an intelligent optical cable monitoring system, including: a data acquisition module, a data preprocessing module, a status evaluation module, a fault detection module, and a data analysis and decision-making module;

[0209] The data acquisition module is used to collect optical cable-related data in real time;

[0210] The data preprocessing module is used to preprocess the collected optical cable-related data;

[0211] The status evaluation module is used to calculate the status of the optical cable transmission line based on the preprocessed optical cable-related data and evaluate the status of the optical cable transmission line;

[0212] The status evaluation module includes: an attenuation loss calculation unit, a damage judgment unit, and an overall status evaluation unit;

[0213] The attenuation loss calculation unit is used to calculate the optical signal attenuation loss of the optical cable transmission line based on the preprocessed optical cable-related data;

[0214] The damage judgment unit is used to generate a time-domain reflection diagram based on the optical signal of the optical cable and judge the damage position and severity of the optical cable;

[0215] The overall status evaluation unit is used to comprehensively consider the optical signal attenuation loss, the damage position of the optical cable, and the evaluation value of the damage severity, and establish an overall status evaluation model of the optical cable.

[0216] The damage judgment unit includes: a loss position calculation subunit and a loss severity evaluation subunit;

[0217] The loss position calculation subunit is used to calculate the position of the optical cable damage point based on the reflection time delay of the reflected optical signal of the optical cable;

[0218] The loss severity evaluation subunit is used to establish an optical cable damage evaluation model and evaluate the severity of the optical cable damage.

[0219] The fault detection module is used to extract the features of the pre - processed optical cable - related data, including: frequency - domain features, instantaneous frequency. Combining the health assessment results of the optical cable transmission line and external environmental factors, it establishes an optical cable fault identification model to judge the abnormal conditions and abnormal types of the optical cable, and predict the fault conditions of the optical cable within a preset time;

[0220] The fault detection module includes a feature extraction unit, a model training unit, a fault detection unit, and a prediction unit;

[0221] The feature extraction unit is used to extract the features of the pre - processed optical cable - related data;

[0222] The model training unit is used to establish an optical cable fault identification model based on deep learning and the historical data set of the optical cable, and train the optical cable fault identification model;

[0223] The fault detection unit is used to use the trained optical cable fault identification model, combined with the health assessment results of the optical cable transmission line, to detect the faults during the optical cable transmission in real - time;

[0224] The prediction unit is used to predict the fault conditions of the optical cable within a preset time on the basis of fault detection.

[0225] The fault detection unit includes: a preliminary fault identification subunit and a fault identification subunit;

[0226] The preliminary fault identification subunit is used to calculate the preliminary fault identification probability during the optical cable transmission by using the trained optical cable fault identification model;

[0227] The fault identification subunit is used to comprehensively consider the influence of the health assessment results of the optical cable transmission line and external environmental factors, and calculate the fault identification probability during the optical cable transmission.

[0228] The data analysis and decision - making module is used to analyze the pre - processed optical cable - related data, combine the fault prediction results and fault detection results of the optical cable transmission line, allocate the transmitted optical signal data to the optical cable, and make an optimal decision on the operation state of the optical cable transmission line.

[0229] The data analysis and decision - making module includes: a channel optimization unit, a load calculation unit, a load intelligent allocation unit, and an intelligent scheduling unit;

[0230] The channel optimization unit is used to calculate and select the optimal transmission channel for the optical signal data transmission;

[0231] The load calculation unit is used to calculate the real - time load of the optical cable transmission line;

[0232] The load intelligent distribution unit is used to solve the overall efficiency model of the optical cable power transmission line, and obtain the optimal load distribution and the highest overall efficiency of the optical cable power transmission line;

[0233] The intelligent scheduling unit is used to intelligently schedule the maintenance and repair work of the optical cable.

[0234] The load intelligent distribution unit includes: a modeling subunit, an objective function subunit, a constraint subunit, and a solution subunit;

[0235] The modeling subunit is used to construct an overall efficiency model of the optical cable power transmission line according to the health status evaluation value, fault prediction result, and real-time load of the optical cable power transmission line;

[0236] The objective function subunit is used to set the objective function of the overall efficiency model of the optical cable power transmission line;

[0237] The constraint subunit is used to set the constraint conditions of the overall efficiency model of the optical cable power transmission line;

[0238] The solution subunit is used to solve the overall efficiency model of the optical cable power transmission line through the objective function and constraint conditions.

[0239] In addition, the parts of the above technical solutions provided in the embodiments of the present application that are consistent with the corresponding technical solutions in the prior art in terms of implementation principles are not described in detail to avoid excessive elaboration.

[0240] As described above in the specific embodiments, the purpose, technical solutions, and beneficial effects of the present invention are further described in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent optical cable monitoring method, characterized in that, It includes: Collect real-time data related to the optical cable, including temperature and humidity, pressure, and vibration; Preprocess the data related to the optical cable collected; Extract the features of the preprocessed data related to the optical cable, including: frequency-domain features, instantaneous frequency, combine the health assessment results of the optical cable transmission line and external environmental factors, establish an optical cable fault identification model, judge the abnormal conditions and abnormal types of the optical cable, and predict the fault conditions of the optical cable within a preset time.

2. The intelligent optical cable monitoring method according to claim 1, wherein, The extracting the features of the preprocessed data related to the optical cable, including: frequency-domain features, instantaneous frequency, combine the health assessment results of the optical cable transmission line and external environmental factors, establish an optical cable fault identification model, judge the abnormal conditions and abnormal types of the optical cable, and predict the fault conditions of the optical cable within a preset time, includes: Extract the features of the preprocessed data related to the optical cable; Based on deep learning and the historical dataset of the optical cable, establish an optical cable fault identification model and train the optical cable fault identification model; Use the trained optical cable fault identification model, combine the health assessment results of the optical cable transmission line, and conduct real-time detection of the faults during the optical cable transmission; On the basis of fault detection, predict the fault conditions of the optical cable within a preset time.

3. The intelligent optical cable monitoring method according to claim 2, wherein The extracting the features of the preprocessed data related to the optical cable, includes: Extract the time-domain features of the optical cable-related data after preprocessing, including: the change rate ΔA(t) of the optical cable transmission loss, the maximum value V max (t) and the minimum value V min (t); Extract the frequency-domain features of the preprocessed data related to the optical cable, including: the spectral features of the optical signal and the frequency response and resonance features of the optical signal; Extract the frequency features of the preprocessed data related to the optical cable, including: instantaneous frequency f(t), and the calculation method of the instantaneous frequency is: transform the original optical signal into a complex signal, the complex signal includes the real part of the original optical signal and the imaginary part generated by the transformation, calculate the phase angle of the complex signal, take the derivative of the phase angle of the complex signal with respect to time t to obtain the phase angle change rate, and divide the phase angle change rate by 2π to obtain the instantaneous frequency f(t) of the optical signal at time t; Fuse the extracted features to obtain the feature vector F(t) of the data related to the optical cable after fusion.

4. The intelligent optical cable monitoring method according to claim 3, wherein The based on deep learning and the historical dataset of the optical cable, establish an optical cable fault identification model and train the optical cable fault identification model, includes: Select a deep learning algorithm to construct an optical cable fault identification model, use the historical dataset of the optical cable to train the optical cable fault identification model, and set the training objective of the model to minimize the loss function; Train the optical cable fault identification model until the minimum loss function of the training objective of the model converges and remains unchanged, then stop training to obtain the trained optical cable fault identification model.

5. The intelligent optical cable monitoring method according to claim 4, characterized in that The historical dataset of the optical cable is a labeled historical dataset of the optical cable, which is processed by artificial or artificial intelligence models.

6. The intelligent optical cable monitoring method according to claim 5, wherein The using the trained optical cable fault identification model, combine the health assessment results of the optical cable transmission line, and conduct real-time detection of the faults during the optical cable transmission, includes: Input the feature vector F(t) of the fused optical cable related data into the trained optical cable fault identification model, and calculate the probability P of the occurrence of the c-th type of fault at time t given the feature vector F(t). flaut (t, y = c|F(t)), where y represents the fault category; Considering the health assessment results of the optical cable transmission line and the influence of external environmental factors comprehensively, according to the probability of the occurrence of the c-th type of fault at time t under the given feature vector F(t) and the health state evaluation value of the optical cable transmission line at time t, calculate the fault recognition probability P flaut (t); Select P flaut (t) The maximum value corresponding to the fault category is used as the fault category of the optical cable.

7. The intelligent optical cable monitoring method according to claim 6, wherein The preprocessing includes: data cleaning, duplicate removal, and standardization; The data cleaning eliminates invalid, duplicate, incorrect, or incomplete data records; The data duplicate removal identifies and removes duplicate records or redundant information; The standardization converts the original data from one format to another format for analysis and processing.

8. An intelligent optical cable monitoring system for implementing an intelligent optical cable monitoring method according to any one of claims 1-7, characterized in that, It includes: A data acquisition module, a data preprocessing module, and a fault detection module; The data acquisition module is used to collect real-time data related to the optical cable, including temperature and humidity, pressure, and vibration; The data preprocessing module is used to preprocess the data related to the optical cable collected; The fault detection module is used to extract the features of the preprocessed data related to the optical cable, including: frequency domain features, instantaneous frequency, combine the health assessment results of the optical cable transmission line and external environmental factors, establish an optical cable fault identification model, judge the abnormal conditions and abnormal types of the optical cable, and predict the fault conditions of the optical cable within a preset time.

9. The intelligent optical cable monitoring system according to claim 8, wherein, The fault detection module includes a feature extraction unit, a model training unit, a fault detection unit, and a prediction unit; The feature extraction unit is used to extract the features of the preprocessed data related to the optical cable; The model training unit is used to establish an optical cable fault identification model based on deep learning and the historical data set of the optical cable, and train the optical cable fault identification model; The fault detection unit is used to use the trained optical cable fault identification model, combine the health assessment results of the optical cable transmission line, and perform real-time detection of the faults during the optical cable transmission; The prediction unit is used to predict the fault conditions of the optical cable within a preset time on the basis of fault detection.

10. An intelligent optical cable monitoring system according to claim 9, characterized in that, The fault detection unit includes: a preliminary fault identification subunit and a fault identification subunit; The preliminary fault identification subunit is used to calculate the preliminary fault identification probability during the optical cable transmission in the trained optical cable fault identification model; The fault identification subunit is used to comprehensively consider the influence of the health assessment results of the optical cable transmission line and external environmental factors, and calculate the fault identification probability during the optical cable transmission.

Images