Long-distance communication optical cable fault automatic detection and positioning system and method

Abstract

The application discloses a long-distance communication optical cable fault automatic detection and positioning system and method, which comprises the following steps: collecting optical signal data in an optical fiber link in real time by deploying a multi-fiber sensor or a distributed optical fiber sensing technology; carrying out denoising processing on the collected data, and applying an adaptive algorithm to analyze abnormal fluctuations and identify the type of an impending fault; classifying the fault by using a machine learning classification algorithm; combining time domain reflection and wavelength multiplexing technology, and adopting a composite algorithm to accurately locate a fault point, and optimizing a path and correcting an error by comprehensively analyzing sensor node data; introducing an environmental compensation algorithm to analyze the influence of environmental factors on optical signals in real time and eliminate errors; and based on the fault positioning and analysis results, using an AI algorithm to evaluate the influence range of the fault, automatically generating a repair scheme and scheduling a priority for repair.

Description

Technical Field

[0001] This invention belongs to the field of automatic detection and location of faults in long-distance optical fiber communication cables, and specifically relates to an automatic detection and location system and method for faults in long-distance optical fiber communication cables. Background Technology

[0002] The long-distance optical fiber cable fault automatic detection and location system is used to monitor and locate optical fiber cable faults in long-distance optical fiber communication networks. Its main function is to monitor the status of the optical fiber link in real time. Once a fault occurs, the system can automatically detect the specific location of the fault and provide accurate location information to facilitate maintenance personnel in repairing it. Utilizing the characteristics of the optical fiber itself, it determines whether there is a problem with the optical fiber link by detecting changes in optical signal attenuation, reflection, and scattering. Based on the characteristics of the optical fiber link and combined with signal changes after a fault occurs, the system uses algorithms to accurately locate the fault. It can collect and analyze the health status of the optical fiber link in real time, issue fault alarms in a timely manner, and transmit the detailed location of the fault to maintenance personnel. Through continuous data collection and analysis, the system optimizes its fault detection and location capabilities, improving accuracy and response speed.

[0003] However, existing long-distance optical cable fault detection and location systems, while capable of identifying and locating faults in optical fiber links, still suffer from problems such as insufficient location accuracy, limited fault type identification, and poor system adaptability in certain complex network environments. Furthermore, existing technologies still face certain challenges in handling different types of faults, adapting to changes in network topology, and providing real-time fault response. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the purpose of this invention is to provide an automatic detection and location system and method for long-distance communication optical cable faults. The aim is to overcome the deficiencies of existing technologies through innovative technical means, and to achieve the goals of accurate fault location, diverse fault type identification, strong environmental adaptability, and fast real-time response.

[0005] The technical solution adopted by this invention to solve its technical problem is:

[0006] The automatic detection and location system for long-distance optical cable faults includes:

[0007] Optical signal monitoring module: Employs multiple fiber optic sensors and distributed sensing technology to monitor optical cables in real time, detecting signal attenuation, delay, and changes in temperature and humidity within the optical fiber;

[0008] Signal processing and fault analysis module: Based on adaptive signal processing algorithms and machine learning models, it analyzes optical signal data, automatically identifies the fault type of optical fiber, and estimates the location of the fault.

[0009] Fault location module: Combining time-domain reflectometry and wavelength multiplexing technology, a composite algorithm is used to optimize the accuracy of fault location, calculate the location of the fiber optic fault point, and improve the location accuracy through multipath correction algorithm in long-distance and complex network environments.

[0010] Intelligent Decision and Repair Suggestion Module: Based on the fault detection and location results, and combined with artificial intelligence algorithms, it automatically assesses the severity of the fault and generates optimized repair plans and priorities to guide maintenance personnel in carrying out repairs;

[0011] Network topology adaptive module: Through dynamic network topology analysis, this module can perceive changes in network topology in real time, ensuring that the fault location system can accurately adapt to different network environments.

[0012] An automatic detection and location method for long-distance optical cable faults includes the following steps:

[0013] By deploying multiple fiber optic sensors or using distributed fiber optic sensing technology, optical signal data in the fiber optic link can be collected in real time, including parameters such as optical signal attenuation, delay, and temperature and humidity changes.

[0014] The collected optical signal data is denoised, and an adaptive algorithm is used to analyze abnormal fluctuations in the signal, identify the type of fault that is about to occur, and determine whether further fault localization is needed.

[0015] A machine learning-based classification algorithm is used to classify fiber optic faults and identify fault types, including fiber breakage, connector failure, connector loosening, and bending damage.

[0016] By combining time-domain reflectometry and wavelength multiplexing technology, a composite algorithm is used to accurately locate fiber optic faults. For long-distance fiber optic links, path optimization and error correction are performed through comprehensive analysis of data from multiple sensor nodes to accurately determine the fault location.

[0017] An environmental compensation algorithm is introduced into the fiber optic network to analyze the impact of environmental changes on optical signals in real time, and to identify and eliminate errors caused by environmental factors.

[0018] Based on the fault location and analysis results, artificial intelligence algorithms are used to assess the scope of the fault's impact, automatically generate repair plans and present them to maintenance personnel, and schedule repair plans according to their priority.

[0019] As a preferred method, the real-time acquisition of optical signal data in the optical fiber link, including parameters such as optical signal attenuation, delay, and temperature and humidity changes, is achieved by deploying multiple fiber optic sensors or employing distributed fiber optic sensing technology.

[0020] Signal attenuation in optical fiber refers to the gradual weakening of the optical signal intensity during transmission due to absorption and scattering. The attenuation rate is expressed in decibels (dB), and the formula is:

[0021]

[0022] α is the fiber attenuation coefficient;

[0023] P in Input optical power;

[0024] P out For output optical power;

[0025] L is the length of the optical fiber;

[0026] The time delay in optical fiber refers to the time required for an optical signal to travel from the light source to the receiver. The time delay is related to the length of the optical fiber, the speed of light, and the refractive index of the fiber. The formula is:

[0027]

[0028] t dclay This refers to the signal propagation delay;

[0029] L is the length of the optical fiber;

[0030] v is the speed at which the optical signal propagates in the optical fiber;

[0031] The propagation speed v of an optical fiber is related to the refractive index n of the fiber. The propagation speed of an optical fiber is:

[0032]

[0033] c is the speed of light in a vacuum;

[0034] n is the refractive index of the optical fiber;

[0035] Fiber Bragg grating technology detects temperature and stress changes in optical fibers by measuring the wavelength changes of reflected light signals. The formula for temperature versus wavelength change is:

[0036] Δλ B =λ B ·α T ·ΔT

[0037] Δλ B For the change in Bragg wavelength;

[0038] λ B The original Bragg wavelength;

[0039] α T This is the temperature sensitivity coefficient;

[0040] ΔT is the temperature change;

[0041] Distributed temperature sensing technology uses optical fiber as the sensing element to measure temperature along the entire length of the fiber. The Rayleigh scattering signal formula is:

[0042]

[0043] P R (z) represents the Rayleigh scattering signal at position z;

[0044] P in The power of the input optical signal;

[0045] L0 is the starting length of the optical fiber;

[0046] The relationship between temperature and scattered signal intensity is established using the correlation formula between Brillouin scattering and temperature, which is:

[0047] ΔP Brillouin (T)=γ·(T-T0)

[0048] ΔP Brillouin The change in the Brillouin scattering signal;

[0049] γ is the temperature sensitivity coefficient;

[0050] T represents the current temperature;

[0051] T0 is the reference temperature.

[0052] As a preferred method, the acquired optical signal data is denoised, and an adaptive algorithm is used to analyze abnormal fluctuations in the signal, identify the type of impending fault, and determine whether further fault localization is necessary.

[0053] Kalman filtering is used to estimate and predict the optimal filter for noisy signals. It is based on recursive least squares estimation, with the following recursive formula:

[0054] Prediction steps:

[0055]

[0056] P k =AP k1 A T +Q

[0057] Update steps:

[0058] K k =P k H T HP k H T +R) 1

[0059]

[0060] P k =(IK k H)P k

[0061] The estimated state;

[0062] A is the system dynamic matrix;

[0063] B is the control matrix;

[0064] u k For control input;

[0065] y k These are the observed values;

[0066] P k It is the covariance matrix;

[0067] Q is the process noise covariance matrix;

[0068] R is the observation noise covariance matrix;

[0069] H is the observation matrix;

[0070] After denoising the optical signal, an adaptive algorithm is used to analyze abnormal fluctuations in the signal. The LMS algorithm is a commonly used adaptive filtering algorithm, and the LMS algorithm formula is as follows:

[0071]

[0072]

[0073] w(n+1)=w(n)+μx(n)e(n)

[0074] To estimate signal value

[0075] w(n) represents the filter coefficients;

[0076] x(n) is the input signal vector;

[0077] e(n) represents the error;

[0078] μ is the step size factor;

[0079] d(n) is the target signal;

[0080] Support Vector Machine (SVM) is a supervised learning algorithm. In fiber optic signal fault identification, SVM extracts and classifies features from the denoised signal to identify different types of faults. The SVM optimization formula is as follows:

[0081]

[0082] w is the weight vector of the decision hyperplane;

[0083] b is the bias;

[0084] x i For input samples;

[0085] y i For tags;

[0086] C is the penalty factor;

[0087] For abnormal fluctuations in the signal, statistical methods are used to detect outliers. The Z-Score formula is:

[0088]

[0089] x is the current signal value;

[0090] μ is the mean of the signal;

[0091] σ is the standard deviation of the signal;

[0092] Once the fault type is identified, the location of the fault can be determined using localization methods. Common fault localization methods include optical time domain reflectometry (OTDR) and time delay-based localization methods.

[0093] Optical Time Domain Reflectometers (OTDRs) locate faults by analyzing the time it takes for an optical signal to reflect in an optical fiber. OTDRs, on the other hand, locate faults by sending pulsed light, recording the reflected light signals, and calculating the propagation time of the light signal in the optical fiber. The OTDR fault location formula is as follows:

[0094]

[0095] d represents the fault location;

[0096] c is the speed of light;

[0097] t is the time delay of the optical signal return.

[0098] As a preferred method, a machine learning-based classification algorithm is used to classify fiber optic faults and identify fault types, including fiber breakage, connector failure, connector loosening, and bending damage.

[0099] SVM is a supervised learning algorithm that constructs a hyperplane to separate samples of different categories. For classifying fiber optic faults, SVM distinguishes different fault types. SVM classifies faults by finding the hyperplane with the maximum margin, as shown in the following formula:

[0100]

[0101] w is the weight vector of the decision hyperplane;

[0102] b is the bias term;

[0103] x i Let be the feature vector of the i-th sample;

[0104] y i The category label indicates which type of failure the sample belongs to;

[0105] In practical applications, fiber optic signal data is non-linearly separable. Therefore, kernel functions are used to map the data to a high-dimensional space for linear separability. Commonly used kernel functions include:

[0106] Linear kernel function:

[0107] K(x, x′) = x·x′

[0108] Gaussian kernel function:

[0109]

[0110] Polynomial kernel function:

[0111] K(x, x′) = (x·x′+1) d

[0112] Where d is the degree of the polynomial, and σ is the parameter of the Gaussian kernel;

[0113] The training process includes the following steps:

[0114] Data preparation: Extract the characteristics of various fault signals based on the signal data collected by the OTDR device;

[0115] Data preprocessing: standardizing or normalizing feature data;

[0116] Training the SVM model: Using training set data to learn the optimal parameters of the SVM;

[0117] Model validation: The generalization ability of the model is validated through cross-validation, and parameters are adjusted to improve classification accuracy;

[0118] Distance-based classification is suitable for cases where samples have high similarity in their feature space. The basic idea is to find the K nearest neighbors of a sample in the feature space and select the class with the most similar neighbors as the predicted class for that sample. The KNN classification formula is:

[0119]

[0120] in, For the predicted category, y iTags for neighbors.

[0121] As a preferred approach, a composite algorithm is used to accurately locate fiber optic faults by combining time-domain reflectometry and wavelength multiplexing techniques. For long-distance fiber optic links, the method involves comprehensive analysis of data from multiple sensor nodes to optimize the path and correct errors, thereby accurately determining the fault location.

[0122] Time-domain reflectometry (OTDR) is used to detect faults in fiber optic links. It locates the fault by sending optical pulses and measuring the time it takes for the reflected signals to travel. The basic formula for OTDR measurement is:

[0123]

[0124] d is the distance from the fault point to the sensor;

[0125] c is the speed of light in the optical fiber;

[0126] The round-trip time delay of the t signal;

[0127] When performing fault location, multiple sensing nodes will operate at different wavelengths. Therefore, by comprehensively analyzing the reflection data of signals at multiple wavelengths, more information can be obtained.

[0128] Suppose there are N reflected signals of different wavelengths, and the time delay for each wavelength is defined as t. n (n = 1, 2, ..., N), the fault distance for each wavelength is d. n Then, for the reflected signal of each wavelength, there is a similar formula:

[0129]

[0130] Fault distance data from multiple sensor nodes are synthesized using a weighted average method. Assume the fault distances obtained from M sensor nodes are d1, d2, ..., d... M The weighting coefficients are w1, w2, ..., u M Then the weighted average fault location d avg Calculated using the following formula:

[0131]

[0132] In the case of multiple sensor nodes, the true location of the fault point is determined by minimizing the error between the measured data and the theoretical value. Assume there are M measured values ​​d1, d2, ..., d... M The theoretical fault point is d true The objective of the least squares method is to minimize the following error function:

[0133]

[0134] Minimizing this error function yields:

[0135]

[0136] In the process of fiber optic fault location, Kalman filtering is used to fuse data from multiple sensor nodes and estimate system noise. The state equation of the Kalman filter is:

[0137] x k+1 =Ax k +Bu k +w k

[0138] z k =Hx k +v k

[0139] x k The state of the system;

[0140] A is the state transition matrix;

[0141] B is the control input matrix;

[0142] u k For control vectors;

[0143] w k This is process noise;

[0144] z k These are measured values;

[0145] H is the measurement matrix;

[0146] v k For measuring noise;

[0147] To optimize the path, the goal is to select the shortest path and minimize error propagation. A graph-based algorithm is used to calculate the optimal path, and the distance d of the optimized path is calculated. opt Obtained through the following methods:

[0148]

[0149] Where, d i denoted as the actual distance between nodes, and ∈ represents the error correction term.

[0150] As a preferred approach, an environmental compensation algorithm is introduced into the fiber optic network to analyze the impact of environmental changes on optical signals in real time, and to identify and eliminate errors caused by environmental factors.

[0151] Fiber optic attenuation is mainly affected by environmental factors such as temperature changes, humidity changes, and mechanical stress. Assuming that fiber attenuation α is affected by temperature T, humidity H, and mechanical stress σ, it can be described by the following formula:

[0152] α(T, H, σ) = α0 + Δα T (T)+Δα H (H)+Δα σ (σ)

[0153] Wherein, α0 decays under standard environmental conditions;

[0154] Δα T (T) represents the attenuation change caused by temperature change, which is usually the coefficient of temperature influence on optical fiber multiplied by the amount of temperature change.

[0155] Δα H (H) represents the attenuation change caused by humidity changes, which is usually the influence coefficient of humidity on optical fiber multiplied by the amount of humidity change;

[0156] Δα σ (σ) represents the attenuation change caused by mechanical stress, which is usually the stress influence coefficient on the optical fiber multiplied by the stress change.

[0157] To analyze the impact of environmental changes on optical signals in real time and eliminate errors caused by environmental factors, environmental compensation is achieved through the following steps:

[0158] Real-time monitoring of environmental factors is typically achieved by installing temperature and humidity sensors and stress sensors to obtain changes in environmental parameters T, H, and σ in real time.

[0159] When environmental parameters change, the signal attenuation value of the optical fiber is corrected using the following compensation formula:

[0160] α comp =α measurcd -(Δα T (T)+Δα H (H)+Δα σ (σ))

[0161] Where, α mcasured The fiber attenuation value is measured in real time using an OTDR.

[0162] α comp This is the attenuation value after compensation;

[0163] Δα T (T,Δα H (H), Δα σ (σ) is the correction value for fiber attenuation based on real-time monitored environmental parameters such as temperature, humidity, and stress.

[0164] Environmental changes are dynamic, therefore, the attenuation model needs to be corrected in real time based on changing environmental factors. By introducing a dynamic update mechanism, the attenuation model is corrected in real time. Assuming that temperature, humidity, and stress change at time t, the following dynamic correction formula is used:

[0165] α comp (t)=α mcasurcd (t)-[Δα T (T(t))+Δα H (H(t))+Δα σ (σ(t))]

[0166] To eliminate errors caused by environmental factors, filtering techniques are used to identify and correct these errors. The Kalman filter formula is as follows:

[0167]

[0168] in, This is the estimated environmentally corrected attenuation value;

[0169] K k Kalman gain;

[0170] z k The attenuation value is obtained by measurement using an OTDR.

[0171] H k For environmental correction matrix;

[0172] After environmental compensation, the fault location of the optical fiber is corrected using the following formula:

[0173]

[0174] Where, d comp The location of the fiber optic fault after environmental compensation.

[0175] t measurcd This refers to the initial propagation time of the fault signal obtained through OTDR measurement.

[0176] Δt cnvironmcnt This refers to the propagation time error caused by environmental changes.

[0177] As a preferred approach, based on fault location and analysis results, an artificial intelligence algorithm is used to assess the impact range of the fault, automatically generate a repair plan, and present it to the maintenance personnel. The method for scheduling repair plans according to their priority is as follows:

[0178] Assume that the specific location d of the fault is obtained through fiber optic fault location technology. faultFurthermore, the scope of the impact is calculated based on historical and real-time monitoring data. It is assumed that the scope of the impact of the fault can be assessed using the following formula:

[0179] R impact =f(d fault α fibcr , ΔT, ΔH, σ strcss )

[0180] Among them, R impact The scope of the fault

[0181] d fault The specific location where the fault occurred;

[0182] α fibcr This is the attenuation coefficient of the optical fiber;

[0183] ΔT, ΔH, σ strcss This is a correction factor for the effects of temperature changes, humidity changes, and mechanical stress on optical fibers;

[0184] The generation of the repair solution depends on the fault location d. fault and the scope of influence R impact Different repair solutions are generated based on the type of fault. It is assumed that the generation of repair solutions is automated through artificial intelligence algorithms, which consider the type and location of the fault, the scope of the fault's impact, and the resource input required for repair.

[0185] The repair solutions generated by AI algorithms are represented as a set of solutions:

[0186] S = {s1, s2, s3, ..., s} n}

[0187] Where S represents all possible repair solutions, s i Let represent the i-th repair scheme, indicating the specific repair measures and steps;

[0188] To evaluate the priority of remediation options, a comprehensive priority scoring model is introduced, considering multiple factors. It is assumed that each remediation option s... i Each has a priority rating P i The score can be calculated using the following formula:

[0189] P i =w1·S severity (s i )+w2·S busincss_impact (s i )+w3·S rcpair_timc (s i )-w4·S cost (s i )

[0190] Among them, S scvcrity (s i ) is the repair solution s i Severity score;

[0191] S busincss_inpact (s i ) is the repair solution s i Score of impact on business;

[0192] S rcpair_timc (s i ) is the repair solution s i Time required;

[0193] S cost (s i ) is the repair solution s i Cost rating;

[0194] The weighting coefficients w1, w2, w3, and w4 are used to adjust the influence of each factor on the final priority score.

[0195] After generating multiple remediation plans and calculating their priority scores, the remediation plans are ranked three-dimensionally based on their priority. Assuming there are n remediation plans, the operations and maintenance personnel sort the remediation tasks according to their priority. According to the priority ranking algorithm, the scheduling order of the remediation plans is as follows:

[0196] Scheduled_order=sort(P1,P2,...,P n )

[0197] The sort() function scores the repair solutions according to their priority P. i Sort them from highest to lowest to obtain the scheduling order;

[0198] According to the scheduling order, the operations and maintenance personnel will start executing the repair tasks according to the priority of the repair plan. Assume that the execution progress of the repair task can be represented by a status variable. i :

[0199] Status i =f(P i T elapscd (resources_used)

[0200] Among them, Status i For repair solution s i The current execution status;

[0201] T clapscd The time elapsed for the repair task;

[0202] resources_used represents the resources consumed by the repair task.

[0203] The beneficial effects of this invention are:

[0204] Deploying multiple fiber optic sensors or distributed fiber optic sensing technology can acquire key signal data in fiber optic links in real time, including parameters such as optical attenuation, latency, temperature, and humidity. After data acquisition, noise reduction techniques are used to remove noise interference, and adaptive algorithms are used to analyze abnormal fluctuations in the signal. Using machine learning-based classification algorithms, the type of fault can be accurately identified, such as fiber breakage, connector failure, loose connector, bending damage, etc. Combining time domain reflectance (OTDR) technology and wavelength multiplexing technology, the precise location of fiber optic fault points can be achieved. Especially for long-distance fiber optic links, path optimization and error correction can be performed by integrating data from multiple sensor nodes. Environmental factors (such as changes in temperature and humidity) can affect optical signals. By introducing environmental compensation algorithms, the system can analyze the interference of environmental changes on optical signals in real time and correct errors caused by environmental factors. Based on fault location and analysis results, the system can automatically generate repair plans using artificial intelligence algorithms and present the plans to maintenance personnel. Through automated fault detection, location, repair plan generation, and scheduling, the workload of maintenance personnel is greatly reduced, allowing them to focus on handling more complex tasks. Through multi-level technical support and intelligent fault diagnosis methods, the network can maintain efficient and stable operation over a long period of time. This solution has strong scalability and can support the management of large-scale fiber optic networks. Whether it is a city-level or inter-provincial fiber optic link, this technical architecture can achieve unified monitoring, data analysis, and fault handling of a large number of sensor nodes, significantly improving the scale and intelligence of network management. Attached Figure Description

[0205] Figure 1 This is a schematic diagram of the automatic detection and location system for long-distance optical cable faults according to the present invention. Detailed Implementation

[0206] The principles and features of the present invention are described below. The examples given are for illustrative purposes only and are not intended to limit the scope of the invention. The invention is described more specifically by way of example in the following paragraphs. The advantages and features of the invention will become clearer from the following description and claims.

[0207] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0208] Example

[0209] The technical solution adopted by this invention to solve its technical problem is:

[0210] The automatic detection and location system for long-distance optical cable faults includes:

[0211] Optical signal monitoring module: Employs multiple fiber optic sensors and distributed sensing technology to monitor optical cables in real time, detecting signal attenuation, delay, and changes in temperature and humidity within the optical fiber;

[0212] Signal processing and fault analysis module: Based on adaptive signal processing algorithms and machine learning models, it analyzes optical signal data, automatically identifies the fault type of optical fiber, and estimates the location of the fault.

[0213] Fault location module: Combining time-domain reflectometry and wavelength multiplexing technology, a composite algorithm is used to optimize the accuracy of fault location, calculate the location of the fiber optic fault point, and improve the location accuracy through multipath correction algorithm in long-distance and complex network environments.

[0214] Intelligent Decision and Repair Suggestion Module: Based on the fault detection and location results, and combined with artificial intelligence algorithms, it automatically assesses the severity of the fault and generates optimized repair plans and priorities to guide maintenance personnel in carrying out repairs;

[0215] Network topology adaptive module: Through dynamic network topology analysis, this module can perceive changes in network topology in real time, ensuring that the fault location system can accurately adapt to different network environments.

[0216] An automatic detection and location method for long-distance optical cable faults includes the following steps:

[0217] By deploying multiple fiber optic sensors or using distributed fiber optic sensing technology, optical signal data in the fiber optic link can be collected in real time, including parameters such as optical signal attenuation, delay, and temperature and humidity changes.

[0218] The collected optical signal data is denoised, and an adaptive algorithm is used to analyze abnormal fluctuations in the signal, identify the type of fault that is about to occur, and determine whether further fault localization is needed.

[0219] A machine learning-based classification algorithm is used to classify fiber optic faults and identify fault types, including fiber breakage, connector failure, connector loosening, and bending damage.

[0220] By combining time-domain reflectometry and wavelength multiplexing technology, a composite algorithm is used to accurately locate fiber optic faults. For long-distance fiber optic links, path optimization and error correction are performed through comprehensive analysis of data from multiple sensor nodes to accurately determine the fault location.

[0221] An environmental compensation algorithm is introduced into the fiber optic network to analyze the impact of environmental changes on optical signals in real time, and to identify and eliminate errors caused by environmental factors.

[0222] Based on the fault location and analysis results, artificial intelligence algorithms are used to assess the scope of the fault's impact, automatically generate repair plans and present them to maintenance personnel, and schedule repair plans according to their priority.

[0223] The method for real-time acquisition of optical signal data in optical fiber links, including parameters such as optical signal attenuation, delay, and temperature and humidity changes, by deploying multiple fiber optic sensors or employing distributed fiber optic sensing technology is as follows:

[0224] Signal attenuation in optical fiber refers to the gradual weakening of the optical signal intensity during transmission due to absorption and scattering. The attenuation rate is expressed in decibels (dB), and the formula is:

[0225]

[0226] α is the fiber attenuation coefficient; P in P is the input optical power. out L represents the output optical power; L represents the fiber length.

[0227] The time delay in optical fiber refers to the time required for an optical signal to travel from the light source to the receiver. The time delay is related to the length of the optical fiber, the speed of light, and the refractive index of the fiber. The formula is:

[0228]

[0229] t dclay is the signal propagation delay; L is the fiber length; v is the speed at which the optical signal propagates in the fiber.

[0230] The propagation speed v of an optical fiber is related to the refractive index n of the fiber. The propagation speed of an optical fiber is:

[0231]

[0232] c is the speed of light in a vacuum; n is the refractive index of the optical fiber;

[0233] Fiber Bragg grating technology detects temperature and stress changes in optical fibers by measuring the wavelength changes of reflected light signals. The formula for temperature versus wavelength change is:

[0234] Δλ B =λ B ·α T ·ΔT

[0235] Δλ B For the variation of the Bragg wavelength; λ B The original Bragg wavelength; α TΔT is the temperature sensitivity coefficient; ΔT is the temperature change.

[0236] Distributed temperature sensing technology uses optical fiber as the sensing element to measure temperature along the entire length of the fiber. The Rayleigh scattering signal formula is:

[0237]

[0238] P R (z) represents the Rayleigh scattering signal at position z; P in L0 represents the power of the input optical signal; L0 represents the starting length of the optical fiber.

[0239] The relationship between temperature and scattered signal intensity is established using the correlation formula between Brillouin scattering and temperature, which is:

[0240] ΔP Brillouin (T)=γ·(T-T0)

[0241] ΔP Brillouin γ represents the change in the Brillouin scattering signal; γ is the temperature sensitivity coefficient; T is the current temperature; and T0 is the reference temperature.

[0242] The method for denoising the acquired optical signal data, analyzing abnormal fluctuations in the signal using an adaptive algorithm, identifying the type of impending fault, and determining whether further fault localization is necessary is as follows:

[0243] Kalman filtering is used to estimate and predict the optimal filter for noisy signals. It is based on recursive least squares estimation, with the following recursive formula:

[0244] Prediction steps:

[0245]

[0246] P k =AP k1 A T +Q

[0247] Update steps:

[0248] K k =P k H T HP k H T +R) 1

[0249]

[0250] P k =(IK k H)P k

[0251] The estimated state; A is the system dynamic matrix; B is the control matrix; u k For control input; y k For observations; P k R is the covariance matrix; Q is the process noise covariance matrix; R is the observation noise covariance matrix; H is the observation matrix;

[0252] After denoising the optical signal, an adaptive algorithm is used to analyze abnormal fluctuations in the signal. The LMS algorithm is a commonly used adaptive filtering algorithm, and the LMS algorithm formula is as follows:

[0253]

[0254]

[0255] w(n+1)=w(n)+μx(n)e(n)

[0256] To estimate the signal value; w(n) are the filter coefficients; x(n) is the input signal vector; e(n) is the error; μ is the step size factor; d(n) is the target signal;

[0257] Support Vector Machine (SVM) is a supervised learning algorithm. In fiber optic signal fault identification, SVM extracts and classifies features from the denoised signal to identify different types of faults. The SVM optimization formula is as follows:

[0258]

[0259] w is the weight vector of the decision hyperplane; b is the bias; x i For the input sample; y i C represents the label; C represents the penalty factor.

[0260] For abnormal fluctuations in the signal, statistical methods are used to detect outliers. The Z-Score formula is:

[0261]

[0262] x is the current signal value; μ is the signal mean; σ is the signal standard deviation;

[0263] Once the fault type is identified, the location of the fault can be determined using localization methods. Common fault localization methods include optical time domain reflectometry (OTDR) and time delay-based localization methods.

[0264] Optical Time Domain Reflectometers (OTDRs) locate faults by analyzing the time it takes for an optical signal to reflect in an optical fiber. OTDRs, on the other hand, locate faults by sending pulsed light, recording the reflected light signals, and calculating the propagation time of the light signal in the optical fiber. The OTDR fault location formula is as follows:

[0265]

[0266] d represents the fault location; c represents the speed of light; and t represents the time delay for the light signal to return.

[0267] By employing Kalman filtering and the LMS algorithm, noise in optical signals can be removed, improving signal quality. Z-Score is used for abnormal fluctuation detection, enabling timely identification of potential faults. The Support Vector Machine (SVM) algorithm can accurately classify different types of faults, reducing misdiagnosis and missed diagnosis. OTDR technology allows for rapid and accurate location of faults in the fiber optic link, improving fault response speed and maintenance efficiency. This solution can process fiber optic signals in real time and provide fault warnings, identifying potential problems early and preventing fault escalation. Furthermore, this solution achieves fully automated processing from signal acquisition to fault diagnosis and location, improving the efficiency and intelligence of fiber optic maintenance.

[0268] The method for classifying fiber optic faults and identifying fault types, including fiber breakage, connector failure, connector loosening, and bending damage, using a machine learning-based classification algorithm is as follows:

[0269] SVM is a supervised learning algorithm that constructs a hyperplane to separate samples of different categories. For classifying fiber optic faults, SVM distinguishes different fault types. SVM classifies faults by finding the hyperplane with the maximum margin, as shown in the following formula:

[0270]

[0271] w is the weight vector of the decision hyperplane; b is the bias term; x i Let y be the feature vector of the i-th sample; i The category label indicates which type of failure the sample belongs to;

[0272] In practical applications, fiber optic signal data is non-linearly separable. Therefore, kernel functions are used to map the data to a high-dimensional space for linear separability. Commonly used kernel functions include:

[0273] Linear kernel function:

[0274] K(x, x′) = x·x′

[0275] Gaussian kernel function:

[0276]

[0277] Polynomial kernel function:

[0278] K(x, x′) = (x·x′+1) d

[0279] Where d is the degree of the polynomial, and σ is the parameter of the Gaussian kernel;

[0280] The training process includes the following steps:

[0281] Data preparation: Extract the characteristics of various fault signals based on the signal data collected by the OTDR device;

[0282] Data preprocessing: standardizing or normalizing feature data;

[0283] Training the SVM model: Using training set data to learn the optimal parameters of the SVM;

[0284] Model validation: The generalization ability of the model is validated by cross-validation, and parameters are adjusted to improve classification accuracy;

[0285] Distance-based classification is suitable for cases where samples have high similarity in their feature space. The basic idea is to find the K nearest neighbors of a sample in the feature space and select the class with the most similar neighbors as the predicted class for that sample. The KNN classification formula is:

[0286]

[0287] in, For the predicted category, y i Tags for neighbors.

[0288] Combining time-domain reflectometry and wavelength multiplexing techniques, a composite algorithm is used to accurately locate fiber optic faults. For long-distance fiber optic links, path optimization and error correction are performed through comprehensive analysis of data from multiple sensor nodes. The method for accurately determining the fault location is as follows:

[0289] Time-domain reflectometry (OTDR) is used to detect faults in fiber optic links. It locates the fault by sending optical pulses and measuring the time it takes for the reflected signals to travel. The basic formula for OTDR measurement is:

[0290]

[0291] d is the distance from the fault point to the sensor; c is the speed of light in the optical fiber; t is the round-trip time delay of the signal.

[0292] When performing fault location, multiple sensing nodes will operate at different wavelengths. Therefore, by comprehensively analyzing the reflection data of signals at multiple wavelengths, more information can be obtained.

[0293] Suppose there are N reflected signals of different wavelengths, and the time delay for each wavelength is defined as t. n (n = 1, 2, ..., N), the fault distance for each wavelength is d. nThen, for the reflected signal of each wavelength, there is a similar formula:

[0294]

[0295] Fault distance data from multiple sensor nodes are synthesized using a weighted average method. Assume the fault distances obtained from M sensor nodes are d1, d2, ..., d... M The weighting coefficients are w1, w2, ..., w M Then the weighted average fault location d avg Calculated using the following formula:

[0296]

[0297] In the case of multiple sensor nodes, the true location of the fault point is determined by minimizing the error between the measured data and the theoretical value. Assume there are M measured values ​​d1, d2, ..., d... M The theoretical fault point is d truc The objective of the least squares method is to minimize the following error function:

[0298]

[0299] Minimizing this error function yields:

[0300]

[0301] In the process of fiber optic fault location, Kalman filtering is used to fuse data from multiple sensor nodes and estimate system noise. The state equation of the Kalman filter is:

[0302] x k+1 =Ax k +Bu k +w k

[0303] z k =Hx k +v k

[0304] x k Let A be the system state; let B be the state transition matrix; let U be the control input matrix; u be the system state. k w is the control vector. k For process noise; z k V represents the measured value; H represents the measurement matrix; v k For measuring noise;

[0305] To optimize the path, the goal is to select the shortest path and minimize error propagation. A graph-based algorithm is used to calculate the optimal path, and the distance d of the optimized path is calculated. optObtained through the following methods:

[0306]

[0307] Where, d i denoted as the actual distance between nodes, and ∈ represents the error correction term.

[0308] By combining time-domain reflectometry with multi-wavelength signals and comprehensively analyzing data from multiple sensor nodes, more accurate fault location results can be obtained. The combination of weighted average, least squares, and Kalman filtering makes the location process more accurate and robust. Reflection data from multiple wavelengths provides more comprehensive information, helping to overcome errors that may occur with a single wavelength and improving the stability of fault location. Minimizing the error between measured data and theoretical values, combined with path optimization algorithms, reduces error propagation, thereby improving the accuracy of fault location. Path optimization not only selects the shortest path but also considers error correction, ensuring optimal performance during data transmission. Kalman filtering, by fusing data from multiple sensor nodes and estimating and correcting noise, improves the overall system performance and ensures the reliability of fault location. This method is particularly suitable for long-distance fiber optic links, enabling multiple nodes to work collaboratively to gradually correct location errors, ensuring accurate fault location even over long distances. Due to the combination of multi-wavelength and composite algorithms, the system can flexibly adapt to different network environments and practical application requirements, possessing strong versatility.

[0309] An environmental compensation algorithm is introduced into the fiber optic network to analyze the impact of environmental changes on optical signals in real time, and to identify and eliminate errors caused by environmental factors.

[0310] Fiber optic attenuation is mainly affected by environmental factors such as temperature changes, humidity changes, and mechanical stress. Assuming that fiber attenuation α is affected by temperature T, humidity H, and mechanical stress σ, it can be described by the following formula:

[0311] α(T, H, σ) = α0 + Δα T (T)+Δα H (H)+Δα σ (σ)

[0312] Wherein, α0 decays under standard environmental conditions;

[0313] Δα T (T) represents the attenuation change caused by temperature change, which is usually the coefficient of temperature influence on optical fiber multiplied by the amount of temperature change.

[0314] Δα H (H) represents the attenuation change caused by humidity changes, which is usually the influence coefficient of humidity on optical fiber multiplied by the amount of humidity change;

[0315] Δα σ (σ) represents the attenuation change caused by mechanical stress, which is usually the stress influence coefficient on the optical fiber multiplied by the stress change.

[0316] To analyze the impact of environmental changes on optical signals in real time and eliminate errors caused by environmental factors, environmental compensation is achieved through the following steps:

[0317] Real-time monitoring of environmental factors is typically achieved by installing temperature and humidity sensors and stress sensors to obtain changes in environmental parameters T, H, and σ in real time.

[0318] When environmental parameters change, the signal attenuation value of the optical fiber is corrected using the following compensation formula:

[0319] α comp =α measurcd -(Δα T (T)+Δα H (H)+Δα σ (σ))

[0320] Where, α mcasurcd The fiber attenuation value is measured in real time using an OTDR.

[0321] α comp This is the attenuation value after compensation;

[0322] Δα T (T), Δα H (H), Δα σ (σ) is the correction value for fiber attenuation based on real-time monitored environmental parameters such as temperature, humidity, and stress.

[0323] Environmental changes are dynamic, therefore, the attenuation model needs to be corrected in real time based on changing environmental factors. By introducing a dynamic update mechanism, the attenuation model is corrected in real time. Assuming that temperature, humidity, and stress change at time t, the following dynamic correction formula is used:

[0324] α comp (t)=α measurcd (t)-[Δα T (T(t))+Δα H (H(t))+Δα σ (σ(t))]

[0325] To eliminate errors caused by environmental factors, filtering techniques are used to identify and correct these errors. The Kalman filter formula is as follows:

[0326]

[0327] in, This is the estimated environmentally corrected attenuation value;

[0328] K k Kalman gain;

[0329] z k The attenuation value is obtained by measurement using an OTDR.

[0330] H k For environmental correction matrix;

[0331] After environmental compensation, the fault location of the optical fiber is corrected using the following formula:

[0332]

[0333] Where, d comp The location of the fiber optic fault after environmental compensation.

[0334] t mcasured This refers to the initial propagation time of the fault signal obtained through OTDR measurement.

[0335] Δt cnvironmcnt This refers to the propagation time error caused by environmental changes.

[0336] This solution monitors changes in environmental factors such as temperature, humidity, and mechanical stress in real time and dynamically adjusts the attenuation model to ensure accurate compensation for fiber optic attenuation under changing environmental conditions, thus providing real-time and accurate fiber optic fault location. Environmental factors are dynamic, and the solution adapts to different environmental changes in real time through a dynamic update mechanism and Kalman filtering algorithm. Filtering techniques such as Kalman filtering effectively identify and eliminate errors caused by environmental factors, reducing noise interference and ensuring more accurate fault location. This is particularly important in complex environments, preventing environmental factors from affecting the location results. By compensating for the impact of environmental factors, the fault location of the fiber optic cable can be more accurately corrected. This solution makes fiber optic maintenance more precise, reduces misjudgments caused by environmental changes, and improves the overall operation and maintenance efficiency of the fiber optic network.

[0337] Based on the fault location and analysis results, artificial intelligence algorithms are used to assess the impact range of the fault, automatically generate repair plans, and present them to maintenance personnel. The method for scheduling repair plans according to their priority is as follows:

[0338] Assume that the specific location d of the fault is obtained through fiber optic fault location technology. fault Furthermore, the scope of the impact is calculated based on historical and real-time monitoring data. It is assumed that the scope of the impact of the fault can be assessed using the following formula:

[0339] R impact =f(d faultα fibcr , ΔT, ΔH, σ strcss )

[0340] Among them, R impact The scope of the fault

[0341] d fault The specific location where the fault occurred;

[0342] α fiber This is the attenuation coefficient of the optical fiber;

[0343] ΔT, ΔH, σ strcss This is a correction factor for the effects of temperature changes, humidity changes, and mechanical stress on optical fibers;

[0344] The generation of the repair solution depends on the fault location d. fault and the scope of influence R impact Different repair solutions are generated based on the type of fault. It is assumed that the generation of repair solutions is automated through artificial intelligence algorithms, which consider the type and location of the fault, the scope of the fault's impact, and the resource input required for repair.

[0345] The repair solutions generated by AI algorithms are represented as a set of solutions:

[0346] S = {s1, s2, s3, ..., s} n}

[0347] Where S represents all possible repair solutions, s i Let represent the i-th repair scheme, indicating the specific repair measures and steps;

[0348] To evaluate the priority of remediation options, a comprehensive priority scoring model is introduced, considering multiple factors. It is assumed that each remediation option s... i Each has a priority rating P i The score can be calculated using the following formula:

[0349] P i =w1·S severity (s i )+w2·S busincss_impact (s i )+w3·S rcpair_timc (s i )-w4·S cost (s i )

[0350] Among them, S scvcrity (s i ) is the repair solution s i Severity score;

[0351] Sbusincss_impact (s i ) is the repair solution s i Score of impact on business;

[0352] S rcpair_timc (s i ) is the repair solution s i Time required;

[0353] S cost (s i ) is the repair solution s i Cost rating;

[0354] The weighting coefficients w1, w2, w3, and w4 are used to adjust the influence of each factor on the final priority score.

[0355] After generating multiple remediation plans and calculating their priority scores, the remediation plans are scheduled according to their priorities. Assuming there are n remediation plans, the operations and maintenance personnel sort the remediation tasks according to their priorities. Based on the priority sorting algorithm, the scheduling order of the remediation plans is as follows:

[0356] Scheduled_order=sort(P1,P2,...,P n )

[0357] The sort() function scores the repair solutions according to their priority P. i Sort them from highest to lowest to obtain the scheduling order;

[0358] According to the scheduling order, the operations and maintenance personnel will start executing the repair tasks according to the priority of the repair plan. Assume that the execution progress of the repair task can be represented by a status variable. i :

[0359] Status i =f(P i T clapscl (resources_used)

[0360] Among them, Status i For repair solution s i The current execution status;

[0361] T clapscd The time elapsed for the repair task;

[0362] resources_used represents the resources consumed by the repair task.

[0363] This solution uses artificial intelligence algorithms to automatically assess the impact of faults, generate repair plans, and schedule them based on priority scores. It introduces a comprehensive priority scoring model, considering multiple factors (severity, business impact, time cost, and expense) to ensure a more scientific and reasonable prioritization of repair plans. Automated repair plan scheduling and execution progress management ensure rapid fault response and optimized resource allocation. The assessment of resource consumption and repair time in the repair plans enables more precise resource management during execution, avoiding waste and ensuring timely completion of tasks. Prioritized scheduling and efficient repair reduce operational downtime caused by faults, ensuring stable fiber optic network operation. The solution continuously optimizes fault location and repair plan generation processes using historical and real-time monitoring data; the AI ​​algorithm learns continuously to improve decision-making quality and further optimize the fault repair process.

[0364] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the automatic detection and location system and method for long-distance communication optical cable faults as described above.

[0365] This embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the automatic detection and location system and method for long-distance communication optical cable faults as described above.

[0366] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0367] Those skilled in the art will understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0368] The above embodiments of the present invention are not intended to limit the scope of protection of the present invention. The implementation of the present invention is not limited thereto. All other modifications, substitutions or alterations made to the above structure of the present invention based on the above content of the present invention, in accordance with ordinary technical knowledge and common practice in the field, without departing from the basic technical idea of ​​the present invention, shall fall within the scope of protection of the present invention.

Claims

1. An automatic detection and location system for long-distance optical cable faults, characterized in that, Including: Optical signal monitoring module: Employs multiple fiber optic sensors and distributed sensing technology to monitor optical cables in real time, detecting signal attenuation, delay, and changes in temperature and humidity within the optical fiber; Signal processing and fault analysis module: Based on adaptive signal processing algorithms and machine learning models, it analyzes optical signal data, automatically identifies the fault type of optical fiber, and estimates the location of the fault. Fault location module: Combining time-domain reflectometry and wavelength multiplexing technology, a composite algorithm is used to optimize the accuracy of fault location, calculate the location of the fiber optic fault point, and improve the location accuracy through multipath correction algorithm in long-distance and complex network environments. Intelligent Decision and Repair Suggestion Module: Based on the fault detection and location results, and combined with artificial intelligence algorithms, it automatically assesses the severity of the fault and generates optimized repair plans and priorities to guide maintenance personnel in carrying out repairs; Network topology adaptive module: Through dynamic network topology analysis, this module can perceive changes in network topology in real time to ensure that the fault location system can accurately adapt to different network environments; The automatic detection and location method for long-distance communication optical cable faults includes the following steps: By deploying multiple fiber optic sensors or using distributed fiber optic sensing technology, optical signal data in the fiber optic link can be collected in real time, including parameters such as optical signal attenuation, delay, and temperature and humidity changes. The acquired optical signal data is denoised, and an adaptive algorithm is used to analyze abnormal fluctuations in the signal, identify the type of fault that is about to occur, and determine whether further fault localization is needed. A machine learning-based classification algorithm is used to classify fiber optic faults and identify fault types, including fiber breakage, connector failure, connector loosening, and bending damage. By combining time-domain reflectometry and wavelength multiplexing technology, a composite algorithm is used to accurately locate fiber optic faults. For long-distance fiber optic links, path optimization and error correction are performed through comprehensive analysis of data from multiple sensor nodes to accurately determine the fault location. An environmental compensation algorithm is introduced into the fiber optic network to analyze the impact of environmental changes on optical signals in real time, and to identify and eliminate errors caused by environmental factors. Based on the fault location and analysis results, artificial intelligence algorithms are used to assess the scope of the fault's impact, automatically generate repair plans and present them to maintenance personnel, and schedule repair plans according to their priority. Combining time-domain reflectometry and wavelength multiplexing techniques, a composite algorithm is used to accurately locate fiber optic faults. For long-distance fiber optic links, path optimization and error correction are performed through comprehensive analysis of data from multiple sensor nodes. The method for accurately determining the fault location is as follows: Time-domain reflectometry (OTDR) is used to detect faults in fiber optic links. It locates the fault by sending optical pulses and measuring the time it takes for the reflected signals to travel. The basic formula for OTDR measurement is: ； The distance from the fault point to the sensor; The speed of light in an optical fiber; The round-trip time delay of the signal; When performing fault location, multiple sensing nodes will operate at different wavelengths. Therefore, by comprehensively analyzing the reflection data of signals at multiple wavelengths, more information can be obtained. Assume there is Given reflected signals of different wavelengths, the time delay at each wavelength is defined as... The fault distance for each wavelength is Then, for the reflected signal of each wavelength, there is a similar formula: ； Fault distance data from multiple sensor nodes are synthesized using a weighted average method, assuming that from The fault distances obtained from the sensor nodes are respectively The weighting coefficient is The weighted average fault location Calculated using the following formula: 。 2. The automatic detection and location system for long-distance optical cable faults according to claim 1, characterized in that, The method for real-time acquisition of optical signal data in optical fiber links, including parameters such as optical signal attenuation, delay, and temperature and humidity changes, by deploying multiple fiber optic sensors or employing distributed fiber optic sensing technology is as follows: Signal attenuation in optical fiber refers to the gradual weakening of the optical signal intensity during transmission due to absorption and scattering. The attenuation rate is expressed in decibels (dB), and the formula is: ； The fiber attenuation coefficient; Input optical power; For output optical power; This refers to the length of the optical fiber. The time delay in optical fiber refers to the time required for an optical signal to travel from the light source to the receiver. The time delay is related to the length of the optical fiber, the speed of light, and the refractive index of the fiber. The formula is: ； This refers to the signal propagation delay; This refers to the length of the optical fiber. The speed at which light signals propagate in an optical fiber; The propagation speed of optical fiber Refractive index of optical fiber Relatedly, the propagation speed of optical fiber is: ； The speed of light in a vacuum; The refractive index of the optical fiber; Fiber Bragg grating technology detects temperature and stress changes in optical fibers by measuring the wavelength changes of reflected light signals. The formula for temperature versus wavelength change is: ； For the change in Bragg wavelength; The original Bragg wavelength; This is the temperature sensitivity coefficient; This refers to the change in temperature. Distributed temperature sensing technology uses optical fiber as the sensing element to measure temperature along the entire length of the fiber. The Rayleigh scattering signal formula is: ； For in position Rayleigh scattering signal at the location; The power of the input optical signal; This represents the starting length of the optical fiber; The relationship between temperature and scattered signal intensity is established using the correlation formula between Brillouin scattering and temperature, which is: ； The change in the Brillouin scattering signal; This is the temperature sensitivity coefficient; The current temperature; This is the reference temperature.

3. The automatic detection and location system for long-distance optical cable faults according to claim 1, characterized in that, The method for denoising the acquired optical signal data, analyzing abnormal fluctuations in the signal using an adaptive algorithm, identifying the type of impending fault, and determining whether further fault localization is necessary is as follows: Kalman filtering is used to estimate and predict the optimal filter for noisy signals. It is based on recursive least squares estimation, with the following recursive formula: Prediction steps: ； ； Update steps: ； ； ； The estimated state; For the system dynamic matrix; For control matrix; For control input; These are the observed values; It is the covariance matrix; The process noise covariance matrix; To observe the noise covariance matrix; The observation matrix; After denoising the optical signal, an adaptive algorithm is used to analyze abnormal fluctuations in the signal. The LMS algorithm is a commonly used adaptive filtering algorithm, and the LMS algorithm formula is as follows: ； ； ； To estimate the signal value; These are the filter coefficients; The input signal vector; For error; Step size factor; For target signal; Support Vector Machine (SVM) is a supervised learning algorithm. In fiber optic signal fault identification, SVM extracts and classifies features from the denoised signal to identify different types of faults. The SVM optimization formula is as follows: ； ； Let be the weight vector of the decision hyperplane; For bias; For input samples; For tags; For abnormal fluctuations in the signal, statistical methods are used to detect outliers. The Z-Score formula is: ； The current signal value; The mean of the signal; The standard deviation of the signal; Once the fault type is identified, the location of the fault can be determined using localization methods. Common fault localization methods include optical time domain reflectometry (OTDR) and time delay-based localization methods. Optical Time Domain Reflectometers (OTDRs) locate faults by analyzing the time it takes for an optical signal to reflect in an optical fiber. OTDRs, on the other hand, locate faults by sending pulsed light, recording the reflected light signals, and calculating the propagation time of the light signal in the optical fiber. The OTDR fault location formula is as follows: ； Location of the fault; The speed of light; This refers to the delay in the return of the optical signal. The method for classifying fiber optic faults and identifying fault types, including fiber breakage, connector failure, connector loosening, and bending damage, using a machine learning-based classification algorithm is as follows: In practical applications, fiber optic signal data is non-linearly separable. Therefore, kernel functions are used to map the data to a high-dimensional space for linear separability. Commonly used kernel functions include: Linear kernel function: ； Gaussian kernel function: ； Polynomial kernel function: ； in, Let be the degree of the polynomial. These are the parameters of the Gaussian kernel; The training process includes the following steps: Data preparation: Extract the characteristics of various fault signals based on the signal data collected by the OTDR device; Data preprocessing: standardizing or normalizing feature data; Training the SVM model: Using training set data to learn the optimal parameters of the SVM; Model validation: The generalization ability of the model is validated by cross-validation, and parameters are adjusted to improve classification accuracy; Distance-based classification is suitable for cases where samples have high similarity in their feature space. The basic idea is to find the K nearest neighbors of a sample in the feature space and select the class with the most similar neighbors as the predicted class for that sample. The KNN classification formula is: ； in, For the predicted category, Tags for neighbors.

4. The automatic detection and location system for long-distance optical cable faults according to claim 1, characterized in that, In the case of multiple sensor nodes, the true location of the fault point is determined by minimizing the error between the measured data and the theoretical value. Assuming there are... Measured values The theoretical fault point is The objective of the least squares method is to minimize the following error function: ； Minimizing this error function yields: ； In the process of fiber optic fault location, Kalman filtering is used to fuse data from multiple sensor nodes and estimate system noise. The state equation of the Kalman filter is: ； ； The state of the system; This is the state transition matrix; To control the input matrix; For control vectors; This is process noise; These are measured values; For measurement matrix; For measuring noise; To optimize the path, the goal is to select the shortest path and minimize error propagation. A graph-based algorithm is used to calculate the optimal path, and the distance of the optimized path is... Obtained through the following methods: ； in, This represents the actual distance between nodes. This is the error correction term.

5. The automatic detection and location system for long-distance optical cable faults according to claim 4, characterized in that, An environmental compensation algorithm is introduced into the fiber optic network to analyze the impact of environmental changes on optical signals in real time, and to identify and eliminate errors caused by environmental factors. Fiber optic attenuation is mainly affected by environmental factors such as temperature changes, humidity changes, and mechanical stress. Assuming fiber attenuation... Affected by temperature ,humidity and mechanical stress The effect is described by the following formula: ； in, Attenuation under standard environmental conditions; The attenuation change caused by temperature change is usually the coefficient of temperature effect on optical fiber multiplied by the amount of temperature change. The attenuation change caused by humidity variation is usually calculated by multiplying the humidity effect coefficient of optical fiber by the amount of humidity change. The attenuation change caused by mechanical stress is usually the stress influence coefficient on the optical fiber multiplied by the stress change. To analyze the impact of environmental changes on optical signals in real time and eliminate errors caused by environmental factors, environmental compensation is achieved through the following steps: Real-time monitoring of environmental factors typically involves installing temperature and humidity sensors, stress sensors, and other environmental parameters to acquire real-time data. , , Changes; When environmental parameters change, the signal attenuation value of the optical fiber is corrected using the following compensation formula: ； in, The fiber attenuation value is measured in real time using an OTDR. This is the attenuation value after compensation; , , This is a correction value for fiber optic attenuation based on real-time monitored environmental parameters such as temperature, humidity, and stress. Environmental changes are dynamic, therefore, the degradation model needs to be adjusted in real time based on changing environmental factors. This is achieved by introducing a dynamic update mechanism to continuously modify the degradation model. (Assuming that over time...) When temperature, humidity, and stress change, the following dynamic correction formula is used: ； To eliminate errors caused by environmental factors, filtering techniques are used to identify and correct these errors. The Kalman filter formula is as follows: ； in, This is the estimated environmentally corrected attenuation value; Kalman gain; The attenuation value is obtained by measuring with an OTDR. For environmental correction matrix; After environmental compensation, the fault location of the optical fiber is corrected using the following formula: ； in, The location of the fiber optic fault after environmental compensation. This refers to the initial propagation time of the fault signal obtained through OTDR measurement. This refers to the propagation time error caused by environmental changes.

6. The automatic detection and location system for long-distance optical cable faults according to claim 5, characterized in that, Based on the fault location and analysis results, artificial intelligence algorithms are used to assess the impact range of the fault, automatically generate repair plans, and present them to maintenance personnel. The method for scheduling repair plans according to their priority is as follows: Assuming the specific location of the fault can be obtained through fiber optic fault location technology. Furthermore, the scope of the impact is calculated based on historical and real-time monitoring data. It is assumed that the scope of the impact of the fault can be assessed using the following formula: ； in, The extent of the fault's impact; The specific location where the fault occurred; This is the attenuation coefficient of the optical fiber; This is a correction factor for the effects of temperature changes, humidity changes, and mechanical stress on optical fibers; The generation of a repair solution depends on the location of the fault. and scope of influence Different repair solutions are generated based on the type of fault. It is assumed that the generation of repair solutions is automated through artificial intelligence algorithms, which consider the type and location of the fault, the scope of the fault's impact, and the resource input required for repair. The repair solutions generated by AI algorithms are represented as a set of solutions: ； in, For all possible repair solutions, For the first of them Each repair plan indicates specific repair measures and steps; To evaluate the priority of remediation options, a comprehensive priority scoring model is introduced, considering multiple factors and assuming that each remediation option... Each has a priority rating. The score can be calculated using the following formula: ； in, For the repair plan Severity score; For the repair plan Score of impact on business; For the repair plan Time required; For the repair plan Cost rating; , , , Weighting coefficients are used to adjust the impact of each factor on the final priority score. After generating multiple remediation plans and calculating priority scores, the remediation plans are scheduled according to their priorities. Assume there are... There are several repair plans. The operations and maintenance personnel prioritize the repair tasks. Based on the priority ranking algorithm, the scheduling order of the repair plans is as follows: ； in, The function scores the repair solutions according to their priority. Sort them from highest to lowest to obtain the scheduling order; According to the scheduling order, the operations and maintenance personnel will start executing the repair tasks according to the priority of the repair plan. Assume that the execution progress of the repair task can be represented as a state variable. : ； in, For the repair plan The current execution status; The time elapsed for the repair task; Resources consumed for repairing the task.

7. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the automatic detection and location method for long-distance communication optical cable faults as described in any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the automatic detection and location method for long-distance communication optical cable faults as described in any one of claims 1-6.

Images