Optical cable fault diagnosis system and method based on vibration filtering algorithm

Abstract

The invention discloses an optical cable fault diagnosis system and method based on a vibration filtering algorithm, relates to the technical field of optical cable fault diagnosis, and solves the problems of low efficiency, long response time and the like in the prior art and the technical problem that the health condition of an optical cable is difficult to comprehensively assess through single optical power data. The quality data of the optical cable are acquired; training an artificial intelligence model based on the historical vibration signal data to obtain an optical cable fault identification model; recognizing the vibration data based on an optical cable fault recognition model to obtain a recognition result; calculating an optical cable aging evaluation coefficient based on the vibration signal data and the optical power loss data; constructing an optical cable aging evaluation coefficient correction model based on the environment data to correct the optical cable aging evaluation coefficient obtained through calculation, and obtaining a target optical cable aging evaluation coefficient; and judging whether to carry out fault early warning based on the identification result and the target optical cable aging evaluation coefficient. The technical problem is solved.

Description

Technical Field

[0001] The invention belongs to the field of optical cable fault diagnosis, and in particular relates to an optical cable fault diagnosis system and method based on a vibration filtering algorithm. Background Art

[0002] With the development of information technology, optical cables, as an important carrier of information transmission, play an increasingly important role in communication networks. However, due to external factors (such as natural disasters, man-made damage, etc.), optical cables often break, wear and tear, which not only affects the quality of communication, but also may cause serious economic losses.

[0003] Existing methods for diagnosing optical cable faults mainly rely on manual inspections or equipment such as OTDR for troubleshooting, as well as measuring the optical power at both ends of the optical cable, calculating the optical power loss, and evaluating the transmission quality of the optical cable; however, troubleshooting through manual inspections or equipment such as OTDR has problems such as low efficiency, high cost, and long response time. In addition, optical power loss is greatly affected by factors such as ambient temperature and humidity, and a single optical power data is difficult to fully evaluate the health of the optical cable.

[0004] Therefore, the present invention solves the above-mentioned problem by proposing an optical cable fault diagnosis system and method based on a vibration filtering algorithm. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an optical cable fault diagnosis system and method based on a vibration filtering algorithm, which is used to solve the existing method for optical cable fault diagnosis, which mainly relies on manual inspection or OTDR and other equipment to perform fault troubleshooting, and calculate the optical power loss by measuring the optical power at both ends of the optical cable, and evaluate the transmission quality of the optical cable; however, the fault troubleshooting by manual inspection or OTDR and other equipment has the problems of low efficiency, high cost, long response time, etc., and the optical power loss is greatly affected by factors such as ambient temperature and humidity, and a single optical power data is difficult to comprehensively evaluate the health status of the optical cable.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides an optical cable fault diagnosis system based on a vibration filtering algorithm, comprising: a data acquisition module, a data analysis module and a fault warning module;

[0007] Data acquisition module: used to obtain the quality data of the optical cable; the quality data includes: vibration signal data, optical power loss data and environmental data;

[0008] Data analysis module: training an artificial intelligence model based on historical vibration signal data to obtain an optical cable fault identification model; identifying vibration data based on the optical cable fault identification model to obtain identification results; and,

[0009] The optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data; an optical cable aging assessment coefficient correction model is constructed based on the environmental data to correct the calculated optical cable aging assessment coefficient to obtain the target optical cable aging assessment coefficient;

[0010] Fault warning module: Determines whether to issue a fault warning based on the identification results and the target optical cable aging assessment coefficient.

[0011] Preferably, the data analysis system is communicated and / or electrically connected to the data acquisition module and the fault warning module respectively.

[0012] Preferably, the obtaining of quality data of the optical cable includes:

[0013] Vibration is generated according to preset parameters by a mechanical vibration device installed on the optical cable, and vibration signals are collected based on an optical fiber vibration sensor installed on the optical cable;

[0014] By preprocessing the vibration signal, a preprocessed vibration signal is obtained; wherein the preprocessing includes: denoising, trend item removal and filtering;

[0015] Vibration signal data is obtained by performing time domain analysis and frequency domain analysis on the preprocessed vibration signal; wherein the vibration signal data includes: vibration amplitude, peak value, peak-to-peak value, root mean square value, standard deviation, power spectrum density and spectrum entropy, etc.;

[0016] By inputting a light source into one end of the optical cable, using an optical power meter to collect the optical power of the light source at the other end of the optical cable, and calculating the difference between the optical power of the initial light source and the optical power of the collected light source, the optical power loss is obtained; wherein the optical power of the initial light source refers to the optical power of the light source input into one end of the optical cable;

[0017] The environmental data of the environment where the optical cable is located is collected based on the data sensor; wherein the environmental data includes: environmental temperature and environmental humidity.

[0018] It should be noted that the preset parameters include: vibration amplitude and vibration frequency.

[0019] Preferably, the training of the artificial intelligence model based on historical vibration signal data includes:

[0020] Integrate historical vibration signal data into standard input data, and integrate the fault types corresponding to the historical vibration signal data into standard output data; wherein the fault types corresponding to the historical vibration signal data are obtained by manual identification; the fault types include: normal, broken, loose joints and wear;

[0021] An artificial intelligence model is trained based on standard input data and standard output data to obtain an optical cable fault identification model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0022] It should be noted that the historical vibration signal data refers to past vibration signal data, that is, historical data of collected vibration signal data.

[0023] Preferably, the identifying of vibration signal data based on the optical cable fault identification model includes:

[0024] The real-time acquired vibration signal data is extracted and input into the optical cable fault identification model to obtain the fault type.

[0025] It should be noted that the failure of the optical cable will cause changes in multiple key parameters of the vibration signal. Specifically, the break of the optical fiber in the optical cable will completely interrupt the signal transmission, making it impossible to calculate time domain parameters such as vibration amplitude, peak value, peak-to-peak value, root mean square value (RMS), standard deviation, etc., and frequency domain parameters such as power spectral density (PSD) and spectrum entropy will also be unable to obtain complete information due to the interruption of the spectrum graph; bending or twisting of the optical fiber in the optical cable will cause signal attenuation or distortion, resulting in a decrease in vibration amplitude, peak value, peak-to-peak value, RMS and standard deviation, and additional noise or frequency component changes will appear in the spectrum graph. PSD and spectral entropy increase; loose fiber connectors in the optical cable will cause signal instability, time domain parameters such as vibration amplitude, peak, peak-to-peak value, RMS and standard deviation will fluctuate, and frequency domain parameters such as PSD and spectral entropy will have low-frequency noise or intermittent peaks; optical fiber contamination in the optical cable will increase background noise, reduce vibration amplitude, peak, peak-to-peak value, RMS and standard deviation, increase noise in the spectrum diagram, and increase PSD and spectral entropy. Therefore, by continuously monitoring and analyzing these vibration signal data, optical cable faults can be discovered and diagnosed in a timely manner, so that corresponding repair or maintenance measures can be taken.

[0026] Preferably, the optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data, including:

[0027] The vibration amplitude is marked as F; the optical power loss is marked as G;

[0028] By formula: P = A × e^[(F-ZF)^2 / ZF]+B×ln(1+G)×e^[1 / (1+G)];

[0029] The optical cable aging assessment coefficient is calculated; wherein P is the optical cable aging assessment coefficient, A and B are proportional coefficients, and 0<A<1, 0<B<1, and ZF refers to the vibration amplitude of the normal optical cable.

[0030] It should be noted that the proportional coefficients A and B are set by experts based on experience;

[0031] The aging of optical cables can cause changes in the physical properties of the optical fibers, such as microscopic cracks and material degradation, which will increase the transmission loss of optical signals, thereby weakening the intensity of optical signals and reducing transmission efficiency. The aging of optical cables can cause the stiffness of the materials to decrease, making them more sensitive to vibrations and increasing the vibration amplitude. At the same time, aging can also cause the fibers or wires inside the optical cables to loosen, which can also increase the vibration amplitude.

[0032] Preferably, the optical cable aging assessment coefficient correction model is constructed based on the environmental data to correct the calculated optical cable aging assessment coefficient, including:

[0033] The environmental data is used as the independent variable, and the environmental temperature and environmental humidity are marked as W and H respectively. The corrected optical cable aging assessment coefficient is used as the dependent variable and marked as the target optical cable aging assessment coefficient MP.

[0034] The independent variables and dependent variables are fitted by polynomial fitting to establish a correction model; the correction model is specifically as follows:

[0035] MP=P[1-α×e^tanh(W)-β×ln(H) / (ln(H)+1)];

[0036] Among them, α and β are proportional coefficients, and 0<α<1, 0<β<1, tanh(*) is the hyperbolic tangent function, and ln(*) is the logarithmic function with the natural number e as the base.

[0037] It should be noted that the proportional coefficients α and β are set by experts based on experience;

[0038] As the temperature rises, the loss characteristics of the optical cable material may change, resulting in increased optical power loss. For example, optical fiber may increase attenuation due to thermal effects at high temperatures, thereby affecting the transmission quality of the optical signal. Excessive humidity may cause water mist or water droplets to form on the surface of the optical cable. These attachments will scatter or absorb optical signals, thereby increasing optical power loss.

[0039] Preferably, judging whether to perform a fault warning based on the identification result and the target optical cable aging assessment coefficient includes:

[0040] Determine whether the fault type in the identification result is normal; if yes, continue monitoring and judging; if no, generate warning information and send it to the client;

[0041] Determine whether the target optical cable aging assessment coefficient is greater than the preset assessment threshold; if yes, generate an early warning message and send it to the client; if not, continue to monitor and judge.

[0042] It should be noted that the preset evaluation threshold is set by experts based on experience according to actual safety requirements of optical cables.

[0043] A second aspect of the present invention provides an optical cable fault diagnosis method based on a vibration filtering algorithm, comprising:

[0044] Obtaining quality data of the optical cable; wherein the quality data includes: vibration signal data, optical power loss data and environmental data;

[0045] The artificial intelligence model is trained based on historical vibration signal data to obtain the optical cable fault identification model;

[0046] Identify the vibration data based on the optical cable fault identification model and obtain the identification result;

[0047] The optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data;

[0048] Based on the environmental data, an optical cable aging assessment coefficient correction model is constructed to correct the calculated optical cable aging assessment coefficient to obtain the target optical cable aging assessment coefficient;

[0049] Whether to issue a fault warning is determined based on the identification result and the target optical cable aging assessment coefficient.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The existing method for diagnosing optical cable faults mainly relies on manual inspection or OTDR and other equipment to perform troubleshooting, and measures the optical power at both ends of the optical cable, calculates the optical power loss, and evaluates the transmission quality of the optical cable; however, troubleshooting by manual inspection or OTDR and other equipment has the problems of low efficiency, high cost, long response time, etc., and the optical power loss is greatly affected by factors such as ambient temperature and humidity, and single optical power data is difficult to comprehensively evaluate the health status of the optical cable; the present invention obtains the vibration signal data, optical power loss data and environmental data of the optical cable through a data acquisition module, uses a data analysis module to train an artificial intelligence model based on historical vibration signal data, realizes intelligent recognition of vibration data, and calculates the optical cable aging assessment coefficient through the vibration signal data and the optical power loss data, and corrects it in combination with the environmental data, and finally the fault warning module determines whether to perform a fault warning according to the recognition result and the target optical cable aging assessment coefficient, which not only improves the efficiency and accuracy of fault diagnosis and shortens the response time, but also comprehensively evaluates the health status of the optical cable, and effectively solves the shortcomings of the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a system module according to an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of a specific process of an embodiment of the present invention;

[0055] Figure 3 Schematic diagram of the method steps of an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] See also Figure 1-Figure 2 , the first aspect of the present invention provides an optical cable fault diagnosis system based on a vibration filtering algorithm, including: a data acquisition module, a data analysis module and a fault warning module;

[0058] Data acquisition module: used to obtain the quality data of the optical cable; the quality data includes: vibration signal data, optical power loss data and environmental data;

[0059] Data analysis module: training an artificial intelligence model based on historical vibration signal data to obtain an optical cable fault identification model; identifying vibration data based on the optical cable fault identification model to obtain identification results; and,

[0060] The optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data; an optical cable aging assessment coefficient correction model is constructed based on the environmental data to correct the calculated optical cable aging assessment coefficient to obtain the target optical cable aging assessment coefficient;

[0061] Fault warning module: Determines whether to issue a fault warning based on the identification results and the target optical cable aging assessment coefficient.

[0062] Obtain quality data of optical cables, including:

[0063] Vibration is generated according to preset parameters by a mechanical vibration device installed on the optical cable, and vibration signals are collected based on an optical fiber vibration sensor installed on the optical cable;

[0064] By preprocessing the vibration signal, a preprocessed vibration signal is obtained; wherein the preprocessing includes: denoising, trend item removal and filtering;

[0065] Vibration signal data is obtained by performing time domain analysis and frequency domain analysis on the preprocessed vibration signal; wherein the vibration signal data includes: vibration amplitude, peak value, peak-to-peak value, root mean square value, standard deviation, power spectrum density and spectrum entropy, etc.;

[0066] By inputting a light source into one end of the optical cable, using an optical power meter to collect the optical power of the light source at the other end of the optical cable, and calculating the difference between the optical power of the initial light source and the optical power of the collected light source, the optical power loss is obtained; wherein the optical power of the initial light source refers to the optical power of the light source input into one end of the optical cable;

[0067] The environmental data of the environment where the optical cable is located is collected based on the data sensor; wherein the environmental data includes: environmental temperature and environmental humidity.

[0068] Training AI models based on historical vibration signal data, including:

[0069] Integrate historical vibration signal data into standard input data, and integrate the fault types corresponding to the historical vibration signal data into standard output data; wherein the fault types corresponding to the historical vibration signal data are obtained by manual identification; the fault types include: normal, broken, loose joints and wear;

[0070] An artificial intelligence model is trained based on standard input data and standard output data to obtain an optical cable fault identification model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0071] Identify vibration signal data based on the optical cable fault identification model, including:

[0072] The real-time acquired vibration signal data is extracted and input into the optical cable fault identification model to obtain the fault type.

[0073] The optical cable aging assessment coefficient is calculated based on the vibration signal data and optical power loss data, including:

[0074] The vibration amplitude is marked as F; the optical power loss is marked as G;

[0075] By formula: P = A × e^[(F-ZF)^2 / ZF]+B×ln(1+G)×e^[1 / (1+G)];

[0076] The optical cable aging assessment coefficient is calculated; wherein P is the optical cable aging assessment coefficient, A and B are proportional coefficients, and 0<A<1, 0<B<1, and ZF refers to the vibration amplitude of the normal optical cable.

[0077] Based on the environmental data, a correction model for the optical cable aging assessment coefficient is constructed to correct the calculated optical cable aging assessment coefficient, including:

[0078] The environmental data is used as the independent variable, and the environmental temperature and environmental humidity are marked as W and H respectively. The corrected optical cable aging assessment coefficient is used as the dependent variable and marked as the target optical cable aging assessment coefficient MP.

[0079] The independent variables and dependent variables are fitted by polynomial fitting to establish a correction model; the correction model is specifically as follows:

[0080] MP=P[1-α×e^tanh(W)-β×ln(H) / (ln(H)+1)];

[0081] Among them, α and β are proportional coefficients, and 0<α<1, 0<β<1, tanh(*) is the hyperbolic tangent function, and ln(*) is the logarithmic function with the natural number e as the base.

[0082] Determine whether to issue a fault warning based on the identification result and the target optical cable aging assessment coefficient, including:

[0083] Determine whether the fault type in the identification result is normal; if yes, continue monitoring and judging; if no, generate warning information and send it to the client;

[0084] Determine whether the target optical cable aging assessment coefficient is greater than the preset assessment threshold; if yes, generate an early warning message and send it to the client; if not, continue to monitor and judge.

[0085] For example, suppose a certain optical cable needs to be diagnosed for a fault. The specific diagnostic steps are as follows:

[0086] Data acquisition module;

[0087] 1. Vibration signal data collection:

[0088] Mechanical vibration device: A mechanical vibration device is installed on the optical cable, and the vibration amplitude is set to 10μm and the vibration frequency is set to 50Hz.

[0089] Fiber optic vibration sensor: Fiber optic vibration sensor installed on optical cable collects vibration signals.

[0090] Preprocessing: De-noise, remove trend items and filter the collected vibration signal to obtain a preprocessed vibration signal.

[0091] 2. Optical power loss data collection:

[0092] Light source input: Input the light source to one end of the optical cable. The initial light power of the light source is 1mW.

[0093] Optical power meter: Use an optical power meter to collect the optical power of the light source at the other end of the optical cable, and the measured optical power of the collected light source is 0.8mW.

[0094] Optical power loss: Calculate the difference between the optical power of the initial light source and the optical power of the acquisition light source to obtain the optical power loss: G = 1mW-0.8mW = 0.2mW;

[0095] 3. Environmental data collection:

[0096] Ambient temperature: The temperature of the environment where the optical cable is located is collected by a temperature sensor, and the measured ambient temperature is 30°C.

[0097] Ambient humidity: The humidity of the environment where the optical cable is located is collected by a humidity sensor, and the measured ambient humidity is 70% RH.

[0098] Data analysis module;

[0099] 1. Artificial intelligence model training:

[0100] Historical vibration signal data: It is assumed that historical vibration signal data is available, including data of various fault types such as normal, broken, loose joints and wear.

[0101] Standard input data: Integrate historical vibration signal data into standard input data.

[0102] Standard output data: Integrate the fault types corresponding to the historical vibration signal data into standard output data.

[0103] Training model: A convolutional neural network (CNN) is trained based on standard input data and standard output data to obtain an optical cable fault recognition model.

[0104] 2. Vibration signal recognition:

[0105] Real-time vibration signal data: Extract vibration signal data acquired in real time.

[0106] Input model: Input the real-time vibration signal data into the optical cable fault identification model to obtain the fault type. Assume that the model identification result is "breakage".

[0107] 3. Calculation of optical cable aging assessment coefficient:

[0108] Vibration amplitude: Assume that the vibration signal data collected in real time is analyzed in the time domain and frequency domain to obtain a vibration amplitude of F = 12 μm.

[0109] Normal vibration amplitude of optical cable: Assume that the normal vibration amplitude of optical cable ZF = 10μm.

[0110] Proportional coefficient: Assume that the proportional coefficients A = 0.5 and B = 0.3.

[0111] Calculation formula: P = A × e^[(F-ZF)^2 / ZF]+B × ln(1+G) × e^[1 / (1+G)];

[0112] P=0.5×e^[(12-10)^2 / 10]+0.3×ln(1+0.2)×e^[1 / (1+0.2)]≈0.8719;

[0113] 4.Correction of optical cable aging assessment coefficient:

[0114] Ambient temperature: W = 30°C.

[0115] Ambient humidity: H = 70% RH.

[0116] Proportional coefficient: Assume that the proportional coefficient α=0.2, β=0.1.

[0117] Modified model: MP = P[1-α×e^tanh(W)-β×ln(H) / (ln(H)+1)];

[0118] MP=0.8719×[1-0.2×e^tanh(30)-0.1×ln(70) / (ln(70)+1)]≈0.3272;

[0119] Fault warning module;

[0120] 1. Determine the fault type:

[0121] Identification result: Fault type is "fracture".

[0122] Judgment: Since the identification result is "break", a "break" warning signal is generated and sent to the client to remind the staff that the optical cable has a fault and the fault type is "break".

[0123] 2. Determine the aging assessment coefficient:

[0124] Preset evaluation threshold: Assume that the preset evaluation threshold is 0.2.

[0125] Since the target optical cable aging assessment coefficient MP=0.3272 is greater than the preset assessment threshold value 0.2, an early warning message is sent to the client to remind the staff that the optical cable is aging and needs maintenance.

[0126] The present invention effectively acquires and analyzes the quality data of optical cables, uses artificial intelligence models to intelligently identify vibration signals, and comprehensively evaluates the health of optical cables by calculating and correcting the optical cable aging assessment coefficient. Finally, the fault warning module determines whether to issue a fault warning based on the identification results and the target optical cable aging assessment coefficient, which improves the efficiency and accuracy of fault diagnosis, shortens the response time, and effectively solves the shortcomings of the prior art.

[0127] See also Figure 3 The second aspect of the present invention provides a method for diagnosing optical cable faults based on a vibration filtering algorithm, comprising:

[0128] Obtaining quality data of the optical cable; wherein the quality data includes: vibration signal data, optical power loss data and environmental data;

[0129] The artificial intelligence model is trained based on historical vibration signal data to obtain the optical cable fault identification model;

[0130] Identify the vibration data based on the optical cable fault identification model and obtain the identification result;

[0131] The optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data;

[0132] Based on the environmental data, an optical cable aging assessment coefficient correction model is constructed to correct the calculated optical cable aging assessment coefficient to obtain the target optical cable aging assessment coefficient;

[0133] Whether to issue a fault warning is determined based on the identification result and the target optical cable aging assessment coefficient.

[0134] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0135] Working principle of the present invention:

[0136] The present invention obtains the quality data of the optical cable; trains an artificial intelligence model based on historical vibration signal data to obtain an optical cable fault recognition model; recognizes the vibration data based on the optical cable fault recognition model to obtain a recognition result; calculates the optical cable aging assessment coefficient based on the vibration signal data and optical power loss data; constructs an optical cable aging assessment coefficient correction model based on environmental data to correct the calculated optical cable aging assessment coefficient to obtain a target optical cable aging assessment coefficient; and determines whether to perform a fault warning based on the recognition result and the target optical cable aging assessment coefficient. The present invention solves the problems of low efficiency and long response time in the prior art, as well as the technical problem that it is difficult to comprehensively evaluate the health status of the optical cable through single optical power data.

[0137] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An optical cable fault diagnosis system based on vibration filtering algorithm, characterized in that: include: Data acquisition module, data analysis module and fault warning module; Data acquisition module: used to obtain the quality data of the optical cable; the quality data includes: vibration signal data, optical power loss data and environmental data; Data analysis module: training an artificial intelligence model based on historical vibration signal data to obtain an optical cable fault identification model; identifying vibration data based on the optical cable fault identification model to obtain identification results; and, The optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data; an optical cable aging assessment coefficient correction model is constructed based on the environmental data to correct the calculated optical cable aging assessment coefficient to obtain the target optical cable aging assessment coefficient; Fault warning module: Determines whether to issue a fault warning based on the identification results and the target optical cable aging assessment coefficient.

2. The optical cable fault diagnosis system based on vibration filtering algorithm according to claim 1 is characterized in that: The obtaining of quality data of the optical cable comprises: Vibration is generated according to preset parameters by a mechanical vibration device installed on the optical cable, and vibration signals are collected based on an optical fiber vibration sensor installed on the optical cable; By preprocessing the vibration signal, a preprocessed vibration signal is obtained; wherein the preprocessing includes: denoising, trend item removal and filtering; Vibration signal data is obtained by performing time domain analysis and frequency domain analysis on the pre-processed vibration signal; By inputting a light source into one end of the optical cable, using an optical power meter to collect the optical power of the light source at the other end of the optical cable, and calculating the difference between the optical power of the initial light source and the optical power of the collected light source, the optical power loss is obtained; wherein the optical power of the initial light source refers to the optical power of the light source input into one end of the optical cable; The environmental data of the environment where the optical cable is located is collected based on the data sensor; wherein the environmental data includes: environmental temperature and environmental humidity.

3. The optical cable fault diagnosis system based on vibration filtering algorithm according to claim 1 is characterized in that: The training of the artificial intelligence model based on historical vibration signal data includes: Integrate historical vibration signal data into standard input data, and integrate the fault types corresponding to the historical vibration signal data into standard output data; wherein the fault types corresponding to the historical vibration signal data are obtained by manual identification; the fault types include: normal, broken, loose joints and wear; An artificial intelligence model is trained based on standard input data and standard output data to obtain an optical cable fault identification model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

4. The optical cable fault diagnosis system based on vibration filtering algorithm according to claim 1 is characterized in that: The identifying of vibration signal data based on the optical cable fault identification model includes: The real-time acquired vibration signal data is extracted and input into the optical cable fault identification model to obtain the fault type.

5. The optical cable fault diagnosis system based on vibration filtering algorithm according to claim 1 is characterized in that: The optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data, including: The vibration amplitude is marked as F; the optical power loss is marked as G; By formula: P = A × e^[(F-ZF)^2 / ZF]+B×ln(1+G)×e^[1 / (1+G)]; The optical cable aging assessment coefficient is calculated; wherein P is the optical cable aging assessment coefficient, A and B are proportional coefficients, and 0<A<1, 0<B<1, and ZF refers to the vibration amplitude of the normal optical cable.

6. The optical cable fault diagnosis system based on vibration filtering algorithm according to claim 1 is characterized in that: The method of constructing an optical cable aging assessment coefficient correction model based on environmental data to correct the calculated optical cable aging assessment coefficient includes: The environmental data is used as the independent variable, and the environmental temperature and environmental humidity are marked as W and H respectively. The corrected optical cable aging assessment coefficient is used as the dependent variable and marked as the target optical cable aging assessment coefficient MP. The independent variables and dependent variables are fitted by polynomial fitting to establish a correction model; the correction model is specifically as follows: MP=P[1-α×e^tanh(W)-β×ln(H) / (ln(H)+1)]; Among them, α and β are proportional coefficients, and 0<α<1, 0<β<1, tanh(*) is the hyperbolic tangent function, and ln(*) is the logarithmic function with the natural number e as the base.

7. The optical cable fault diagnosis system based on vibration filtering algorithm according to claim 1 is characterized in that: The determining whether to perform a fault warning based on the identification result and the target optical cable aging assessment coefficient includes: Determine whether the fault type in the identification result is normal; if yes, continue monitoring and judging; if no, generate warning information and send it to the client; Determine whether the target optical cable aging assessment coefficient is greater than the preset assessment threshold; if yes, generate an early warning message and send it to the client; if not, continue to monitor and judge.

8. An optical cable fault diagnosis method based on a vibration filtering algorithm, applied to an optical cable fault diagnosis system based on a vibration filtering algorithm as claimed in any one of claims 1 to 7, characterized in that: include: Obtaining quality data of the optical cable; wherein the quality data includes: vibration signal data, optical power loss data and environmental data; The artificial intelligence model is trained based on historical vibration signal data to obtain the optical cable fault identification model; Identify the vibration data based on the optical cable fault identification model and obtain the identification result; The optical cable aging assessment coefficient is calculated based on the vibration signal data and the optical power loss data; Based on the environmental data, an optical cable aging assessment coefficient correction model is constructed to correct the calculated optical cable aging assessment coefficient to obtain the target optical cable aging assessment coefficient; Whether to issue a fault warning is determined based on the identification result and the target optical cable aging assessment coefficient.

Images