Optical fiber characteristic intelligent diagnosis and optimization system

Abstract

The invention discloses an optical fiber characteristic intelligent diagnosis and optimization system, which relates to the technical field of optical fiber communication and comprises an optical characteristic data acquisition module, a physical characteristic data acquisition module, an environmental characteristic data acquisition module, a data fusion module and a diagnosis and optimization module. According to the optical fiber characteristic intelligent diagnosis and optimization system, various factors influencing the performance of the optical fiber can be comprehensively considered by fusing the optical characteristic data, the physical characteristic data and the environmental data of the optical fiber, and the multi-modal data is comprehensively analyzed by using a data fusion algorithm, so that various states of the optical fiber are accurately diagnosed, and the optical fiber performance is optimized. The method has the advantages that the diagnosis accuracy and reliability are greatly improved, the possibility of missed diagnosis and misdiagnosis of faults is reduced, and a powerful guarantee is provided for stable operation of an optical fiber communication system.

Description

Technical Field

[0001] The present invention relates to the field of optical fiber communication technology, and in particular to an optical fiber characteristic intelligent diagnosis and optimization system. Background Art

[0002] With the rapid development of optical communication technology, fiber optic networks have become an important infrastructure for modern information transmission. Optical fiber has the advantages of high bandwidth, low loss and resistance to electromagnetic interference, and is widely used in telecommunications, the Internet, data centers and other fields. However, in actual operation, optical fiber will be affected by many factors, such as temperature changes, mechanical stress, humidity, and electromagnetic fields. These factors may cause changes in optical fiber characteristics, thereby affecting communication quality and system stability. In order to ensure the efficient and stable operation of the optical fiber network, it is necessary to regularly monitor and diagnose the optical fiber characteristics and take corresponding optimization measures.

[0003] However, in terms of fiber characteristic diagnosis, existing technologies only focus on a single type of data, which cannot fully reflect the actual status of the fiber, and lack effective fusion methods when dealing with multiple factors. It is often difficult to accurately diagnose the root cause of fiber performance degradation.

[0004] In summary, the existing optical fiber characteristic diagnosis technology has obvious shortcomings when facing the increasingly complex optical fiber communication systems and diversified application scenarios. In order to improve the reliability and stability of optical fiber communication systems, there is an urgent need for an intelligent diagnosis and optimization system that can integrate multimodal data to achieve comprehensive and accurate diagnosis and optimization of optical fiber characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide an intelligent diagnosis and optimization system for optical fiber characteristics. The system, by integrating optical characteristic data, physical characteristic data and environmental data, can comprehensively capture the complexity of the optical fiber status, provide more accurate diagnostic results, and monitor and analyze the various characteristics of the optical fiber in real time, and timely adjust and optimize the performance of the optical fiber communication system, thereby improving the stability and reliability of the optical fiber communication system.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent optical fiber characteristic diagnosis and optimization system, the system comprising an optical characteristic data acquisition module, a physical characteristic data acquisition module, an environmental characteristic data acquisition module, a data fusion module, and a diagnosis and optimization module;

[0007] The optical characteristic data acquisition module uses an optical detection device to emit light pulses into the optical fiber and receive light signals reflected from different positions along the optical fiber, and uses multiple light sources with different wavelengths to alternately measure the refractive index distribution and light loss of the optical fiber, wherein:

[0008] For the measurement of refractive index distribution, based on the principle of optical interference: Where n(z represents the refractive index of the optical fiber at the position, λ0 is the initial wavelength of the light source, L is the length of the optical fiber, Δφ(z is the phase difference of the reflected light at the position, and the refractive index distribution along the optical fiber is calculated by measuring the phase difference at different positions;

[0009] For the measurement of optical loss, the formula is used Where α is the optical loss coefficient, L is the fiber length, P r (z) is the reflected light power received at position z, P i It is the transmitted optical power. By alternately measuring light sources of different wavelengths, the optical loss at different wavelengths can be obtained.

[0010] The physical property data acquisition module is composed of a strain sensor and an optical fiber temperature sensor, which monitors the physical property data of optical fiber temperature and strain value in real time under different environments and working conditions, wherein:

[0011] The optical fiber temperature sensor uses the thermo-optical effect of optical fiber to determine the temperature by measuring the change of optical signal. The relationship between temperature and optical signal wavelength is λ T =λ0(1+ξT), where λ T is the wavelength of the optical signal at temperature T, λ0 is the initial wavelength, ξ is the thermo-optical coefficient of the optical fiber, and the change in the wavelength of the optical signal Δλ = λ T -λ0, combined with the thermo-optical coefficient ξ, calculate the temperature T;

[0012] The strain sensor monitors the strain of the optical fiber under different external forces in real time, and accurately calculates the strain value of the optical fiber by measuring the wavelength drift. The relationship between strain and wavelength drift is Δλ B =λ B (1-p e )ε, where Δλ B is the drift of the fiber Bragg grating reflection wavelength, λ B is the initial reflection wavelength of the fiber Bragg grating, p e is the effective elastic-optical coefficient of the optical fiber, ε is the strain on the optical fiber, and the wavelength drift Δλ is measured B , combined with the initial reflection wavelength λ of the fiber Bragg grating B and the effective elastic-optical coefficient p e , calculate the strain ε;

[0013] The environmental characteristic data acquisition module is composed of a humidity sensor and an electromagnetic field sensor, and is used to collect environmental data of humidity and electromagnetic field in the environment where the optical fiber is located, wherein:

[0014] The humidity sensor reflects the change of humidity by measuring the change of capacitance value, that is, Where H is the current humidity, H0 is the reference humidity, ΔC is the change in capacitance, k H is the humidity sensitivity coefficient;

[0015] The electromagnetic field sensor is used to detect the electromagnetic field strength and frequency distribution around the optical fiber. The electromagnetic field strength calculation formula is: Where E is the electromagnetic field intensity, Ex, Ey, and Ez are the components of the electromagnetic field in the x, y, and z directions respectively, and the electromagnetic field frequency distribution calculation formula is Where f(ω) is the spectrum distribution of the electromagnetic field, E(t) is the time domain electromagnetic field signal, and iωt is the electromagnetic angular frequency;

[0016] The data fusion module includes a data preprocessing unit, a feature extraction unit and a fusion algorithm unit. The data preprocessing unit is used to perform a comprehensive data cleaning operation on the collected optical characteristic data, physical characteristic data and environmental data. The feature extraction unit is used to extract features from the preprocessed data. The fusion algorithm unit fuses the features of the optical characteristic data, physical characteristic data and environmental data.

[0017] The diagnosis and optimization module includes an intelligent diagnosis unit, an optimization strategy generation unit and a strategy implementation and feedback unit. The intelligent diagnosis unit is used to diagnose the optical fiber characteristics based on the fused data, the optimization strategy generation unit is used to generate an optimization strategy according to the diagnosis results, and the strategy implementation and feedback unit is used to implement the optimization strategy into the optical fiber communication system and adjust and optimize according to the feedback data.

[0018] Furthermore, the feature extraction unit in the data fusion module extracts features from the preprocessed optical characteristic data, including:

[0019] For optical loss data, extract the statistical characteristics of the mean, variance, and peak value of the loss;

[0020] For the refractive index distribution data, the gradient characteristics of the refractive index are extracted by performing Fourier transform on the spectral data to extract the frequency characteristics and bandwidth characteristics of the spectrum.

[0021] Furthermore, the feature extraction unit has a mean value of where α i represents the optical loss value measured at different positions, n is the number of measurements, and the variance is The peak value P is the maximum value in the optical loss data, that is, P = max{α i}.

[0022] Furthermore, for the refractive index distribution data, the gradient feature G of the refractive index is Where n(z1) and n(z2) are the refractive indices of the optical fiber at positions z1 and z2 respectively, and z2-z1 is the distance between the two positions. The gradient characteristics of the refractive index are obtained by calculating the rate of change of the refractive index between different positions.

[0023] Furthermore, the feature extraction unit extracts the maximum value, minimum value, and change rate characteristics of the strain, as well as the fluctuation amplitude and period characteristics of the temperature from the physical property data, wherein:

[0024] For strain data, the strain value is ε i , and i=1,2,…,n, the maximum value of strain E max For E max =max{ε i}, the minimum value of strain E min For E min =min{ε i}, the strain change rate R is calculated by the strain values ​​at adjacent time points, that is, Where Δt is the time interval between adjacent time points, and j = 1, 2, ..., n-1;

[0025] For temperature data, the temperature value is T i , the temperature fluctuation range A is A = T max -T min , where T max is the maximum temperature, T min is the minimum temperature, the temperature period P T The temperature data is obtained by Fourier transform, that is, the temperature data is Where kωt is the temperature angular frequency, k is the number of transformations and k = 1, 2, ..., m. The temperature period is determined by analyzing the value of ω.

[0026] Furthermore, the feature extraction unit extracts the mean and variation range features of humidity, and the maximum and average features of electromagnetic field intensity from the environmental data, wherein:

[0027] For humidity data, the mean humidity is in is the mean humidity, N is the number of sampling points, H i is the humidity value of the i-th sampling point, and its humidity variation range ΔH is ΔH=max9H i )-min(H i ), where max(H i ) and min(H i ) are the maximum and minimum humidity values ​​among all sampling points respectively;

[0028] For electromagnetic data, the maximum electromagnetic field strength E max For E max =max(E i ), where E i is the electromagnetic field strength at the i-th sampling point, and its average electromagnetic field strength for Where N is the number of sampling points, E i is the electromagnetic field intensity at the i-th sampling point.

[0029] Furthermore, the fusion algorithm unit in the data fusion module fuses various data features, that is, the mean value μ of the optical loss data α ,variance Peak P α , refractive index gradient feature G n , the maximum value of strain E max , minimum value E min , rate of change R E , the temperature fluctuation range A T , period P T , the mean humidity Variation range ΔH, maximum value of electromagnetic field strength E E ,average value Each feature is normalized, and the normalization formula is: Where X is the eigenvalue to be normalized, X min is the minimum value of the eigenvalue, X max is the maximum value of the eigenvalue, and the eigenvalue of each data normalization is the mean value μ of the optical loss data. α,norm ,variance Peak P α,norm , refractive index gradient feature G n,norm , the maximum value of strain E max,norm , minimum value E min,norm , rate of change R E,norm , the temperature fluctuation range A T,norm , period P T,norm , the mean humidity Variation range ΔH norm , the maximum value of the electromagnetic field strength average value Using the fusion algorithm based on weighted summation, the eigenvalue F after fusion is

[0030] Where w1+…w 13 =1.

[0031] Furthermore, the intelligent diagnosis unit in the diagnosis and optimization module diagnoses the characteristic value F after the optical fiber data is fused, and according to the diagnosis result, the optimization strategy generation unit automatically generates a targeted optimization strategy, wherein:

[0032] For the diagnosis of large optical fiber loss, optimization strategies include adjusting the optical transmission power, optimizing the signal modulation method, and replacing the optical fiber connector;

[0033] For the degradation of optical fiber performance caused by excessive temperature, optimization strategies include strengthening heat dissipation measures;

[0034] When external stress is detected on the optical fiber, the optimization strategy includes adjusting the optical fiber support structure, adding buffer materials, and changing the optical fiber wiring method;

[0035] Regarding the influence of environmental factors, take moisture-proof measures when humidity is high and use moisture-proof materials to protect the optical fiber.

[0036] Compared with the prior art, this optical fiber characteristic intelligent diagnosis and optimization system has the following beneficial effects:

[0037] 1. The optical fiber characteristic intelligent diagnosis and optimization system of the present invention can comprehensively consider various factors affecting the performance of optical fiber by integrating the optical characteristic data, physical characteristic data and environmental data of the optical fiber, and use the data fusion algorithm to comprehensively analyze the multimodal data, so as to accurately diagnose various states of the optical fiber, including normal state and various abnormal states, greatly improving the accuracy and reliability of diagnosis, reducing the possibility of missed diagnosis and misdiagnosis of faults, and providing a strong guarantee for the stable operation of the optical fiber communication system.

[0038] 2. Based on the results of multimodal data fusion diagnosis, the system can automatically generate an adaptive optimization strategy. This optimization strategy can not only make real-time adjustments to the current optical fiber status to improve the performance and efficiency of the optical fiber communication system, but also predict the changing trend of optical fiber performance through long-term monitoring and analysis of multimodal data, so as to take preventive measures in advance, perform forward-looking maintenance, reduce the probability of failure, extend the service life of the optical fiber, and reduce the operation and maintenance cost of the optical fiber communication system.

[0039] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] 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 prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 It is an operation flow chart of an intelligent diagnosis and optimization system for optical fiber characteristics;

[0042] Figure 2 The figure is a flow chart of an intelligent optical fiber characteristic diagnosis and optimization system. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0044] Embodiment 1

[0045] This embodiment describes in detail the process of applying the optical fiber characteristic intelligent diagnosis and optimization system in the long-distance optical fiber communication network. By arranging multiple sensors at key nodes along the optical fiber to collect multimodal data and using the system's data fusion and diagnosis optimization functions, the stability and reliability of long-distance optical fiber communication can be ensured.

[0046] In the specific implementation, first of all, in the long-distance optical fiber communication network, considering that the optical fiber may experience various complex environmental conditions, optical characteristic data acquisition equipment (such as OTDR), physical characteristic sensors (such as strain sensors, temperature sensors) and environmental sensors (such as humidity sensors, electromagnetic field sensors) are arranged along the key nodes of the optical fiber in mountainous areas, desert areas and other different geographical areas. The arrangement density of these sensors is adjusted according to the complexity and importance of the environment in which the optical fiber is located. For example, in the bends of mountainous areas where the environment changes drastically or in areas with severe wind and sand erosion in the desert, the sensors are arranged more densely.

[0047] Then, the optical characteristic data is collected, and multiple light sources with different wavelengths are used to alternately measure the refractive index distribution of the optical fiber. The measurement of the refractive index distribution is based on the principle of optical interference: In actual operation, in order to improve the measurement accuracy, a high-precision phase measurement device is used to obtain the phase difference Δφ(z1) of the reflected light at different positions. For example, at the key node position z1 in the mountain area, the initial wavelength of the light source λ0=1550nm, the optical fiber length L=1000m, and the phase difference of the reflected light obtained by the phase measurement device Δφ(z1)=0.1π, then the refractive index at this position Repeat this measurement process at different wavelengths to obtain more comprehensive refractive index distribution information. For the measurement of optical loss, the formula is used. At each measuring point along the optical fiber, accurately record the transmitted optical power P i and the received reflected light power P r (z), for example, in the desert area z2, the emitted optical power P i =1mW. Considering the dust in the desert and other factors that may affect the transmission of light, the received reflected light power P r (z2) = 0.8mW, fiber length L = 1000m, then the optical loss coefficient is By alternately measuring light sources of different wavelengths, the optical loss conditions at different wavelengths can be obtained, so as to have a more comprehensive understanding of the transmission loss characteristics of light in optical fibers.

[0048] Subsequently, the physical property data is collected, and the strain sensor monitors the strain of the optical fiber under different external forces in real time. The relationship between strain and wavelength drift is Δλ B =λ B (1-p e )ε, during the fiber laying process, especially in mountainous areas that may be affected by geological activities, the strain sensor is closely attached to the fiber, for example, the initial reflection wavelength of the fiber Bragg grating is λ B =1550nm, effective elastic-optical coefficient p e =0.2, when the optical fiber is subjected to a certain external force, the wavelength drift Δλ is measured B =10nm, then the strain on the optical fiber is By continuously monitoring the changes in strain values, it is possible to promptly detect whether the optical fiber is stretched or squeezed by excessive external force. The optical fiber temperature sensor uses the thermal-optical effect of the optical fiber to determine the temperature by measuring the changes in the optical signal. The relationship between the temperature and the wavelength of the optical signal is λ T=λ0(1+ξT), at the key nodes of the optical fiber, especially in areas with large temperature changes, such as places with large day and night temperature differences in mountainous areas and high temperature areas in desert areas, the temperature sensor accurately measures the change in the wavelength of the optical signal. For example, in mountainous areas, the initial wavelength λ0=1550nm, the thermal optical coefficient λ0=1550nm, and the optical signal wavelength change Δλ is measured at different times of the day. Assuming that Δλ=5nm at noon, the temperature Through real-time temperature monitoring, we can understand the temperature conditions of the optical fiber environment and the impact of temperature on optical fiber performance.

[0049] Secondly, the environmental data is collected. The humidity sensor reflects the change of humidity by measuring the change of capacitance value, that is, In the optical fiber environment, the humidity sensor is installed in a position that can accurately reflect the ambient humidity. For example, in a humid area in a mountainous area or in a desert area where there is dew in the early morning, the reference humidity H0 = 30%, the capacitance change ΔC = 2pF, and the humidity sensitivity coefficient k H =1pF / %, then the current humidity By monitoring humidity, we can evaluate the impact of ambient humidity on optical fiber performance. For example, humidity may cause water vapor condensation on the surface of the optical fiber, thereby affecting the transmission of light. The electromagnetic field sensor is used to detect the electromagnetic field strength and frequency distribution around the optical fiber. The electromagnetic field strength calculation formula is: In areas where electromagnetic interference exists, such as near high-voltage lines or communication base stations, electromagnetic field sensors accurately measure the various components of the electromagnetic field. x =2V / m,E y =3V / m,E z =1V / m, then the electromagnetic field strength Electromagnetic field frequency distribution calculation formula f(ω)=(t)e -iωt dt, by analyzing the electromagnetic field signal, we can understand the frequency characteristics of the electromagnetic field and its interference with the optical signal transmission in the optical fiber.

[0050] Next, the collected optical characteristic data, physical characteristic data and environmental data are first transmitted to the data fusion module for data preprocessing. Data preprocessing includes data cleaning, normalization, denoising and other operations. During the data cleaning process, by setting reasonable thresholds and algorithms, outliers in the data are identified and removed. For example, for optical loss data, if the optical loss value of a certain measurement point differs too much from the optical loss value of the adjacent measurement point (by calculating the difference between the optical loss values ​​of adjacent measurement points and comparing it with the set threshold), it is considered that the data of the measurement point may be erroneous and is eliminated. The normalization operation adopts the minimum-maximum normalization method to convert data of different dimensions and magnitudes into a unified standard format. Taking optical loss data as an example, assuming that the optical loss value measured on a certain section of optical fiber ranges from 0.05dB / km to 0.5dB / km, for a certain measurement value α=0.2dB / km, the normalized optical loss value For temperature data, the high-frequency noise components in the temperature data are removed by wavelet transform to obtain a smoother temperature change curve, so as to better extract the characteristic information of temperature. Then, features are extracted from the preprocessed optical characteristic data. For optical loss data, the statistical characteristics of the mean, variance, and peak value of the loss are extracted. Assuming that the optical loss values ​​measured at multiple locations on a section of optical fiber are α2 = 0.3dB / km, α3 = 0.25dB / km, α4 = 0.18dB / km, α5 = 0.22dB / km (n = 5 measurements), the mean variance Peak value P = max{α i}=0.3dB / km; For the refractive index distribution data, the gradient characteristics of the refractive index are extracted. By analyzing the refractive index data at different positions along the optical fiber, for example, at positions z1=100m and z2=200m, the refractive indices are n(z1)=1.45 and n(z2)=1.46 respectively, then the gradient characteristics of the refractive index are At the same time, the spectrum data is Fourier transformed to extract the frequency characteristics, bandwidth characteristics, etc. of the spectrum to more comprehensively understand the optical properties of the optical fiber; from the physical property data, the maximum value, minimum value, and change rate characteristics of the strain, as well as the fluctuation amplitude and period characteristics of the temperature are extracted. Assuming that the strain values ​​measured in a certain period of time are ε1 = 0.001, ε2 = 0.002, ε3 = 0.0015, ε4 = 0.0008, ε5 = 0.0012, n = 5), the maximum value of the strain E max =max{ε i}=0.002, the minimum value of strain E min =min{ε i}=0.0008, the rate of change of strain but

[0051] For temperature data, assuming that the temperature values ​​measured in a certain period of time are T1 = 25°C, T2 = 28°C, T3 = 26°C, T4 = 24°C, and T5 = 27°C, then the temperature fluctuation range A = T max -T min =28-24=4℃, temperature cycle P T It is obtained by Fourier transforming the temperature data. Assuming that the temperature data can be expressed as By analyzing the temperature data, we can get a0=26℃, a1=1℃, b1=0.5℃, k=1, ω=2π / 12h, so the temperature cycle is

[0052] Finally, the intelligent diagnosis unit diagnoses the characteristic values ​​after the fusion of optical fiber data. First, through a large number of experiments and historical data accumulation, the reasonable range of characteristic values ​​under normal conditions is determined. For example, after monitoring and analyzing a large number of long-distance optical fiber communication networks, it is determined that when the value is within the range, the optical fiber is in a normal state. If the value exceeds this range, the optical fiber is judged to be abnormal. When the optical loss is found to increase abnormally (such as the optical loss data accounts for a large proportion of the characteristic values ​​after fusion and exceeds the normal threshold), and at the same time the temperature sensor detects that the temperature is too high (features such as temperature fluctuation amplitude and mean value also show abnormalities after fusion), and the humidity sensor shows that the ambient humidity is high, the diagnosis and optimization module will judge that the optical fiber performance may be degraded due to the high temperature and high humidity environment. For example, when the characteristic value of the optical loss data accounts for more than % of the fusion, and the temperature fluctuation amplitude exceeds %, the humidity mean exceeds %, and it is similar to the case characteristics of optical fiber failures caused by high temperature and high humidity environments in history, the above judgment will be made. According to the diagnosis results, the optimization strategy generation unit will generate targeted optimization strategies. For the case of excessive optical loss, considering that it may be affected by environmental factors such as temperature and humidity, the optimization strategy includes adjusting the optical transmission power, optimizing the signal modulation method, replacing the optical fiber connector, etc.; for the degradation of optical fiber performance caused by excessive temperature, the optimization strategy includes strengthening heat dissipation measures; for the case of high humidity, take moisture-proof measures, such as using moisture-proof coating or installing dehumidification equipment. Moisture-proof coating can form a protective film on the surface of the optical fiber to prevent water vapor from entering the inside of the optical fiber; dehumidification equipment can reduce the humidity of the environment around the optical fiber and reduce the impact of humidity on the performance of the optical fiber; when it is detected that the optical fiber is subjected to external stress, the optimization strategy includes adjusting the optical fiber support structure, adding buffer materials and changing the wiring method of the optical fiber. For example, the fixing points of the optical fiber can be increased to reduce the shaking of the optical fiber; buffer materials such as rubber or foam can be added around the optical fiber to absorb the impact of external forces; or the wiring path of the optical fiber can be changed to avoid areas with greater external forces.

[0053] In addition, the strategy implementation and feedback unit applies these strategies to the actual communication network, for example, by controlling the output power of the optical transmitter to adjust the optical transmission power; by installing heat dissipation equipment to enhance heat dissipation; by coating moisture-proof materials on the surface of the optical fiber to implement moisture-proof measures; by adjusting the optical fiber fixtures and wiring to change the optical fiber support structure and wiring method, at the same time, the system will continue to monitor the optical fiber characteristics and adjust the optimization strategy according to the feedback data. For example, if it is found that the temperature is still too high after the heat dissipation measures are strengthened, it may be necessary to further check whether the heat dissipation equipment is working properly, or consider other factors such as the air circulation around the optical fiber, and adjust the optimization strategy accordingly. If it is found that the humidity is still high after the moisture-proof measures are implemented, it can be considered to increase the power of the dehumidification equipment or replace more effective moisture-proof materials. If it is found that the optical fiber support structure is still affected by external forces after adjusting the optical fiber support structure, the design of the support structure can be further optimized or the thickness of the buffer material can be increased.

[0054] In summary, this embodiment elaborates on the process of applying the optical fiber characteristic intelligent diagnosis and optimization system in the long-distance optical fiber communication network. Through multimodal data collection, fusion, diagnosis and optimization, the system can effectively cope with the impact of complex environments on optical fibers, ensure the stability and reliability of long-distance optical fiber communications, and reflect the advantages and value of the system in practical applications.

[0055] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and range of equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent optical fiber characteristic diagnosis and optimization system, characterized in that: The system includes an optical characteristic data acquisition module, a physical characteristic data acquisition module, an environmental characteristic data acquisition module, a data fusion module, and a diagnosis and optimization module; The optical characteristic data acquisition module uses an optical detection device to emit light pulses into the optical fiber and receive light signals reflected from different positions along the optical fiber, and uses multiple light sources with different wavelengths to alternately measure the refractive index distribution and light loss of the optical fiber, wherein: For the measurement of refractive index distribution, based on the principle of optical interference: Where n(z) represents the refractive index of the optical fiber at the position, λ0 is the initial wavelength of the light source, L is the length of the optical fiber, Δφ(z) is the phase difference of the reflected light at the position, and the refractive index distribution along the optical fiber is calculated by measuring the phase difference at different positions; For the measurement of optical loss, the formula is used Where α is the optical loss coefficient, L is the fiber length, P r (z) is the reflected light power received at position z, P i It is the transmitted optical power. By alternately measuring light sources of different wavelengths, the optical loss at different wavelengths can be obtained. The physical property data acquisition module is composed of a strain sensor and an optical fiber temperature sensor, which monitors the physical property data of optical fiber temperature and strain value in real time under different environments and working conditions, wherein: The optical fiber temperature sensor uses the thermo-optical effect of optical fiber to determine the temperature by measuring the change of optical signal. The relationship between temperature and optical signal wavelength is λ T =λ0(1+ξT), where λ T is the wavelength of the optical signal at temperature T, λ0 is the initial wavelength, ξ is the thermo-optical coefficient of the optical fiber, and the change in the wavelength of the optical signal Δλ = λ T -λ0, combined with the thermo-optical coefficient ξ, calculate the temperature T; The strain sensor monitors the strain of the optical fiber under different external forces in real time, and accurately calculates the strain value of the optical fiber by measuring the wavelength drift. The relationship between strain and wavelength drift is Δλ B =λ B (1-p e )ε, where Δλ B is the drift of the fiber Bragg grating reflection wavelength, λ B is the initial reflection wavelength of the fiber Bragg grating, p e is the effective elastic-optical coefficient of the optical fiber, ε is the strain on the optical fiber, and the wavelength drift Δλ is measured B , combined with the initial reflection wavelength λ of the fiber Bragg grating B and the effective elastic-optical coefficient p e , calculate the strain ε; The environmental characteristic data acquisition module is composed of a humidity sensor and an electromagnetic field sensor, and is used to collect environmental data of humidity and electromagnetic field in the environment where the optical fiber is located, wherein: The humidity sensor reflects the change of humidity by measuring the change of capacitance value, that is, Where H is the current humidity, H0 is the reference humidity, ΔC is the change in capacitance, k H is the humidity sensitivity coefficient; The electromagnetic field sensor is used to detect the electromagnetic field strength and frequency distribution around the optical fiber. The electromagnetic field strength calculation formula is: Where E is the electromagnetic field intensity, Ex, Ey, and Ez are the components of the electromagnetic field in the x, y, and z directions respectively, and the electromagnetic field frequency distribution calculation formula is Where f(ω) is the spectrum distribution of the electromagnetic field, E(t) is the time domain electromagnetic field signal, and iωt is the electromagnetic angular frequency; The data fusion module includes a data preprocessing unit, a feature extraction unit and a fusion algorithm unit. The data preprocessing unit is used to perform a comprehensive data cleaning operation on the collected optical characteristic data, physical characteristic data and environmental data. The feature extraction unit is used to extract features from the preprocessed data. The fusion algorithm unit fuses the features of the optical characteristic data, physical characteristic data and environmental data. The diagnosis and optimization module includes an intelligent diagnosis unit, an optimization strategy generation unit and a strategy implementation and feedback unit. The intelligent diagnosis unit is used to diagnose the optical fiber characteristics based on the fused data, the optimization strategy generation unit is used to generate an optimization strategy according to the diagnosis results, and the strategy implementation and feedback unit is used to implement the optimization strategy into the optical fiber communication system and adjust and optimize according to the feedback data.

2. The optical fiber characteristic intelligent diagnosis and optimization system according to claim 1, characterized in that: The feature extraction unit in the data fusion module extracts features from the preprocessed optical characteristic data, including: For optical loss data, extract the statistical characteristics of the mean, variance, and peak value of the loss; For the refractive index distribution data, the gradient characteristics of the refractive index are extracted by performing Fourier transform on the spectral data to extract the frequency characteristics and bandwidth characteristics of the spectrum.

3. The optical fiber characteristic intelligent diagnosis and optimization system according to claim 2, characterized in that: The feature extraction unit has a mean value of the optical loss data: where α i represents the optical loss value measured at different positions, n is the number of measurements, and the variance is The peak value P is the maximum value in the optical loss data, that is, P = max{α i }.

4. The optical fiber characteristic intelligent diagnosis and optimization system according to claim 2, characterized in that: For the refractive index distribution data, the feature extraction unit has a refractive index gradient feature G as follows: Where n(z1) and n(z2) are the refractive indices of the optical fiber at positions z1 and z2 respectively, and z2-z1 is the distance between the two positions. The gradient characteristics of the refractive index are obtained by calculating the rate of change of the refractive index between different positions.

5. The optical fiber characteristic intelligent diagnosis and optimization system according to claim 1, characterized in that: The feature extraction unit extracts the maximum value, minimum value, and change rate characteristics of strain, as well as the fluctuation amplitude and period characteristics of temperature from the physical property data, wherein: For strain data, the strain value is ε i , and i=1,2,…,n, the maximum value of strain E max For E max =max{ε i }, the minimum value of strain E min For E min =min{ε i }, the strain change rate R is calculated by the strain values ​​at adjacent time points, that is, Where Δt is the time interval between adjacent time points, and j = 1, 2, ..., n-1; For temperature data, the temperature value is T i , the temperature fluctuation range A is A = T max -T min , where T max is the maximum temperature, T min is the minimum temperature, the temperature period P T The temperature data is obtained by Fourier transform, that is, the temperature data is Where kωt is the temperature angular frequency, k is the number of transformations and k = 1, 2, ..., m. The temperature period is determined by analyzing the value of ω.

6. The optical fiber characteristic intelligent diagnosis and optimization system according to claim 1, characterized in that: The feature extraction unit extracts the mean and variation range features of humidity, and the maximum and average features of electromagnetic field intensity from the environmental data, wherein: For humidity data, the mean humidity is in is the mean humidity, N is the number of sampling points, H i is the humidity value of the i-th sampling point, and its humidity variation range ΔH is ΔH=max(H i )-min(H i ), where max(H i ) and min(H i ) are the maximum and minimum humidity values ​​among all sampling points respectively; For electromagnetic data, the maximum electromagnetic field strength E max For E max =max(E i ), where E i is the electromagnetic field strength at the i-th sampling point, and its average electromagnetic field strength for Where N is the number of sampling points, E i is the electromagnetic field intensity at the i-th sampling point.

7. The optical fiber characteristic intelligent diagnosis and optimization system according to claim 1, characterized in that: The fusion algorithm unit in the data fusion module fuses various data features, that is, the mean value μ of the optical loss data α ,variance Peak P α , refractive index gradient feature G n , the maximum value of strain E max , minimum value E min , rate of change R E , the temperature fluctuation range A T , period P T , the mean humidity Variation range ΔH, maximum value of electromagnetic field strength E E ,average value Each feature is normalized, and the normalization formula is: Where X is the eigenvalue to be normalized, X min is the minimum value of the eigenvalue, X max is the maximum value of the eigenvalue, and the eigenvalue of each data normalization is the mean value μ of the optical loss data. α,norm ,variance Peak P α,norm , refractive index gradient feature G n,norm , the maximum value of strain E max,norm , minimum value E min,norm , rate of change R E,norm , the temperature fluctuation range A T,norm , period P T,norm , the mean humidity Variation range ΔH norm , the maximum value of the electromagnetic field strength average value Using the fusion algorithm based on weighted summation, the eigenvalue F after fusion is Where w1+…w 13 =1.

8. The optical fiber characteristic intelligent diagnosis and optimization system according to claim 1, characterized in that: The intelligent diagnosis unit in the diagnosis and optimization module diagnoses the characteristic value F after the optical fiber data is fused, and the optimization strategy generation unit automatically generates a targeted optimization strategy according to the diagnosis result, wherein: For the diagnosis of large optical fiber loss, optimization strategies include adjusting the optical transmission power, optimizing the signal modulation method, and replacing the optical fiber connector; For the degradation of optical fiber performance caused by excessive temperature, optimization strategies include strengthening heat dissipation measures; When external stress is detected on the optical fiber, the optimization strategy includes adjusting the optical fiber support structure, adding buffer materials, and changing the optical fiber wiring method; Regarding the influence of environmental factors, take moisture-proof measures when humidity is high and use moisture-proof materials to protect the optical fiber.

Images