A big data-based optical fiber communication device monitoring method, system and medium

Abstract

The application provides a kind of big data-based optical fiber communication equipment monitoring method, system and medium, belong to optical fiber communication and big data technical field.The method comprises: the operating parameters and environmental parameters of optical fiber equipment are synchronously collected by multi-source sensor network, and standard parameter information matrix is generated after space-time alignment and noise suppression;Further, through time-frequency domain joint analysis, features such as optical signal stability index, vibration energy anomaly degree are extracted, and equipment health state matrix is constructed;The deterioration process is predicted based on the bidirectional LSTM model of attention mechanism, and the visual diagnosis result is output combined with the dynamic threshold grading alarm mechanism.The scheme solves the problem of high false alarm rate and insufficient prediction ability of traditional monitoring method, reduces the false alarm rate, and improves the fault prediction accuracy.

Description

Technical Field

[0001] This application relates to the fields of optical fiber communication and big data technology, and more specifically, to a method, system and medium for monitoring optical fiber communication equipment based on big data. Background Technology

[0002] Traditional fiber optic communication equipment monitoring methods rely on single sensors such as optical power meters, failing to integrate multi-dimensional data such as temperature and vibration. This leads to a high rate of false fault detection, and fixed threshold alarm mechanisms cannot adapt to environmental changes such as diurnal temperature variations, resulting in a high false trigger rate. 80% of faults rely on human experience for judgment, lacking the ability to analyze degradation trends based on historical data. While existing technologies have proposed monitoring schemes based on optical signal analysis, they have not solved the problems of multi-source data fusion and dynamic threshold setting, exhibiting significant limitations, especially in real-time anomaly detection scenarios in long-distance fiber optic networks.

[0003] Therefore, there is an urgent need for a big data-based monitoring method for fiber optic communication equipment to reduce false alarm rates while improving fault prediction accuracy. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, and medium for monitoring fiber optic communication equipment based on big data. Its core lies in synchronously collecting operating and environmental parameters of the fiber optic equipment through a multi-source sensor network, generating a standard parameter information matrix through spatiotemporal alignment and noise suppression; further, extracting features such as optical signal stability index and vibration energy anomaly through joint time-frequency domain analysis to construct an equipment health status matrix; predicting the degradation process using a bidirectional LSTM model based on an attention mechanism, and outputting visualized diagnostic results combined with a dynamic threshold-based hierarchical alarm mechanism. This solution solves the problems of high false alarm rate and insufficient predictive ability in traditional monitoring methods, thereby reducing the false alarm rate and improving the accuracy of fault prediction.

[0005] This application provides a method for monitoring fiber optic communication equipment based on big data, including the following steps:

[0006] The optical fiber equipment operating parameter set and environmental parameter set are synchronously collected within a preset time window by a multi-source sensor network and preprocessed to generate a standard parameter information matrix of the optical fiber equipment.

[0007] Extract time-frequency domain feature data from the standard parameter information matrix of the optical fiber equipment and construct the health status matrix of the optical fiber equipment.

[0008] The system predicts the equipment degradation process based on a pre-set deep learning model and outputs diagnostic results through a visual interface.

[0009] In the big data-based fiber optic communication equipment monitoring method described in this application, the multi-source sensor includes:

[0010] Optical time domain reflectometer, triaxial MEMS accelerometer and distributed fiber optic temperature sensor.

[0011] In the fiber optic communication equipment monitoring method based on big data described in this application, the step of synchronously collecting and preprocessing the fiber optic equipment operating parameter set and environmental parameter set within a preset time window to generate a standard parameter information matrix for the fiber optic equipment specifically involves:

[0012] Synchronously collect the set of operating parameters and environmental parameters of the fiber optic equipment within a preset time window;

[0013] The set of operating parameters for the optical fiber equipment includes optical signal strength, wavelength offset, bit error rate, and polarization mode dispersion;

[0014] The set of environmental parameters includes the equipment surface temperature gradient, ambient relative humidity, and three-dimensional vibration acceleration.

[0015] Based on the set of operating parameters and environmental parameters of the optical fiber equipment, a standard parameter information matrix of the optical fiber equipment is generated through spatiotemporal alignment and noise suppression processing.

[0016] In the big data-based fiber optic communication equipment monitoring method described in this application, the step of extracting time-frequency domain feature data and constructing a fiber optic equipment health status matrix based on the fiber optic equipment standard parameter information matrix specifically includes:

[0017] Extract time-frequency domain feature data based on the standard parameter information matrix of the optical fiber equipment, including optical signal time domain, optical signal frequency domain, vibration characteristics and environmental compensation parameters;

[0018] A health status matrix for optical fiber equipment is constructed based on the optical signal time domain, optical signal frequency domain, vibration characteristics, and environmental compensation parameters.

[0019] In the big data-based fiber optic communication equipment monitoring method described in this application, the step of predicting the equipment degradation process based on a preset deep learning model and outputting diagnostic results through a visual interface specifically includes:

[0020] Predict the equipment degradation process based on a pre-set deep learning model;

[0021] The preset deep learning model is a bidirectional LSTM prediction model based on an attention mechanism, which includes an input layer, a bidirectional LSTM layer, a temporal attention layer, and an output layer.

[0022] The diagnostic results are output through a visual interface, including a heat map of fault probability, an AR augmented reality view, and maintenance suggestion generation rules.

[0023] In the big data-based fiber optic communication equipment monitoring method described in this application, the maintenance suggestion generation rule is specifically as follows:

[0024] The failure probability of the optical fiber device is obtained and compared with a preset first failure probability threshold and a preset second failure probability threshold, respectively.

[0025] The preset first fault probability threshold is greater than the preset second fault probability threshold;

[0026] If the failure probability is greater than or equal to the preset first failure probability threshold, then a shutdown maintenance message is sent.

[0027] If the failure probability is less than the preset first failure probability threshold and greater than or equal to the preset second failure probability threshold, then priority investigation information is sent.

[0028] If the failure probability is less than the preset second failure probability threshold, then continuous monitoring information is sent.

[0029] Secondly, this application provides a big data-based fiber optic communication equipment monitoring system, which includes a memory and a processor. The memory includes a program for a big data-based fiber optic communication equipment monitoring method. When the program for the big data-based fiber optic communication equipment monitoring method is executed by the processor, it implements the following steps:

[0030] The optical fiber equipment operating parameter set and environmental parameter set are synchronously collected within a preset time window by a multi-source sensor network and preprocessed to generate a standard parameter information matrix of the optical fiber equipment.

[0031] Extract time-frequency domain feature data from the standard parameter information matrix of the optical fiber equipment and construct the health status matrix of the optical fiber equipment.

[0032] The system predicts the equipment degradation process based on a pre-set deep learning model and outputs diagnostic results through a visual interface.

[0033] In the big data-based fiber optic communication equipment monitoring system described in this application, the multi-source sensor includes:

[0034] Optical time domain reflectometer, triaxial MEMS accelerometer and distributed fiber optic temperature sensor.

[0035] In the fiber optic communication equipment monitoring system based on big data described in this application, the synchronous acquisition and preprocessing of the fiber optic equipment operating parameter set and environmental parameter set within a preset time window to generate a standard parameter information matrix for the fiber optic equipment specifically involves:

[0036] Synchronously collect the set of operating parameters and environmental parameters of the fiber optic equipment within a preset time window;

[0037] The set of operating parameters for the optical fiber equipment includes optical signal strength, wavelength offset, bit error rate, and polarization mode dispersion;

[0038] The set of environmental parameters includes the equipment surface temperature gradient, ambient relative humidity, and three-dimensional vibration acceleration.

[0039] Based on the set of operating parameters and environmental parameters of the optical fiber equipment, a standard parameter information matrix of the optical fiber equipment is generated through spatiotemporal alignment and noise suppression processing.

[0040] Thirdly, this application also provides a computer-readable storage medium including a big data-based fiber optic communication equipment monitoring method program. When the big data-based fiber optic communication equipment monitoring method program is executed by a processor, it implements the steps of the big data-based fiber optic communication equipment monitoring method as described in any of the above claims.

[0041] As described above, the fiber optic communication equipment monitoring method, system, and medium provided in this application embodiment, based on big data, synchronously collects the operating parameters and environmental parameters of the fiber optic equipment through a multi-source sensor network, and generates a standard parameter information matrix through spatiotemporal alignment and noise suppression. Furthermore, it extracts features such as the optical signal stability index and vibration energy anomaly degree through joint time-frequency domain analysis to construct an equipment health status matrix. A bidirectional LSTM model based on an attention mechanism predicts the degradation process, and a dynamic threshold-based hierarchical alarm mechanism outputs visualized diagnostic results. This solution solves the problems of high false alarm rate and insufficient predictive ability in traditional monitoring methods, thereby reducing the false alarm rate and improving the accuracy of fault prediction.

[0042] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart illustrating a big data-based fiber optic communication equipment monitoring method provided in this application embodiment;

[0045] Figure 2 A flowchart illustrating the generation of a standard parameter information matrix for optical fiber communication equipment using a big data-based optical fiber communication equipment monitoring method provided in this application embodiment;

[0046] Figure 3 A flowchart illustrating the construction of a fiber optic device health status matrix using a big data-based fiber optic communication device monitoring method provided in this application embodiment;

[0047] Figure 4 A flowchart illustrating a big data-based optical fiber communication equipment monitoring method for predicting equipment degradation processes and outputting diagnostic results through a visual interface, provided in this application embodiment; Detailed Implementation

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0049] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first" and "second" are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0050] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a big data-based fiber optic communication equipment monitoring method according to some embodiments of this application. This big data-based fiber optic communication equipment monitoring method is used in terminal devices, such as computers and mobile terminals. The big data-based fiber optic communication equipment monitoring method includes the following steps:

[0051] S101. Synchronously collect the set of operating parameters and environmental parameters of the optical fiber equipment within a preset time window through a multi-source sensor network and preprocess them to generate a standard parameter information matrix of the optical fiber equipment.

[0052] S102. Extract time-frequency domain feature data based on the standard parameter information matrix of the optical fiber equipment and construct the health status matrix of the optical fiber equipment.

[0053] S103. Predict the equipment degradation process based on a preset deep learning model and output the diagnostic results through a visual interface.

[0054] First, a heterogeneous sensor network consisting of an optical time-domain reflectometer, a triaxial MEMS accelerometer, and a distributed fiber optic temperature sensor is used to simultaneously collect the operating parameters (optical signal intensity, polarization mode dispersion, bit error rate) and environmental parameters (temperature gradient, three-dimensional vibration acceleration, ambient humidity) of the fiber optic equipment. Dynamic time warping (DTW) is then used to align the multi-source time-series data, and wavelet soft thresholding is combined to generate a standard parameter information matrix. Next, wavelet packet decomposition is performed on the optical signal to extract the energy entropy ratio feature of a fixed frequency band. Simultaneously, modal decomposition is performed on the vibration signal to calculate the sample entropy of the first three IMF components. A sparse autoencoder is used to fuse multi-dimensional features, constructing a 6-dimensional health state matrix including optical stability index, vibration anomaly degree, and temperature coupling factor. Based on this, a bidirectional LSTM prediction model is used to analyze 72 hours of historical data, and a time attention mechanism is used to output the probability of failure in the next 24 hours. A multi-level response is triggered according to a dynamic threshold-based alarm strategy—SMS notification to maintenance personnel or automatic switching to a backup link. Finally, an AR-enhanced view is used to mark the fault point and generate a priority maintenance work order (combined with Dijkstra's algorithm to optimize the maintenance path). This solution achieves significant results in reducing false alarm rates, improving fault prediction accuracy, and shortening response delays. It overcomes the technical bottlenecks of traditional monitoring methods, such as limited data dimensions and poor environmental adaptability, and provides an efficient and reliable intelligent solution for fiber optic network operation and maintenance.

[0055] According to an embodiment of the present invention, the multi-source sensor includes:

[0056] Optical time domain reflectometer, triaxial MEMS accelerometer and distributed fiber optic temperature sensor.

[0057] Among them, the Optical Time Domain Reflectometer (OTDR) adopts a wide spectral design of 1260-1650nm to detect fiber optic link loss events in real time (accuracy ±0.02dB / km), and accurately locates breakpoints and bending faults with 0.1m-level spatial resolution; the triaxial MEMS accelerometer has a range of ±16g and a wide frequency response of 0.5Hz-5kHz (noise density 100μg / √Hz), and accurately captures abnormal mechanical vibrations of equipment by eliminating electromagnetic interference through Butterworth bandpass filtering; the Distributed Fiber Temperature Sensor (DTS) realizes full-link temperature field monitoring. The multi-source collaborative technology has significant effects, reducing false alarm rate and improving fault location accuracy. The core innovation lies in the spectrum collaborative coverage and data fusion mechanism (vibration-temperature joint alarm threshold, OTDR and DTS co-fiber deployment), and in engineering, it achieves IP68 protection level MEMS sensor adaptability to harsh environments, providing a highly reliable solution for intelligent operation and maintenance of fiber optic networks.

[0058] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the generation of a standard parameter information matrix for optical fiber communication equipment using a big data-based monitoring method in some embodiments of this application. According to an embodiment of the present invention, the step of synchronously collecting and preprocessing the optical fiber equipment operating parameter set and environmental parameter set within a preset time window to generate the standard parameter information matrix for the optical fiber equipment specifically involves:

[0059] S201. Synchronously collect the set of operating parameters and environmental parameters of the fiber optic equipment within the preset time window;

[0060] S202, The set of operating parameters for the optical fiber equipment includes optical signal strength, wavelength offset, bit error rate, and polarization mode dispersion;

[0061] S203, The set of environmental parameters includes the equipment surface temperature gradient, ambient relative humidity, and three-dimensional vibration acceleration;

[0062] S204. Based on the optical fiber equipment operating parameter set and environmental parameter set, a standard parameter information matrix for the optical fiber equipment is generated through spatiotemporal alignment and noise suppression processing.

[0063] In step S201, based on a timestamp synchronization triggering mechanism, the operating parameter set and environmental parameter set of the optical fiber equipment are synchronously collected within a preset time window (typically 10 minutes, which can be dynamically adjusted according to network load). The operating parameter set defined in step S202 includes optical signal intensity, wavelength offset, bit error rate, and polarization mode dispersion. The environmental parameter set covered in step S203 consists of the equipment surface temperature gradient, ambient relative humidity, and three-dimensional vibration acceleration. Step S204 performs spatiotemporal alignment and noise suppression processing on the raw data: Dynamic Time Warping (DTW) is used to eliminate multi-sensor transmission delay and achieve data point-level alignment; wavelet soft thresholding is used to suppress random noise in the optical signal, and adaptive Kalman filtering is combined to remove electromagnetic interference components from the vibration signal. The final generated standard parameter information matrix is ​​stored in a structured form, resulting in a lower false alarm rate and improved data processing efficiency compared to traditional methods.

[0064] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the construction of a fiber optic equipment health status matrix using a big data-based fiber optic communication equipment monitoring method according to some embodiments of this application. According to an embodiment of the present invention, the step of extracting time-frequency domain feature data based on the fiber optic equipment standard parameter information matrix and constructing the fiber optic equipment health status matrix specifically involves:

[0065] S301. Extract time-frequency domain feature data based on the standard parameter information matrix of the optical fiber equipment, including optical signal time domain, optical signal frequency domain, vibration characteristics and environmental compensation parameters;

[0066] S302. Construct a health status matrix for optical fiber equipment based on the optical signal time domain, optical signal frequency domain, vibration characteristics, and environmental compensation parameters.

[0067] In step S301, four core features are extracted based on the standard parameter information matrix: optical signal time-domain features (calculating mean optical power, kurtosis (for detecting pulse anomalies), and zero-crossing rate (for monitoring signal oscillation frequency); optical signal frequency-domain features (using wavelet packet decomposition to extract the energy entropy ratio of a fixed frequency band); vibration features (using the CEEMDAN algorithm to decompose the vibration signal and extract the sample entropy and instantaneous frequency variance of the first three IMF components); and environmental compensation parameters (establishing a temperature-light attenuation dynamic compensation model to reduce the false alarm rate). In step S302, the 14-dimensional initial features are reduced in dimensionality using a sparse autoencoder. The optical signal time-domain features contain 3 features, the optical signal frequency-domain features contain 4 features, the vibration features contain 2 features, and the environmental compensation parameters contain 5 features. A 6-dimensional health state matrix is ​​constructed, including optical stability index, vibration anomaly degree, and temperature coupling factor. The row vectors correspond to the time series, and the column vectors are standardized before being input into a bidirectional LSTM model, improving model training efficiency. The technological breakthrough lies in cross-domain feature fusion (optical, mechanical, and thermal) and dynamic weighting mechanisms. In engineering, the feature extraction time meets the real-time requirements of telecommunications, providing core support for intelligent operation and maintenance of fiber optic networks.

[0068] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating a big data-based fiber optic communication equipment monitoring method in some embodiments of this application, which predicts the equipment degradation process and outputs diagnostic results through a visual interface. According to an embodiment of the present invention, the step of predicting the equipment degradation process based on a preset deep learning model and outputting diagnostic results through a visual interface specifically includes:

[0069] S401. Predict the equipment degradation process based on a preset deep learning model;

[0070] S402. The preset deep learning model is a bidirectional LSTM prediction model based on an attention mechanism, including an input layer, a bidirectional LSTM layer, a temporal attention layer, and an output layer.

[0071] S403. Output diagnostic results through a visual interface, including a fault probability heat map, an AR augmented reality view, and maintenance suggestion generation rules.

[0072] In step S401, a historical health status matrix (time span ≥ 72 hours) is analyzed based on a preset deep learning model to predict the equipment failure development trend in the next 24 hours. Step S402 defines a prediction model using a bidirectional LSTM architecture based on an attention mechanism. The input layer receives multi-dimensional feature vectors; the bidirectional LSTM layer has a time step of 72 (corresponding to 3 days of historical data); the time attention layer calculates the weights at each moment using the Softmax function; and the output layer uses the Sigmoid function to generate 0-1 failure probability values. Training employs the Focal Loss loss function. Step S403's visualization output system includes three core modules: a failure probability heatmap displaying historical failure rates for similar equipment; and an AR augmented reality view where scanning the equipment's QR code with a mobile phone overlays a fiber optic stress distribution cloud map and 3D navigation arrows guiding users to the nearest maintenance entrance. This deep integration of deep learning prediction and augmented reality visualization overcomes pain points in traditional operation and maintenance, such as decision-making lag and information silos, setting a new benchmark for intelligent operation and maintenance of fiber optic networks.

[0073] According to an embodiment of the present invention, the maintenance suggestion generation rule is specifically as follows:

[0074] The failure probability of the optical fiber device is obtained and compared with a preset first failure probability threshold and a preset second failure probability threshold, respectively.

[0075] The preset first fault probability threshold is greater than the preset second fault probability threshold;

[0076] If the failure probability is greater than or equal to the preset first failure probability threshold, then a shutdown maintenance message is sent.

[0077] If the failure probability is less than the preset first failure probability threshold and greater than or equal to the preset second failure probability threshold, then priority investigation information is sent.

[0078] If the failure probability is less than the preset second failure probability threshold, then continuous monitoring information is sent.

[0079] The system first obtains the failure probability of the fiber optic equipment calculated by a deep learning model, and then compares this probability value with two preset thresholds (where the first failure probability threshold is greater than the second failure probability threshold). When the failure probability is greater than or equal to the first threshold, a highest-level alarm is triggered, and the system automatically sends an instruction requiring immediate shutdown and maintenance. When the failure probability is between the first and second thresholds, a medium-level alarm is generated, and a prompt suggesting priority troubleshooting is sent. If the failure probability is less than the second threshold, the system is determined to be in a low-risk state, and only a routine prompt to maintain continuous monitoring is sent. This three-level threshold judgment mechanism realizes a tiered response strategy from emergency handling and preventive maintenance to routine monitoring.

[0080] According to an embodiment of the present invention, it further includes:

[0081] Based on the optical fiber equipment health status matrix, the optical signal stability index is extracted and input into a preset optical fiber equipment health list for querying to obtain the health status deviation value.

[0082] By comparing the health status deviation value with a preset health status deviation threshold, multiple deviation value deviation rates are obtained;

[0083] The deviation rate is compared with a preset deviation rate threshold.

[0084] If the deviation rate is greater than or equal to the preset deviation rate threshold, an unhealthy status message will be sent.

[0085] If the deviation rate is less than the preset deviation rate threshold, then health status information is sent.

[0086] The system analyzes the fluctuation characteristics of optical signals within a preset time period (e.g., 10 minutes) by collecting time-series datasets of optical signal parameters such as optical power and wavelength offset in real time. Abnormal pulses and trend-based attenuation are identified, and the results are normalized to map the calculation results to a standardized score range of 0-100, with higher values ​​indicating better stability. A preset fiber optic equipment health list database stores the baseline values ​​of optical signal stability for different equipment models under standard operating conditions, recording the linear attenuation coefficient of the stability index due to equipment aging (e.g., a decrease of 1.2% per year). The baseline values ​​are automatically adjusted based on real-time ambient temperature (e.g., a decrease of 2% for every 5°C increase in temperature). The query process is achieved through two-factor matching: the equipment model is determined based on the MAC address / serial number, and the current valid baseline value is calculated by combining the equipment's commissioning time and ambient temperature. The deviation value indicates the degree of difference between the real-time stability index and the database baseline value.

[0087] According to an embodiment of the present invention, it further includes:

[0088] Obtain the historical health status matrix of the fiber optic equipment;

[0089] The historical health state matrix is ​​trained unsupervised based on the isolated forest algorithm to generate a benchmark model of normal equipment status.

[0090] The system dynamically adjusts the anomaly detection threshold based on the ambient temperature gradient to perform multi-level anomaly detection on real-time collected data, including primary alarm, intermediate alarm, and emergency alarm.

[0091] The system continuously collects equipment operating parameters, including key indicators such as optical power, wavelength shift, and vibration spectrum, from sensor nodes deployed in the fiber optic network. At least six months of historical data are organized into a multi-dimensional matrix according to time windows (typically 10-minute intervals). Each time, several features are randomly selected to construct an isolation tree, segmenting the data until a preset depth is reached. A temperature binning model is established, and historical data is categorized and stored according to operating temperature ranges (e.g., 20-25℃, 25-30℃, etc.). A sub-model is independently trained for each temperature range, forming a temperature-adaptive model cluster. A dynamic threshold multi-level alarm mechanism is implemented, consisting of primary, intermediate, and emergency alarms. Primary alarms are responded to with log recording and a yellow warning on the interface; intermediate alarms are responded to by sending a notification to maintenance personnel; and emergency alarms are responded to by automatically activating protection devices and issuing a telephone alarm.

[0092] This invention also discloses a big data-based fiber optic communication equipment monitoring system, including a memory and a processor. The memory includes a big data-based fiber optic communication equipment monitoring method program. When the processor executes the big data-based fiber optic communication equipment monitoring method program, it performs the following steps:

[0093] The optical fiber equipment operating parameter set and environmental parameter set are synchronously collected within a preset time window by a multi-source sensor network and preprocessed to generate a standard parameter information matrix of the optical fiber equipment.

[0094] Extract time-frequency domain feature data from the standard parameter information matrix of the optical fiber equipment and construct the health status matrix of the optical fiber equipment.

[0095] The system predicts the equipment degradation process based on a pre-set deep learning model and outputs diagnostic results through a visual interface.

[0096] First, a heterogeneous sensor network consisting of an optical time-domain reflectometer, a triaxial MEMS accelerometer, and a distributed fiber optic temperature sensor is used to simultaneously collect the operating parameters (optical signal intensity, polarization mode dispersion, bit error rate) and environmental parameters (temperature gradient, three-dimensional vibration acceleration, ambient humidity) of the fiber optic equipment. Dynamic time warping (DTW) is then used to align the multi-source time-series data, and wavelet soft thresholding is combined to generate a standard parameter information matrix. Next, wavelet packet decomposition is performed on the optical signal to extract the energy entropy ratio feature of a fixed frequency band. Simultaneously, modal decomposition is performed on the vibration signal to calculate the sample entropy of the first three IMF components. A sparse autoencoder is used to fuse multi-dimensional features, constructing a 6-dimensional health state matrix including optical stability index, vibration anomaly degree, and temperature coupling factor. Based on this, a bidirectional LSTM prediction model is used to analyze 72 hours of historical data, and a time attention mechanism is used to output the probability of failure in the next 24 hours. A multi-level response is triggered according to a dynamic threshold-based alarm strategy—SMS notification to maintenance personnel or automatic switching to a backup link. Finally, an AR-enhanced view is used to mark the fault point and generate a priority maintenance work order (combined with Dijkstra's algorithm to optimize the maintenance path). This solution achieves significant results in reducing false alarm rates, improving fault prediction accuracy, and shortening response delays. It overcomes the technical bottlenecks of traditional monitoring methods, such as limited data dimensions and poor environmental adaptability, and provides an efficient and reliable intelligent solution for fiber optic network operation and maintenance.

[0097] According to an embodiment of the present invention, the multi-source sensor includes:

[0098] Optical time domain reflectometer, triaxial MEMS accelerometer and distributed fiber optic temperature sensor.

[0099] Among them, the Optical Time Domain Reflectometer (OTDR) adopts a wide spectral design of 1260-1650nm to detect fiber optic link loss events in real time (accuracy ±0.02dB / km), and accurately locates breakpoints and bending faults with 0.1m-level spatial resolution; the triaxial MEMS accelerometer has a range of ±16g and a wide frequency response of 0.5Hz-5kHz (noise density 100μg / √Hz), and accurately captures abnormal mechanical vibrations of equipment by eliminating electromagnetic interference through Butterworth bandpass filtering; the Distributed Fiber Temperature Sensor (DTS) realizes full-link temperature field monitoring. The multi-source collaborative technology has significant effects, reducing false alarm rate and improving fault location accuracy. The core innovation lies in the spectrum collaborative coverage and data fusion mechanism (vibration-temperature joint alarm threshold, OTDR and DTS co-fiber deployment), and in engineering, it achieves IP68 protection level MEMS sensor adaptability to harsh environments, providing a highly reliable solution for intelligent operation and maintenance of fiber optic networks.

[0100] According to an embodiment of the present invention, the synchronous acquisition of the optical fiber equipment operating parameter set and environmental parameter set within a preset time window, followed by preprocessing, to generate a standard parameter information matrix for the optical fiber equipment, specifically involves:

[0101] Synchronously collect the set of operating parameters and environmental parameters of the fiber optic equipment within a preset time window;

[0102] The set of operating parameters for the optical fiber equipment includes optical signal strength, wavelength offset, bit error rate, and polarization mode dispersion;

[0103] The set of environmental parameters includes the equipment surface temperature gradient, ambient relative humidity, and three-dimensional vibration acceleration.

[0104] Based on the set of operating parameters and environmental parameters of the optical fiber equipment, a standard parameter information matrix of the optical fiber equipment is generated through spatiotemporal alignment and noise suppression processing.

[0105] In step S201, based on a timestamp synchronization triggering mechanism, the operating parameter set and environmental parameter set of the optical fiber equipment are synchronously collected within a preset time window (typically 10 minutes, which can be dynamically adjusted according to network load). The operating parameter set defined in step S202 includes optical signal intensity, wavelength offset, bit error rate, and polarization mode dispersion. The environmental parameter set covered in step S203 consists of the equipment surface temperature gradient, ambient relative humidity, and three-dimensional vibration acceleration. Step S204 performs spatiotemporal alignment and noise suppression processing on the raw data: Dynamic Time Warping (DTW) is used to eliminate multi-sensor transmission delay and achieve data point-level alignment; wavelet soft thresholding is used to suppress random noise in the optical signal, and adaptive Kalman filtering is combined to remove electromagnetic interference components from the vibration signal. The final generated standard parameter information matrix is ​​stored in a structured form, resulting in a lower false alarm rate and improved data processing efficiency compared to traditional methods.

[0106] According to an embodiment of the present invention, the step of extracting time-frequency domain feature data and constructing an optical fiber equipment health status matrix based on the standard parameter information matrix of the optical fiber equipment specifically includes:

[0107] Extract time-frequency domain feature data based on the standard parameter information matrix of the optical fiber equipment, including optical signal time domain, optical signal frequency domain, vibration characteristics and environmental compensation parameters;

[0108] A health status matrix for optical fiber equipment is constructed based on the optical signal time domain, optical signal frequency domain, vibration characteristics, and environmental compensation parameters.

[0109] In step S301, four core features are extracted based on the standard parameter information matrix: optical signal time-domain features (calculating mean optical power, kurtosis (for detecting pulse anomalies), and zero-crossing rate (for monitoring signal oscillation frequency); optical signal frequency-domain features (using wavelet packet decomposition to extract the energy entropy ratio of a fixed frequency band); vibration features (using the CEEMDAN algorithm to decompose the vibration signal and extract the sample entropy and instantaneous frequency variance of the first three IMF components); and environmental compensation parameters (establishing a temperature-light attenuation dynamic compensation model to reduce the false alarm rate). In step S302, the 14-dimensional initial features are reduced in dimensionality using a sparse autoencoder. The optical signal time-domain features contain 3 features, the optical signal frequency-domain features contain 4 features, the vibration features contain 2 features, and the environmental compensation parameters contain 5 features. A 6-dimensional health state matrix is ​​constructed, including optical stability index, vibration anomaly degree, and temperature coupling factor. The row vectors correspond to the time series, and the column vectors are standardized before being input into a bidirectional LSTM model, improving model training efficiency. The technological breakthrough lies in cross-domain feature fusion (optical, mechanical, and thermal) and dynamic weighting mechanisms. In engineering, the feature extraction time meets the real-time requirements of telecommunications, providing core support for intelligent operation and maintenance of fiber optic networks.

[0110] According to an embodiment of the present invention, the step of predicting the device degradation process based on a preset deep learning model and outputting diagnostic results through a visual interface specifically includes:

[0111] Predict the equipment degradation process based on a pre-set deep learning model;

[0112] The preset deep learning model is a bidirectional LSTM prediction model based on an attention mechanism, which includes an input layer, a bidirectional LSTM layer, a temporal attention layer, and an output layer.

[0113] The diagnostic results are output through a visual interface, including a heat map of fault probability, an AR augmented reality view, and maintenance suggestion generation rules.

[0114] In step S401, a historical health status matrix (time span ≥ 72 hours) is analyzed based on a preset deep learning model to predict the equipment failure development trend in the next 24 hours. Step S402 defines a prediction model using a bidirectional LSTM architecture based on an attention mechanism. The input layer receives multi-dimensional feature vectors; the bidirectional LSTM layer has a time step of 72 (corresponding to 3 days of historical data); the time attention layer calculates the weights at each moment using the Softmax function; and the output layer uses the Sigmoid function to generate 0-1 failure probability values. Training employs the Focal Loss loss function. Step S403's visualization output system includes three core modules: a failure probability heatmap displaying historical failure rates for similar equipment; and an AR augmented reality view where scanning the equipment's QR code with a mobile phone overlays a fiber optic stress distribution cloud map and 3D navigation arrows guiding users to the nearest maintenance entrance. This deep integration of deep learning prediction and augmented reality visualization overcomes pain points in traditional operation and maintenance, such as decision-making lag and information silos, setting a new benchmark for intelligent operation and maintenance of fiber optic networks.

[0115] According to an embodiment of the present invention, the maintenance suggestion generation rule is specifically as follows:

[0116] The failure probability of the optical fiber device is obtained and compared with a preset first failure probability threshold and a preset second failure probability threshold, respectively.

[0117] The preset first fault probability threshold is greater than the preset second fault probability threshold;

[0118] If the failure probability is greater than or equal to the preset first failure probability threshold, then a shutdown maintenance message is sent.

[0119] If the failure probability is less than the preset first failure probability threshold and greater than or equal to the preset second failure probability threshold, then priority investigation information is sent.

[0120] If the failure probability is less than the preset second failure probability threshold, then continuous monitoring information is sent.

[0121] The system first obtains the failure probability of the fiber optic equipment calculated by a deep learning model, and then compares this probability value with two preset thresholds (where the first failure probability threshold is greater than the second failure probability threshold). When the failure probability is greater than or equal to the first threshold, a highest-level alarm is triggered, and the system automatically sends an instruction requiring immediate shutdown and maintenance. When the failure probability is between the first and second thresholds, a medium-level alarm is generated, and a prompt suggesting priority troubleshooting is sent. If the failure probability is less than the second threshold, the system is determined to be in a low-risk state, and only a routine prompt to maintain continuous monitoring is sent. This three-level threshold judgment mechanism realizes a tiered response strategy from emergency handling and preventive maintenance to routine monitoring.

[0122] According to an embodiment of the present invention, it further includes:

[0123] Based on the optical fiber equipment health status matrix, the optical signal stability index is extracted and input into a preset optical fiber equipment health list for querying to obtain the health status deviation value.

[0124] By comparing the health status deviation value with a preset health status deviation threshold, multiple deviation value deviation rates are obtained;

[0125] The deviation rate is compared with a preset deviation rate threshold.

[0126] If the deviation rate is greater than or equal to the preset deviation rate threshold, an unhealthy status message will be sent.

[0127] If the deviation rate is less than the preset deviation rate threshold, then health status information is sent.

[0128] The system analyzes the fluctuation characteristics of optical signals within a preset time period (e.g., 10 minutes) by collecting time-series datasets of optical signal parameters such as optical power and wavelength offset in real time. Abnormal pulses and trend-based attenuation are identified, and the results are normalized to map the calculation results to a standardized score range of 0-100, with higher values ​​indicating better stability. A preset fiber optic equipment health list database stores the baseline values ​​of optical signal stability for different equipment models under standard operating conditions, recording the linear attenuation coefficient of the stability index due to equipment aging (e.g., a decrease of 1.2% per year). The baseline values ​​are automatically adjusted based on real-time ambient temperature (e.g., a decrease of 2% for every 5°C increase in temperature). The query process is achieved through two-factor matching: the equipment model is determined based on the MAC address / serial number, and the current valid baseline value is calculated by combining the equipment's commissioning time and ambient temperature. The deviation value indicates the degree of difference between the real-time stability index and the database baseline value.

[0129] According to an embodiment of the present invention, it further includes:

[0130] Obtain the historical health status matrix of the fiber optic equipment;

[0131] The historical health state matrix is ​​trained unsupervised based on the isolated forest algorithm to generate a benchmark model of normal equipment status.

[0132] The system dynamically adjusts the anomaly detection threshold based on the ambient temperature gradient to perform multi-level anomaly detection on real-time collected data, including primary alarm, intermediate alarm, and emergency alarm.

[0133] The system continuously collects equipment operating parameters, including key indicators such as optical power, wavelength shift, and vibration spectrum, from sensor nodes deployed in the fiber optic network. At least six months of historical data are organized into a multi-dimensional matrix according to time windows (typically 10-minute intervals). Each time, several features are randomly selected to construct an isolation tree, segmenting the data until a preset depth is reached. A temperature binning model is established, and historical data is categorized and stored according to operating temperature ranges (e.g., 20-25℃, 25-30℃, etc.). A sub-model is independently trained for each temperature range, forming a temperature-adaptive model cluster. A dynamic threshold multi-level alarm mechanism is implemented, consisting of primary, intermediate, and emergency alarms. Primary alarms are responded to with log recording and a yellow warning on the interface; intermediate alarms are responded to by sending a notification to maintenance personnel; and emergency alarms are responded to by automatically activating protection devices and issuing a telephone alarm.

[0134] A third aspect of the present invention provides a computer-readable storage medium comprising a big data-based fiber optic communication equipment monitoring method program, wherein when the big data-based fiber optic communication equipment monitoring method program is executed by a processor, it implements the steps of the big data-based fiber optic communication equipment monitoring method as described in any of the preceding claims.

[0135] This invention discloses a method, system, and medium for monitoring fiber optic communication equipment based on big data. Its core technology lies in achieving high-precision fault prediction and graded response through multi-dimensional data fusion and a dynamic deep learning model. First, a heterogeneous sensor network consisting of an optical time-domain reflectometer (OTDR, operating wavelength 1260-1650nm), a triaxial MEMS accelerometer (±16g range), and a distributed fiber optic temperature sensor (DTS, ±0.5℃ accuracy) synchronously collects fiber optic equipment operating parameters (optical signal intensity, wavelength offset, bit error rate, polarization mode dispersion) and environmental parameters (temperature gradient, three-dimensional vibration acceleration, relative humidity). The time-series data is aligned using a dynamic time warping algorithm (DTW), and noise is eliminated by wavelet soft thresholding and Kalman filtering, generating a structured standard parameter information matrix (600×6-dimensional). Subsequently, the optical signal stability index, vibration characteristics (CEEMDAN decomposition sample entropy), and temperature compensation parameters are extracted from the time-frequency domain and fused into a 6-dimensional health state matrix using a sparse autoencoder. Building upon this foundation, a bidirectional LSTM model based on an attention mechanism is employed to analyze historical data. Combined with temporal attention weights, the probability of failure in the next 24 hours is dynamically predicted. A dynamic threshold-based alarm mechanism triggers responses: when the failure probability is ≥ the first threshold (e.g., 0.8), a shutdown and maintenance command is sent; when it falls between the first and second thresholds (e.g., 0.6), priority troubleshooting is suggested; and when it falls below the second threshold, continuous monitoring continues. The system innovatively integrates an augmented reality (AR) view to intuitively display the stress distribution at the fault point. Combined with Dijkstra's algorithm, maintenance paths are optimized. An isolated forest algorithm is used to establish a temperature-adaptive anomaly detection model, reducing false alarm rates and improving fault prediction accuracy. This overcomes the technical bottlenecks of traditional methods that rely on a single data source and have poor environmental adaptability, providing a real-time, accurate, and intelligent operation and maintenance solution for fiber optic networks.

[0136] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0137] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0138] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0139] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory, random access memory, magnetic disks, or optical disks.

[0140] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for monitoring fiber optic communication equipment based on big data, characterized in that, Includes the following steps: The system synchronously collects the set of operating parameters and environmental parameters of the fiber optic equipment within a preset time window using a multi-source sensor network. The set of operating parameters for the optical fiber equipment includes optical signal strength, wavelength offset, bit error rate, and polarization mode dispersion; The set of environmental parameters includes the equipment surface temperature gradient, ambient relative humidity, and three-dimensional vibration acceleration. Based on the set of operating parameters and environmental parameters of the optical fiber equipment, a standard parameter information matrix of the optical fiber equipment is generated through spatiotemporal alignment and noise suppression processing. Extract time-frequency domain feature data based on the standard parameter information matrix of the optical fiber equipment, including optical signal time domain, optical signal frequency domain, vibration characteristics and environmental compensation parameters; A health status matrix for optical fiber equipment is constructed based on the optical signal time domain, optical signal frequency domain, vibration characteristics, and environmental compensation parameters. Predict the equipment degradation process based on a pre-set deep learning model; The preset deep learning model is a bidirectional LSTM prediction model based on an attention mechanism, which includes an input layer, a bidirectional LSTM layer, a temporal attention layer, and an output layer. The diagnostic results are output through a visual interface, including a fault probability heat map, an AR augmented reality view, and maintenance suggestion generation rules. Also includes: Based on the optical fiber equipment health status matrix, the optical signal stability index is extracted and input into a preset optical fiber equipment health list for querying to obtain the health status deviation value. By comparing the health status deviation value with a preset health status deviation threshold, multiple deviation value deviation rates are obtained; The deviation rate is compared with a preset deviation rate threshold. If the deviation rate is greater than or equal to the preset deviation rate threshold, an unhealthy status message will be sent. If the deviation rate is less than the preset deviation rate threshold, then send health status information; Also includes: Obtain the historical health status matrix of the fiber optic equipment; The historical health state matrix is ​​trained unsupervised based on the isolated forest algorithm to generate a benchmark model of normal equipment status. The system dynamically adjusts the anomaly detection threshold based on the ambient temperature gradient to perform multi-level anomaly detection on real-time collected data, including primary alarm, intermediate alarm, and emergency alarm.

2. The method for monitoring fiber optic communication equipment based on big data according to claim 1, characterized in that, The multi-source sensor includes: Optical time domain reflectometer, triaxial MEMS accelerometer and distributed fiber optic temperature sensor.

3. The method for monitoring fiber optic communication equipment based on big data according to claim 1, characterized in that, The maintenance suggestion generation rules are as follows: The failure probability of the optical fiber device is obtained and compared with a preset first failure probability threshold and a preset second failure probability threshold, respectively. The preset first fault probability threshold is greater than the preset second fault probability threshold; If the failure probability is greater than or equal to the preset first failure probability threshold, then a shutdown maintenance message is sent. If the failure probability is less than the preset first failure probability threshold and greater than or equal to the preset second failure probability threshold, then priority investigation information is sent. If the failure probability is less than the preset second failure probability threshold, then continuous monitoring information is sent.

4. A monitoring system for fiber optic communication equipment based on big data, characterized in that, The device includes a memory and a processor. The memory includes a big data-based fiber optic communication equipment monitoring method program. When the big data-based fiber optic communication equipment monitoring method program is executed by the processor, it implements the steps of the big data-based fiber optic communication equipment monitoring method as described in any one of claims 1 to 3.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a big data-based fiber optic communication equipment monitoring method program. When the big data-based fiber optic communication equipment monitoring method program is executed by a processor, it implements the steps of the big data-based fiber optic communication equipment monitoring method as described in any one of claims 1 to 3.

Images