Intelligent optical fiber distribution equipment health degree analysis method and device

Abstract

The invention provides an intelligent optical fiber distribution equipment health degree analysis method and device, and belongs to the technical field of optical fiber communication. A global LSTM model is constructed, and initialized global model parameters are issued to each intelligent optical fiber distribution equipment for local LSTM model training; and executing a parameter alignment compensation and parameter aggregation strategy on the global LSTM model by using the local training parameters obtained by each intelligent optical fiber wiring device, obtaining updated global model parameters, issuing the updated global model parameters to the local LSTM model of each intelligent optical fiber wiring device, and evaluating the current health state of each intelligent optical fiber wiring device. Through a distributed federated learning framework, local data distributed training and global model aggregation of intelligent optical fiber distribution equipment are realized, data such as optical power loss and plugging times are monitored and analyzed in real time, potential health risks are found in time, equipment damage caused by problem accumulation is avoided, and adaptability and accuracy of equipment health degree monitoring are improved.

Description

Technical Field

[0001] The present application relates to the field of optical fiber communication technology, and more specifically, to a method and apparatus for analyzing the health of intelligent optical fiber distribution equipment. Background Art

[0002] With the surge in demand for services such as 5G and data centers, the scale of optical cable networks continues to expand, and the number of network nodes and the mileage of optical cables are both growing exponentially, creating an urgent need for intelligent operation and maintenance. Currently, optical fiber network operation and maintenance are still mainly manual operations. Fiber patching configuration, troubleshooting, and other tasks rely on manual on-site operations, which are inefficient and susceptible to human error. As the scale of optical cable networks continues to expand, intelligent optical fiber distribution equipment is gradually replacing traditional manual methods. It uses robotic arms to complete functions such as automated fiber patching and optical cable core quality monitoring, realizing dynamic resource allocation and intelligent management of optical fiber networks. This type of equipment can remotely complete fiber core plugging and unplugging, path switching, and performance testing, significantly improving operation and maintenance efficiency, but it also places higher demands on the accurate assessment of equipment health status.

[0003] Intelligent fiber optic distribution equipment features high-frequency plugging and unplugging and strong adaptability to dynamic environments. Its health status is affected by the coupling of multiple factors, including mechanical fatigue, optical signal attenuation, and ambient temperature and humidity. Existing industrial equipment health analysis methods (such as motor vibration monitoring and bearing life prediction) are mostly based on fixed-cycle offline data training models and cannot adapt to the dynamic scenarios where fiber optic equipment experiences both instantaneous operation and long-term aging. In addition, the strong correlation between the optical signal characteristics (such as optical power loss) and mechanical movement (such as plug-in force control) of fiber optic distribution equipment makes it difficult for traditional single-dimensional health assessment models to accurately reflect the true status of the equipment. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method and device for analyzing the health of intelligent fiber optic distribution equipment, which, through a distributed federated learning framework, realizes distributed training of local data and global model aggregation of intelligent fiber optic distribution equipment, thereby improving the adaptability and accuracy of equipment health monitoring.

[0005] The present invention provides a method for analyzing the health of an intelligent optical fiber distribution device, including the following steps:

[0006] Preprocess the device data collected by intelligent optical fiber distribution equipment to construct time series data of different modes;

[0007] Constructing a global LSTM model for predicting the health status of intelligent optical fiber distribution devices, and distributing the initialized global model parameters to each intelligent optical fiber distribution device so that each intelligent optical fiber distribution device performs local LSTM model training based on the time series data;

[0008] Utilize the local training parameters obtained from each intelligent fiber optic distribution device to perform parameter alignment compensation and parameter aggregation strategies on the global LSTM model, and obtain the updated global model parameters;

[0009] The updated global model parameters are loaded into the local LSTM model of each intelligent optical fiber distribution device to evaluate the current health status of each intelligent optical fiber distribution device.

[0010] In some embodiments, the method further comprises the following steps:

[0011] Monitor the optical power loss and plug-in frequency fluctuations of each intelligent fiber optic distribution device for abnormalities. If the optical power loss fluctuation or plug-in frequency fluctuation of a certain intelligent fiber optic distribution device exceeds the set threshold, retrain the local LSTM model and update the global model parameters based on the current and historical time series data.

[0012] In some embodiments, the device data includes optical power loss, the number of plugging and unplugging times of the optical fiber connector, the mileage of the lead screw, and environmental data. Preprocessing the device data collected by the intelligent optical fiber distribution device to construct time series data of different modes includes the following steps:

[0013] The number of plug-in / plug-out times within each window is counted based on a sliding window mechanism, and is divided into low-frequency plug-in / plug-out scenarios and high-frequency plug-in / plug-out scenarios according to a preset threshold value. In the low-frequency plug-in / plug-out scenario, the optical power loss is normalized using extreme value; in the high-frequency plug-in / plug-out scenario, the optical power loss is normalized using standard deviation.

[0014] The cumulative fatigue is calculated based on the number of plug-in and pull-out times, the screw mileage and the time decay effect, which is used to measure the cumulative stress and loss that the equipment is subjected to during use;

[0015] Obtaining the timestamp of each plugging and unplugging operation, and converting it into a first time code and a second time code according to the periodicity of plugging and unplugging of the intelligent optical fiber distribution device;

[0016] The normalized optical power loss, cumulative fatigue, number of plug-in and unplugging times, first time code, second time code, and environmental data are aligned by time step to form a two-dimensional input tensor as time series data of different modalities.

[0017] In some embodiments, when each intelligent fiber optic distribution device performs local LSTM model training based on the time series data, a momentum stochastic gradient descent algorithm is used to adjust local training parameters.

[0018] In some embodiments, the method of using the local training parameters obtained from each intelligent optical fiber distribution device to perform parameter alignment compensation and parameter aggregation strategy on the global LSTM model and obtain updated global model parameters includes the following steps:

[0019] Obtain local training parameters obtained by each intelligent optical fiber distribution device;

[0020] Calculating a first standard deviation of optical power loss of each intelligent optical fiber distribution device within a set accumulation period and a second standard deviation of current optical power loss of all intelligent optical fiber distribution devices; and performing feature scaling compensation on the local training parameters based on the first standard deviation and the second standard deviation;

[0021] Calculate the number of optical power loss data samples, the historical average plugging and unplugging frequency, and the cumulative fatigue of each intelligent optical fiber distribution device, as well as the total number of optical power loss data samples, the global average plugging and unplugging frequency, and the overall cumulative fatigue of the intelligent optical fiber distribution device; and aggregate the local training parameters based on the set adjustment factor, activity coefficient, the number of optical power loss data samples, the historical average plugging and unplugging frequency, the cumulative fatigue, the total number of optical power loss data samples, the global average plugging and unplugging frequency, and the overall cumulative fatigue to obtain updated global model parameters.

[0022] In some embodiments, the step of evaluating the current health status of each intelligent fiber optic distribution device comprises the following steps:

[0023] The collected and preprocessed time series data is input into the trained local LSTM model to obtain the current health prediction value of the intelligent fiber optic wiring equipment;

[0024] The health prediction value is normalized and mapped to a set score range, and the current health status of the intelligent optical fiber distribution device is represented according to the obtained score.

[0025] In some embodiments, monitoring the optical power loss and plug-in frequency fluctuation of each intelligent optical fiber distribution device to see if there is any abnormality includes the following steps:

[0026] Calculate the third standard deviation of the optical power loss of each intelligent optical fiber distribution device within the statistical period. If the third standard deviation exceeds the set optical power loss fluctuation threshold, determine that the optical power loss fluctuation is abnormal. The statistical periods set for low-frequency plug-in scenarios and high-frequency plug-in scenarios are different.

[0027] If the number of plug-in and unplugging times in both the short-term and long-term time windows exceeds the set plug-in frequency fluctuation threshold, it is determined that the plug-in frequency fluctuation is abnormal; the plug-in frequency fluctuation threshold is set based on the average and standard deviation of the plug-in frequency in the short-term and long-term time windows.

[0028] In some embodiments, a device for analyzing the health of an intelligent optical fiber distribution device is further provided, the device comprising:

[0029] The data acquisition and preprocessing module is used to preprocess the device data collected by the intelligent optical fiber distribution equipment and construct time series data of different modes;

[0030] A model training module is used to build a global LSTM model for predicting the health status of intelligent optical fiber distribution devices, and to distribute the initialized global model parameters to each intelligent optical fiber distribution device so that each intelligent optical fiber distribution device performs local LSTM model training based on the time series data;

[0031] The global model parameter aggregation module is used to use the local training parameters obtained by each intelligent fiber optic distribution device to perform parameter alignment compensation and parameter aggregation strategies on the global LSTM model and obtain the updated global model parameters;

[0032] The health status assessment module is used to load the updated global model parameters into the local LSTM model of each intelligent optical fiber distribution device to evaluate the current health status of each intelligent optical fiber distribution device.

[0033] In some embodiments, an electronic device is also provided, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the health analysis method of an intelligent optical fiber distribution equipment described above are performed.

[0034] In some embodiments, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above-mentioned methods for analyzing the health of intelligent optical fiber distribution equipment are executed.

[0035] The health status analysis method and device of intelligent fiber optic distribution equipment described in this application pre-processes the equipment data collected by the intelligent fiber optic distribution equipment to construct time series data of different modes; constructs a global LSTM model for predicting the health status of the intelligent fiber optic distribution equipment, and sends the initialized global model parameters to each intelligent fiber optic distribution equipment so that each intelligent fiber optic distribution equipment performs local LSTM model training based on the time series data; uses the local training parameters obtained by each intelligent fiber optic distribution equipment to perform parameter alignment compensation and parameter aggregation strategy on the global LSTM model, and obtains updated global model parameters; and carries the updated global model parameters into the local LSTM model of each intelligent fiber optic distribution equipment to evaluate the current health status of each intelligent fiber optic distribution equipment. Thus, through the distributed federated learning framework, the distributed training of local data of intelligent fiber optic distribution equipment and the global model aggregation are realized, and then the optical power loss, plug-in and unplug count and other data are monitored and analyzed in real time, potential health risks are discovered in a timely manner, and the accumulation of problems leading to equipment damage is avoided. Compared with the traditional manual operation and maintenance mode, the adaptability and accuracy of equipment health monitoring are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A flow chart of the method for analyzing the health of an intelligent optical fiber distribution device according to an embodiment of the present application is shown;

[0038] Figure 2 A flowchart of preprocessing device data collected by an intelligent optical fiber distribution device and constructing time series data of different modalities according to an embodiment of the present application is shown;

[0039] Figure 3 A flowchart of an embodiment of the present application is shown for performing parameter alignment compensation and parameter aggregation strategies on a global LSTM model using local training parameters obtained from each intelligent fiber optic distribution device, and obtaining updated global model parameters;

[0040] Figure 4 A flowchart showing whether abnormalities occur in optical power loss and plug-in frequency fluctuations of each intelligent optical fiber distribution device according to an embodiment of the present application is shown;

[0041] Figure 5 The figure shows a schematic diagram of the structure of the intelligent optical fiber distribution equipment health analysis device according to an embodiment of the present application;

[0042] Figure 6 A schematic structural diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0044] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0045] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0046] In view of the technical problems raised by the background technology, the present application provides a method, device, electronic device and storage medium for analyzing the health of intelligent fiber optic distribution equipment. Through a distributed federated learning framework, distributed training of local data and global model aggregation of intelligent fiber optic distribution equipment are realized, thereby improving the adaptability and accuracy of equipment health monitoring.

[0047] See the instructions attached Figure 1 The present application provides a method for analyzing the health of an intelligent optical fiber distribution device, comprising the following steps:

[0048] S1. Preprocess the device data collected by the intelligent optical fiber distribution equipment to construct time series data of different modes;

[0049] S2. Build a global LSTM model for predicting the health status of intelligent optical fiber distribution devices, and distribute the initialized global model parameters to each intelligent optical fiber distribution device, so that each intelligent optical fiber distribution device performs local LSTM model training based on the time series data;

[0050] S3. Utilize the local training parameters obtained from each intelligent fiber optic distribution device to perform parameter alignment compensation and parameter aggregation strategies on the global LSTM model, and obtain updated global model parameters.

[0051] S4. Load the updated global model parameters into the local LSTM model of each intelligent optical fiber distribution device to evaluate the current health status of each intelligent optical fiber distribution device.

[0052] In step S1, the equipment data collected by the intelligent optical fiber distribution equipment include optical power loss of the optical fiber channel, plug-in and unplug times of the optical fiber connector, temperature, humidity, vibration intensity (time series data), screw running mileage and other optical, mechanical and environmental data. Figure 2 The preprocessing of the device data collected by the intelligent optical fiber distribution device to construct time series data of different modes includes the following steps:

[0053] S101. Counting the number of plug-in / plug-out times within each window based on a sliding window mechanism, and dividing the number of plug-in / plug-out times into a low-frequency plug-in / plug-out scenario and a high-frequency plug-in / plug-out scenario according to a preset threshold; wherein, in the low-frequency plug-in / plug-out scenario, the optical power loss is normalized by extreme value; and in the high-frequency plug-in / plug-out scenario, the optical power loss is normalized by standard deviation;

[0054] S102. Calculate the cumulative fatigue based on the number of plugging and unplugging times, the screw mileage, and the time decay effect to measure the cumulative stress and loss the equipment endures during use;

[0055] S103, obtaining a timestamp of each plugging and unplugging operation, and converting it into a first time code and a second time code according to the periodicity of plugging and unplugging of the intelligent optical fiber distribution device;

[0056] S104: Align the normalized optical power loss, accumulated fatigue, number of plug-in and unplugging times, first time code, second time code, and environmental data by time step to form a two-dimensional input tensor as time series data of different modalities.

[0057] In step S101, the optical power loss is dynamically normalized by using the plug-in frequency segmentation method. This is because, in the low-frequency plug-in scenario, there are few plug-in operations, the optical power loss data is relatively stable, and the noise ratio is high; in the high-frequency plug-in scenario, plug-in is frequent, and the optical power loss fluctuates violently (such as a surge in loss at the moment of plug-in). The optical power loss data is divided into multiple subsets according to the plug-in frequency interval (such as low and high), and the normalization parameters (mean, standard deviation or extreme value) are calculated independently for each subset, so as to adapt to the data distribution differences at different frequencies. "High-frequency amplification and low-frequency smoothing" is achieved by plug-in frequency segmentation, and the fluctuation characteristics of the optical power loss are directly associated with the plug-in frequency, thereby improving the model's response to extreme scenarios.

[0058] In specific implementations, a sliding window mechanism can be used to define short-term time windows Tshort (in days) and count the number of plug-ins F within each window. Because both low-frequency and high-frequency plug-ins exist, statistics on the number of plug-ins within a long-term time window Tlong are added in addition to the plug-in count within the time window. Tlong is the sum of multiple consecutive time windows Tshort. The average plug-in frequency within the Tlong time window is evaluated using an exponentially weighted moving average (EWMA).

[0059] F AVG (t) = α·Ft + (1-α)·F AVG (t-1)

[0060] Among them, α is the forgetting factor. The larger α is, the smaller the influence of historical data is. Ft represents the number of plug-ins and unplugs in the time window t; F AVG (t-1) represents the historical average number of plug-in and plug-out times before the time window t. In one embodiment, the average plug-in and plug-out frequency of the time window Tlong is divided into low frequency and high frequency by a preset threshold value.

[0061] In a low-frequency plug-in / plug-out scenario, extreme value normalization is performed on the optical power loss.

[0062] Take the maximum and minimum values within the Tlong time window and calculate the normalized optical power loss data:

[0063]

[0064] Among them, P is the optical power loss data collected by a certain intelligent optical fiber distribution device, P norm is the calculated normalized data, P max is the maximum value of P in the Tlong time window, P minis the minimum value of P in the Tlong time window, S is the scaling factor (range: 0.7-0.9, default: 0.8), and O is the offset (default 0.1). The purpose of setting S and O is to compress the normalized range to the middle interval and ensure that the minimum value is not zero, thereby ensuring the physical meaning of the value.

[0065] In a high-frequency plug-in / plug-out scenario, the optical power loss is normalized using standard deviation.

[0066]

[0067] Among them, P avg is the average optical power loss in the window, P σ is the standard deviation of optical power loss within the window.

[0068] In step S102, accumulated fatigue is a measure of the cumulative stress and wear experienced by the device during long-term use. Intelligent fiber optic patching equipment measures the degree of optical and mechanical wear and aging, or accumulated fatigue factor (AEF), by factoring in plug-in and unplug cycles, lead screw mileage, and time decay.

[0069]

[0070] in, is the dynamic attenuation of plugging and unplugging, β is the basic damage of a single plugging and unplugging, usually 0.15; γ is the overload force multiple, usually 1.2, and takes effect when Fk>0.8Fmax; λ is the stress relaxation coefficient, which depends on the material and is usually 0.02 / hour for optical fiber connectors;

[0071] is the dynamic wear of the screw mileage, μ is the basic wear rate, and the stainless steel guide rail is usually 0.003; α is the nonlinear wear acceleration index, usually 2.1; v crit The speed threshold refers to the point in time during the operation of intelligent fiber optic patching equipment where the lead screw speed reaches a certain value, which significantly affects the wear of the equipment. This value is determined based on the mechanical properties and design specifications of the equipment.

[0072] In step S103, the plug-in and unplug-in timestamp records the specific time when each plug-in and unplug-in operation occurs. It can provide information about the time regularity and periodicity of the plug-in and unplug-in operations, and convert the timestamp into a numerical value suitable for model processing as an acquisition input data set. Convert the plug-in and unplug-in timestamp into a time interval, that is, the time difference (in hours) between the current time and the most recent plug-in and unplug-in. According to the periodic characteristics of the plug-in and unplug-in of the intelligent optical fiber distribution equipment, monthly and daily periodicity are selected to obtain the periodic information of the plug-in and unplug-in operations. Among them, time code 1 represents periodicity within 30 days: convert the timestamp into the number of hours within 30 days (0-720), and embed it through sine / cosine coding: sin(2πt / 720), cos(2πt / 720);

[0073] Time code 2 indicates intraday periodicity: the timestamp is converted to the hour of the day (0-23), and similarly, sine / cosine encoding is performed: sin(2πt / 24), cos(2πt / 24).

[0074] In step S104, the time series data of different modalities are aligned by time step to form a two-dimensional input tensor:

[0075] X t =[optical power, AEF, plug-in / plug-out cycles, time code 1, time code 2, temperature, humidity]

[0076] Considering that the plugging and unplugging of optical fiber connectors has a great impact on the performance and health of intelligent optical fiber distribution equipment, the number of plugging and unplugging of optical fiber connectors at each time step is added to Xt as a new feature. The Min-Max normalization method can be used to convert the plugging and unplugging times n into

[0077] In step S2, a global long-short-term memory (LSTM) model is first constructed to predict the health status of intelligent fiber optic distribution equipment. This model effectively processes time series data and captures the temporal changes in connector plugging and unplugging frequency, cumulative fatigue, and other parameters. After model initialization, global model parameters, including LSTM layer weights, fully connected layer weights, LSTM layer biases, and fully connected layer biases, are distributed to each intelligent fiber optic distribution equipment. Each intelligent fiber optic distribution equipment receives these global model parameters and, combined with locally collected and preprocessed time series data (optical power, cumulative fatigue, plugging and unplugging frequency, temperature, and humidity), inputs them into the local LSTM model of the intelligent fiber optic distribution equipment for training. The accuracy of the model predictions is evaluated by calculating the mean squared error (MSE) between the predicted and true values using the mean squared error (MSE) function.

[0078]

[0079] Where L represents the loss function value, which is used to measure the difference between the model prediction value and the true value. The smaller the loss function value, the closer the model prediction result is to the true value, and the better the model performance. N represents the total number of time series data samples involved in model training, including information such as optical power loss, accumulated fatigue, and plug-in frequency. The more samples there are, the more comprehensive the model learning features are, and the stronger the generalization ability of the model training results is; X i represents the true health of the intelligent fiber optic wiring robot labeled by the i-th sample; It represents the health prediction value of the intelligent fiber optic wiring robot obtained by analyzing the i-th sample, that is, the model analyzes the input sample data X according to the currently set parameters. i The output result obtained after forward propagation calculation. During the local LSTM model training process, the model parameters are continuously adjusted to make As close to X as possible i , thereby reducing the loss function L value.

[0080] Furthermore, during the training process of the intelligent fiber optic distribution equipment health status prediction model, considering the imbalance of data volume among different intelligent fiber optic distribution equipment and the fact that the processing efficiency of intelligent fiber optic distribution equipment is limited by computing power, the momentum stochastic gradient descent algorithm (Momentum SGD) is used to adjust the model parameters to obtain the smallest possible L value. The parameter adjustment process is as follows:

[0081] θ t =θ t-1 -v t

[0082] Among them, θ t Represents the parameter value of the t-th iteration model, that is, the latest parameter value after this update. θ t-1 Represents the model parameter value at the t-1th iteration, that is, the parameter value at the end of the previous iteration. t represents the momentum at the tth iteration, representing the cumulative effect of the gradient update direction; v t Calculated using the following formula:

[0083]

[0084] Where t represents the current iteration step, which indicates the current number of iterations. Model training will be repeated multiple times, and each iteration will update the model parameters. μ is the momentum coefficient, which ranges from [0, 1] and is usually set to 0.9. μ determines the degree of influence of the previous momentum on the current momentum. The larger μ is, the greater the influence of past gradient information on the current update, and the more the model can maintain the previous direction of movement during the update process. The smaller μ is, the greater the influence of the current gradient is. v t-1is the momentum at iteration t-1, representing the momentum calculated in the previous iteration. η is the learning rate, which controls the step size of each parameter update. If the learning rate is too large, the model may oscillate around the optimal solution or even diverge. If the learning rate is too small, the model converges very slowly. Represents the gradient of the loss function L with respect to the parameter θ at the t-1th iteration. The gradient represents the rate of change of the loss function at the current parameter value. Its direction points to the direction in which the loss function increases fastest, and the negative gradient direction is the direction in which the loss function decreases fastest.

[0085] After the intelligent fiber optic distribution equipment completes the local LSTM model parameter optimization, it feeds the updated LSTM layer weights, fully connected layer weights, LSTM layer bias, and fully connected layer bias parameters back to the global model for parameter alignment compensation and parameter aggregation strategy, and iteratively updates the model.

[0086] In step S3, see the attached Figure 3 , the local training parameters obtained from each intelligent optical fiber distribution device are used to perform parameter alignment compensation and parameter aggregation strategy on the global LSTM model, and obtain updated global model parameters, including the following steps:

[0087] S301, obtaining local training parameters of each intelligent optical fiber distribution device;

[0088] S302: Calculate a first standard deviation of optical power loss of each intelligent optical fiber distribution device within a set accumulation period, and a second standard deviation of current optical power loss of all intelligent optical fiber distribution devices; and perform feature scaling compensation on the local training parameters based on the first standard deviation and the second standard deviation;

[0089] S303. Calculate the number of optical power loss data samples, the historical average plugging and unplugging frequency, and the cumulative fatigue of each intelligent optical fiber distribution device, as well as the total number of optical power loss data samples, the global average plugging and unplugging frequency, and the overall cumulative fatigue of the intelligent optical fiber distribution device; and aggregate the local training parameters based on the set adjustment factor, activity coefficient, the number of optical power loss data samples, the historical average plugging and unplugging frequency, the cumulative fatigue, the total number of optical power loss data samples, the global average plugging and unplugging frequency, and the overall cumulative fatigue to obtain updated global model parameters.

[0090] In step S301, after the global model receives the parameters uploaded by the local training of the intelligent optical fiber distribution device, it executes the parameter alignment compensation and parameter aggregation strategies in steps S302 and S303.

[0091] Specifically, in step S302, due to the large difference in optical power normalization parameters between low-frequency plugging and high-frequency plugging intelligent optical fiber distribution devices, feature scaling compensation is performed using the local standard deviation and global standard deviation of accumulated cycle statistics before federation aggregation:

[0092]

[0093] in, The original model parameters of the i-th intelligent optical fiber distribution device are obtained after the local LSTM model is trained. They are trained based on the local data of device i and reflect the operating characteristics of device i itself. is the standard deviation of the local optical power loss of the i-th intelligent optical fiber distribution device within the set accumulation period, reflecting the degree of dispersion of the local optical power loss data of device i. It is compared with the global standard deviation to determine the degree of difference between the data characteristics of device i and the global data characteristics; σ hlobal It is the standard deviation of the current optical power loss data of all intelligent fiber optic patching devices. It represents the degree of global data dispersion and is used to unify the characteristic scales of different intelligent fiber optic patching devices. By calculating the standard deviation of the optical power loss data of all devices, a global standard can be obtained to measure the fluctuation of data from different devices and avoid the impact of low-frequency plugging and unplugging of intelligent fiber optic patching devices on the model. After feature scaling compensation, the local model parameters of the i-th device are obtained. This parameter not only takes into account the local optical power loss data characteristics of device i, but also adjusts the parameters by comparing them with the global standard deviation to make them more consistent with the requirements of the global model parameters.

[0094] In step S303, the plugging and unplugging frequency reflects the differences in the intensity of equipment use. Different intelligent fiber optic distribution devices have different plugging and unplugging frequencies, which affects the optical power loss. When plugging and unplugging at a low frequency, the optical power loss data is relatively stable but the noise ratio is high; when plugging and unplugging at a high frequency, the optical power loss will surge and fluctuate violently at the moment of plugging and unplugging. Considering the weight influence of low-frequency plugging and unplugging devices and high-frequency plugging and unplugging devices during parameter aggregation can more accurately learn the relationship between optical power loss and plugging and unplugging operations, improve the model's ability to respond to the health status of the equipment in extreme plugging and unplugging scenarios, and ensure that the model output is more in line with the actual operation of the equipment.

[0095] Cumulative fatigue measures the long-term health loss of equipment. Intelligent fiber optic patching equipment experiences continuous wear and aging of its optical and mechanical components over long periods of operation. Cumulative fatigue integrates factors such as the number of plugging and unplugging cycles and the mileage of the leadscrew, combined with the time decay effect, to measure the cumulative stress and wear experienced by the equipment. Introducing cumulative fatigue allows the model to comprehensively consider the health risks accumulated over the long term of equipment operation, rather than focusing solely on current plugging and unplugging operations. It complements this with information from the dimension of long-term equipment aging, complementing short-term performance indicators such as optical power loss.

[0096]

[0097] in, Represents the global model parameters updated after parameter aggregation, by updating the local model parameters Perform weighted summation. N i N is the number of local optical power loss data samples of the i-th intelligent optical fiber distribution device; total The sum of the local optical power loss data samples of all intelligent optical fiber distribution devices; F i is the historical average plugging and unplugging frequency (times / hour) of the i-th intelligent optical fiber distribution device; The global average plug-in frequency is used to measure the plug-in frequency level of the entire device; AEF i is the cumulative fatigue of the i-th intelligent optical fiber distribution device; It represents the average cumulative fatigue of all intelligent optical fiber distribution devices, which measures the fatigue level of the entire device. α is the adjustment factor. The increase of α will increase the weight of high-frequency plug-in intelligent optical fiber distribution devices. α is usually 0.5. i is the activity coefficient, which is determined based on the number of plug-ins and unplugs in the past 30 days. i (such as β i =1+number of plugging and unplugging times in the last 30 days), thereby ensuring that intelligent fiber optic distribution devices with different plugging and unplugging frequencies contribute more reasonably to the calculation results of the global model parameters.

[0098] By taking into account the data volume, plug-in and unplugging frequency, and activity differences of different devices in a weighted manner, the parameters of intelligent fiber optic distribution devices with a high plug-in and unplugging frequency have a greater weight when the global model is aggregated. At the same time, the characteristics of low-frequency plug-in and unplugging intelligent fiber optic distribution devices are not ignored, making the global model more reasonable in integrating the information of each local model, and improving the adaptability and prediction accuracy of the health status of different devices.

[0099] After the global model completes dual weight aggregation and parameter alignment, the updated model parameters Distributed to each intelligent optical fiber distribution device.

[0100] In step S4, after the global model completes dual weight aggregation and parameter alignment, the updated model parameters The data is distributed to each intelligent fiber optic distribution device. Each intelligent fiber optic distribution device collects fiber-related data for the current time and a historical period (such as the past 24 hours), including optical power loss, plug-in / plug-out times, temperature, humidity, and so on. This data is organized into time series data in the same format as used during training, and an input tensor X is constructed. This prepared input tensor X is input into the trained local LSTM model, which then outputs a predicted value for device health.

[0101] Furthermore, the health prediction value is normalized and mapped to a score range of 0-100, which is recorded as Hscore. The higher the score, the better the current health status of the intelligent optical fiber distribution equipment; the closer to 0, the worse the health status.

[0102] It can be seen that the application provides a health analysis method for intelligent fiber optic distribution equipment, based on a federated learning framework, which solves the problem that different intelligent fiber optic distribution equipment models are difficult to coordinate and optimize and cannot fully utilize the overall data characteristics. Through distributed modeling and global model aggregation, each device can share the training results of other devices, improving model performance and adaptability. This enables the model to more comprehensively capture the operating rules of each intelligent fiber optic distribution device in the network and accurately assess the health status of the equipment to meet the operation and maintenance needs of different intelligent fiber optic distribution devices in large-scale fiber optic networks, thereby improving the overall operation and maintenance efficiency of the fiber optic network.

[0103] Furthermore, plug-in / plug-out event markers and fatigue accumulation counters are embedded in the LSTM model. This approach solves the difficulty in capturing the combined effects of instantaneous operation and long-term aging of intelligent fiber-optic patching equipment. It overcomes the limitations of traditional models that can only process single-type or static data. It enables dynamic and comprehensive modeling of device status, ensuring accurate assessment of device health and timely identification of potential equipment issues, ensuring stable operation of intelligent fiber-optic patching equipment, and enhancing fiber-optic network reliability.

[0104] Furthermore, during parameter aggregation, dual weighting is applied, taking into account plugging frequency and accumulated fatigue, while also implementing an event alignment compensation mechanism. This solves the generalization challenge of heterogeneous data across multiple devices, improving upon the limitations of traditional federated aggregation strategies in handling data differences between devices. This ensures that the global model rationally integrates local model information from each intelligent fiber optic distribution device, enhancing its adaptability and prediction accuracy for different device health states, making the model more applicable to complex, real-world intelligent fiber optic distribution device scenarios.

[0105] In other embodiments, the present application provides a method for analyzing the health of an intelligent optical fiber distribution device, further comprising the steps of:

[0106] S5. Monitor the optical power loss and plug-in frequency fluctuations of each intelligent optical fiber distribution device for abnormalities. If the optical power loss fluctuation or plug-in frequency fluctuation of a certain intelligent optical fiber distribution device exceeds the set threshold, re-train the local LSTM model and update the global model parameters based on the current and historical time series data.

[0107] For details, see the attached manual. Figure 4 The monitoring of the optical power loss and plug-in frequency fluctuation of each intelligent optical fiber distribution device to see if there is any abnormality includes the following steps:

[0108] S501. Calculate the third standard deviation of the optical power loss of each intelligent optical fiber distribution device within a statistical period. If the third standard deviation exceeds a set optical power loss fluctuation threshold, determine that the optical power loss fluctuation is abnormal. The statistical periods set for low-frequency plug-in scenarios and high-frequency plug-in scenarios are different.

[0109] S502. If the number of plugging and unplugging times in both the short-term time window and the long-term time window exceeds a set plugging and unplugging frequency fluctuation threshold, it is determined that the plugging and unplugging frequency fluctuation is abnormal; the plugging and unplugging frequency fluctuation threshold is set based on the average and standard deviation of the plugging and unplugging frequencies in the short-term time window and the long-term time window.

[0110] In step S501, the focus is on monitoring optical power loss fluctuations and analyzing anomalies. Optical power loss is a key indicator of optical fiber transmission performance, and fluctuations in optical power loss can affect the communication quality of the optical fiber core connections provided by intelligent fiber distribution equipment. In actual use, optical power loss data is continuously collected, and the historical average fluctuation range of optical power loss is calculated, denoted as ±σ. Optical power loss fluctuations ΔP are calculated for low-frequency and high-frequency scenarios, and abnormal fluctuations in optical power loss are identified.

[0111] In low-frequency plug-in / plug-out scenarios, select a longer time period (such as one containing multiple T long In the high-frequency plug-in scenario, each plug-in operation is used as an analysis unit, and the optical power loss value after each plug-in is recorded. Statistics are collected over a period of time (such as a T long ) The average optical power loss fluctuation over multiple plugging and unplugging operations. The average optical power loss fluctuation in low-frequency scenarios and high-frequency scenarios are both denoted as ΔP. Calculate the standard deviation σ of the optical power loss over the statistical period. If |ΔP|>kσ (k is the fluctuation anomaly coefficient), the optical power loss fluctuation is considered abnormal.

[0112] In step S502, the main task is to monitor and analyze the plugging and unplugging frequency fluctuations. Specifically, during the operation of the intelligent optical fiber distribution equipment, the plugging and unplugging times of the intelligent optical fiber distribution equipment at the current time and within a historical period (the previous 24 hours) are continuously monitored and counted. To more accurately determine the plugging and unplugging frequency fluctuations, the judgment results of both short-term and long-term time windows are comprehensively considered.

[0113] In a short time window, a large number of historical T short The plug-in fluctuation is calculated by taking the average statistics of the plug-in times F within a long time window; long Average plugging and unplugging frequency F within the time window avg Perform mean statistics to calculate the plug-in fluctuation. Calculate the average plug-in frequency in the short-term time window. and standard deviation σ short, the average plug-in and plug-out frequency in the long-term time window and standard deviation σ long Short-term high-frequency threshold Long-term high-frequency threshold

[0114] In the short-term time window, when a certain T short Insertion and removal times F>F short-high , it is determined that the plug-in frequency fluctuates abnormally in the short-term time window; in the long-term time window, when F avg >F long-high , determining that the plugging and unplugging frequency fluctuations within the long-term time window are abnormal. When abnormal fluctuations occur simultaneously in the short term and the long term, or when abnormal fluctuations occur frequently in the short term and the long-term fluctuation trend also deviates from the normal range, it is determined that the device plugging and unplugging frequency is seriously abnormal.

[0115] When optical power loss or plugging frequency fluctuates abnormally and reaches a threshold, the intelligent fiber optic distribution device initiates a model parameter update. The abnormal intelligent fiber optic distribution device inputs the optical power loss and plugging frequency data for the current moment and a period of time (such as the past 24 hours) into the local LSTM model, recalculates the optimized local model parameters, and uploads them to the global model. The global model then obtains the other local model parameters, executes the parameter aggregation strategy and parameter alignment compensation, and distributes the updated model parameters to all intelligent fiber optic distribution devices.

[0116] Based on the same inventive concept, an embodiment of the present application also provides a device for analyzing the health of an intelligent optical fiber distribution device. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned method for analyzing the health of an intelligent optical fiber distribution device in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0117] As the instruction manual Figure 5 As shown, the embodiment of the present application also provides a health analysis device for intelligent optical fiber distribution equipment, the device comprising:

[0118] The data acquisition and preprocessing module 501 is used to preprocess the device data collected by the intelligent optical fiber distribution device and construct time series data of different modes;

[0119] A model training module 502 is configured to construct a global LSTM model for predicting the health status of an intelligent optical fiber distribution device, and to distribute the initialized global model parameters to each intelligent optical fiber distribution device so that each intelligent optical fiber distribution device performs local LSTM model training based on the time series data;

[0120] A global model parameter aggregation module 503 is configured to use the local training parameters obtained by each intelligent optical fiber distribution device to perform parameter alignment compensation and parameter aggregation strategies on the global LSTM model and obtain updated global model parameters;

[0121] The health status evaluation module 504 is configured to load the updated global model parameters into the local LSTM model of each intelligent optical fiber distribution device to evaluate the current health status of each intelligent optical fiber distribution device.

[0122] In one embodiment, the device data includes optical power loss, the number of plug-in and unplug-out times of the optical fiber connector, the mileage of the lead screw, and environmental data. The data acquisition preprocessing module 501 preprocesses the device data collected by the intelligent optical fiber distribution device to construct time series data of different modes, including: counting the number of plug-in and unplug-out times in each window based on a sliding window mechanism, and dividing the data into low-frequency plug-in and unplug-out scenarios and high-frequency plug-in and unplug-out scenarios according to a preset threshold value; wherein, in the low-frequency plug-in and unplug-out scenario, the optical power loss is normalized by extreme value; in the high-frequency plug-in and unplug-out scenario, the optical power loss is normalized by standard deviation; based on the number of plug-in and unplug-out times, the mileage of the lead screw, and the time attenuation effect, the cumulative fatigue is calculated to measure the cumulative stress and loss suffered by the device during use; the timestamp of each plug-in and unplug-out operation is obtained, and converted into a first time code and a second time code according to the periodicity of the plug-in and unplug-out of the intelligent optical fiber distribution device; the normalized optical power loss, cumulative fatigue, number of plug-in and unplug-out times, the first time code, the second time code, and the environmental data are aligned according to the time step to form a two-dimensional input tensor as time series data of different modes.

[0123] In one embodiment, the global model parameter aggregation module 503 uses the local training parameters obtained by each intelligent fiber optic distribution device to perform parameter alignment compensation and parameter aggregation strategy on the global LSTM model, and obtains updated global model parameters, including: obtaining the local training parameters obtained by each intelligent fiber optic distribution device; calculating the first standard deviation of the optical power loss of each intelligent fiber optic distribution device within a set cumulative period, and the second standard deviation of the current optical power loss of all intelligent fiber optic distribution devices; and performing feature scaling compensation on the local training parameters based on the first standard deviation and the second standard deviation; calculating the number of optical power loss data samples, the historical average plugging and unplugging frequency, and the cumulative fatigue of each intelligent fiber optic distribution device, as well as the sum of the number of optical power loss data samples of the intelligent fiber optic distribution device, the global average plugging and unplugging frequency, and the overall cumulative fatigue; and aggregating the local training parameters based on the set adjustment factor, activity coefficient, number of optical power loss data samples, the historical average plugging and unplugging frequency, cumulative fatigue, the sum of the number of optical power loss data samples, the global average plugging and unplugging frequency, and the overall cumulative fatigue to obtain updated global model parameters.

[0124] In one embodiment, the health status assessment module 504 assesses the current health status of each intelligent fiber optic distribution device, including: inputting the collected and pre-processed time series data into a trained global LSTM model to obtain the current health prediction value of the intelligent fiber optic distribution device; normalizing the health prediction value and mapping it to a set score range, and characterizing the current health status of the intelligent fiber optic distribution device according to the obtained score.

[0125] In one embodiment, the apparatus further comprises:

[0126] The update module is used to monitor whether the optical power loss and plug-in frequency fluctuations of each intelligent optical fiber distribution device are abnormal. If the optical power loss fluctuation or plug-in frequency fluctuation of a certain intelligent optical fiber distribution device exceeds the set threshold, the local LSTM model is retrained and the global model parameters are updated based on the time series data of the current and historical period. Among them, the third standard deviation of the optical power loss of each intelligent optical fiber distribution device within the statistical period is calculated. If the third standard deviation exceeds the set optical power loss fluctuation threshold, it is determined that the optical power loss fluctuation is abnormal. Among them, the statistical periods set for low-frequency plug-in scenarios and high-frequency plug-in scenarios are different. If the number of plug-ins in the short-term time window and the long-term time window both exceed the set plug-in frequency fluctuation threshold, it is determined that the plug-in frequency fluctuation is abnormal. The plug-in frequency fluctuation threshold is set based on the average value and standard deviation of the plug-in frequency in the short-term time window and the long-term time window.

[0127] The health analysis device for intelligent fiber optic distribution equipment described in this application pre-processes the equipment data collected by the intelligent fiber optic distribution equipment through a data acquisition and processing module to construct time series data of different modes; constructs a global LSTM model for predicting the health status of the intelligent fiber optic distribution equipment through a model training module, and sends the initialized global model parameters to each intelligent fiber optic distribution equipment so that each intelligent fiber optic distribution equipment performs local LSTM model training based on the time series data; uses the local training parameters obtained by each intelligent fiber optic distribution equipment through a global model parameter aggregation module to perform parameter alignment compensation and parameter aggregation strategies on the global LSTM model and obtain updated global model parameters; and uses the health status evaluation module to load the updated global model parameters into the local LSTM model of each intelligent fiber optic distribution equipment to evaluate the current health status of each intelligent fiber optic distribution equipment. Thus, through a distributed federated learning framework, distributed training of local data and global model aggregation of intelligent fiber optic distribution equipment are realized, and then data such as optical power loss and plug-in / plug-out times are monitored and analyzed in real time, potential health risks are discovered in a timely manner, and equipment damage is avoided due to accumulation of problems. Compared with the traditional manual operation and maintenance mode, the adaptability and accuracy of equipment health monitoring are improved.

[0128] Based on the same concept of the present invention, as shown in the attached specification Figure 6 As shown, an embodiment of the present application provides a structure of an electronic device 600, which includes: at least one processor 601, at least one network interface 604 or other user interface 603, a memory 605, and at least one communication bus 602. The communication bus 602 is used to realize the connection and communication between these components. The electronic device 600 optionally includes a user interface 603, including a display (for example, a touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (for example, a mouse, trackball (trackball), touchpad or touch screen, etc.).

[0129] The memory 605 may include a read-only memory and a random access memory, and provides instructions and data to the processor 601. A portion of the memory 605 may also include a non-volatile random access memory (NVRAM).

[0130] In some embodiments, the memory 605 stores the following elements, executable modules, or data structures, or a subset or extended set thereof:

[0131] Operating system 6051, including various system programs used to implement various basic services and handle hardware-based tasks;

[0132] The application module 6052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0133] In the embodiment of the present application, the processor 601 is configured to execute steps of a method for analyzing the health of an intelligent optical fiber distribution device by calling a program or instruction stored in the memory 605 .

[0134] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in a method for analyzing the health of intelligent optical fiber distribution equipment are executed.

[0135] Specifically, the storage medium can be a general storage medium, such as a mobile disk, hard disk, etc. When the computer program on the storage medium is run, it can realize distributed training of local data of intelligent wiring equipment and global model aggregation through a distributed federated learning framework, thereby improving the adaptability and accuracy of equipment health monitoring.

[0136] In the 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 schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0138] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0140] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above embodiments within the technical scope disclosed in the present application, or replace some of the technical features therein with equivalents. However, these modifications, changes, or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for analyzing the health of intelligent optical fiber distribution equipment, characterized in that: The method comprises the following steps: Preprocess the device data collected by intelligent optical fiber distribution equipment to construct time series data of different modes; Constructing a global LSTM model for predicting the health status of intelligent optical fiber distribution devices, and distributing the initialized global model parameters to each intelligent optical fiber distribution device so that each intelligent optical fiber distribution device performs local LSTM model training based on the time series data; Utilize the local training parameters obtained from each intelligent fiber optic distribution device to perform parameter alignment compensation and parameter aggregation strategies on the global LSTM model, and obtain the updated global model parameters; The updated global model parameters are loaded into the local LSTM model of each intelligent optical fiber distribution device to evaluate the current health status of each intelligent optical fiber distribution device.

2. The method for analyzing the health of an intelligent optical fiber distribution device according to claim 1, characterized in that: The method further comprises the following steps: Monitor the optical power loss and plug-in frequency fluctuations of each intelligent fiber optic distribution device for abnormalities. If the optical power loss fluctuation or plug-in frequency fluctuation of a certain intelligent fiber optic distribution device exceeds the set threshold, retrain the local LSTM model and update the global model parameters based on the current and historical time series data.

3. The method for analyzing the health of an intelligent optical fiber distribution device according to claim 2, characterized in that: in, The device data includes optical power loss, number of plugging and unplugging of optical fiber connectors, lead screw mileage and environmental data. The device data collected by the intelligent optical fiber distribution equipment is preprocessed to construct time series data of different modes, including the following steps: The number of plug-in / plug-out times within each window is counted based on a sliding window mechanism, and is divided into low-frequency plug-in / plug-out scenarios and high-frequency plug-in / plug-out scenarios according to a preset threshold value. In the low-frequency plug-in / plug-out scenario, the optical power loss is normalized using extreme value; in the high-frequency plug-in / plug-out scenario, the optical power loss is normalized using standard deviation. The cumulative fatigue is calculated based on the number of plug-in and pull-out times, the screw mileage and the time decay effect, which is used to measure the cumulative stress and loss that the equipment is subjected to during use; Obtaining the timestamp of each plugging and unplugging operation, and converting it into a first time code and a second time code according to the periodicity of plugging and unplugging of the intelligent optical fiber distribution device; The normalized optical power loss, cumulative fatigue, number of plug-in and unplugging times, first time code, second time code, and environmental data are aligned by time step to form a two-dimensional input tensor as time series data of different modalities.

4. The method for analyzing the health of an intelligent optical fiber distribution device according to claim 1, characterized in that: in, When each intelligent optical fiber distribution device performs local LSTM model training based on the time series data, a momentum stochastic gradient descent algorithm is used to adjust local training parameters.

5. The method for analyzing the health of an intelligent optical fiber distribution device according to claim 3, characterized in that: The method of using the local training parameters obtained from each intelligent optical fiber distribution device to perform parameter alignment compensation and parameter aggregation strategy on the global LSTM model and obtain updated global model parameters includes the following steps: Obtain local training parameters obtained by each intelligent optical fiber distribution device; Calculating a first standard deviation of optical power loss of each intelligent optical fiber distribution device within a set accumulation period and a second standard deviation of current optical power loss of all intelligent optical fiber distribution devices; and performing feature scaling compensation on the local training parameters based on the first standard deviation and the second standard deviation; Calculate the number of optical power loss data samples, the historical average plugging and unplugging frequency, and the cumulative fatigue of each intelligent optical fiber distribution device, as well as the total number of optical power loss data samples, the global average plugging and unplugging frequency, and the overall cumulative fatigue of the intelligent optical fiber distribution device; and aggregate the local training parameters based on the set adjustment factor, activity coefficient, the number of optical power loss data samples, the historical average plugging and unplugging frequency, the cumulative fatigue, the total number of optical power loss data samples, the global average plugging and unplugging frequency, and the overall cumulative fatigue to obtain updated global model parameters.

6. The method for analyzing the health of an intelligent optical fiber distribution device according to claim 1, characterized in that: The evaluation of the current health status of each intelligent optical fiber distribution device includes the following steps: The collected and preprocessed time series data is input into the trained local LSTM model to obtain the current health prediction value of the intelligent fiber optic wiring equipment; The health prediction value is normalized and mapped to a set score range, and the current health status of the intelligent optical fiber distribution device is represented according to the obtained score.

7. A method for analyzing the health of intelligent optical fiber distribution equipment according to claim 5, characterized in that: The monitoring of the optical power loss and plug-in frequency fluctuation of each intelligent optical fiber distribution device to see if there is any abnormality includes the following steps: Calculate the third standard deviation of the optical power loss of each intelligent optical fiber distribution device within the statistical period. If the third standard deviation exceeds the set optical power loss fluctuation threshold, determine that the optical power loss fluctuation is abnormal. The statistical periods set for low-frequency plug-in scenarios and high-frequency plug-in scenarios are different. If the number of plug-in and unplugging times in both the short-term and long-term time windows exceeds the set plug-in frequency fluctuation threshold, it is determined that the plug-in frequency fluctuation is abnormal; the plug-in frequency fluctuation threshold is set based on the average and standard deviation of the plug-in frequency in the short-term and long-term time windows.

8. An intelligent optical fiber distribution equipment health analysis device, characterized in that: The device comprises: The data acquisition and preprocessing module is used to preprocess the device data collected by the intelligent optical fiber distribution equipment and construct time series data of different modes; A model training module is used to build a global LSTM model for predicting the health status of intelligent optical fiber distribution devices, and to distribute the initialized global model parameters to each intelligent optical fiber distribution device so that each intelligent optical fiber distribution device performs local LSTM model training based on the time series data; The global model parameter aggregation module is used to use the local training parameters obtained by each intelligent fiber optic distribution device to perform parameter alignment compensation and parameter aggregation strategies on the global LSTM model and obtain the updated global model parameters; The health status assessment module is used to load the updated global model parameters into the local LSTM model of each intelligent optical fiber distribution device to evaluate the current health status of each intelligent optical fiber distribution device.

9. An electronic device, characterized in that: include: A processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus. When the machine-readable instructions are executed by the processor, the steps of the health analysis method of an intelligent optical fiber distribution device as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the health analysis method of an intelligent optical fiber distribution device according to any one of claims 1 to 7.

Images