An intelligent assessment method for online operation and maintenance status of optical cables

Abstract

An intelligent evaluation method for online operation and maintenance status of an optical cable relates to the technical field of data processing. The method comprises the following steps: obtaining physical parameters along an optical cable, performing statistical analysis on the physical parameters, and obtaining stability coefficients of the physical parameters along the optical cable; constructing an interval distance comparison table, and deploying Internet of Things monitoring nodes along the optical cable according to the stability coefficients of the physical parameters along the optical cable and the interval distance comparison table; performing real-time monitoring on the physical parameters and network performance indicators along the optical cable, generating abnormal alarm signals or performing situation analysis along the optical cable according to the monitoring results; when performing situation analysis along the optical cable, performing feature extraction on the physical parameters and network performance indicators within a historical collection period along the optical cable in advance, constructing a state prediction model according to the feature extraction results, performing prediction marking on the current collection period according to the state prediction model, and performing early detection on the optical cable according to the prediction marking results, thereby significantly improving the safety and reliability of the optical cable network.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent evaluation method for online operation and maintenance status of optical cables. Background Art

[0002] CN114826389B "A method and system for evaluating the safety level of an optical cable line" includes a safety level evaluation when the line is interrupted and a safety level evaluation when the line is lost; the safety level evaluation when the line is interrupted is to take the line interruption in a protection channel of a certain line segment as one level, and to take the interruption of both the working channel and the protection channel of a certain line segment as one level; the safety level evaluation process when the line is lost is to determine the current working channel of the entire network line segment in real time according to the alarm status of the OLP board, and then calculate the loss amount according to the specific channel where the line loss occurs, and then evaluate based on the availability of the line channel where the loss occurs, the performance of the line board on the corresponding loop when the loss occurs, and the OSNR value of the relevant channel.

[0003] CN117408544A "A method for evaluating and analyzing the entire life cycle of optical cables" tracks changes in core quality and calculates the cable quality score in the optical cable quality assessment by counting the core quality and calculating the core quality score. In the optical cable archive assessment, archive management is performed based on the year of the optical cable and the archive score is calculated. In the optical cable status assessment, the status of the optical cable is graded according to the level of the service it carries and the status score is calculated. In the optical cable operation and maintenance assessment, statistics are taken on the number of splicing times, number of failures, monitoring time, inspection frequency and other data, and the operation and maintenance score is calculated. The scores of each item are weighted averaged according to the weight to obtain the entire life cycle score of a single optical cable.

[0004] With the development of information technology, optical cables, as an important carrier of information transmission, have been widely used around the world. However, due to environmental factors (such as temperature changes) and mechanical stress, optical cables may have various faults that affect their normal operation. Existing optical cable maintenance methods mostly rely on regular inspections or post-event repairs, lacking effective preventive measures. Therefore, it is particularly important to develop an intelligent evaluation system that can monitor the health of optical cables in real time and respond quickly to potential problems. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide an intelligent evaluation method for online operation and maintenance of optical cables, comprising the following steps:

[0006] Step s1: Obtain the physical parameters along the optical cable and mark the acquisition time, set the acquisition cycle, perform statistical analysis on the physical parameters, and obtain the stability coefficient of the physical parameters along the optical cable;

[0007] Step s2: construct an interval distance comparison table, and deploy IoT monitoring nodes along the optical cable according to the stability coefficient of the physical parameters along the optical cable and the interval distance comparison table;

[0008] Step s3: real-time monitoring of physical parameters and network performance indicators along the optical cable, generating abnormal alarm signals or performing situation analysis along the optical cable according to the monitoring results;

[0009] Step s4: When conducting a situation analysis along the optical cable, perform feature extraction on the physical parameters and network performance indicators in the historical collection period along the optical cable in advance, build a state prediction model based on the feature extraction results, make a prediction mark on the current collection period based on the state prediction model, and conduct advance detection along the optical cable based on the prediction marking results.

[0010] Furthermore, the physical parameters along the optical cable are obtained, and statistical analysis is performed on the physical parameters to obtain the stability coefficient of the physical parameters along the optical cable. The process includes:

[0011] Use distributed fiber optic sensing technology to obtain physical parameters along the optical cable;

[0012] Performing statistical analysis on the physical parameters along the optical cable in several historical collection periods, obtaining the numerical average amplitude of the physical parameters along the optical cable in several historical collection periods, and the frequency at which the physical parameters are within the corresponding standard threshold range;

[0013] The stability coefficient of the physical parameter is obtained according to the average amplitude of the numerical value of the physical parameter and the frequency at which the physical parameter is within the corresponding standard threshold range.

[0014] Furthermore, according to the stability coefficient and spacing distance comparison table of the physical parameters along the optical cable, the process of deploying the Internet of Things monitoring nodes along the optical cable includes:

[0015] Constructing an interval distance comparison table, the interval distance comparison table includes average bit error rates corresponding to different stability coefficients and interval distances, and obtaining average bit error rates corresponding to different interval distances according to the stability coefficient along the optical cable and the interval distance comparison table;

[0016] The upper limit of the bit error rate of the optical cable is obtained, and the interval distance corresponding to the average bit error rate less than the upper limit of the bit error rate is screened out; the interval distance of the Internet of Things monitoring nodes along the optical cable is determined according to the interval distance; and the Internet of Things monitoring points are set along the optical cable. The Internet of Things monitoring points are used to collect network performance indicators of the optical cable and mark the collection time. The network performance indicators include bit error rate and throughput of different signal frequencies.

[0017] Furthermore, the process of constructing the interval distance comparison table includes:

[0018] Preset a stability coefficient threshold range and an interval distance threshold range, generate a number of simulated optical cables with different stability coefficients within the stability coefficient threshold range, and mark the interval distances of the simulated optical cables with different stability coefficients within the interval distance threshold range, set IoT monitoring points according to the interval distances, and generate a number of simulated optical cables with different stability coefficients under different interval distance conditions;

[0019] Generate an analog baseband signal, transmit the analog baseband signal through analog optical cables with different stability coefficients under several different spacing distances, collect an average bit error rate through the Internet of Things monitoring points of the analog optical cables, associate the average bit error rate with the stability coefficient and spacing distance corresponding to the analog optical cables, obtain the average bit error rate corresponding to the analog baseband signal under different stability coefficients and spacing distances, construct an spacing distance comparison table, and store the average bit error rates corresponding to different stability coefficients and spacing distances in the spacing distance comparison table.

[0020] Furthermore, the process of real-time monitoring of physical parameters and network performance indicators along the optical cable and generating abnormal alarm signals or performing situation analysis along the optical cable according to the monitoring results includes:

[0021] Obtain the physical parameters and network performance indicators along the optical cable in the current collection cycle, compare the physical parameters along the optical cable with the preset physical parameter qualified threshold interval, and generate an external abnormal alarm signal along the optical cable if there is a physical parameter that is not within the physical parameter qualified threshold interval;

[0022] If the physical parameters are all within the qualified threshold interval of the physical parameters, the compensation parameters of the network performance indicators under different physical parameters are obtained, the compensation parameters of the network performance indicators are extracted according to the physical parameters along the optical cable in the current collection period, the network performance indicators are compensated and adjusted according to the compensation parameters, the network performance indicators after the compensation adjustment are compared with the preset qualified threshold interval of the network performance indicators, and the cumulative time during which the network performance indicators after the compensation adjustment are not within the qualified threshold interval of the network performance indicators is obtained, and the cumulative time is compared with the preset cumulative time threshold. If the cumulative time is less than or equal to the cumulative time threshold, a situation analysis is performed along the optical cable. If the cumulative time is greater than the cumulative time threshold, an abnormal network performance alarm signal along the optical cable is generated.

[0023] Furthermore, the process of pre-extracting features of physical parameters and network performance indicators in the historical collection period along the optical cable includes:

[0024] Marking several historical collection periods, marking a historical collection period that generates abnormal network performance indicator signals as an abnormal historical collection period, and marking a historical collection period that does not generate abnormal network performance indicator signals as a normal historical collection period;

[0025] Extract the numerical time series sequences of physical parameters and network performance indicators along the optical cable in several normal historical collection cycles and abnormal historical collection cycles, perform feature extraction on the numerical time series sequences of physical parameters and network performance indicators along the optical cable, and obtain key features in several normal historical collection cycles and key features in abnormal historical collection cycles, wherein the key features include the fluctuation coefficient of the physical parameters, the fluctuation coefficient of the network performance indicators, the correlation coefficient between the physical parameters and the network performance indicators, the correlation coefficient of the bit error rate between different signal frequencies, and the correlation coefficient of the throughput between different signal frequencies.

[0026] Furthermore, a state prediction model is constructed according to the feature extraction result, and a process of predicting and marking the current acquisition cycle according to the state prediction model includes:

[0027] Construct a state prediction model based on deep learning, use key features in a number of normal historical acquisition cycles and key features in an abnormal historical acquisition cycle as a training set and a test set, input the training set into the state prediction model for training until the loss function training is stable, save the model parameters, test the state prediction model with the test set until it meets the preset requirements, and output the state prediction model;

[0028] Feature extraction is performed on the numerical time series of physical parameters along the optical cable and the numerical time series of network performance indicators in the current collection cycle to obtain key features, and the key features are input into the state prediction model. The current collection cycle is estimated and marked according to the state prediction model, and the current collection cycle is marked as an estimated normal collection cycle or an estimated abnormal collection cycle.

[0029] Furthermore, the process of performing early detection along the optical cable according to the estimated marking result includes:

[0030] If the current collection period is marked as an estimated abnormal collection period, the fluctuation coefficients of the physical parameters along the optical cable and the fluctuation coefficients of the network performance indicators are used as evaluation indicators, the indicator weights, membership functions and several vulnerability levels of the evaluation indicators are preset, and the membership matrix of the evaluation indicators along the optical cable for several vulnerability levels is obtained through fuzzy comprehensive evaluation;

[0031] The vulnerability level of the evaluation indicator is obtained according to the membership matrix and the indicator weight, the vulnerability level of the evaluation indicator is compared with the preset vulnerability level threshold, the evaluation indicator with a vulnerability level greater than the vulnerability level threshold is screened out, the evaluation indicator is marked as a key evaluation indicator, and the key evaluation indicators are sorted according to their vulnerability levels. The higher the vulnerability level, the higher the ranking. According to the sorting results, the optical cables to which the key evaluation indicators belong are selected in turn for early detection.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. Improve the safety and reliability of the optical cable network. Traditional optical cable maintenance methods rely on regular inspections or post-event repairs, lacking effective preventive measures. The present invention introduces distributed optical fiber sensing technology and Internet of Things monitoring nodes to obtain physical parameters and network performance indicators along the optical cable in real time, and analyze and warn them. This not only improves the fault response speed, but also enables action to be taken before potential problems develop into serious faults, thereby greatly improving the safety and reliability of the optical cable network.

[0034] 2. Optimize resource allocation and reduce costs. By calculating the stability coefficient of physical parameters along the optical cable and using the interval distance comparison table, the present invention can scientifically and rationally determine the optimal deployment location of the IoT monitoring node, avoiding unnecessary equipment deployment and reducing construction and operation costs. At the same time, the state prediction model built based on historical data can help operators identify areas that need to be focused on in advance, concentrate resources for maintenance, and further save manpower and material resources.

[0035] 3. Realize intelligent operation and maintenance management. The present invention uses deep learning algorithms to build a state prediction model, which can automatically extract features and learn rules from a large amount of historical data, and provide accurate and reliable predictions for future optical cable operation conditions. This method not only reduces the need for human intervention, but also improves decision-making efficiency, allowing optical cable operation and maintenance to shift from passive response to active prevention, truly realizing intelligent management. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a schematic diagram of an intelligent assessment method for online operation and maintenance status of optical cables according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0038] like Figure 1 As shown, a method for intelligently evaluating the online operation and maintenance status of an optical cable comprises the following steps:

[0039] Step s1: Obtain the physical parameters along the optical cable and mark the acquisition time, set the acquisition cycle, perform statistical analysis on the physical parameters, and obtain the stability coefficient of the physical parameters along the optical cable;

[0040] Step s2: construct an interval distance comparison table, and deploy IoT monitoring nodes along the optical cable according to the stability coefficient of the physical parameters along the optical cable and the interval distance comparison table;

[0041] Step s3: real-time monitoring of physical parameters and network performance indicators along the optical cable, generating abnormal alarm signals or performing situation analysis along the optical cable according to the monitoring results;

[0042] Step s4: When conducting a situation analysis along the optical cable, perform feature extraction on the physical parameters and network performance indicators in the historical collection period along the optical cable in advance, build a state prediction model based on the feature extraction results, make a prediction mark on the current collection period based on the state prediction model, and conduct advance detection along the optical cable based on the prediction marking results.

[0043] It should be further explained that, in the specific implementation process, the physical parameters along the optical cable are obtained, and statistical analysis is performed on the physical parameters to obtain the stability coefficient of the physical parameters along the optical cable. The process includes:

[0044] Using distributed optical fiber sensing technology to obtain physical parameters along the optical cable, the physical parameters include temperature and stress;

[0045] Performing statistical analysis on the physical parameters along the optical cable in several historical collection periods, obtaining the numerical average amplitude of the physical parameters along the optical cable in several historical collection periods, and the frequency at which the physical parameters are within the corresponding standard threshold range;

[0046] Obtaining a stability coefficient of the physical parameter according to an average amplitude of the numerical value of the physical parameter and a frequency at which the physical parameter is within a corresponding standard threshold range;

[0047] The calculation formula for obtaining the stability coefficient is:

[0048] ;

[0049] in, represents the stability coefficient, Indicates the average amplitude of the value, Indicates frequency, , Represents the weight factor.

[0050] It should be further explained that, in the specific implementation process, according to the stability coefficient and spacing distance comparison table of the physical parameters along the optical cable, the process of deploying the Internet of Things monitoring nodes along the optical cable includes:

[0051] Constructing an interval distance comparison table, the interval distance comparison table includes average bit error rates corresponding to different stability coefficients and interval distances, and obtaining average bit error rates corresponding to different interval distances according to the stability coefficient along the optical cable and the interval distance comparison table;

[0052] The upper limit of the bit error rate of the optical cable is obtained, and the interval distance corresponding to the average bit error rate less than the upper limit of the bit error rate is screened out; the interval distance of the Internet of Things monitoring nodes along the optical cable is determined according to the interval distance; and the Internet of Things monitoring points are set along the optical cable. The Internet of Things monitoring points are used to collect network performance indicators of the optical cable and mark the collection time. The network performance indicators include bit error rate and throughput of different signal frequencies.

[0053] It should be further explained that, in the specific implementation process, the process of constructing the interval distance comparison table includes:

[0054] Preset a stability coefficient threshold range and an interval distance threshold range, generate a number of simulated optical cables with different stability coefficients within the stability coefficient threshold range, and mark the interval distances of the simulated optical cables with different stability coefficients within the interval distance threshold range, set IoT monitoring points according to the interval distances, and generate a number of simulated optical cables with different stability coefficients under different interval distance conditions;

[0055] Generate an analog baseband signal, transmit the analog baseband signal through analog optical cables with different stability coefficients under several different spacing distances, collect an average bit error rate (i.e., the average bit error rate of different signal frequencies) through the Internet of Things monitoring points of the analog optical cables, associate the average bit error rate with the stability coefficient and spacing distance corresponding to the analog optical cables, obtain the average bit error rate of the analog baseband signal under different stability coefficients and spacing distances, construct an spacing distance comparison table, and store the average bit error rates under different stability coefficients and spacing distances in the spacing distance comparison table.

[0056] It should be further explained that, in the specific implementation process, the physical parameters and network performance indicators along the optical cable are monitored in real time, and the process of generating abnormal alarm signals or performing situation analysis along the optical cable according to the monitoring results includes:

[0057] Obtain the physical parameters and network performance indicators along the optical cable in the current collection cycle, compare the physical parameters along the optical cable with the preset physical parameter qualified threshold interval, and generate an external abnormal alarm signal along the optical cable if there is a physical parameter that is not within the physical parameter qualified threshold interval;

[0058] If the physical parameters are all within the qualified threshold interval of the physical parameters, the compensation parameters of the network performance indicators under different physical parameters are obtained, the compensation parameters of the network performance indicators are extracted according to the physical parameters along the optical cable in the current collection period, the network performance indicators are compensated and adjusted according to the compensation parameters, the network performance indicators after the compensation adjustment are compared with the preset qualified threshold interval of the network performance indicators, and the cumulative time during which the network performance indicators after the compensation adjustment are not within the qualified threshold interval of the network performance indicators is obtained, and the cumulative time is compared with the preset cumulative time threshold. If the cumulative time is less than or equal to the cumulative time threshold, a situation analysis is performed along the optical cable. If the cumulative time is greater than the cumulative time threshold, an abnormal network performance alarm signal along the optical cable is generated.

[0059] It should be further explained that, in the specific implementation process, the process of obtaining the compensation parameters of the network performance indicators under different physical parameters includes:

[0060] Generate several simulated optical cables under different physical parameter conditions within the physical parameter qualified threshold range, generate simulated baseband signals, transmit the simulated baseband signals through the simulated optical cables under different physical parameter conditions, obtain network performance indicators corresponding to the simulated baseband signals under different physical parameter conditions, obtain standard physical parameters of the optical cable, obtain network performance indicators corresponding to the simulated optical cable under standard physical parameter conditions, mark the network performance indicators as standard network performance indicators, and set compensation parameters under different physical parameter conditions according to the deviations between the network performance indicators corresponding to the simulated baseband signals under different physical parameter conditions and the standard network performance indicators.

[0061] It should be further explained that, in the specific implementation process, the process of pre-extracting features of physical parameters and network performance indicators in the historical collection period along the optical cable includes:

[0062] Marking several historical collection periods, marking a historical collection period that generates abnormal network performance indicator signals as an abnormal historical collection period, and marking a historical collection period that does not generate abnormal network performance indicator signals as a normal historical collection period;

[0063] Extract numerical time series sequences of physical parameters along the optical cable within several normal historical collection cycles and abnormal historical collection cycles and numerical time series sequences of network performance indicators, perform feature extraction on the numerical time series sequences of physical parameters along the optical cable and the numerical time series sequences of network performance indicators, and obtain key features within several normal historical collection cycles and key features within abnormal historical collection cycles, wherein the key features include fluctuation coefficients of physical parameters, fluctuation coefficients of network performance indicators, correlation coefficients between physical parameters and network performance indicators (including correlation coefficients between physical parameters and bit error rates of different signal frequencies, correlation coefficients between physical parameters and throughputs of different signal frequencies), correlation coefficients between bit error rates of different signal frequencies, and correlation coefficients between throughputs of different signal frequencies.

[0064] It should be further explained that, in the specific implementation process, the calculation formula for obtaining the correlation coefficient between the physical parameters and the network performance indicators is:

[0065] ;

[0066] in, represents the correlation coefficient between physical parameter i and network performance index j, represents the value of physical parameter i at time t, It represents the average value of physical parameter i during the acquisition period. represents the value of network performance index j at the tth moment, It represents the numerical average value of network performance index j in the collection period, and n represents the total number of moments in the collection period;

[0067] The calculation formula for obtaining the fluctuation coefficient of the physical parameter is:

[0068] ;

[0069] in, Represents the coefficient of fluctuation of physical parameter i.

[0070] It should be further explained that, in the specific implementation process, a state prediction model is constructed according to the feature extraction result, and the process of predicting and marking the current acquisition cycle according to the state prediction model includes:

[0071] Construct a state prediction model based on deep learning, use key features in a number of normal historical acquisition cycles and key features in an abnormal historical acquisition cycle as a training set and a test set, input the training set into the state prediction model for training until the loss function training is stable, save the model parameters, test the state prediction model with the test set until it meets the preset requirements, and output the state prediction model;

[0072] Feature extraction is performed on the numerical time series of physical parameters along the optical cable and the numerical time series of network performance indicators in the current collection cycle to obtain key features, and the key features are input into the state prediction model. The current collection cycle is estimated and marked according to the state prediction model, and the current collection cycle is marked as an estimated normal collection cycle or an estimated abnormal collection cycle.

[0073] Building a state prediction model based on deep learning is a complex process, which involves multiple steps such as model selection, training, verification, and testing. The following is a detailed supplementary explanation of this process:

[0074] The present invention selects the long short-term memory network (LSTM) suitable for time series analysis as the deep learning architecture. After extracting key features, LSTM is used to model the time series characteristics. After determining the model architecture, the loss function is defined next. In the present invention, since the goal is to distinguish between qualified and abnormal collection cycles, the binary cross-entropy loss (Binary Cross-Entropy Loss) is selected as the optimization target, and then the prepared training set is input into the selected deep learning model to start training. During the training process, the weights are continuously updated by the back propagation algorithm, so that the loss function gradually decreases until a stable state is reached. During this period, the Early Stopping method and other techniques are used to avoid overfitting. In addition to the basic training process, various parameters of the model are tuned by Grid Search, and the parameters include learning rate, batch size, regularization coefficient, etc.

[0075] After the model training is completed and the parameters are adjusted, the final evaluation is performed through the test set to obtain the evaluation results of the model, which include classification indicators such as accuracy, recall, F1 score, etc. Based on the evaluation results on the test set, it is judged whether the model has reached the expected standards. If the requirements are met, the model parameters are saved and ready for deployment; if not ideal, it is necessary to return to a previous stage to re-examine issues such as data quality, model structure or training strategy.

[0076] It should be further explained that, in the specific implementation process, the process of conducting advance detection along the optical cable according to the estimated marking results includes:

[0077] If the current collection period is marked as an estimated abnormal collection period, the fluctuation coefficients of the physical parameters along the optical cable and the fluctuation coefficients of the network performance indicators are used as evaluation indicators, the indicator weights, membership functions and several vulnerability levels of the evaluation indicators are preset, and the membership matrix of the evaluation indicators along the optical cable for several vulnerability levels is obtained through fuzzy comprehensive evaluation;

[0078] The vulnerability level of the evaluation indicator is obtained according to the membership matrix and the indicator weight, the vulnerability level of the evaluation indicator is compared with the preset vulnerability level threshold, the evaluation indicator with a vulnerability level greater than the vulnerability level threshold is screened out, the evaluation indicator is marked as a key evaluation indicator, and the key evaluation indicators are sorted according to their vulnerability levels. The higher the vulnerability level, the higher the ranking. According to the sorting results, the optical cables to which the key evaluation indicators belong are selected in turn for early detection.

[0079] It should be further explained that, in the specific implementation process, the process of obtaining the vulnerability level of the evaluation index according to the membership matrix and the index weight includes:

[0080] The indicator weights and the membership matrix of the evaluation indicators are integrated through a formula to obtain a fuzzy comprehensive evaluation matrix of the evaluation indicators, the membership of the evaluation indicators for different vulnerability levels is obtained according to the fuzzy comprehensive evaluation matrix, the vulnerability level with the highest membership corresponding to the evaluation indicators is screened out, and the vulnerability level with the highest membership corresponding to the evaluation indicators is used as the vulnerability level of the evaluation indicators;

[0081] Wherein, the formula is:

[0082] ;

[0083] in, is the fuzzy comprehensive evaluation matrix of the evaluation index, is the indicator weight of the evaluation indicator, is the membership matrix, " represents the multiplication of the weight matrix of the evaluation index and the elements at the corresponding positions of the membership matrix, It is a weighted parameter for controlling the balance between the weight matrix and the membership matrix in the fuzzy comprehensive evaluation matrix of the evaluation index.

[0084] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent assessment method for online operation and maintenance of optical cables, characterized in that: The following steps are involved: Step s1: Obtain the physical parameters along the optical cable and mark the acquisition time, set the acquisition cycle, perform statistical analysis on the physical parameters, and obtain the stability coefficient of the physical parameters along the optical cable; Step s2: construct an interval distance comparison table, and deploy IoT monitoring nodes along the optical cable according to the stability coefficient of the physical parameters along the optical cable and the interval distance comparison table; Step s3: real-time monitoring of physical parameters and network performance indicators along the optical cable, generating abnormal alarm signals or performing situation analysis along the optical cable according to the monitoring results; Step s4: When performing situation analysis along the optical cable, perform feature extraction on the physical parameters and network performance indicators in the historical collection period along the optical cable in advance, build a state prediction model based on the feature extraction results, perform prediction marking on the current collection period based on the state prediction model, and perform advance detection along the optical cable based on the prediction marking results; The process of obtaining the physical parameters along the optical cable and performing statistical analysis on the physical parameters to obtain the stability coefficient of the physical parameters along the optical cable includes: Use distributed fiber optic sensing technology to obtain physical parameters along the optical cable; Performing statistical analysis on the physical parameters along the optical cable in several historical collection periods, obtaining the numerical average amplitude of the physical parameters along the optical cable in several historical collection periods, and the frequency at which the physical parameters are within the corresponding standard threshold range; Obtaining a stability coefficient of the physical parameter according to an average amplitude of the numerical value of the physical parameter and a frequency at which the physical parameter is within a corresponding standard threshold range; According to the stability coefficient and spacing distance comparison table of physical parameters along the optical cable, the process of deploying IoT monitoring nodes along the optical cable includes: Constructing an interval distance comparison table, the interval distance comparison table includes average bit error rates corresponding to different stability coefficients and interval distances, and obtaining average bit error rates corresponding to different interval distances according to the stability coefficient along the optical cable and the interval distance comparison table; Obtain the upper limit of the bit error rate of the optical cable, screen out the interval distance at which the corresponding average bit error rate is less than the upper limit of the bit error rate, determine the interval distance of the Internet of Things monitoring nodes along the optical cable according to the interval distance, set the Internet of Things monitoring points along the optical cable, and the Internet of Things monitoring points are used to collect network performance indicators of the optical cable and mark the collection time, wherein the network performance indicators include bit error rates and throughputs of different signal frequencies; The process of constructing the interval distance comparison table includes: Preset a stability coefficient threshold range and an interval distance threshold range, generate a number of simulated optical cables with different stability coefficients within the stability coefficient threshold range, and mark the interval distances of the simulated optical cables with different stability coefficients within the interval distance threshold range, set IoT monitoring points according to the interval distances, and generate a number of simulated optical cables with different stability coefficients under different interval distance conditions; Generate an analog baseband signal, transmit the analog baseband signal through analog optical cables with different stability coefficients under several different spacing distances, collect an average bit error rate through the Internet of Things monitoring points of the analog optical cables, associate the average bit error rate with the stability coefficient and spacing distance corresponding to the analog optical cables, obtain the average bit error rate corresponding to the analog baseband signal under different stability coefficients and spacing distances, construct an spacing distance comparison table, and store the average bit error rates corresponding to different stability coefficients and spacing distances in the spacing distance comparison table.

2. According to claim 1, a method for intelligently evaluating the online operation and maintenance status of optical cables is characterized in that: The process of real-time monitoring of the physical parameters and network performance indicators along the optical cable and generating abnormal alarm signals or performing situation analysis along the optical cable according to the monitoring results includes: Obtain the physical parameters and network performance indicators along the optical cable in the current collection cycle, compare the physical parameters along the optical cable with the preset physical parameter qualified threshold interval, and generate an external abnormal alarm signal along the optical cable if there is a physical parameter that is not within the physical parameter qualified threshold interval; If the physical parameters are all within the qualified threshold interval of the physical parameters, the compensation parameters of the network performance indicators under different physical parameters are obtained, the compensation parameters of the network performance indicators are extracted according to the physical parameters along the optical cable in the current collection period, the network performance indicators are compensated and adjusted according to the compensation parameters, the network performance indicators after the compensation adjustment are compared with the preset qualified threshold interval of the network performance indicators, and the cumulative time during which the network performance indicators after the compensation adjustment are not within the qualified threshold interval of the network performance indicators is obtained, and the cumulative time is compared with the preset cumulative time threshold. If the cumulative time is less than or equal to the cumulative time threshold, a situation analysis is performed along the optical cable. If the cumulative time is greater than the cumulative time threshold, an abnormal network performance alarm signal along the optical cable is generated.

3. According to claim 2, a method for intelligently evaluating the online operation and maintenance status of optical cables is characterized in that: The process of pre-feature extraction of physical parameters and network performance indicators along the optical cable during the historical collection period includes: Marking several historical collection periods, marking a historical collection period that generates abnormal network performance indicator signals as an abnormal historical collection period, and marking a historical collection period that does not generate abnormal network performance indicator signals as a normal historical collection period; Extract the numerical time series sequences of physical parameters and network performance indicators along the optical cable in several normal historical collection cycles and abnormal historical collection cycles, perform feature extraction on the numerical time series sequences of physical parameters and network performance indicators along the optical cable, and obtain key features in several normal historical collection cycles and key features in abnormal historical collection cycles, wherein the key features include the fluctuation coefficient of the physical parameters, the fluctuation coefficient of the network performance indicators, the correlation coefficient between the physical parameters and the network performance indicators, the correlation coefficient of the bit error rate between different signal frequencies, and the correlation coefficient of the throughput between different signal frequencies.

4. The method for intelligently evaluating the online operation and maintenance status of optical cables according to claim 3, characterized in that: The state prediction model is constructed based on the feature extraction results. The process of predicting and marking the current acquisition cycle based on the state prediction model includes: Construct a state prediction model based on deep learning, use key features in a number of normal historical acquisition cycles and key features in an abnormal historical acquisition cycle as a training set and a test set, input the training set into the state prediction model for training until the loss function training is stable, save the model parameters, test the state prediction model with the test set until it meets the preset requirements, and output the state prediction model; Feature extraction is performed on the numerical time series of physical parameters along the optical cable and the numerical time series of network performance indicators in the current collection cycle to obtain key features, and the key features are input into the state prediction model. The current collection cycle is estimated and marked according to the state prediction model, and the current collection cycle is marked as an estimated normal collection cycle or an estimated abnormal collection cycle.

5. The method for intelligently evaluating the online operation and maintenance status of optical cables according to claim 4, characterized in that: The process of early detection along the optical cable according to the estimated marking results includes: If the current collection period is marked as an estimated abnormal collection period, the fluctuation coefficients of the physical parameters along the optical cable and the fluctuation coefficients of the network performance indicators are used as evaluation indicators, the indicator weights, membership functions and several vulnerability levels of the evaluation indicators are preset, and the membership matrix of the evaluation indicators along the optical cable for several vulnerability levels is obtained through fuzzy comprehensive evaluation; The vulnerability level of the evaluation indicator is obtained according to the membership matrix and the indicator weight, the vulnerability level of the evaluation indicator is compared with the preset vulnerability level threshold, the evaluation indicator with a vulnerability level greater than the vulnerability level threshold is screened out, the evaluation indicator is marked as a key evaluation indicator, and the key evaluation indicators are sorted according to their vulnerability levels. The higher the vulnerability level, the higher the ranking. According to the sorting results, the optical cables to which the key evaluation indicators belong are selected in turn for early detection.

Images