Optical cable safety monitoring and early warning method and system based on data analysis

Abstract

The invention discloses an optical cable safety monitoring and early warning method and system based on data analysis, and relates to the technical field of optical cable monitoring, and the method comprises the following steps: S1, arranging a plurality of monitoring devices on an optical cable at intervals, and recording the length of the optical cable between two adjacent monitoring devices; s2, the monitoring devices are used for monitoring the optical cable in real time, monitoring information of all the monitoring devices is acquired and gathered, and the monitoring information is optical signals; according to the optical cable safety monitoring and early warning method and system based on data analysis, a monitoring device, an information classification module, an information prediction module, a monitoring device, a map module and a communication module are arranged, monitoring information is classified according to the influence of analysis temperature and humidity on an optical cable, and the classified monitoring information is used for training prediction models respectively; and a plurality of prediction models are obtained to analyze and predict the monitoring information under different temperature and humidity conditions, so that the prediction precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of optical cable monitoring, and in particular to an optical cable safety monitoring and early warning method and system based on data analysis. Background Art

[0002] As a new generation of optical cable alarm monitoring system, the optical cable monitoring system can give timely alarms before transmission failures occur, analyze the cause of the failure in time when a failure occurs (transmission network or transmission equipment), and accurately locate the distance to the fault point, thus improving the time for rapid repairs.

[0003] The invention patent with the publication number CN116405107A discloses an optical cable online monitoring fault location system, which belongs to the field of optical cable monitoring technology. The system includes a cable information acquisition module and an optical cable resource management subsystem; the optical cable information acquisition module collects the signal data of each section of optical cable through an optical time domain reflectometer and an optical power meter, and provides it to the optical cable resource management subsystem; the optical cable signal fault analysis module analyzes and determines whether an optical cable fault occurs according to the optical cable signal data, and records the location of the optical cable section; the fault display module displays the location of the faulty optical cable through a GIS map; the operation and maintenance dispatching module notifies the operation and maintenance personnel to repair the faulty optical cable; the optical cable degradation early warning module analyzes the real-time collected optical cable signal data according to the historical optical cable signal data in the database, determines whether there is a tendency of optical cable fault, and performs degradation early warning for optical cables with a tendency of fault. The present invention realizes the signal acquisition of online business optical fibers and redundant optical fibers, timely discovers faults, and gives early warnings of faults.

[0004] However, in the actual monitoring process, if the optical cable covers a large area, the temperature, humidity and other environmental conditions of the optical cable at different locations may be different. These different environmental conditions will cause some basic parameters of the optical cable to change, thereby affecting the refraction of light in the optical cable and the changes in external conditions of the optical cable, resulting in certain errors in the measured data, affecting the accuracy of monitoring and early warning. Summary of the invention

[0005] The purpose of the present invention is to provide a data analysis-based optical cable safety monitoring and early warning method and system to solve the above-mentioned deficiencies in the prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solution: an optical cable safety monitoring and early warning method based on data analysis, comprising the following steps:

[0007] S1. Install several monitoring devices on the optical cable at intervals and record the length of the optical cable between two adjacent monitoring devices;

[0008] S2. Use a monitoring device to monitor the optical cable in real time, and obtain and summarize monitoring information of each monitoring device, where the monitoring information is an optical signal;

[0009] S3, extracting temperature and humidity from the monitoring information, and classifying the monitoring information according to the difference in temperature and humidity in the monitoring information;

[0010] S4. Establish an analysis and prediction model, and use different types of monitoring information to train the analysis and prediction model;

[0011] S5, inputting the monitoring information into the analysis and prediction model trained in the corresponding category to predict the state of the optical cable;

[0012] S6. Establish a map model of the optical cable line, mark the locations of the optical cables predicted to have abnormalities in the map model, and issue an early warning to the staff;

[0013] S7. Monitoring devices are installed along the optical fiber line, and monitoring videos of the monitoring devices at corresponding locations are retrieved according to the locations of optical cables predicted to have abnormalities marked on the map model.

[0014] Furthermore, in step S3, the monitoring information is classified into:

[0015] a1. Customize multiple continuous temperature intervals and humidity intervals;

[0016] a2. Classify the monitoring information of the same temperature range into the same major category, and then classify the monitoring information of the same humidity range in the same major category into the same minor category.

[0017] Furthermore, after the monitoring information is classified in step S3, the optical cables are tested and analyzed, and the categories are reclassified according to the analysis results, which specifically includes the following steps:

[0018] b1. Select monitoring information of the optical cable subjected to the same external factors, filter out the temperature and humidity information in each sub-category of monitoring information to obtain characteristic information, analyze the characteristic information of each sub-category, and calculate the similarity of the characteristic information of each sub-category in the same category;

[0019] b2. If the similarity of feature information of adjacent subcategories reaches the preset similarity standard, they are merged and updated into the same subcategory;

[0020] b3. If the humidity ranges of the subcategories in the adjacent categories are the same, the feature information of the subcategories in the adjacent categories with the same humidity ranges is analyzed and the similarity is calculated;

[0021] b4. If the similarity of the feature information of subcategories with the same humidity range in adjacent major categories reaches the similarity standard, the adjacent major categories are merged and updated into the same major category.

[0022] Furthermore, when establishing the analysis and prediction model in step S4, the recurrent neural network algorithm is selected, tanh and softmax are selected as activation functions, and the cross entropy loss function is selected as the loss function.

[0023] Furthermore, the training of the analysis prediction model in step S4 specifically includes the following steps:

[0024] c1. Collect and monitor the external factors corresponding to the information, and the impact of the external factors on the optical cable;

[0025] c2. Preprocess the monitoring information, input the preprocessed monitoring information into a recurrent neural network algorithm to obtain a corresponding output, and associate the external factors corresponding to the input monitoring information and the impact of the external factors on the optical cable as labels with the corresponding output;

[0026] c3. Taking the preprocessed monitoring information, the corresponding output and its associated labels as samples, and randomly dividing the samples into a training set and a test set;

[0027] c4. Use the training set to train the recurrent neural network algorithm to obtain the algorithm parameters that minimize the loss function;

[0028] c5. Use the test set to test the accuracy of the algorithm. If the algorithm is qualified, use the obtained parameters to update the algorithm; if it is not qualified, return to c4.

[0029] Furthermore, the specific steps of step S6 are:

[0030] d1. Import the electronic map of the area where the optical cable route is located;

[0031] d2. Draw the location of the optical cable and the monitoring device on the electronic map;

[0032] d3. When an abnormal optical cable state is predicted, obtain the monitoring device from which the monitoring information corresponding to the abnormal optical cable state comes, and mark the location of the monitoring device on the electronic map.

[0033] Furthermore, after marking the location of the monitoring device on the map in step d3, the monitoring device is used to measure the distance between the location of the optical cable anomaly and the monitoring device, and the location of the optical cable anomaly is marked on the electronic map.

[0034] An optical cable safety monitoring and early warning system based on data analysis, comprising a monitoring device, an information classification module, an information prediction module, a monitoring device, a map module, and a communication module;

[0035] The monitoring device is used to monitor the optical signal of the optical cable;

[0036] The information classification module is used to classify the monitoring information;

[0037] The information prediction module is used to establish and train the analysis prediction model, and predict the state of the optical cable;

[0038] The monitoring module is used to monitor the area along the optical cable line;

[0039] The map module is used to display the map model and abnormal information of the optical cable line;

[0040] The communication module is used to send abnormal information to the user.

[0041] Compared with the prior art, the present invention provides a method and system for optical cable safety monitoring and early warning based on data analysis. By setting a monitoring device, an information classification module, an information prediction module, a monitoring device, a map module, and a communication module, and analyzing the influence of temperature and humidity on the optical cable, the monitoring information is classified, and the prediction models are trained respectively using the classified monitoring information to obtain multiple prediction models to analyze and predict the monitoring information under different temperature and humidity conditions, thereby improving the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0043] Figure 1 A method step diagram provided for an embodiment of the present invention;

[0044] Figure 2 A system structure block diagram provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0046] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0047] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0048] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0049] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0050] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0051] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0052] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of idealized schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.

[0053] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0054] See also Figure 1 , an optical cable safety monitoring and early warning method based on data analysis, comprising the following steps:

[0055] S1. Install several monitoring devices on the optical cable at intervals and record the length of the optical cable between two adjacent monitoring devices;

[0056] S2. Use a monitoring device to monitor the optical cable in real time, and obtain and summarize monitoring information of each monitoring device, where the monitoring information is an optical signal;

[0057] S3. Extracting temperature and humidity from the monitoring information, and classifying the monitoring information according to the difference in temperature and humidity in the monitoring information; the classification of the monitoring information specifically includes:

[0058] a1. Customize and set multiple continuous temperature intervals and multiple humidity intervals; preferably, the length of the temperature interval is 1-5 degrees Celsius, and the length of the humidity interval is 2-5%.

[0059] a2. Classify the monitoring information of the same temperature range into the same major category, and then classify the monitoring information of the same humidity range in the same major category into the same minor category.

[0060] After the monitoring information is classified, the optical cables are tested and analyzed, and the categories are reclassified according to the analysis results, which specifically includes the following steps:

[0061] b1. Select monitoring information of the optical cable subjected to the same external factors, filter out the temperature and humidity information in each sub-category of monitoring information to obtain characteristic information, analyze each sub-category of characteristic information, and calculate the similarity of each sub-category of characteristic information in the same category;

[0062] b2. If the similarity of feature information of adjacent subcategories reaches a preset similarity standard, they are merged and updated into the same subcategory. The similarity standard can be obtained through industry standards. Preferably, the similarity standard is 98.0%-99.5%;

[0063] b3. If the humidity ranges of the subcategories in the adjacent categories are the same, the feature information of the subcategories in the adjacent categories with the same humidity ranges is analyzed and the similarity is calculated;

[0064] b4. If the similarity of feature information of subcategories with the same humidity range in adjacent major categories reaches the similarity standard, the adjacent major categories will be merged and updated into the same major category.

[0065] S4. Establish an analysis and prediction model, and use different categories of monitoring information to train the analysis and prediction model respectively; when establishing the analysis and prediction model, select the recurrent neural network algorithm, select tanh and softmax as activation functions, and select the cross entropy loss function as the loss function.

[0066] The training of the analytical prediction model includes the following steps:

[0067] c1. Collect and monitor the external factors corresponding to the information, and the impact of the external factors on the optical cable;

[0068] c2. Preprocess the monitoring information, input the preprocessed monitoring information into the recurrent neural network algorithm to obtain the corresponding output, and associate the external factors corresponding to the input monitoring information and the impact of the external factors on the optical cable as labels with the corresponding output;

[0069] c3. Take the preprocessed monitoring information, the corresponding output and its associated labels as samples, and randomly divide the samples into training sets and test sets;

[0070] c4. Use the training set to train the recurrent neural network algorithm to obtain the algorithm parameters that minimize the loss function;

[0071] c5. Use the test set to test the accuracy of the algorithm. If the algorithm is qualified, use the obtained parameters to update the algorithm; if it is not qualified, return to c4.

[0072] S5, inputting the monitoring information into the analysis and prediction model trained in the corresponding category to predict the state of the optical cable;

[0073] S6. Establish a map model of the optical cable line, mark the optical cable locations predicted to be abnormal in the map model, and issue an early warning to the staff; the specific steps of establishing the map model of the optical cable line are:

[0074] d1. Import the electronic map of the area where the optical cable route is located. The electronic map of the area where the optical cable route is located can be obtained through the Internet and imported into the map module;

[0075] d2. Draw the location of the optical cable and the location of the monitoring device on the electronic map. Preferably, the optical cable is displayed on the map in the form of a thick line, and the monitoring device is displayed on the map in the form of a node;

[0076] d3. When an abnormal optical cable status is predicted, obtain the monitoring device from which the monitoring information corresponding to the abnormal optical cable status comes, and mark the location of the monitoring device on the electronic map. Preferably, the monitoring device from which the monitoring information corresponding to the abnormal optical cable status comes changes to red and becomes bold and flashes.

[0077] Preferably, after marking the location of the monitoring device on the map in step d3, the monitoring device is used to measure the distance of the abnormal optical cable location from the monitoring device, and the abnormal optical cable location is marked on the electronic map. Preferably, the abnormal optical cable location is changed to red and bolded and flashing.

[0078] S7. Monitoring devices are installed along the optical fiber line, and monitoring videos of the monitoring devices at corresponding locations are retrieved according to the locations of optical cables predicted to have abnormalities marked on the map model.

[0079] Please refer to Figure 2 , the present invention also provides an optical cable safety monitoring and early warning system based on data analysis, including a monitoring device, an information classification module, an information prediction module, a monitoring device, a map module, and a communication module;

[0080] The monitoring device is used to monitor the optical signal of the optical cable. The monitoring device can adopt an optical time domain reflectometer, which can monitor the fault position of the optical cable through its own function. The monitoring device also includes an FBG temperature sensor and an FBG humidity sensor, and the two sensors are connected in series. When the ambient temperature of the two sensors is the same, the wavelength drift caused by the temperature change is completely determined by the temperature sensitivity coefficient. When the temperature sensitivity coefficient is known, the wavelength drift of the humidity sensor caused by the ambient temperature change can be eliminated, thereby accurately measuring the humidity; and the monitoring devices are connected to the information classification module to send the monitored information to the information classification module.

[0081] The information classification module is used to classify monitoring information;

[0082] The information prediction module is used to establish and train the analysis prediction model and predict the status of the optical cable;

[0083] The monitoring module is used to monitor the area along the optical cable line, and the monitoring module includes a camera and a display device. The user can connect to the display device through the communication module to view the monitoring;

[0084] The map module is used to display the map model and abnormal information of the optical cable line;

[0085] The communication module is used to send abnormal information to the user.

[0086] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An optical cable safety monitoring and early warning method based on data analysis, characterized in that: The following steps are involved: S1. Install several monitoring devices on the optical cable at intervals and record the length of the optical cable between two adjacent monitoring devices; S2. Use a monitoring device to monitor the optical cable in real time, and obtain and summarize monitoring information of each monitoring device, where the monitoring information is an optical signal; S3, extracting temperature and humidity from the monitoring information, and classifying the monitoring information according to the difference in temperature and humidity in the monitoring information; S4. Establish an analysis and prediction model, and use different types of monitoring information to train the analysis and prediction model; S5, inputting the monitoring information into the analysis and prediction model trained for the corresponding category to predict the state of the optical cable; S6. Establish a map model of the optical cable line, mark the locations of the optical cables predicted to have abnormalities in the map model, and issue an early warning to the staff; S7. Monitoring devices are installed along the optical fiber line, and monitoring videos of the monitoring devices at corresponding locations are retrieved according to the locations of optical cables predicted to have abnormalities marked on the map model.

2. The optical cable safety monitoring and early warning method based on data analysis according to claim 1 is characterized in that: In step S3, the monitoring information is classified into: a1. Customize multiple continuous temperature intervals and humidity intervals; a2. Classify the monitoring information of the same temperature range into the same major category, and then classify the monitoring information of the same humidity range in the same major category into the same minor category.

3. The optical cable safety monitoring and early warning method based on data analysis according to claim 2 is characterized in that: After the monitoring information is classified in step S3, the optical cable is tested and analyzed, and the categories are reclassified according to the analysis results, which specifically includes the following steps: b1. Select monitoring information of the optical cable subjected to the same external factors, filter out the temperature and humidity information in each sub-category of monitoring information to obtain characteristic information, analyze the characteristic information of each sub-category, and calculate the similarity of the characteristic information of each sub-category in the same category; b2. If the similarity of feature information of adjacent subcategories reaches the preset similarity standard, they are merged and updated into the same subcategory; b3. If the humidity ranges of the subcategories in the adjacent categories are the same, the feature information of the subcategories in the adjacent categories with the same humidity ranges is analyzed and the similarity is calculated; b4. If the similarity of the feature information of subcategories with the same humidity range in adjacent major categories reaches the similarity standard, the adjacent major categories are merged and updated into the same major category.

4. The optical cable safety monitoring and early warning method based on data analysis according to claim 1 is characterized in that: When establishing the analysis and prediction model in step S4, select the recurrent neural network algorithm, select tanh and softmax as the activation function, and select the cross entropy loss function as the loss function.

5. The optical cable safety monitoring and early warning method based on data analysis according to claim 4 is characterized in that: The training of the analysis prediction model in step S4 specifically includes the following steps: c1. Collect and monitor the external factors corresponding to the information, and the impact of the external factors on the optical cable; c2. Preprocess the monitoring information, input the preprocessed monitoring information into a recurrent neural network algorithm to obtain a corresponding output, and associate the external factors corresponding to the input monitoring information and the impact of the external factors on the optical cable as labels with the corresponding output; c3. Taking the preprocessed monitoring information, the corresponding output and its associated labels as samples, and randomly dividing the samples into a training set and a test set; c4. Use the training set to train the recurrent neural network algorithm to obtain the algorithm parameters that minimize the loss function; c5. Use the test set to test the accuracy of the algorithm. If the algorithm is qualified, use the obtained parameters to update the algorithm; if it is not qualified, return to c4.

6. The optical cable safety monitoring and early warning method based on data analysis according to claim 1 is characterized in that: The specific steps of establishing the map model of the optical cable line in step S6 are: d1. Import the electronic map of the area where the optical cable route is located; d2. Draw the location of the optical cable and the monitoring device on the electronic map; d3. When an abnormal optical cable state is predicted, obtain the monitoring device from which the monitoring information corresponding to the abnormal optical cable state comes, and mark the location of the monitoring device on the electronic map.

7. The optical cable safety monitoring and early warning method based on data analysis according to claim 6 is characterized in that: In step d3, after marking the location of the monitoring device on the map, the monitoring device is used to measure the distance from the location of the optical cable anomaly to the monitoring device, and the location of the optical cable anomaly is marked on the electronic map.

8. An optical cable safety monitoring and early warning system based on data analysis, applicable to an optical cable safety monitoring and early warning method based on data analysis according to any one of claims 1 to 7, characterized in that: It includes a monitoring device, an information classification module, an information prediction module, a surveillance device, a map module, and a communication module; The monitoring device is used to monitor the optical signal of the optical cable; The information classification module is used to classify the monitoring information; The information prediction module is used to establish and train the analysis prediction model, and predict the state of the optical cable; The monitoring module is used to monitor the area along the optical cable line; The map module is used to display the map model and abnormal information of the optical cable line; The communication module is used to send abnormal information to the user.

Images