Optical cable operation and maintenance system and method combined with optical cable invasion event feature analysis

Abstract

The invention discloses an optical cable operation and maintenance system and method combined with optical cable invasion event characteristic analysis, and relates to the field of optical cable operation and maintenance, and the method comprises the steps: setting corresponding monitoring equipment which is used for collecting the optical cable characteristic information of a to-be-monitored region; acquiring characteristic information of an optical cable invasion event and characteristic information of the optical cable in normal operation; extracting frequency domain information in the acquired optical cable feature information, and establishing an optical cable feature information frequency domain database; classifying and identifying optical cable features of the optical cable feature information frequency domain database; establishing an optical cable invasion judgment model, judging information of different clusters, judging whether the optical cable in the to-be-monitored area is invaded or not, and judging the invasion type; a ground monitoring platform is established, and monitoring, access and abnormity display are carried out on the optical cable in the to-be-monitored area through the Internet of Things technology. The method has the advantages that whether the optical cable in the to-be-monitored area is invaded or not and the invading type are effectively identified and judged, and the reliability and stability of operation and maintenance of the optical cable are improved.

Description

Technical Field

[0001] The present invention relates to the field of optical cable operation and maintenance, and in particular to an optical cable operation and maintenance system and method combined with optical cable intrusion event feature analysis. Background Art

[0002] With the development of the information age, the use of optical cable technology is an important means to ensure the stability and reliability of communication data transmission and to meet the demand for high-speed data transmission in the era of big data and cloud computing. Effectively identifying the characteristics of existing optical cable intrusion events, timely detecting optical cable intrusion events, and ensuring the normal operation of optical cables are important contents for maintaining communication networks. Existing optical cable intrusion events mainly include: man-made damage, construction damage, natural factors, and illegal occupation. These optical cable intrusion events can be confirmed and identified from characteristics such as vibration information, flow data, and natural environmental factors. Therefore, it is of great significance to analyze the optical cable operation information by combining the characteristics of optical cable intrusion events.

[0003] Existing optical cable operation and maintenance technologies mainly focus on real-time monitoring of key parameters such as temperature, humidity, tension, etc. of optical cables, and use electronic tag technology to monitor and analyze optical cables. However, this type of technology has a certain delay in optical cable monitoring and is unable to identify optical cable intrusion events. It lacks effective targeting to accurately respond to different optical cable intrusion events, which is not conducive to timely detection and response to optical cable intrusion events. It may cause optical cables to be damaged or dug up, thereby causing communication anomalies and operators facing huge economic losses. Summary of the invention

[0004] In order to solve the above technical problems, an optical cable operation and maintenance system and method combined with optical cable intrusion event feature analysis are provided. This technical solution solves the problems raised in the above background technology, but this type of technology has a certain delay in optical cable monitoring and is unable to identify optical cable intrusion events, lacks effective targeting to accurately respond to different optical cable intrusion events, is not conducive to timely detection and response to optical cable intrusion events, and may cause optical cables to be damaged or dug up, thereby causing communication anomalies and operators facing huge economic losses.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An optical cable operation and maintenance method combined with optical cable intrusion event feature analysis, characterized by comprising:

[0007] At appropriate locations in the area to be monitored, corresponding monitoring equipment is set up to collect optical cable characteristic information of the area to be monitored;

[0008] Based on historical data and big data analysis, obtain the characteristic information of optical cable intrusion events and the characteristic information of optical cable normal operation;

[0009] Based on the Fourier transform formula, the frequency domain information in the collected optical cable characteristic information is extracted and the frequency domain database of the optical cable characteristic information is established;

[0010] According to the K-means clustering algorithm model, the optical cable features in the frequency domain database of optical cable feature information are classified and identified;

[0011] Based on the DS evidence theory, an optical cable intrusion judgment model is established to judge the information of different clusters, determine whether the optical cable in the monitored area is intruded, and determine the type of intrusion;

[0012] A ground monitoring platform is established to monitor, access and display abnormalities of optical cables in the monitored area through Internet of Things technology.

[0013] Preferably, the acquisition of characteristic information of optical cable intrusion events and characteristic information of normal operation of optical cables based on historical data and big data analysis specifically includes:

[0014] Based on historical data and big data analysis, the characteristic information of optical cable intrusion events is obtained, and a characteristic sample set of optical cable intrusion events is established;

[0015] According to the monitoring equipment, the optical cable information of the area to be monitored is obtained, the characteristic information of the optical cable during normal operation is extracted, and a sample set of the normal operation characteristics of the optical cable is established;

[0016] The optical cable characteristic information mainly includes: vibration signals, flow data and natural environment factor information.

[0017] Preferably, the extracting and collecting frequency domain information from the optical cable characteristic information based on the Fourier transform formula and establishing the frequency domain database of the optical cable characteristic information specifically includes:

[0018] According to the characteristic sample set of the optical cable intrusion event and the characteristic sample set of the optical cable normal operation, the data is standardized and preliminarily filtered;

[0019] The processed optical cable characteristic information data is converted into frequency domain using the Fourier transform formula, and the frequency domain information in the collected optical cable characteristic information is extracted;

[0020] According to the frequency domain information in the optical cable characteristic information, the waveform, amplitude and frequency information of the optical cable characteristic information are obtained, and the information is marked and classified;

[0021] According to the marked and classified optical cable characteristic information, an optical cable characteristic information frequency domain database and an optical cable characteristic information frequency domain data matrix are established;

[0022] The Fourier transform formula is:

[0023]

[0024] Where F(u,v) is the frequency domain information matrix after Fourier transform, G(x,y) is the frequency domain data matrix of optical cable characteristic information, n is the number of frequency domain data of optical cable characteristic information, and (x,y) is the position information of the frequency domain data of optical cable characteristic information in the coordinate system.

[0025] Preferably, the classifying and identifying the optical cable features of the optical cable feature information frequency domain database according to the K-means clustering algorithm model specifically includes:

[0026] According to the frequency domain information matrix after Fourier transformation, the K value is determined according to its data type;

[0027] Based on the K-means clustering algorithm, a loss function of the characteristic frequency domain data of each optical cable is established;

[0028] According to the loss function of the characteristic frequency domain data of each optical cable, a centroid update function of the characteristic frequency domain data of each optical cable is established;

[0029] According to the frequency domain database of optical cable characteristic information, the K-means clustering algorithm model is trained and learned, and the received optical cable characteristic frequency domain data is classified and identified;

[0030] The loss function expression of each optical cable characteristic frequency domain data is:

[0031]

[0032] Where b i (a) is the distance from the i-th optical cable characteristic frequency domain data point to the cluster center, k is the number of clusters, that is, the type of optical cable characteristic frequency domain data, n is the set of each optical cable characteristic frequency domain data, a i is the characteristic frequency domain data of the i-th optical cable, α j is the jth cluster center of the optical cable characteristic frequency domain data;

[0033] The centroid update function expression of each optical cable characteristic frequency domain data is:

[0034]

[0035] In the formula, is the jth cluster center of the updated optical cable characteristic frequency domain data.

[0036] Preferably, the optical cable intrusion determination model is established based on the DS evidence theory, and the information of different clusters is determined to determine whether the optical cable in the monitored area is intruded, and the intrusion type is determined specifically including:

[0037] According to the characteristic sample set data of optical cable intrusion events, the optical cable intrusion events corresponding to different data combinations are analyzed, and an optical cable intrusion event determination database is established;

[0038] Based on big data analysis, determine the threshold of the probability of the optical cable in the monitored area being disturbed and the probability threshold of the corresponding intrusion event;

[0039] Based on DS evidence theory and combined with K-means clustering algorithm model, a cable intrusion determination model is established;

[0040] The model calculates the probability of the optical cable being disturbed and the probability of the type of disturbance event in the monitored area by analyzing the data classified and identified by the K-means clustering algorithm model;

[0041] By comparing the probability threshold of the optical cable being disturbed and the probability threshold of the type of the intrusion event, it is determined whether the optical cable in the monitored area is disturbed and the type of intrusion;

[0042] The DS evidence theory expression is:

[0043]

[0044] Where D(A) is the credibility of the Ath optical cable intrusion event type, K is a constant, and D i (A i ) is the probability of the i-th optical cable characteristic frequency domain data of the A-th optical cable intrusion event type, and m is the number of optical cable characteristic frequency domain data of the A-th optical cable intrusion event.

[0045] Preferably, the establishment of a ground monitoring platform to monitor, access and display abnormalities of optical cables in the monitored area through the Internet of Things technology specifically includes:

[0046] Establish a ground monitoring platform to embed the algorithm program of the system to judge whether the optical cable is disturbed, run and output the judgment result of whether the optical cable is disturbed;

[0047] Through cloud technology and Internet of Things technology, the ground monitoring platform is used to receive, store and analyze the optical cable characteristic monitoring data, and display and control the optical cable characteristic data through the human-computer interactive interface;

[0048] According to the type of optical cable intrusion incident, corresponding indicator lights and alarm signals are set, and warnings and prompts are issued through the ground monitoring platform.

[0049] Furthermore, an optical cable operation and maintenance system combined with optical cable intrusion event feature analysis is proposed, which is used to implement the optical cable operation and maintenance method combined with optical cable intrusion event feature analysis as described above, including:

[0050] A hardware acquisition module, wherein the hardware acquisition module is used to set corresponding monitoring equipment at a suitable position in the area to be monitored, and to collect the optical cable characteristic information of the area to be monitored;

[0051] A data extraction module, which is used to obtain the characteristic information of the optical cable intrusion event and the characteristic information of the optical cable during normal operation based on historical data and big data analysis; extract the frequency domain information from the collected optical cable characteristic information based on the Fourier transform formula, and establish a frequency domain database of the optical cable characteristic information;

[0052] An intrusion judgment module is used to classify and identify the optical cable features of the optical cable feature information frequency domain database according to the K-means clustering algorithm model; establish an optical cable intrusion judgment model based on the DS evidence theory, judge the information of different clusters, judge whether the optical cable in the monitored area is intruded, and judge the type of intrusion;

[0053] The monitoring platform module is used to establish a ground monitoring platform, and through the Internet of Things technology, the optical cables in the monitored area are monitored, accessed and abnormalities are displayed.

[0054] Preferably, the data extraction module specifically includes:

[0055] A feature extraction unit, the feature extraction unit is used to obtain feature information of optical cable intrusion events and feature information of normal operation of the optical cable based on historical data and big data analysis;

[0056] A frequency domain conversion unit is used to extract frequency domain information from the collected optical cable characteristic information based on a Fourier transform formula, and to establish an optical cable characteristic information frequency domain database.

[0057] Preferably, the intrusion judgment module specifically includes:

[0058] A feature classification unit, wherein the feature classification unit is used to classify and identify the optical cable features of the optical cable feature information frequency domain database according to a K-means clustering algorithm model;

[0059] The intrusion judgment unit is used to establish an optical cable intrusion judgment model based on the DS evidence theory, judge the information of different clusters, judge whether the optical cable in the monitored area is intruded, and judge the type of intrusion.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] By analyzing the characteristic information of the optical cable intrusion event and the characteristic information of the optical cable during normal operation, the Fourier transform formula is used to convert the acquired characteristic data into frequency domain information. The waveform, amplitude and frequency information of the characteristic information are obtained through the frequency domain data of the optical cable, so that more detailed data can be analyzed. Secondly, the optical cable characteristic data in the frequency domain are classified and identified respectively through the K-means clustering algorithm model, and the frequency domain database of the optical cable characteristic information is obtained. Finally, based on the DS evidence theory, an optical cable intrusion judgment model is established. By analyzing the data classified and identified by the K-means clustering algorithm model, the probability of the optical cable being intruded in the monitored area and the probability of the intrusion event type are calculated. According to the comparison results of the calculated value with the probability threshold of the optical cable being intruded and the probability threshold of the intrusion event type, it is determined whether the optical cable in the monitored area is intruded and the type of intrusion, so as to effectively identify and judge whether the optical cable in the monitored area is intruded and the type of intrusion, improve the reliability and stability of the optical cable operation and maintenance, and take timely measures to improve the response efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flow chart of an optical cable operation and maintenance method combined with optical cable intrusion event feature analysis of the present invention;

[0063] Figure 2 The present invention is based on the Fourier transform formula, extracts the frequency domain information in the collected optical cable characteristic information, and establishes the optical cable characteristic information frequency domain database flow chart;

[0064] Figure 3 A flow chart of classifying and identifying the optical cable features of the optical cable feature information frequency domain database according to the K-means clustering algorithm model of the present invention;

[0065] Figure 4 The present invention establishes an optical cable intrusion determination model based on the DS evidence theory, determines the information of different clusters, determines whether the optical cable in the monitored area is intruded, and determines the intrusion type flow chart. DETAILED DESCRIPTION

[0066] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0067] Reference Figure 1 As shown, an optical cable operation and maintenance method combined with optical cable intrusion event feature analysis includes:

[0068] At appropriate locations in the area to be monitored, corresponding monitoring equipment is set up to collect optical cable characteristic information of the area to be monitored;

[0069] Based on historical data and big data analysis, obtain the characteristic information of optical cable intrusion events and the characteristic information of optical cable normal operation;

[0070] Based on the Fourier transform formula, the frequency domain information in the collected optical cable characteristic information is extracted and the frequency domain database of the optical cable characteristic information is established;

[0071] According to the K-means clustering algorithm model, the optical cable features in the frequency domain database of optical cable feature information are classified and identified;

[0072] Based on the DS evidence theory, an optical cable intrusion judgment model is established to judge the information of different clusters, determine whether the optical cable in the monitored area is intruded, and determine the type of intrusion;

[0073] A ground monitoring platform is established to monitor, access and display abnormalities of optical cables in the monitored area through Internet of Things technology.

[0074] It can be understood that this scheme analyzes the characteristic information of the optical cable intrusion event and the characteristic information of the optical cable during normal operation, and converts the acquired characteristic data into frequency domain information using the Fourier transform formula. The waveform, amplitude and frequency information of the characteristic information are obtained through the frequency domain data of the optical cable, so that the analysis can be performed from more detailed data. Secondly, the optical cable characteristic data in the frequency domain are classified and identified respectively through the K-means clustering algorithm model, and the frequency domain database of the optical cable characteristic information is obtained. Finally, based on the DS evidence theory, an optical cable intrusion determination model is established. By analyzing the data classified and identified by the K-means clustering algorithm model, the probability of the optical cable being intruded in the monitored area and the probability of the intrusion event type are calculated, and according to the comparison result of the calculated value with the probability threshold of the optical cable being intruded and the probability threshold of the intrusion event type, it is determined whether the optical cable in the monitored area is intruded and the intrusion type, thereby realizing effective identification and judgment of whether the optical cable in the monitored area is intruded and the intrusion type, improving the reliability and stability of the optical cable operation and maintenance, and taking timely measures to improve the response efficiency.

[0075] Reference Figure 2 As shown, the method of extracting frequency domain information from the collected optical cable characteristic information based on the Fourier transform formula and establishing an optical cable characteristic information frequency domain database specifically includes:

[0076] According to the characteristic sample set of the optical cable intrusion event and the characteristic sample set of the optical cable normal operation, the data is standardized and preliminarily filtered;

[0077] The processed optical cable characteristic information data is converted into frequency domain using the Fourier transform formula, and the frequency domain information in the collected optical cable characteristic information is extracted;

[0078] According to the frequency domain information in the optical cable characteristic information, the waveform, amplitude and frequency information of the optical cable characteristic information are obtained, and marked and classified;

[0079] According to the marked and classified optical cable characteristic information, an optical cable characteristic information frequency domain database and an optical cable characteristic information frequency domain data matrix are established;

[0080] The Fourier transform formula is:

[0081]

[0082] Where F(u,v) is the frequency domain information matrix after Fourier transform, G(x,y) is the frequency domain data matrix of optical cable characteristic information, n is the number of frequency domain data of optical cable characteristic information, and (x,y) is the position information of the frequency domain data of optical cable characteristic information in the coordinate system.

[0083] It is understandable that optical cable intrusion incidents such as human destruction, construction damage, natural factors and illegal occupation can be confirmed and identified from characteristics such as vibration information, flow data and natural environmental factor information. Different events have different waveforms, amplitudes and frequency information. This solution converts the optical cable characteristic data into frequency domain data through the Fourier transform formula, carefully classifies and identifies different frequency domain data, and establishes an optical cable characteristic information frequency domain database to facilitate subsequent analysis and processing of the data.

[0084] Reference Figure 3 As shown, the classification and identification of the optical cable features of the optical cable feature information frequency domain database according to the K-means clustering algorithm model specifically includes:

[0085] According to the frequency domain information matrix after Fourier transformation, the K value is determined according to its data type;

[0086] Based on the K-means clustering algorithm, the loss function of the characteristic frequency domain data of each optical cable is established;

[0087] According to the loss function of the characteristic frequency domain data of each optical cable, a centroid update function of the characteristic frequency domain data of each optical cable is established;

[0088] According to the frequency domain database of optical cable characteristic information, the K-means clustering algorithm model is trained and learned, and the received optical cable characteristic frequency domain data is classified and identified;

[0089] The loss function expression of each optical cable characteristic frequency domain data is:

[0090]

[0091] Where b i(a) is the distance from the i-th optical cable characteristic frequency domain data point to the cluster center, k is the number of clusters, that is, the type of optical cable characteristic frequency domain data, n is the set of each optical cable characteristic frequency domain data, a i is the characteristic frequency domain data of the i-th optical cable, α j is the jth cluster center of the optical cable characteristic frequency domain data;

[0092] The centroid update function expression of each optical cable characteristic frequency domain data is:

[0093]

[0094] In the formula, is the jth cluster center of the updated optical cable characteristic frequency domain data.

[0095] It can be understood that by training and learning the data in the frequency domain database of optical cable characteristic information using the K-means clustering algorithm model, the frequency domain data converted by the Fourier transform formula can be effectively identified and classified in real time. By performing correlation analysis on the identified and classified frequency domain data of optical cable characteristic information, it is possible to effectively determine whether the optical cable in the monitored area is disturbed and the type of intrusion.

[0096] Reference Figure 4 As shown, based on the DS evidence theory, an optical cable intrusion determination model is established to determine the information of different clusters, determine whether the optical cable in the monitored area is intruded, and determine the intrusion type, including:

[0097] According to the characteristic sample set data of optical cable intrusion events, the optical cable intrusion events corresponding to different data combinations are analyzed, and an optical cable intrusion event determination database is established;

[0098] Based on big data analysis, determine the threshold of the probability of the optical cable in the monitored area being disturbed and the probability threshold of the corresponding intrusion event;

[0099] Based on DS evidence theory and combined with K-means clustering algorithm model, a cable intrusion determination model is established;

[0100] The model calculates the probability of the optical cable being disturbed and the probability of the type of disturbance event in the monitored area by analyzing the data classified and identified by the K-means clustering algorithm model;

[0101] By comparing the probability threshold of the optical cable being disturbed and the probability threshold of the type of the intrusion event, it is determined whether the optical cable in the monitored area is disturbed and the type of intrusion;

[0102] The DS evidence theory expression is:

[0103]

[0104] Where D(A) is the credibility of the Ath optical cable intrusion event type, K is a constant, and D i (A i ) is the probability of the i-th optical cable characteristic frequency domain data of the A-th optical cable intrusion event type, and m is the number of optical cable characteristic frequency domain data of the A-th optical cable intrusion event.

[0105] It can be understood that this scheme establishes an optical cable intrusion event determination library by performing correlation analysis on the frequency domain data of historical optical cable characteristic information, and establishes an optical cable intrusion determination model based on the DS evidence theory. By analyzing the data classified and identified by the K-means clustering algorithm model, the probability of the optical cable being intruded and the probability of the type of intrusion event in the area to be monitored are calculated, and based on the comparison results of the calculated value with the probability threshold of the optical cable being intruded and the probability threshold of the type of intrusion event, it is determined whether the optical cable in the area to be monitored is intruded and the type of intrusion, thereby achieving effective identification and judgment of whether the optical cable in the area to be monitored is intruded and the type of intrusion.

[0106] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An optical cable operation and maintenance method combined with optical cable intrusion event feature analysis, characterized in that: include: At appropriate locations in the area to be monitored, corresponding monitoring equipment is set up to collect optical cable characteristic information of the area to be monitored; Based on historical data and big data analysis, obtain the characteristic information of optical cable intrusion events and the characteristic information of optical cable normal operation; Based on the Fourier transform formula, the frequency domain information in the collected optical cable characteristic information is extracted and the frequency domain database of the optical cable characteristic information is established; According to the K-means clustering algorithm model, the optical cable features in the frequency domain database of optical cable feature information are classified and identified; Based on the DS evidence theory, an optical cable intrusion judgment model is established to judge the information of different clusters, determine whether the optical cable in the monitored area is intruded, and determine the type of intrusion; A ground monitoring platform is established to monitor, access and display abnormalities of optical cables in the monitored area through Internet of Things technology.

2. The optical cable operation and maintenance method combined with the optical cable intrusion event feature analysis according to claim 1, characterized in that: The acquisition of characteristic information of optical cable intrusion events and characteristic information of normal operation of optical cables based on historical data and big data analysis specifically includes: Based on historical data and big data analysis, the characteristic information of optical cable intrusion events is obtained, and a characteristic sample set of optical cable intrusion events is established; According to the monitoring equipment, the optical cable information of the area to be monitored is obtained, the characteristic information of the optical cable during normal operation is extracted, and a sample set of the normal operation characteristics of the optical cable is established; The optical cable characteristic information mainly includes: vibration signals, flow data and natural environment factor information.

3. The optical cable operation and maintenance method combined with the characteristic analysis of optical cable intrusion events according to claim 2 is characterized in that: The method of extracting frequency domain information from the collected optical cable characteristic information based on the Fourier transform formula and establishing an optical cable characteristic information frequency domain database specifically includes: According to the characteristic sample set of the optical cable intrusion event and the characteristic sample set of the optical cable normal operation, the data is standardized and preliminarily filtered; The processed optical cable characteristic information data is converted into frequency domain using the Fourier transform formula, and the frequency domain information in the collected optical cable characteristic information is extracted; According to the frequency domain information in the optical cable characteristic information, the waveform, amplitude and frequency information of the optical cable characteristic information are obtained, and the information is marked and classified; According to the marked and classified optical cable characteristic information, an optical cable characteristic information frequency domain database and an optical cable characteristic information frequency domain data matrix are established; The Fourier transform formula is: Where F(u,v) is the frequency domain information matrix after Fourier transform, G(x,y) is the frequency domain data matrix of optical cable characteristic information, n is the number of frequency domain data of optical cable characteristic information, and (x,y) is the position information of the frequency domain data of optical cable characteristic information in the coordinate system.

4. The optical cable operation and maintenance method combined with the optical cable intrusion event feature analysis according to claim 3 is characterized in that: The classification and identification of the optical cable features of the optical cable feature information frequency domain database according to the K-means clustering algorithm model specifically includes: According to the frequency domain information matrix after Fourier transformation, the K value is determined according to its data type; Based on the K-means clustering algorithm, a loss function of the characteristic frequency domain data of each optical cable is established; According to the loss function of the characteristic frequency domain data of each optical cable, a centroid update function of the characteristic frequency domain data of each optical cable is established; According to the frequency domain database of optical cable characteristic information, the K-means clustering algorithm model is trained and learned, and the received optical cable characteristic frequency domain data is classified and identified; The loss function expression of each optical cable characteristic frequency domain data is: Among them, b i (a) is the distance from the i-th optical cable characteristic frequency domain data point to the cluster center, k is the number of clusters, that is, the type of optical cable characteristic frequency domain data, n is the set of each optical cable characteristic frequency domain data, a i is the characteristic frequency domain data of the i-th optical cable, α j is the jth cluster center of the optical cable characteristic frequency domain data; The centroid update function expression of each optical cable characteristic frequency domain data is: in, is the jth cluster center of the updated optical cable characteristic frequency domain data.

5. The optical cable operation and maintenance method combined with the characteristic analysis of optical cable intrusion events according to claim 4 is characterized in that: According to the DS evidence theory, an optical cable intrusion determination model is established to determine the information of different clusters, determine whether the optical cable in the monitored area is intruded, and determine the intrusion type, including: According to the characteristic sample set data of optical cable intrusion events, the optical cable intrusion events corresponding to different data combinations are analyzed, and an optical cable intrusion event determination database is established; Based on big data analysis, determine the threshold of the probability of the optical cable in the monitored area being disturbed and the probability threshold of the corresponding intrusion event; Based on DS evidence theory and combined with K-means clustering algorithm model, a cable intrusion determination model is established; The model calculates the probability of the optical cable being disturbed and the probability of the type of disturbance event in the monitored area by analyzing the data classified and identified by the K-means clustering algorithm model; By comparing the probability threshold of the optical cable being disturbed and the probability threshold of the type of the intrusion event, it is determined whether the optical cable in the monitored area is disturbed and the type of intrusion; The DS evidence theory expression is: Where D(A) is the credibility of the A-th optical cable intrusion event type, K is a constant, and D i (A i ) is the probability of the i-th optical cable characteristic frequency domain data of the A-th optical cable intrusion event type, and m is the number of optical cable characteristic frequency domain data of the A-th optical cable intrusion event.

6. The optical cable operation and maintenance method combined with optical cable intrusion event feature analysis according to claim 5, characterized in that: The establishment of a ground monitoring platform to monitor, access and display abnormalities of optical cables in the monitored area through the Internet of Things technology specifically includes: Establish a ground monitoring platform to embed the algorithm program of the system to judge whether the optical cable is disturbed, run and output the judgment result of whether the optical cable is disturbed; Through cloud technology and Internet of Things technology, the ground monitoring platform is used to receive, store and analyze the optical cable characteristic monitoring data, and display and control the optical cable characteristic data through the human-computer interactive interface; According to the type of optical cable intrusion incident, corresponding indicator lights and alarm signals are set, and warnings and prompts are issued through the ground monitoring platform.

7. An optical cable operation and maintenance system combined with optical cable intrusion event feature analysis, used to implement the optical cable operation and maintenance method combined with optical cable intrusion event feature analysis as claimed in any one of claims 1 to 6, characterized in that: include: A hardware acquisition module, wherein the hardware acquisition module is used to set corresponding monitoring equipment at a suitable position in the area to be monitored, and to collect the optical cable characteristic information of the area to be monitored; A data extraction module, the data extraction module is used to obtain characteristic information of optical cable intrusion events and characteristic information of normal operation of the optical cable based on historical data and big data analysis; Based on the Fourier transform formula, the frequency domain information in the collected optical cable characteristic information is extracted and the frequency domain database of the optical cable characteristic information is established; An intrusion judgment module is used to classify and identify the optical cable features of the optical cable feature information frequency domain database according to the K-means clustering algorithm model; establish an optical cable intrusion judgment model based on the DS evidence theory, judge the information of different clusters, judge whether the optical cable in the monitored area is intruded, and judge the type of intrusion; The monitoring platform module is used to establish a ground monitoring platform, and through the Internet of Things technology, the optical cables in the monitored area are monitored, accessed and abnormalities are displayed.

8. The optical cable operation and maintenance method combined with the optical cable intrusion event feature analysis according to claim 7, characterized in that: The data extraction module specifically includes: A feature extraction unit, the feature extraction unit is used to obtain feature information of optical cable intrusion events and feature information of normal operation of the optical cable based on historical data and big data analysis; A frequency domain conversion unit is used to extract frequency domain information from the collected optical cable characteristic information based on a Fourier transform formula, and to establish an optical cable characteristic information frequency domain database.

9. The optical cable operation and maintenance method combined with optical cable intrusion event feature analysis according to claim 8, characterized in that: The intrusion judgment module specifically includes: A feature classification unit, wherein the feature classification unit is used to classify and identify the optical cable features of the optical cable feature information frequency domain database according to a K-means clustering algorithm model; The intrusion judgment unit is used to establish an optical cable intrusion judgment model based on the DS evidence theory, judge the information of different clusters, judge whether the optical cable in the monitored area is intruded, and judge the type of intrusion.

Images