Optical fiber cable intelligent fault diagnosis system based on artificial intelligence

Abstract

The invention discloses an optical fiber cable intelligent fault diagnosis system based on artificial intelligence, and relates to the technical field of fault diagnosis. The method comprises the following steps: constructing a distribution map of an optical fiber cable, dividing the optical fiber cable into a plurality of monitoring sections, setting an acquisition unit, obtaining acquisition data, obtaining historical fault records and historical acquisition data and data characteristics of the optical fiber cable, and constructing a fault judgment model according to historical fault records and historical acquisition data of different monitoring sections. The method comprises the following steps: acquiring real-time acquired data, judging whether a fault exists or not by utilizing a fault judgment model, generating a fault judgment record, acquiring the fault judgment record with a misjudgment state and environmental parameters thereof, constructing a misjudgment evaluation model, and evaluating whether the fault judgment record has misjudgment or not by utilizing the misjudgment evaluation model; an effective fault judgment mechanism can be formed and optimized, and the accuracy of fault judgment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to an optical fiber and cable intelligent fault diagnosis system based on artificial intelligence. Background Art

[0002] As the transmission medium of modern communication networks, optical fiber cables play an important role in communication systems. However, in practical applications, optical fiber cables are easily affected by the external environment, resulting in various types of faults. Traditional optical fiber cable fault diagnosis methods have problems such as low judgment efficiency, high misjudgment rate, and poor positioning accuracy. They are difficult to meet the high requirements of modern communication networks for optical fiber cable fault diagnosis.

[0003] In the prior art, there have been technical solutions for using artificial intelligence technology to diagnose optical fiber and cable faults. However, they lack effective means for integrating multi-source data for comprehensive judgment. In addition, the prior art often only has fault judgment solutions but lacks means for evaluating the judgment results. In response to the shortcomings of the prior art, the present invention provides an optical fiber and cable intelligent fault diagnosis system based on artificial intelligence. Summary of the Invention

[0004] The purpose of the present invention is to provide an optical fiber and cable intelligent fault diagnosis system based on artificial intelligence.

[0005] The purpose of the present invention can be achieved through the following technical solutions: an artificial intelligence-based optical fiber and cable intelligent fault diagnosis system, comprising the following modules:

[0006] A map construction module is used to obtain the distribution information of optical fiber and cable and construct a corresponding distribution map, in which the optical fiber and cable are divided into several monitoring sections;

[0007] The data acquisition module is used to set different acquisition units in each monitoring section and obtain corresponding acquisition data respectively, obtain historical fault records of optical fiber cables and their historical acquisition data, and obtain data features of different historical fault records based on the historical acquisition data;

[0008] The fault judgment module is used to build a corresponding fault judgment model based on the historical fault records and historical collected data of different monitoring sections, obtain the current real-time collected data, use the fault judgment model to determine whether there is a fault, and generate a fault judgment record;

[0009] The misjudgment assessment module is used to obtain fault judgment records with misjudgment status and their environmental parameters, and build a corresponding misjudgment assessment model. The misjudgment assessment model is used in combination with environmental parameters to evaluate whether subsequent fault judgment records contain misjudgments.

[0010] Furthermore, the process of obtaining the distribution information of the optical fiber and cable and constructing a corresponding distribution map, and dividing the optical fiber and cable into several monitoring sections in the distribution map includes:

[0011] The distribution information refers to various data related to the distribution of optical fiber and cable, including geographical location information, cable specification information, and network topology information. The optical fiber and cable contain several key nodes.

[0012] The key nodes refer to the starting point, end point, relay station, and junction box in the optical fiber cable. GIS technology is used to construct a distribution map of the optical fiber cable based on the distribution information. The optical fiber cable is divided into different monitoring sections according to the key nodes, and the optical fiber cable between adjacent key nodes is regarded as a monitoring section.

[0013] Furthermore, different collection units are respectively set in each monitoring section, and the process of respectively obtaining corresponding collection data includes:

[0014] A first-class acquisition unit and a second-class acquisition unit are respectively set on each monitoring segment. The first-class acquisition unit collects the optical power difference of the corresponding monitoring segment in real time, and the second-class acquisition unit collects the network performance parameters of the corresponding monitoring segment in real time, including bit error rate, transmission rate, and bandwidth utilization;

[0015] The acquisition units include a first-class acquisition unit and a second-class acquisition unit, and the acquired data include optical power difference, bit error rate, transmission rate, and bandwidth utilization.

[0016] Furthermore, the process of obtaining historical fault records of optical fiber cables and their historical collected data and obtaining data features of different historical fault records based on the historical collected data includes:

[0017] The historical fault records refer to data related to faults that have occurred in optical fiber cables, including the time, location, type and cause of the fault;

[0018] Upload each historical fault record to the distribution map for synchronization based on the fault location, and use the total number of historical fault records in each monitoring segment as the number of existing faults in the corresponding monitoring segment;

[0019] All collected data of the monitoring segment corresponding to a single historical fault record within a preset fixed time period before the fault moment is used as the historical collected data of the historical fault record;

[0020] The characteristic information of optical power difference, bit error rate, transmission rate, and bandwidth utilization in the historical collected data of a single historical fault record is used as its data features, including mean, variance, and trend.

[0021] Furthermore, the process of constructing a corresponding fault judgment model based on historical fault records and historical collected data of different monitoring sections includes:

[0022] Generate a fault judgment set based on historical collected data and data features corresponding to different historical fault records in different monitoring sections, and divide the fault judgment set into a first training set and a first test set;

[0023] Constructing a first convolutional neural network, using different historically collected data and data features in the first training set as input data of the first convolutional neural network, using whether a fault will occur as output data of the first convolutional neural network, and training the first convolutional neural network to obtain an initial first convolutional neural network;

[0024] The initial first convolutional neural network is model verified using the first test set, and the initial first convolutional neural network with a value less than or equal to a preset first test error threshold is output as a fault judgment model.

[0025] Furthermore, the process of obtaining the current real-time collected data, determining whether a fault exists using the fault judgment model, and generating a fault judgment record includes:

[0026] All collected data of each monitoring segment within a preset fixed time period before the current moment is used as its real-time collected data, and the data characteristics of the real-time collected data are obtained, including mean, variance, and trend;

[0027] Input the single real-time collected data and its data features into the fault judgment model, and use the fault judgment model to determine whether there is a fault in the corresponding monitoring section;

[0028] If it exists, a fault judgment record is generated for the corresponding monitoring segment and fed back to the relevant personnel. If it does not exist, no other operations are performed.

[0029] Furthermore, the process of obtaining fault judgment records and environmental parameters of misjudgment states and building a corresponding misjudgment assessment model includes:

[0030] When a fault judgment record is generated, the monitoring segment where the fault is judged to exist is tested using an optical time domain reflectometer to obtain the fault location and fault type. If no fault is detected, the corresponding fault judgment record is marked as a misjudgment state.

[0031] Obtaining environmental parameters and the number of faults corresponding to the fault judgment record marked as a misjudgment state, where the environmental parameters and the number of faults respectively refer to the temperature and humidity, pressure, pH, electromagnetic radiation, and the number of existing faults in the corresponding monitoring segment when the fault judgment record marked as a misjudgment state is generated;

[0032] Generate a misjudgment evaluation set based on historical collected data, data features, environmental parameters, and the number of faults corresponding to different fault judgment records marked as misjudgment states, and divide the misjudgment evaluation set into a second training set and a second test set;

[0033] Constructing a second convolutional neural network, using different historically collected data, data features, environmental parameters, and the number of faults in the second training set as input data of the second convolutional neural network, using whether a misjudgment occurs as output data of the second convolutional neural network, and training the second convolutional neural network to obtain an initial second convolutional neural network;

[0034] The initial second convolutional neural network is model verified using the second test set, and the initial second convolutional neural network with a preset second test error threshold is output as the misjudgment assessment model.

[0035] Furthermore, the process of using the misjudgment assessment model in combination with environmental parameters to assess whether subsequent fault judgment records contain misjudgments includes:

[0036] When a fault judgment record is subsequently generated, the environmental parameters and fault quantity corresponding to the fault judgment record are obtained, and the real-time collected data and data features of the monitoring section corresponding to the fault judgment record are input into the misjudgment assessment model. The misjudgment assessment model is used to assess whether there is a misjudgment in the fault judgment record.

[0037] If it exists, a misjudgment signal is generated for the corresponding fault judgment record, and the misjudgment signal and its fault judgment record are fed back to the relevant personnel. If it does not exist, no other operation is performed.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention divides optical fiber cables into different monitoring segments according to their key nodes, obtains historical fault records and historical collected data of different monitoring segments, extracts data features therein, and can obtain changes in the collected data of the optical fiber cables before each fault occurs, thereby constructing a fault judgment model. This is conducive to judging whether a fault will occur in the corresponding monitoring segment based on changes in real-time collected data, and can form an effective fault judgment mechanism.

[0040] By evaluating the accuracy of each fault judgment record and combining the environmental parameters and number of faults in the fault judgment records with misjudgments, we can obtain the potential influencing factors that lead to misjudgments and build a corresponding misjudgment evaluation model. This is conducive to evaluating whether there are misjudgments in subsequent fault judgment records, and can further optimize the formed fault judgment mechanism, which is conducive to improving the accuracy of fault judgment, timely discovering fault conditions and providing feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of the present invention. DETAILED DESCRIPTION

[0042] like Figure 1 As shown in FIG, an artificial intelligence-based intelligent fault diagnosis system for optical fiber and cable includes the following modules:

[0043] A map construction module is used to obtain the distribution information of optical fiber and cable and construct a corresponding distribution map, in which the optical fiber and cable are divided into several monitoring sections;

[0044] The data acquisition module is used to set different acquisition units in each monitoring section and obtain corresponding acquisition data respectively, obtain historical fault records of optical fiber cables and their historical acquisition data, and obtain data features of different historical fault records based on the historical acquisition data;

[0045] The fault judgment module is used to build a corresponding fault judgment model based on the historical fault records and historical collected data of different monitoring sections, obtain the current real-time collected data, use the fault judgment model to determine whether there is a fault, and generate a fault judgment record;

[0046] The misjudgment assessment module is used to obtain fault judgment records with misjudgment status and their environmental parameters, and build a corresponding misjudgment assessment model. The misjudgment assessment model is used in combination with environmental parameters to evaluate whether subsequent fault judgment records contain misjudgments.

[0047] It should be further explained that, in a specific implementation process, the process of obtaining the distribution information of optical fiber cables and constructing a corresponding distribution map, and dividing the optical fiber cables into several monitoring sections in the distribution map includes:

[0048] The distribution information refers to various data related to the distribution of optical fibers and cables, including geographical location information, cable specification information, network topology information, etc.

[0049] The geographical location information refers to the latitude and longitude coordinates and altitude of each key node of the optical fiber cable. The key nodes refer to the starting point, end point, relay station, and junction box in the optical fiber cable. The optical cable specification information refers to the optical cable type, number of cores, and outer sheath material of the optical fiber cable between adjacent key nodes. The network topology information refers to the connection method, sequence, and topological structure between each key node.

[0050] GIS technology is used to construct a distribution map of optical fiber cables based on the acquired geographic location information, optical cable specification information, and network topology information. The optical fiber cables are divided into different monitoring sections according to each key node, and the optical fiber cables between adjacent key nodes are regarded as a monitoring section.

[0051] It should be further explained that, in the specific implementation process, different collection units are respectively set in each monitoring section, and the process of obtaining corresponding collection data respectively includes:

[0052] Taking a single monitoring segment as an example, a first-class acquisition unit and a second-class acquisition unit are respectively set on the single monitoring segment, and the optical power difference of the single monitoring segment is collected in real time by the first-class acquisition unit. The optical power difference refers to the difference between the optical signal power output from the transmitting end and the optical signal power received by the receiving end;

[0053] The transmitting end refers to the starting point of the single monitoring segment relative to the transmission direction of the optical signal, and the receiving end refers to the end point of the single monitoring segment relative to the transmission direction of the optical signal;

[0054] The second type of acquisition unit collects network performance parameters of the single monitoring segment in real time, including bit error rate, transmission rate, bandwidth utilization, etc. The network performance parameters are used to reflect the operating status of the optical fiber cable of each monitoring segment during data transmission;

[0055] The acquisition unit includes a first-class acquisition unit and a second-class acquisition unit. The acquired data includes optical power difference, bit error rate, transmission rate, bandwidth utilization, etc. The same method is adopted to set a first-class acquisition unit and a second-class acquisition unit in each monitoring section, and obtain the corresponding acquisition data respectively.

[0056] It should be further explained that, in a specific implementation process, the process of obtaining historical fault records of optical fiber cables and their historical collected data, and obtaining data features of different historical fault records based on the historical collected data includes:

[0057] The historical fault records refer to data related to faults that have occurred in optical fiber cables, including the time of the fault, the location of the fault, the type of fault, the cause of the fault, etc.

[0058] Upload each historical fault record to the corresponding monitoring segment in the distribution map according to the fault location of the historical fault record for synchronization. Obtain the total number of historical fault records that have occurred in a single monitoring segment in the distribution map and use it as the number of existing faults in the single monitoring segment.

[0059] All collected data of the monitoring segment corresponding to the historical fault record within a preset fixed time period before the fault moment is used as the historical collected data of the historical fault record, including optical power difference, bit error rate, transmission rate, bandwidth utilization, etc.

[0060] Since historically collected data are all quantifiable data, they can be analyzed to obtain their characteristic information, including mean, variance, trend, etc. The data characteristics include the characteristic information of each historically collected data. The data characteristics corresponding to each historical fault record are obtained and bound to the corresponding monitoring segment.

[0061] The mean is used to reflect the average level of the data, the variance is used to reflect the degree of dispersion of the data relative to the mean, and the trend is used to reflect the direction of change of the data over time, including an upward trend, a downward trend, and a horizontal trend.

[0062] It should be further explained that, in the specific implementation process, the process of building a corresponding fault judgment model based on the historical fault records and historical collected data of different monitoring segments includes:

[0063] Generate a fault judgment set based on historical collected data and data features corresponding to different historical fault records of different monitoring sections, and divide the fault judgment set into a first training set and a first test set;

[0064] Constructing a first convolutional neural network, using different historically collected data and data features in the first training set as input data of the first convolutional neural network, using whether a fault will occur as output data of the first convolutional neural network, and training the first convolutional neural network to obtain an initial first convolutional neural network;

[0065] The initial first convolutional neural network is model verified using the first test set, and the initial first convolutional neural network with a preset first test error threshold value is output as the corresponding fault judgment model.

[0066] It should be further explained that, in the specific implementation process, the process of obtaining the current real-time collected data, using the fault judgment model to judge whether there is a fault, and generating a fault judgment record includes:

[0067] Taking a single monitoring segment as an example, all the collected data of the single monitoring segment within a preset fixed time period before the current moment is regarded as its current real-time collected data, including optical power difference, bit error rate, transmission rate, bandwidth utilization, etc.

[0068] The same method is used to obtain the data characteristics of each real-time collected data, including mean, variance, trend, etc. The real-time collected data and data characteristics of the single monitoring segment are input into the constructed fault judgment model, and the fault judgment model is used to determine whether the single monitoring segment has a fault;

[0069] If it exists, a corresponding fault judgment record will be generated for the single monitoring segment and fed back to the relevant personnel. If it does not exist, no other operations will be performed on it. The same method will be used to determine whether there is a fault in each monitoring segment, and a corresponding fault judgment record will be generated for feedback.

[0070] It should be further explained that, in the specific implementation process, the process of obtaining fault judgment records and environmental parameters in the presence of misjudgment and building the corresponding misjudgment assessment model includes:

[0071] When a fault judgment record is generated, relevant personnel use optical time domain reflectometry to detect the monitoring segment where the fault is determined to exist to obtain its fault location and fault type. If no fault is found during the detection, the corresponding fault judgment record will be marked as a misjudgment state.

[0072] Obtain the environmental parameters and number of faults corresponding to the fault judgment record marked as a misjudgment state. The environmental parameters refer to the environmental parameters of the corresponding monitoring segment when the fault judgment record marked as a misjudgment state is generated, including temperature, humidity, pressure, pH, electromagnetic radiation, etc. The number of faults refers to the number of existing faults in the corresponding monitoring segment when the fault judgment record marked as a misjudgment state is generated;

[0073] Generate a misjudgment evaluation set based on historical collected data, data features, environmental parameters, and the number of faults corresponding to different fault judgment records marked as misjudgment states, and divide the misjudgment evaluation set into a second training set and a second test set;

[0074] Constructing a second convolutional neural network, using different historically collected data, data features, environmental parameters, and the number of faults in the second training set as input data of the second convolutional neural network, using whether a misjudgment occurs as output data of the second convolutional neural network, and training the second convolutional neural network to obtain an initial second convolutional neural network;

[0075] The initial second convolutional neural network is model verified using the second test set, and the initial second convolutional neural network with a preset second test error threshold is output as the corresponding misjudgment evaluation model.

[0076] It should be further explained that, in the specific implementation process, the process of using the misjudgment assessment model in combination with environmental parameters to assess whether subsequent fault judgment records contain misjudgments includes:

[0077] When a fault judgment record is subsequently generated, the environmental parameters and the number of faults corresponding to the fault judgment record are obtained, and the real-time collected data and data features of the monitoring section corresponding to the fault judgment record are input into the constructed misjudgment assessment model;

[0078] The misjudgment assessment model is used to evaluate whether there is a misjudgment in the fault judgment record. If so, a corresponding misjudgment signal is generated for the fault judgment record, and the generated misjudgment signal and its fault judgment record are fed back to the relevant personnel. If not, no other operations are performed on it.

[0079] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. 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 artificial intelligence-based intelligent fault diagnosis system for optical fiber and cable, characterized in that: Includes the following modules: A map construction module is used to obtain the distribution information of optical fiber and cable and construct a corresponding distribution map, in which the optical fiber and cable are divided into several monitoring sections; The data acquisition module is used to set different acquisition units in each monitoring section and obtain corresponding acquisition data respectively, obtain historical fault records of optical fiber cables and their historical acquisition data, and obtain data features of different historical fault records based on the historical acquisition data; The fault judgment module is used to build a corresponding fault judgment model based on the historical fault records and historical collected data of different monitoring sections, obtain the current real-time collected data, use the fault judgment model to determine whether there is a fault, and generate a fault judgment record; The misjudgment assessment module is used to obtain fault judgment records with misjudgment status and their environmental parameters, and build a corresponding misjudgment assessment model. The misjudgment assessment model is used in combination with environmental parameters to evaluate whether subsequent fault judgment records contain misjudgments.

2. The optical fiber and cable intelligent fault diagnosis system based on artificial intelligence according to claim 1, characterized in that: The process of constructing a distribution map and dividing the optical fiber cable into several monitoring sections includes: The distribution information refers to various data related to the distribution of optical fiber and cable, including geographical location information, cable specification information, and network topology information. The optical fiber and cable contain several key nodes. The key nodes refer to the starting point, end point, relay station, and junction box in the optical fiber cable. GIS technology is used to construct a distribution map of the optical fiber cable based on the distribution information. The optical fiber cable is divided into different monitoring sections according to the key nodes, and the optical fiber cable between adjacent key nodes is regarded as a monitoring section.

3. The optical fiber and cable intelligent fault diagnosis system based on artificial intelligence according to claim 2, characterized in that: The process of setting up the acquisition unit and obtaining the collected data includes: A first-class acquisition unit and a second-class acquisition unit are respectively set on each monitoring segment. The first-class acquisition unit collects the optical power difference of the corresponding monitoring segment in real time, and the second-class acquisition unit collects the network performance parameters of the corresponding monitoring segment in real time, including bit error rate, transmission rate, and bandwidth utilization; The acquisition units include a first-class acquisition unit and a second-class acquisition unit, and the acquired data include optical power difference, bit error rate, transmission rate, and bandwidth utilization.

4. The optical fiber and cable intelligent fault diagnosis system based on artificial intelligence according to claim 3, characterized in that: The process of obtaining historical fault records and their historical collected data and data features includes: The historical fault records refer to data related to faults that have occurred in optical fiber cables, including the time, location, type and cause of the fault; Upload each historical fault record to the distribution map for synchronization based on the fault location, and use the total number of historical fault records in each monitoring segment as the number of existing faults in the corresponding monitoring segment; All collected data of the monitoring segment corresponding to a single historical fault record within a preset fixed time period before the fault moment is used as the historical collected data of the historical fault record; The characteristic information of optical power difference, bit error rate, transmission rate, and bandwidth utilization in the historical collected data of a single historical fault record is used as its data features, including mean, variance, and trend.

5. The optical fiber and cable intelligent fault diagnosis system based on artificial intelligence according to claim 4, characterized in that: The process of building a fault diagnosis model includes: Generate a fault judgment set based on historical collected data and data features corresponding to different historical fault records in different monitoring sections, and divide the fault judgment set into a first training set and a first test set; Constructing a first convolutional neural network, using different historically collected data and data features in the first training set as input data of the first convolutional neural network, using whether a fault will occur as output data of the first convolutional neural network, and training the first convolutional neural network to obtain an initial first convolutional neural network; The initial first convolutional neural network is model verified using the first test set, and the initial first convolutional neural network with a value less than or equal to a preset first test error threshold is output as a fault judgment model.

6. The optical fiber and cable intelligent fault diagnosis system based on artificial intelligence according to claim 5, characterized in that: The process of obtaining real-time collected data, determining whether there is a fault, and generating a fault judgment record includes: All collected data of each monitoring segment within a preset fixed time period before the current moment is used as its real-time collected data, and the data characteristics of the real-time collected data are obtained, including mean, variance, and trend; Input the single real-time collected data and its data features into the fault judgment model, and use the fault judgment model to determine whether there is a fault in the corresponding monitoring section; If it exists, a fault judgment record is generated for the corresponding monitoring segment and fed back to the relevant personnel. If it does not exist, no other operations are performed.

7. The optical fiber and cable intelligent fault diagnosis system based on artificial intelligence according to claim 6, characterized in that: The process of obtaining fault diagnosis records and environmental parameters in the presence of misjudgment and building a misjudgment assessment model includes: When a fault judgment record is generated, the monitoring segment where the fault is judged to exist is tested using an optical time domain reflectometer to obtain the fault location and fault type. If no fault is detected, the corresponding fault judgment record is marked as a misjudgment state. Obtaining environmental parameters and the number of faults corresponding to the fault judgment record marked as a misjudgment state, where the environmental parameters and the number of faults respectively refer to the temperature and humidity, pressure, pH, electromagnetic radiation, and the number of existing faults in the corresponding monitoring segment when the fault judgment record marked as a misjudgment state is generated; Generate a misjudgment evaluation set based on historical collected data, data features, environmental parameters, and the number of faults corresponding to different fault judgment records marked as misjudgment states, and divide the misjudgment evaluation set into a second training set and a second test set; Constructing a second convolutional neural network, using different historically collected data, data features, environmental parameters, and the number of faults in the second training set as input data of the second convolutional neural network, using whether a misjudgment occurs as output data of the second convolutional neural network, and training the second convolutional neural network to obtain an initial second convolutional neural network; The initial second convolutional neural network is model verified using the second test set, and the initial second convolutional neural network with a preset second test error threshold is output as the misjudgment assessment model.

8. The optical fiber and cable intelligent fault diagnosis system based on artificial intelligence according to claim 7, characterized in that: The process of evaluating whether there are misdiagnoses in subsequent fault diagnosis records includes: When a fault judgment record is subsequently generated, the environmental parameters and fault quantity corresponding to the fault judgment record are obtained, and the real-time collected data and data features of the monitoring section corresponding to the fault judgment record are input into the misjudgment assessment model. The misjudgment assessment model is used to assess whether there is a misjudgment in the fault judgment record. If it exists, a misjudgment signal is generated for the corresponding fault judgment record, and the misjudgment signal and its fault judgment record are fed back to the relevant personnel. If it does not exist, no other operation is performed.

Images