Method, device and equipment for identifying lightning incentive fault and medium

Abstract

The invention discloses a lightning inducement fault identification method, apparatus and device, and a medium. The method comprises the steps of obtaining abnormal alarm information; according to the abnormity alarm information, constructing a lightning incentive abnormity to-be-verified sequence; constructing a system fault matrix according to the lightning cause abnormity to-be-verified sequence; matching the system fault matrix with the obtained thunder and lightning information according to occurrence time to obtain a fault section corresponding to the thunder and lightning information; and according to the lightning information and the lightning cause abnormity to-be-verified sequence, verifying whether a fault occurring in the corresponding fault section is a lightning cause fault. According to the invention, power grid faults caused by transient and high-intensity meteorological factors such as thunder and lightning can be determined, so that fault sections caused by thunder and lightning can be positioned, and system maintenance and power grid channel transformation are facilitated.

Description

Technical Field

[0001] This invention relates to the field of power communication networks, and in particular to a method, apparatus, equipment, and medium for identifying lightning-induced faults. Background Technology

[0002] As the coverage of digital information networks continues to expand and the widespread application of digital terminals drives the continuous expansion of communication network scale, the number of high-capacity optical communication devices and optical transmission links in the network is constantly increasing to meet the demand for low latency and high bandwidth. In power communication networks based on optical communication as an important technology, the backbone communication network mainly uses power-specific fiber-optic composite overhead ground wire (OPGW) optical cables for optical transmission link organization. Optical communication equipment is gradually developing towards high-capacity transmission capabilities, while network technology is evolving from 10Gbit / s SDH to 100Gbit / s OTN. The OPGW is composed of steel and aluminum on the outside and contains optical cables. It is erected at the top of the transmission tower and has lightning protection grounding function. However, when the lightning strike intensity is too high, it will produce a very strong magneto-optical rotation effect on the optical signals carried by the internal optical fibers, which may cause bit errors or interruptions in OTN (Optical Transport Network) systems using phase modulation technology. Because the strong lightning strike occurs for a short time, the circuit fault caused by lightning is easily overlooked among the many alarms in the system, which brings great trouble to the operation and maintenance of OTN systems using digital modulation.

[0003] At present, it is not possible to effectively detect problems through the system's own network management. The only way to reduce the impact of strong lightning is to increase the network signal-to-noise ratio redundancy and improve the system's fault tolerance. Furthermore, it is impossible to identify whether the system failure is caused by strong lightning strikes on the OPGW optical cable. Summary of the Invention

[0004] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes a method for identifying lightning-induced faults, which can determine power grid faults caused by meteorological factors such as lightning, which are brief and intense, thereby locating the faulty segment caused by lightning, facilitating system maintenance and power grid channel upgrades.

[0005] The present invention also proposes an apparatus, device and medium having the above-mentioned method for identifying lightning-induced faults.

[0006] A method for identifying lightning-induced faults according to a first aspect of the present invention, applied to an OTN system, includes: Obtain abnormal alarm information; Based on the abnormal alarm information, construct a sequence of abnormal lightning-induced causes to be verified. Based on the lightning-induced abnormality sequence to be verified, a system fault matrix is ​​constructed; The system fault matrix is ​​matched with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information; Based on the lightning information and the lightning-induced anomaly sequence to be verified, verify whether the fault occurring in the corresponding fault segment is a lightning-induced fault.

[0007] A method for identifying lightning-induced faults according to an embodiment of the present invention has at least the following beneficial effects: First, the present invention obtains a system fault matrix through abnormal alarm information. The system fault matrix actually indicates faults that may be caused by lightning in the abnormal alarm information. Then, by matching the lightning information with the occurrence time, the anomalies caused by each lightning information are determined, and the location segment of the anomaly is the fault segment corresponding to the lightning information, thus refining the abnormal alarms in time and space. Finally, based on the lightning information and the lightning-induced anomaly verification sequence, the method verifies whether the fault occurring in the fault segment is a lightning-induced fault, ultimately identifying the lightning-induced fault. The present invention can identify power grid faults caused by short-lived and high-intensity meteorological factors such as lightning, thereby locating the lightning-induced fault segment, facilitating system maintenance and power grid channel upgrades.

[0008] According to some embodiments of the present invention, constructing the system fault matrix based on the lightning-induced abnormality sequence to be verified includes: Based on the lightning-induced anomaly verification sequence, the occurrence time, alarm type, and occurrence site of each alarm event are obtained; wherein, the lightning-induced anomaly verification sequence includes at least one alarm event, and the alarm event includes the occurrence time, alarm type, and occurrence site; Based on the location of each alarm event and the obtained location information of the alarm event, the coordinates of each alarm event and the multiplexing segment number of each alarm event are obtained. By linking the occurrence time of each alarm event, the coordinates of each occurrence site, the multiplex segment number of each occurrence site, and the alarm type with the occurrence site of each alarm event, a system fault matrix is ​​obtained.

[0009] According to some embodiments of the present invention, the step of matching the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information includes: The system fault matrix and the lightning information are preprocessed respectively; Based on the preprocessed system fault matrix and the lightning information, spatial-temporal weighting is performed to obtain the spatial distance and time difference from each lightning event to each alarm event; Based on the spatial distance and time difference between each lightning event and each alarm event, a similarity matrix corresponding to each lightning event is obtained; In the similarity matrix corresponding to a certain lightning event, the reuse segment number corresponding to the most similarity vector is determined as the fault segment corresponding to that lightning event, until the fault segment corresponding to each lightning event is identified.

[0010] According to some embodiments of the present invention, obtaining the similarity matrix corresponding to each lightning event based on the spatial distance and time difference from each lightning event to each alarm event includes: For a given lightning event, spatial weights and temporal weights are obtained based on the spatial distance and time difference between the lightning event and each alarm event. The weighting coefficients are obtained based on the spatial weights and the temporal weights. A similarity matrix is ​​obtained based on the system fault matrix, the lightning information, and the weighting coefficients.

[0011] According to some embodiments of the present invention, verifying whether the fault occurring in the corresponding fault segment is a lightning-induced fault based on the lightning information and the lightning-induced abnormality sequence to be verified includes: The rate of change of the optical signal is obtained based on the lightning current intensity in the lightning information and the alarm duration in the lightning-induced abnormality unverified sequence. Determine whether the rate of change of the optical signal exceeds the preset lightning protection threshold. If so, the fault occurring in the corresponding fault segment is a lightning-induced fault; otherwise, it is not a lightning-induced fault.

[0012] According to some embodiments of the present invention, it further includes: After verifying whether the fault in the corresponding fault segment is a lightning-induced fault, for a certain fault segment, based on the optical signal change rate and the lightning protection threshold, the segment-level risk of the fault segment, i.e. the risk level of the fault segment experiencing a lightning-induced fault, is obtained. Based on the obtained basic cost of the faulty segment, the preset risk amplification coefficient, and the segment-level risk, the path cost of the faulty segment is obtained. Based on the path cost of each fault segment, a set of alternative paths is obtained; From the set of optional paths, the optional path with the lowest path cost is selected as the path to be used.

[0013] A lightning-induced fault identification device according to a second aspect embodiment of the present invention, applied to an OTN system, includes: The monitoring module is used to acquire abnormal alarm information and send the abnormal alarm information to the fault matrix construction module; The fault matrix construction module is connected to the monitoring module and the identification module respectively, and is used to construct a lightning-induced abnormality unverification sequence based on the abnormal alarm information; construct a system fault matrix based on the lightning-induced abnormality unverification sequence; and send the system fault matrix to the identification module. The identification module is used to acquire lightning information; match the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information; and verify whether the fault occurring in the corresponding fault segment is a lightning-induced fault based on the lightning information and the lightning-induced abnormality unverified sequence.

[0014] According to some embodiments of the present invention, the fault matrix construction module constructs a system fault matrix based on the lightning-induced abnormality sequence to be verified, including: Based on the lightning-induced anomaly verification sequence, the occurrence time, alarm type, and occurrence site of each alarm event are obtained; wherein, the lightning-induced anomaly verification sequence includes at least one alarm event, and the alarm event includes the occurrence time, alarm type, and occurrence site; Based on the location of each alarm event and the obtained location information of the alarm event, the coordinates of each alarm event and the multiplexing segment number of each alarm event are obtained. By linking the occurrence time of each alarm event, the coordinates of each occurrence site, the multiplex segment number of each occurrence site, and the alarm type with the occurrence site of each alarm event, a system fault matrix is ​​obtained.

[0015] According to some embodiments of the present invention, the identification module matches the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information, including: The system fault matrix and the lightning information are preprocessed respectively; Based on the preprocessed system fault matrix and the lightning information, spatial-temporal weighting is performed to obtain the spatial distance and time difference from each lightning event to each alarm event; Based on the spatial distance and time difference between each lightning event and each alarm event, a similarity matrix corresponding to each lightning event is obtained; In the similarity matrix corresponding to a certain lightning event, the reuse segment number corresponding to the most similarity vector is determined as the fault segment corresponding to that lightning event, until the fault segment corresponding to each lightning event is identified.

[0016] According to some embodiments of the present invention, the identification module obtains a similarity matrix corresponding to each lightning event based on the spatial distance and time difference between each lightning event and each alarm event, including: For a given lightning event, spatial weights and temporal weights are obtained based on the spatial distance and time difference between the lightning event and each alarm event. The weighting coefficients are obtained based on the spatial weights and the temporal weights. A similarity matrix is ​​obtained based on the system fault matrix, the lightning information, and the weighting coefficients.

[0017] According to some embodiments of the present invention, verifying whether the fault occurring in the corresponding fault segment is a lightning-induced fault based on the lightning information and the lightning-induced abnormality sequence to be verified includes: The rate of change of the optical signal is obtained based on the lightning current intensity in the lightning information and the alarm duration in the lightning-induced abnormality unverified sequence. Determine whether the rate of change of the optical signal exceeds the preset lightning protection threshold. If so, the fault occurring in the corresponding fault segment is a lightning-induced fault; otherwise, it is not a lightning-induced fault.

[0018] According to some embodiments of the present invention, after verifying whether the fault occurring in the corresponding fault segment is a lightning-induced fault, the identification module obtains the segment-level risk of a certain fault segment, i.e., the risk level of the fault segment experiencing a lightning-induced fault, based on the optical signal change rate and the lightning protection threshold. The device further includes: A path planning module, connected to the identification module, is used to receive the risk level of lightning-induced faults in each fault segment sent by the identification module; obtain the path cost of the fault segment based on the obtained basic cost of the fault segment, the preset risk amplification coefficient, and the segment-level risk; obtain a set of optional paths based on the path costs of each fault segment; and select the optional path with the lowest path cost from the set of optional paths as the path to be used.

[0019] An electronic device according to a third aspect of the present invention includes: Memory, used to store programs; A processor for executing a program stored in the memory, wherein when the processor executes the program stored in the memory, the processor is configured to perform the method as described in any one of the first aspects.

[0020] According to a fourth aspect of the present invention, a storage medium stores computer-executable instructions for performing the method as described in any one of the first aspects.

[0021] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0022] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0023] Figure 1 This is a flowchart of a method for identifying lightning-induced faults according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a lightning-induced fault identification device provided in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0025] It should be understood that in the description of the embodiments of the present invention, "multiple" (or "amounts") means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. If "first," "second," etc., are used in the description, they are only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0026] like Figure 1 As shown, this embodiment of the invention provides a method for identifying lightning-induced faults, applied to an OTN system, including: Step S100: Obtain abnormal alarm information; Step S200: Based on the abnormal alarm information, construct the lightning-induced abnormal sequence to be verified; Step S300: Construct a system fault matrix based on the lightning-induced abnormal sequence to be verified; Step S400: Match the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information; Step S500: Based on the lightning information and the lightning-induced abnormality sequence to be verified, verify whether the fault occurring in the corresponding fault segment is a lightning-induced fault.

[0027] This embodiment first obtains a system fault matrix from abnormal alarm information. The system fault matrix actually indicates the faults that may be caused by lightning in the abnormal alarm information. Then, by matching the occurrence time with the lightning information, the anomalies caused by each lightning information are determined. The location segment of the anomaly is the fault segment corresponding to the lightning information, thus refining the abnormal alarms in time and space. Finally, based on the lightning information and the lightning-induced anomaly verification sequence, it is verified whether the fault occurring in the fault segment is a lightning-induced fault, and the lightning-induced fault is finally identified. This embodiment can identify power grid faults caused by short-lived and high-intensity meteorological factors such as lightning, thereby locating the lightning-induced fault segment, which facilitates system maintenance and power grid channel modification.

[0028] In one embodiment, in step S200, constructing the lightning-induced abnormality verification sequence based on the abnormal alarm information includes: From the abnormal alarm information, those alarm information that all meet the following conditions are selected as the lightning-induced abnormality to be verified sequence: The alarm type is a bit error or interruption, and the alarm duration is within the preset lightning fault duration range.

[0029] In one embodiment, the duration of the lightning fault ranges from 1 to 2 seconds.

[0030] It should be noted that in a typical power OTN optical communication network, the system mainly consists of OTN equipment and OPGW optical cables (with a small amount of ordinary optical cables). During normal operation, the network management system monitors the network's operating status and key indicators in real time, and generates alarm information upon detecting system faults. Issues such as signal errors and interruptions require detailed tracing to effectively resolve, especially when the OPGW optical cable experiences a transient fault like a lightning strike and then returns to normal, making it difficult to pinpoint the root cause. To quickly locate such faults, it is necessary to first monitor the real-time operating status of each device and optical link in the OTN network, and collect signal error and interruption alarm data. For example, if some links in the OTN network repeatedly and randomly flash OTN_LOF alarms, and each alarm is immediately cleared after it occurs, with the abnormal duration lasting 1-2 seconds, a preliminary screening can be conducted to identify the lightning-induced abnormal state alarm information to be verified—that is, the lightning-induced abnormality to be verified sequence.

[0031] In one embodiment, in step S300, constructing the system fault matrix based on the lightning-induced abnormality sequence to be verified includes: Based on the lightning-induced anomaly unverified sequence, the occurrence time, alarm type, and occurrence site of each alarm event are obtained; wherein, the lightning-induced anomaly unverified sequence includes at least one alarm event, and the alarm event includes the occurrence time, alarm type, and occurrence site; Based on the location of each alarm event and the obtained location information of the alarm event, the coordinates of each alarm event and the multiplexing segment number of each alarm event are obtained. By linking the occurrence time of each alarm event, the coordinates of each occurrence site, the multiplex segment number of each occurrence site, and the alarm type with the occurrence site of each alarm event, a system fault matrix is ​​obtained.

[0032] This embodiment is based on the lightning-induced abnormal sequence to be verified constructed in step S200. It combines the GPS positioning information of substations and transmission line towers provided by the GIS system to identify the terminal station location of the optical network multiplexing section and the path of the OPGW optical cable (i.e., the location information of the site where the incident occurred). Based on clarifying the occurrence time, alarm type and occurrence site in the alarm event, it assigns a refined spatial feature vector to the alarm information sequence and constructs a system fault matrix containing refined time and spatial information.

[0033] It should be noted that the multiplexed section of a site is actually the link between sites in the OTN network, and the multiplexed section number is the number of the multiplexed section used to distinguish different optical cable routes.

[0034] In one embodiment, in step S300, constructing the system fault matrix based on the lightning-induced abnormality sequence to be verified specifically includes: The system fault matrix is ​​expressed as follows: , Among them, the abnormal lightning-induced sequence to be verified includes the occurrence time. Alarm Types , where n is the nth alarm time in the lightning-induced abnormality sequence to be verified. Represents the spatial domain eigenvector. The coordinates of each occurrence site, Number the multiplex segment for each occurrence site; It is easy to understand that each row of the system fault matrix represents a specific alarm event.

[0035] In one embodiment, in step S400, matching the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information includes: The system fault matrix and lightning information are preprocessed, specifically by inputting the spatiotemporally discrete lightning information into a spatiotemporal graphical neural network (ST-GNN) to obtain spatiotemporal embedding vectors. Let i represent the spatiotemporal embedding vector corresponding to the i-th lightning information; the system fault matrix, which is discrete in time and continuous in space, is sequentially input into a convolutional neural network (CNN) and a Transformer time series model to obtain the embedding vector. , j represents the spatiotemporal embedding vector corresponding to the alarm event in the j-th row of the system fault matrix; Based on the preprocessed system fault matrix and lightning information, spatial-temporal weighting is performed to obtain the spatial distance from each lightning event to each alarm event. Time difference Specifically, this includes: for a certain lightning event in the lightning information, the distance between the coordinates of the lightning point and the coordinates of the occurrence site in each alarm event in the system fault matrix is ​​taken as the spatial distance, and the time difference between the lightning occurrence time and the occurrence time of each alarm event in the system fault matrix is ​​taken as the time difference, until the spatial distance and time difference corresponding to each lightning event are obtained; Based on the spatial distance from each lightning event to each alarm event Time difference The similarity matrix corresponding to each lightning event is obtained. In the similarity matrix corresponding to a certain lightning event, the reuse segment number corresponding to the most similarity vector is determined as the fault segment corresponding to that lightning event, until the fault segment corresponding to each lightning event is identified.

[0036] It should be noted that lightning information includes at least one lightning event, and a lightning event includes: the coordinates of the lightning point and the time of the lightning occurrence; the similarity matrix includes at least one similarity vector, which is used to characterize the similarity between the alarm event and the lightning event; the spatiotemporal embedding vector is actually a vector that extracts and enhances the temporal and spatial features of the lightning information, and essentially vectorizes the discrete lightning information. The relationship between the embedding vector and the system fault matrix is ​​similar. The similarity vector with the highest similarity is the similarity vector with the highest modulus in the similarity matrix.

[0037] In one embodiment, the spatial distance from each lightning event to each alarm event is considered. Time difference The similarity matrices corresponding to each lightning event are obtained as follows: For a given lightning event, the spatial distance from the lightning event to each alarm event is considered. Time difference Spatial weights are obtained through Gaussian functions. Time weight Specifically: ; Where i is the label of the lightning event, and j is the label of the alarm event. The standard deviation of spatial distance, The standard deviation of the time difference; Based on spatial weight Time weight To obtain the weighting coefficients Specifically: ; Based on the system fault matrix, lightning information, and weighting coefficients, a similarity matrix is ​​obtained, which specifically includes: in, Let be the similarity vector in the i-th row and j-th column of the similarity matrix. These are weighting coefficients. This is the spatiotemporal embedding vector representing lightning information. The embedding vector is used to represent the system fault matrix.

[0038] In one embodiment, in step S500, verifying whether the fault occurring in the corresponding fault segment is a lightning-induced fault, based on lightning information and the lightning-induced abnormality sequence to be verified, includes: Based on the lightning current intensity and alarm duration in the lightning-induced anomaly sequence to be verified from the lightning information, the rate of change of the optical signal is obtained, specifically: in, The rate of change of the optical signal. Let t be the lightning current intensity and t be the alarm duration. For Felder constant, The vacuum permeability; Determine whether the rate of change of the optical signal exceeds the preset lightning protection threshold. If so, the fault occurring in the corresponding fault segment is a lightning-induced fault; otherwise, it is not a lightning-induced fault.

[0039] It should be noted that the formula for calculating the rate of change of the optical signal is derived from the integral form of Ampere-Maxwell's law and the Faraday effect formula; the lightning protection threshold is the lightning protection threshold specified for OTN optical communication equipment. This embodiment can determine that the alarm event is caused by the OPGW optical cable being struck by a strong lightning bolt, resulting in the optical communication equipment exceeding its tolerance range, thus achieving the final confirmation of the cause of bit error or interruption alarms in the optical communication network.

[0040] In one embodiment, the method further includes: After verifying whether the fault in the corresponding fault segment is a lightning-induced fault, for a given fault segment, based on the optical signal change rate and lightning protection threshold, the segment-level risk, i.e., the risk level of a lightning-induced fault in that segment, is obtained. ,in, For the segment-level risk of the faulty segment, The rate of change of the optical signal. To ensure lightning protection thresholds are maximized to 1, extreme values ​​should be avoided. Based on the obtained base cost of the faulty segment, the preset risk amplification factor, and the segment-level risk, the path cost of the faulty segment is obtained, specifically as follows: ,in, For path cost, Based on the cost, This is a risk amplification factor. This is a segment-level risk; Based on the path cost of each fault segment, a set of optional paths is obtained, specifically: the working path is selected on the network graph according to the principle of minimizing the total cost. The calculation method is as follows: ,in, To start from the source To the destination The set of optional paths; From the set of available paths, the path with the lowest path cost is selected as the path to use.

[0041] It is easy to understand that when a faulty segment experiences multiple lightning-induced abnormal sequences that need to be verified, its risk level is determined by the rate of change of the optical signal corresponding to the multiple alarm events.

[0042] In one embodiment, the method further includes: When the segment-level risk of a faulty segment exceeds a preset switching threshold, a backup path is selected as the current path of use based on the set of available paths, specifically: When path Before taking office risk Exceeding the switching threshold At that time, triggering a search for alternative paths The overall migration enables business avoidance and protection based on the impact of lightning strikes: Among them, the switching threshold Designed by humans, .

[0043] like Figure 2 As shown, this embodiment of the invention also provides a lightning-induced fault identification device, applied to an OTN system, comprising: The monitoring module is used to acquire abnormal alarm information and send it to the fault matrix construction module. The fault matrix construction module is connected to the monitoring module and the identification module respectively. It is used to construct a lightning-induced abnormality unverified sequence based on abnormal alarm information; construct a system fault matrix based on the lightning-induced abnormality unverified sequence; and send the system fault matrix to the identification module. The identification module is used to acquire lightning information; match the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information; and verify whether the fault occurring in the corresponding fault segment is a lightning-induced fault based on the lightning information and the lightning-induced abnormal sequence to be verified.

[0044] The fault matrix construction module first obtains a system fault matrix from the abnormal alarm information acquired by the monitoring module. This system fault matrix actually indicates faults that may be caused by lightning in the abnormal alarm information. The identification module then matches the lightning information with its occurrence time to determine the anomalies caused by each lightning event. The location of the anomaly is the fault segment corresponding to the lightning information, thus refining the spatiotemporal nature of the abnormal alarms. Finally, based on the lightning information and the lightning-induced anomaly sequence to be verified, the module verifies whether the fault occurring in the fault segment is a lightning-induced fault, ultimately identifying the lightning-induced fault. This embodiment can identify power grid faults caused by short-lived and high-intensity meteorological factors such as lightning, thereby locating lightning-induced fault segments, facilitating system maintenance and power grid channel upgrades.

[0045] In one embodiment, the fault matrix construction module constructs a lightning-induced abnormality verification sequence based on abnormal alarm information, including: From the abnormal alarm information, those alarm information that all meet the following conditions are selected as the lightning-induced abnormality to be verified sequence: The alarm type is a bit error or interruption, and the alarm duration is within the preset lightning fault duration range.

[0046] In one embodiment, the duration of the lightning fault ranges from 1 to 2 seconds.

[0047] It should be noted that in a typical power OTN optical communication network, the system mainly consists of OTN equipment and OPGW optical cables (with a small amount of ordinary optical cables). During normal operation, the network management system monitors the network's operating status and key indicators in real time, and generates alarm information upon detecting system faults. Issues such as signal errors and interruptions require detailed tracing to effectively resolve, especially when the OPGW optical cable experiences a transient fault like a lightning strike and then returns to normal, making it difficult to pinpoint the root cause. To quickly locate such faults, it is necessary to first monitor the real-time operating status of each device and optical link in the OTN network, and collect signal error and interruption alarm data. For example, if some links in the OTN network repeatedly and randomly flash OTN_LOF alarms, and each alarm is immediately cleared after it occurs, with the abnormal duration lasting 1-2 seconds, a preliminary screening can be conducted to identify the lightning-induced abnormal state alarm information to be verified—that is, the lightning-induced abnormality to be verified sequence.

[0048] In one embodiment, the fault matrix construction module constructs a system fault matrix based on the lightning-induced abnormality sequence to be verified, including: Based on the lightning-induced anomaly unverified sequence, the occurrence time, alarm type, and occurrence site of each alarm event are obtained; wherein, the lightning-induced anomaly unverified sequence includes at least one alarm event, and the alarm event includes the occurrence time, alarm type, and occurrence site; Based on the location of each alarm event and the obtained location information of the alarm event, the coordinates of each alarm event and the multiplexing segment number of each alarm event are obtained. By linking the occurrence time of each alarm event, the coordinates of each occurrence site, the multiplex segment number of each occurrence site, and the alarm type with the occurrence site of each alarm event, a system fault matrix is ​​obtained.

[0049] This embodiment is based on the lightning-induced anomaly sequence to be verified constructed in the above steps. It combines the GPS positioning information of substations and transmission line towers provided by the GIS system to identify the terminal station location of the optical network multiplexing section and the path of the OPGW optical cable (i.e., the location information of the site where the incident occurred). Based on clarifying the occurrence time, alarm type and occurrence site in the alarm event, it assigns a refined spatial feature vector to the alarm information sequence and constructs a system fault matrix containing refined time and spatial information.

[0050] It should be noted that the multiplexed section of a site is actually the link between sites in the OTN network, and the multiplexed section number is the number of the multiplexed section used to distinguish different optical cable routes.

[0051] In one embodiment, the fault matrix construction module constructs a system fault matrix based on the lightning-induced abnormality sequence to be verified, specifically including: The system fault matrix is ​​expressed as follows: , Among them, the abnormal lightning-induced sequence to be verified includes the occurrence time. Alarm Types , where n is the nth alarm time in the lightning-induced abnormality sequence to be verified. Represents the spatial domain eigenvector. The coordinates of each occurrence site, Number the multiplex segment for each occurrence site; It is easy to understand that each row of the system fault matrix represents a specific alarm event.

[0052] In one embodiment, the identification module matches the system fault matrix with the acquired lightning information based on the occurrence time to obtain the fault segment corresponding to the lightning information, including: The system fault matrix and lightning information are preprocessed separately, specifically including: inputting the spatiotemporally discrete lightning information into a spatiotemporal graph neural network (ST-GNN) to obtain spatiotemporal embedding vectors. Let i represent the spatiotemporal embedding vector corresponding to the i-th lightning information; the system fault matrix, which is discrete in time and continuous in space, is sequentially input into a convolutional neural network (CNN) and a Transformer time series model to obtain the embedding vector. , j represents the spatiotemporal embedding vector corresponding to the alarm event in the j-th row of the system fault matrix; Based on the preprocessed system fault matrix and lightning information, spatial-temporal weighting is performed to obtain the spatial distance and time difference between each lightning event and each alarm event. Specifically, for a certain lightning event in the lightning information, the distance between the coordinates of the lightning point and the coordinates of the occurrence site in each alarm event in the system fault matrix is ​​taken as the spatial distance, and the time difference between the lightning occurrence time and the occurrence time of each alarm event in the system fault matrix is ​​taken as the time difference, until the spatial distance and time difference corresponding to each lightning event are obtained. Based on the spatial distance and time difference between each lightning event and each alarm event, a similarity matrix corresponding to each lightning event is obtained; In the similarity matrix corresponding to a certain lightning event, the reuse segment number corresponding to the most similarity vector is determined as the fault segment corresponding to that lightning event, until the fault segment corresponding to each lightning event is identified.

[0053] It should be noted that lightning information includes at least one lightning event, and a lightning event includes: the coordinates of the lightning point and the time of the lightning occurrence; the similarity matrix includes at least one similarity vector, which is used to characterize the similarity between the alarm event and the lightning event; the spatiotemporal embedding vector is actually a vector that extracts and enhances the temporal and spatial features of the lightning information, and essentially vectorizes the discrete lightning information. The relationship between the embedding vector and the system fault matrix is ​​similar. The similarity vector with the highest similarity is the similarity vector with the highest modulus in the similarity matrix.

[0054] In one embodiment, the identification module determines the location of each lightning event based on the spatial distance to each alarm event. Time difference The similarity matrices corresponding to each lightning event are obtained as follows: For a given lightning event, the spatial distance from the lightning event to each alarm event is considered. Time difference Spatial weights are obtained through Gaussian functions. Time weight Specifically: ; Where i is the label of the lightning event, and j is the label of the alarm event. The standard deviation of spatial distance, The standard deviation of the time difference; Based on spatial weight Time weight To obtain the weighting coefficients Specifically: ; Based on the system fault matrix, lightning information, and weighting coefficients, a similarity matrix is ​​obtained, which specifically includes: in, Let be the similarity vector in the i-th row and j-th column of the similarity matrix. These are weighting coefficients. This is the spatiotemporal embedding vector representing lightning information. The embedding vector is used to represent the system fault matrix.

[0055] In one embodiment, verifying whether the fault occurring in the corresponding fault segment is a lightning-induced fault, based on lightning information and the lightning-induced abnormality sequence to be verified, includes: Based on the lightning current intensity and alarm duration in the lightning-induced anomaly sequence to be verified from the lightning information, the rate of change of the optical signal is obtained, specifically: in, The rate of change of the optical signal. Let t be the lightning current intensity and t be the alarm duration. For Felder constant, The vacuum permeability; Determine whether the rate of change of the optical signal exceeds the preset lightning protection threshold. If so, the fault occurring in the corresponding fault segment is a lightning-induced fault; otherwise, it is not a lightning-induced fault.

[0056] It should be noted that the formula for calculating the rate of change of the optical signal is derived from the integral form of Ampere-Maxwell's law and the Faraday effect formula; the lightning protection threshold is the lightning protection threshold specified for OTN optical communication equipment. This embodiment can determine that the alarm event is caused by the OPGW optical cable being struck by a strong lightning bolt, resulting in the optical communication equipment exceeding its tolerance range, thus achieving the final confirmation of the cause of bit error or interruption alarms in the optical communication network.

[0057] In one embodiment, after verifying whether the fault in the corresponding fault segment is a lightning-induced fault, the identification module, for a given fault segment, obtains the segment-level risk, i.e., the risk level of a lightning-induced fault in that fault segment, based on the optical signal change rate and the lightning protection threshold. Specifically: ,in, For the segment-level risk of the faulty segment, The rate of change of the optical signal. To ensure lightning protection thresholds are maximized to 1, extreme values ​​should be avoided. The device also includes: The path planning module, connected to the identification module, is used to receive the risk level of lightning-induced faults in each fault segment sent by the identification module; based on the obtained basic cost of the fault segment, the preset risk amplification coefficient, and the segment-level risk, the path cost of the fault segment is obtained; based on the path cost of each fault segment, a set of optional paths is obtained; and from the set of optional paths, the optional path with the lowest path cost is selected as the path to be used.

[0058] In one embodiment, the path planning module obtains the path cost of the faulty segment based on the acquired basic cost of the faulty segment, a preset risk amplification coefficient, and segment-level risk, including: Select the working path on the network diagram according to the principle of minimizing total cost. The calculation method is as follows: ,in, To start from the source To the destination The set of optional paths; It is easy to understand that when a faulty segment experiences multiple lightning-induced abnormal sequences that need to be verified, its risk level is determined by the rate of change of the optical signal corresponding to the multiple alarm events.

[0059] In one embodiment, the path planning module is further configured to: When the segment-level risk of a faulty segment exceeds a preset switching threshold, a backup path is selected as the current path of use based on the set of available paths, specifically: When path Before taking office risk Exceeding the switching threshold At that time, triggering a search for alternative paths The overall migration enables business avoidance and protection based on the impact of lightning strikes: Among them, the switching threshold Designed by humans, .

[0060] This invention also provides an electronic device, which includes, but is not limited to: Memory, used to store programs; The processor is used to execute programs stored in memory. When the processor executes the programs stored in memory, it is used to perform the aforementioned method for identifying lightning-induced faults.

[0061] The processor and memory can be connected via a bus or other means.

[0062] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the method described in the embodiments of the present invention. The processor implements the above method by running the non-transitory software program and instructions stored in the memory.

[0063] The memory may include a program storage area and a data storage area, wherein the program storage area may store the operating system and application programs required for at least one function; the data storage area may store data for executing the methods described above. Furthermore, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0064] The non-transitory software program and instructions required to implement the above terminal selection method are stored in memory and are executed by one or more processors.

[0065] This invention also provides a storage medium storing computer-executable instructions for performing the above-described methods.

[0066] In one embodiment, the storage medium stores computer-executable instructions that are executed by one or more control processors.

[0067] The embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0068] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0069] This document describes embodiments of the invention, including preferred embodiments known to the inventors for carrying out the invention. Variations of these embodiments will become apparent to those skilled in the art upon reading the foregoing description. The inventors encourage those skilled in the art to adopt such variations as appropriate, and the inventors intend to practice embodiments of the invention in ways other than those specifically described herein. Therefore, the scope of the invention includes all modifications and equivalents of the subject matter set forth in the appended claims, as permitted by applicable law. Furthermore, the scope of the invention covers any combination of the foregoing elements in all possible variations thereof, unless otherwise indicated herein or otherwise clearly contradicted by the context.

Claims

1. A method for identifying lightning-induced faults, applied to an OTN system, characterized in that, include: Obtain abnormal alarm information; Based on the abnormal alarm information, construct a sequence of abnormal lightning-induced causes to be verified. Based on the lightning-induced abnormality sequence to be verified, a system fault matrix is ​​constructed; The system fault matrix is ​​matched with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information; Based on the lightning information and the lightning-induced anomaly sequence to be verified, verify whether the fault occurring in the corresponding fault segment is a lightning-induced fault.

2. The method for identifying lightning-induced faults according to claim 1, characterized in that, The construction of the system fault matrix based on the lightning-induced abnormal sequence to be verified includes: Based on the lightning-induced anomaly verification sequence, the occurrence time, alarm type, and occurrence site of each alarm event are obtained; wherein, the lightning-induced anomaly verification sequence includes at least one alarm event, and the alarm event includes the occurrence time, alarm type, and occurrence site; Based on the location of each alarm event and the obtained location information of the alarm event, the coordinates of each alarm event and the multiplexing segment number of each alarm event are obtained. By linking the occurrence time of each alarm event, the coordinates of each occurrence site, the multiplex segment number of each occurrence site, and the alarm type with the occurrence site of each alarm event, a system fault matrix is ​​obtained.

3. The method for identifying lightning-induced faults according to claim 2, characterized in that, The step of matching the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information includes: The system fault matrix and the lightning information are preprocessed respectively; Based on the preprocessed system fault matrix and the lightning information, spatial-temporal weighting is performed to obtain the spatial distance and time difference from each lightning event to each alarm event; Based on the spatial distance and time difference between each lightning event and each alarm event, a similarity matrix corresponding to each lightning event is obtained; In the similarity matrix corresponding to a certain lightning event, the reuse segment number corresponding to the most similarity vector is determined as the fault segment corresponding to that lightning event, until the fault segment corresponding to each lightning event is identified.

4. The method for identifying lightning-induced faults according to claim 3, characterized in that, The similarity matrix for each lightning event, obtained based on the spatial distance and time difference between each lightning event and each alarm event, includes: For a given lightning event, spatial weights and temporal weights are obtained based on the spatial distance and time difference between the lightning event and each alarm event. The weighting coefficients are obtained based on the spatial weights and the temporal weights. A similarity matrix is ​​obtained based on the system fault matrix, the lightning information, and the weighting coefficients.

5. The method for identifying lightning-induced faults according to claim 1, characterized in that, The step of verifying whether the fault occurring in the corresponding fault segment is a lightning-induced fault based on the lightning information and the lightning-induced abnormality sequence to be verified includes: The rate of change of the optical signal is obtained based on the lightning current intensity in the lightning information and the alarm duration in the lightning-induced abnormality unverified sequence. Determine whether the rate of change of the optical signal exceeds the preset lightning protection threshold. If so, the fault occurring in the corresponding fault segment is a lightning-induced fault; otherwise, it is not a lightning-induced fault.

6. The method for identifying lightning-induced faults according to claim 5, characterized in that, Also includes: After verifying whether the fault in the corresponding fault segment is a lightning-induced fault, for a certain fault segment, based on the optical signal change rate and the lightning protection threshold, the segment-level risk of the fault segment, i.e. the risk level of the fault segment experiencing a lightning-induced fault, is obtained. Based on the obtained basic cost of the faulty segment, the preset risk amplification coefficient, and the segment-level risk, the path cost of the faulty segment is obtained. Based on the path cost of each fault segment, a set of alternative paths is obtained; From the set of optional paths, the optional path with the lowest path cost is selected as the path to be used.

7. A device for identifying lightning-induced faults, applied to an OTN system, characterized in that, include: The monitoring module is used to acquire abnormal alarm information and send the abnormal alarm information to the fault matrix construction module; The fault matrix construction module is connected to the monitoring module and the identification module respectively, and is used to construct a lightning-induced abnormality unverified sequence based on the abnormal alarm information; Based on the lightning-induced abnormality sequence to be verified, a system fault matrix is ​​constructed; the system fault matrix is ​​then sent to the identification module. The identification module is used to acquire lightning information; match the system fault matrix with the acquired lightning information by occurrence time to obtain the fault segment corresponding to the lightning information; and verify whether the fault occurring in the corresponding fault segment is a lightning-induced fault based on the lightning information and the lightning-induced abnormality unverified sequence.

8. The lightning-induced fault identification device according to claim 7, characterized in that, The fault matrix construction module constructs a system fault matrix based on the lightning-induced abnormality sequence to be verified, including: Based on the lightning-induced anomaly verification sequence, the occurrence time, alarm type, and occurrence site of each alarm event are obtained; wherein, the lightning-induced anomaly verification sequence includes at least one alarm event, and the alarm event includes the occurrence time, alarm type, and occurrence site; Based on the location of each alarm event and the obtained location information of the alarm event, the coordinates of each alarm event and the multiplexing segment number of each alarm event are obtained. By linking the occurrence time of each alarm event, the coordinates of each occurrence site, the multiplex segment number of each occurrence site, and the alarm type with the occurrence site of each alarm event, a system fault matrix is ​​obtained.

9. The lightning-induced fault identification device according to claim 8, characterized in that, The identification module matches the system fault matrix with the acquired lightning information based on the occurrence time to obtain the fault segments corresponding to the lightning information, including: The system fault matrix and the lightning information are preprocessed respectively; Based on the preprocessed system fault matrix and the lightning information, spatial-temporal weighting is performed to obtain the spatial distance and time difference from each lightning event to each alarm event; Based on the spatial distance and time difference between each lightning event and each alarm event, a similarity matrix corresponding to each lightning event is obtained; In the similarity matrix corresponding to a certain lightning event, the reuse segment number corresponding to the most similarity vector is determined as the fault segment corresponding to that lightning event, until the fault segment corresponding to each lightning event is identified.

10. The lightning-induced fault identification device according to claim 9, characterized in that, The identification module obtains a similarity matrix for each lightning event based on the spatial distance and time difference between each lightning event and each alarm event, including: For a given lightning event, spatial weights and temporal weights are obtained based on the spatial distance and time difference between the lightning event and each alarm event. The weighting coefficients are obtained based on the spatial weights and the temporal weights. A similarity matrix is ​​obtained based on the system fault matrix, the lightning information, and the weighting coefficients.

11. The lightning-induced fault identification device according to claim 7, characterized in that, The step of verifying whether the fault occurring in the corresponding fault segment is a lightning-induced fault based on the lightning information and the lightning-induced abnormality sequence to be verified includes: The rate of change of the optical signal is obtained based on the lightning current intensity in the lightning information and the alarm duration in the lightning-induced abnormality unverified sequence. Determine whether the rate of change of the optical signal exceeds the preset lightning protection threshold. If so, the fault occurring in the corresponding fault segment is a lightning-induced fault; otherwise, it is not a lightning-induced fault.

12. The lightning-induced fault identification device according to claim 11, characterized in that, After verifying whether the fault in the corresponding fault segment is a lightning-induced fault, the identification module obtains the segment-level risk of a certain fault segment, i.e. the risk level of the fault segment experiencing a lightning-induced fault, based on the optical signal change rate and the lightning protection threshold. The device further includes: A path planning module, connected to the identification module, is used to receive the risk level of lightning-induced faults in each fault segment sent by the identification module; obtain the path cost of the fault segment based on the obtained basic cost of the fault segment, the preset risk amplification coefficient, and the segment-level risk; obtain a set of optional paths based on the path costs of each fault segment; and select the optional path with the lowest path cost from the set of optional paths as the path to be used.

13. An electronic device, characterized in that, include: Memory, used to store programs; A processor for executing a program stored in the memory, wherein when the processor executes the program stored in the memory, the processor is configured to perform the method as described in any one of claims 1 to 6.

14. A storage medium, characterized in that, The device stores computer-executable instructions for performing the method as described in any one of claims 1 to 6.

Images