Submarine cable detection method and device and nonvolatile storage medium

Abstract

The invention discloses a submarine cable detection method and device and a nonvolatile storage medium. The method comprises the following steps: acquiring the position of a fault point under the condition that a submarine cable is detected to have a fault; determining a first target search range corresponding to the position of the fault point based on the fault positioning response time, the submarine cable routing information processing time and the ocean current speed; determining a fault probability of each routing section of the submarine cable in the first target search range based on the submarine cable depth data, the water depth data and the environment data in the first target search range; and sorting the fault probabilities of the routing segments to obtain a routing segment sequence, and scheduling the patrol ship to perform fault detection based on the routing segment sequence. According to the method and the device, the technical problems of low response speed and low processing efficiency caused by inaccurate positioning and large range of the fault range propagated by the fault point when the submarine cable is identified to have a fault when the submarine cable is monitored in the related technology are solved.

Description

Technical Field

[0001] The present application relates to the field of cable detection, and in particular, to a method and device for detecting a submarine cable, and a non-volatile storage medium. Background Art

[0002] Submarine cables (i.e., submarine cables) are the infrastructure of submarine networks and are an important link connecting different sea and land information centers. With the growing trend of global Internet traffic, submarine networks carry more than 50% of global Internet traffic, playing a pivotal role. Submarine cables are mainly composed of multiple optical cables, cables, wires, waterproof layers, outer sheaths, etc.

[0003] When repairing a submarine cable, it is usually necessary to wait for the fleet to depart from the fleet's home port, travel to the vicinity of the fault point, determine the fault condition, and repair the fault point. Due to the long length of the submarine cable and the impact of climate change, there are delays in the transmission of submarine cable status data and the delay in the satellite transmission of patrol ship automatic identification system (Automatic Identification System, referred to as AIS) data, which will lead to inaccurate positioning of the fault location point. It will take a long time for the fleet to depart from the home port to the vicinity of the fault point. In addition, due to the relatively wide positioning range of the fault point in the relevant technology, the response time is relatively long, and the sea conditions are complex, the fleet cannot quickly locate and reach the exact fault location. Therefore, in the relevant technology, when monitoring the submarine cable, when it is identified that the submarine cable has a fault, the fault range of the fault point is inaccurately located and the range is large, resulting in technical problems such as slow response speed and low processing efficiency.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method, device and non-volatile storage medium for detecting a submarine cable, so as to at least solve the technical problem in the related art that when monitoring a submarine cable, when a fault is identified in the submarine cable, the fault range propagated from the fault point is inaccurately located and the range is large, resulting in slow response speed and low processing efficiency.

[0006] According to one aspect of an embodiment of the present application, a method for detecting a submarine cable is provided, comprising: obtaining a fault point location when a fault is detected in the submarine cable; determining a first target search range corresponding to the fault point location based on a fault location response time, a submarine cable routing information processing time, and an ocean current speed, wherein the fault location response time is used to indicate a time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate a time required to obtain routing information of the fault point location; determining a fault probability of each routing segment of the submarine cable in the first target search range based on submarine cable depth data, water depth data, and environmental data in the first target search range, wherein the environmental data at least includes seabed topography and ocean current data in the first target search range; sorting the fault probabilities of each routing segment to obtain a routing segment sequence, and scheduling patrol ships for fault detection based on the routing segment sequence.

[0007] In some embodiments of the present application, when a submarine cable failure is detected, the location of the fault point is obtained, including: forming a mesh communication network based on all patrol ships, wherein each node in the mesh communication network represents a patrol ship; determining the shortest communication path of the mesh communication network; and obtaining the location of the fault point based on the shortest communication path.

[0008] In some embodiments of the present application, based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, a first target search range corresponding to the fault point location is determined, including: determining the sum of the fault location response time and the submarine cable routing information processing time as the fault propagation time; determining the product of the fault propagation time and the ocean current speed as the fault propagation length; taking the fault point location as the starting point, and expanding to both ends according to the routing line indicated by the fault point location to the fault propagation length to obtain the first target search range.

[0009] In some embodiments of the present application, the method also includes: acquiring submarine cable status data at intervals of a first preset time period, wherein the submarine cable status data includes at least the optical signal strength, temperature, and stress of the submarine cable; determining that a submarine cable failure has occurred when the submarine cable status data acquired in any first preset time period satisfies at least one of the following: the change in optical signal strength exceeds a first preset threshold; the change in temperature exceeds a second preset threshold; the change in stress exceeds a third preset threshold.

[0010] In some embodiments of the present application, the failure probabilities of various routing segments are sorted to obtain a routing segment sequence, and patrol ships are scheduled for fault detection based on the routing segment sequence, including: sorting the failure probabilities of various routing segments in order from large to small to obtain a first routing sequence; determining a routing segment whose failure probability is greater than a preset probability threshold as a first routing segment; and scheduling a patrol ship for fault detection based on the first routing sequence when the first routing segment does not exist in the first routing sequence.

[0011] In some embodiments of the present application, when there is a first routing segment in the first routing sequence, the method also includes: determining the total number of first routing segments; when the total number of first routing segments is less than a fourth preset threshold, scheduling patrol ships for fault detection based on the first routing sequence; when the total number of first routing segments is greater than or equal to the fourth preset threshold, clustering all first routing segments into high-risk areas, and sorting routing segments outside the first routing segments in order of fault probability from large to small to obtain a second routing sequence; scheduling patrol ships for fault detection based on the high-risk area and the second routing sequence, wherein the fault detection priority of the high-risk area is higher than the fault detection priority of the second routing sequence.

[0012] In some embodiments of the present application, after determining the first target search range corresponding to the fault point location, the method also includes: acquiring real-time sea condition data, real-time weather data, and historical fault data corresponding to the first target search range, wherein the real-time sea condition data at least includes the wave height and wind speed at the time of acquisition, and the real-time weather data at least includes the visibility and rainfall at the time of acquisition; determining a submarine cable repair plan based on the real-time sea condition data, real-time weather data, and historical fault data.

[0013] In some embodiments of the present application, the method also includes: obtaining the data to be predicted at intervals of a second preset time period, wherein the data to be predicted includes the submarine cable status update frequency, the submarine cable routing information processing time, the submarine cable status data, and the position information and communication capability data of the patrol ship, and the submarine cable status data includes at least the optical signal strength, temperature, and stress of the submarine cable; using the prediction model to predict the data to be predicted to obtain a prediction result, wherein the prediction result is used to predict the change of the submarine cable status within a preset time in the future.

[0014] In some embodiments of the present application, when the prediction result indicates that the predicted signal attenuation exceeds the first preset risk threshold, a first-level alarm is activated, and a first-level alarm information is generated and sent to the user terminal of the corresponding level; when the prediction result indicates that the predicted signal attenuation exceeds the second preset risk threshold, a second-level alarm is activated, and a second-level alarm information is generated and sent to the user terminal of the corresponding level; when the prediction result indicates that the predicted signal attenuation exceeds the third preset risk threshold, a third-level alarm is activated and a third-level alarm information is generated and sent to the user terminal of the corresponding level, wherein the values ​​of the first preset risk threshold, the second preset risk threshold, and the third preset risk threshold gradually increase; the cruise ship density and the submarine cable bandwidth of the predicted abnormal area indicated in the first-level alarm information, the second-level alarm information, and the third-level alarm information are adjusted respectively, wherein the priorities of the first-level alarm information, the second-level alarm information, and the third-level alarm information gradually increase.

[0015] According to another aspect of an embodiment of the present application, a submarine cable detection device is also provided, including: an acquisition module, used to acquire the location of a fault point when a fault is detected in the submarine cable; a first determination module, used to determine a first target search range corresponding to the location of the fault point based on the fault location response time, the submarine cable routing information processing time and the current speed, wherein the fault location response time is used to indicate the time required to determine the location of the fault point, and the submarine cable routing information processing time is used to indicate the time required to obtain routing information of the location of the fault point; a second determination module, used to determine the failure probability of each routing segment of the submarine cable in the first target search range based on the submarine cable depth data, water depth data and environmental data in the first target search range, wherein the environmental data at least includes the seabed topography and ocean current data in the first target search range; a sorting module, used to sort the failure probability of each routing segment, obtain a routing segment sequence, and dispatch patrol ships for fault detection based on the routing segment sequence.

[0016] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a program is stored, wherein when the program is running, a device where the non-volatile storage medium is located is controlled to execute the above-mentioned submarine cable detection method.

[0017] According to another aspect of an embodiment of the present application, there is further provided an electronic device, comprising: a memory and a processor, wherein the processor is configured to run a program stored in the memory, wherein the above-mentioned submarine cable detection method is implemented when the program is run.

[0018] According to another aspect of an embodiment of the present application, a computer program product is further provided, including computer instructions, and when the computer instructions are executed by a processor, the above-mentioned submarine cable detection method is implemented.

[0019] In an embodiment of the present application, when a submarine cable fault is detected, the location of the fault point is obtained; based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, the first target search range corresponding to the fault point location is determined, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain routing information of the fault point location; based on the submarine cable depth data, water depth data and environmental data of the first target search range, the failure probability of each routing segment of the submarine cable in the first target search range is determined, wherein the environmental data at least includes the seabed topography and ocean current data of the first target search range; the failure probability of each routing segment is sorted to obtain a routing segment sequence, and based on The method of scheduling patrol ships for fault detection by using a routing segment sequence obtains the location of the fault point, and then determines the first target search range corresponding to the location of the fault point according to the fault location response time, the submarine cable routing information processing time and the current speed, and then determines the fault probability of each routing segment in the first target search range, sorts the fault probability of each routing segment, obtains the routing segment sequence, and finally schedules patrol ships for fault detection based on the routing segment sequence, thereby achieving the purpose of accurately locating the fault range and improving the response time and fault handling efficiency, thereby solving the technical problem in the related technology that when monitoring the submarine cable, when a fault is identified in the submarine cable, the fault range propagated by the fault point is inaccurately located and the range is large, resulting in slow response speed and low processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a submarine cable detection method provided in an embodiment of the present application;

[0022] Figure 2 is a flow chart of a submarine cable detection method provided according to an embodiment of the present application;

[0023] Figure 3 is a flowchart of submarine cable status prediction provided according to an embodiment of the present application;

[0024] Figure 4 It is a flow chart for comparing a prediction result with actual monitoring data provided in an embodiment of the present application;

[0025] Figure 5 It is a flow chart of a submarine cable intelligent maintenance and monitoring process provided according to an embodiment of the present application;

[0026] Figure 6 It is a structural schematic diagram of a submarine cable detection device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0028] The information collected in the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or reject automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0031] Automatic Identification System (AIS) for patrol vessels: refers to a new navigation aid system used for maritime safety and communication between ships and shores, and between ships. It is usually composed of a Very High Frequency (VHF) communicator (used for short-range wireless communication between ships and between ships and coastal stations), a Global Positioning System (GPS) locator, and a communication controller connected to shipboard displays and sensors. It can automatically exchange important information such as ship position, speed, heading, ship name, call sign, etc. While the AIS installed on the ship sends this information to the outside, it also receives information from other patrol ships within the VHF coverage area, thereby achieving automatic response. In addition, as an open data transmission system, it can be connected to terminal equipment such as radar, Automatic Radar Plotting Aid (ARPA), Electronic Chart Display and Information System (ECDIS), Vessel Traffic Service (VTS) and the Internet to form a maritime traffic control and surveillance network. It is an effective means of obtaining traffic information without radar detection, and can effectively reduce patrol ship collision accidents.

[0032] Universal Transverse Mercator (UTM): is a commonly used map projection method, mainly used in geographic information systems (GIS) and mapping. It divides the earth's surface into multiple longitudinal zones, each of which uses the Transverse Mercator projection. Each zone of the UTM projection has an independent coordinate system measured in meters. This method makes it possible to perform high-precision positioning and mapping within each zone. The UTM coordinate system consists of Easting and Northing. The Easting coordinate represents the east-west distance relative to the center of the zone, and the Northing coordinate represents the distance in the north-south direction. Because the UTM projection maintains a small deformation within each zone, it is suitable for high-precision mapping of smaller areas, such as urban planning, land management, and environmental monitoring. In addition, the UTM projection also facilitates data integration and analysis, allowing users to effectively exchange and use data in different geographic information systems.

[0033] Source-driven routing protocol (Ad hoc On-Demand Distance Vector Routing, referred to as AODV): is a dynamic routing protocol for wireless ad hoc networks (Ad Hoc Network). It is mainly used for communication between mobile nodes. The main feature of AODV is that it only establishes routes when needed. The route discovery process is initiated when the source node needs to send data. This on-demand feature reduces unnecessary routing maintenance overhead. As the network topology changes, AODV can dynamically update routing information to adapt to the movement of nodes. AODV uses a distance vector routing algorithm to calculate the shortest path to the destination node and selects the path during the route discovery process. In the mesh communication network formed by AIS identification patrol ships, the use of the AODV routing protocol has many advantages, especially in a dynamic and mobile marine environment.

[0034] In the related art, when repairing a submarine cable, it is usually necessary to wait for the fleet to depart from the fleet's home port, travel to the vicinity of the fault point, determine the fault condition, and repair the fault point. Due to the long length of the submarine cable and the impact of climate change, there are delays in the transmission of submarine cable status data and the delay in the satellite transmission of patrol ship automatic identification system (Automatic Identification System, referred to as AIS) data, which will lead to inaccurate positioning of the fault location point. Therefore, there is a problem in the related art that when monitoring the submarine cable, when it is identified that the submarine cable has a fault, the fault range of the fault point is inaccurately located and the range is large, resulting in slow response speed and low processing efficiency. In order to solve this problem, a relevant solution is provided in the embodiment of the present application, which is described in detail below.

[0035] In an embodiment of the present application, an embodiment of a method for detecting a submarine cable is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a submarine cable detection method. Figure 1As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0037] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the submarine cable detection method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned submarine cable detection method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0041] In the above operating environment, an embodiment of the present application provides an embodiment of a method for detecting a submarine cable. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] The present application embodiment provides a flow chart of a method for detecting a submarine cable. Figure 2 As shown, including:

[0043] Step S202, when a fault is detected in the submarine cable (ie, the undersea cable), the fault point location is obtained.

[0044] In the technical solution provided in step S202, when a submarine cable failure is detected, there are multiple ways to obtain the location of the fault point, for example: forming a mesh communication network based on all patrol ships, wherein each node in the mesh communication network represents a patrol ship; determining the shortest communication path of the mesh communication network; and obtaining the location of the fault point based on the shortest communication path.

[0045] For example, the failure of the submarine cable can be determined in the following manner: obtaining submarine cable status data at intervals of a first preset time period, wherein the submarine cable status data at least includes the optical signal strength, temperature, and stress of the submarine cable; determining that the submarine cable has failed when the submarine cable status data obtained in any first preset time period meets at least one of the following: the change in optical signal strength exceeds a first preset threshold; the change in temperature exceeds a second preset threshold; the change in stress exceeds a third preset threshold. Step S204, based on the fault location response time, the submarine cable routing information processing time, and the ocean current speed, determine the first target search range corresponding to the fault point location, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain routing information for the fault point location.

[0046] In the technical solution provided in step S204, there are multiple ways to determine the first target search range corresponding to the fault point location based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, for example: determining the sum of the fault location response time and the submarine cable routing information processing time as the fault propagation time; determining the product of the fault propagation time and the ocean current speed as the fault propagation length; taking the fault point location as the starting point, and extending to both ends according to the routing line indicated by the fault point location to the fault propagation length, to obtain the first target search range.

[0047] After determining the first target search range corresponding to the fault point location, obtain real-time sea condition data, real-time weather data, and historical fault data corresponding to the first target search range, wherein the real-time sea condition data at least includes the wave height and wind speed at the time of acquisition, and the real-time weather data at least includes the visibility and rainfall at the time of acquisition; determine the submarine cable repair plan based on the real-time sea condition data, real-time weather data, and historical fault data. The following is a specific embodiment:

[0048] The submarine cable monitoring system of the data processing server (deployed in a data center or a cloud platform) collects the submarine cable status data collected by a submarine cable monitoring terminal fixed next to the submarine cable at intervals of a first preset time period (for example, 1s) or in real time. The submarine cable status data includes at least the optical signal strength, temperature, and stress of the submarine cable, which are recorded in units of 0.1dB, 0.1°C, and 0.1MPa, respectively; the normal ranges of the optical signal strength, temperature, and stress are: optical signal strength (-20dBm to 0dBm), temperature (0°C to 40°C), and stress (0MPa to 100MPa). The optical signal strength is detected in any first preset time period. If the change exceeds the first preset threshold (for example, the optical power drops by more than 5dB within 5 seconds) or the temperature change exceeds the second preset threshold (for example, the temperature changes by more than 10°C within 1 hour) or the stress change exceeds the third preset threshold (for example, the stress increases by more than 20MPa within 10 seconds), it is determined that the submarine cable has failed, and the submarine cable monitoring system in the data processing server immediately triggers the fault location process, and the system optical time domain reflectometer scans the entire submarine cable to locate the fault point with a time resolution of 1ns. Assuming that the fault location response time is 30 seconds, the submarine cable routing information processing time is 15 seconds, and the flat sea current speed is 1.5m / s, the fault propagation time is 45 seconds and the fault propagation length is 67.5 meters. Based on this, the search range is expanded to both ends along the cable route, starting from the fault point location, and expanding to the fault propagation length to both ends according to the routing line indicated by the fault point location, to obtain the first target search range.

[0049] The patrol boat is equipped with AIS equipment. The position of the patrol boat is tracked through the AIS system. The patrol boat and the data processing server and the various systems of the data processing server are connected through the communication base station. The communication base station is a fixed communication tower equipped with satellite or wireless communication equipment. The mesh communication network formed by the patrol boat adopts the AODV routing protocol. The communication radius of each node is 20km. The Dijkstra algorithm is used to determine the shortest communication path of the mesh communication network. The data processing server obtains the fault point location based on the shortest communication path, and the average transmission delay is controlled within 100ms. Through the shortest communication path, the first target search range based on the large model and the fault point location is sent to the data visualization platform of the command center. The command center views the real-time monitoring data, fault status and updates the search area map through the data visualization platform of the data processing server, and formulates the submarine cable fault repair strategy. The data visualization platform also supports viewing the prediction results of the prediction model of the data processing server. After receiving the first target search range corresponding to the fault point location, real-time (current time) sea condition data (wave height and wind speed at the time of acquisition) and real-time weather data (at least including visibility and rainfall) and historical fault data corresponding to the first target search range are obtained and combined with the actual patrol ship position, and a decision tree algorithm is used to determine a submarine cable repair plan. The decision variables of the decision tree algorithm include the real-time sea condition data and the real-time weather data and the fault frequency indicated by the historical fault data corresponding to the first target search range. The submarine cable repair plan includes options such as dispatching a maintenance ship, starting a spare submarine cable, and adjusting network routing. Specifically: the decision tree algorithm is implemented using the C4.5 decision tree algorithm (C4.5 Decision Tree Algorithm, referred to as C4.5), and the input variables include wave height (range 0-10m), wind speed (range 0-50m / s), visibility (range 0-20km), precipitation (range 0-100mm / h) and historical fault frequency (range times / year). The decision tree depth is limited to 5 layers, and the repair solutions corresponding to the leaf nodes include: dispatching maintenance ships (wave height <3m), starting spare submarine cables (fault frequency >5 times / year), and adjusting network routes (identifying that the optical power drops <10dB). When the patrol ship is dispatched for fault detection based on the route segment sequence, the submarine cable repair solution is sent to the fault site for execution through the patrol ship mobile base station network. At the same time, the whole process time from fault detection to the execution of the submarine cable repair solution is recorded, and the average processing time is calculated. If the average processing time exceeds the preset value (for example, 4 hours), the process optimization mechanism is triggered to re-evaluate the response time of each system of the data processing server, including fault location, information transmission, and submarine cable repair solution generation.For example, the average processing time of the entire process is recorded in units of 1 minute. If the average processing time for 30 consecutive days exceeds 4 hours, the optimization mechanism is automatically triggered to adjust the parameter thresholds of each subsystem through the gradient descent method, such as adjusting the optical power mutation detection threshold from 5dB to 4.8dB to improve the response speed.

[0050] Step S206, determining the failure probability of each routing segment of the submarine cable in the first target search range based on the submarine cable depth data, water depth data and environmental data in the first target search range, wherein the environmental data at least includes the seabed topography and ocean current data in the first target search range.

[0051] Step S208, sorting the fault probabilities of the various route segments to obtain a route segment sequence, and scheduling patrol ships to perform fault detection based on the route segment sequence.

[0052] In the technical solution provided in step S208, there are multiple ways to sort the fault probabilities of each routing segment to obtain a routing segment sequence, and to schedule patrol ships for fault detection based on the routing segment sequence, for example: sorting the fault probabilities of each routing segment in descending order to obtain a first routing sequence; determining a routing segment whose fault probability is greater than a preset probability threshold as a first routing segment; and scheduling patrol ships for fault detection based on the first routing sequence when the first routing segment does not exist in the first routing sequence.

[0053] When the first routing segment exists in the first routing sequence, the total number of the first routing segments is determined; when the total number of the first routing segments is less than a fourth preset threshold, patrol ships are scheduled for fault detection based on the first routing sequence; when the total number of the first routing segments is greater than or equal to the fourth preset threshold, all the first routing segments are clustered into high-risk areas, and the routing segments outside the first routing segments are sorted in descending order of fault probability to obtain a second routing sequence; patrol ships are scheduled for fault detection based on the high-risk areas and the second routing sequence, wherein the fault detection priority of the high-risk areas is higher than the fault detection priority of the second routing sequence.

[0054] The following are specific embodiments:

[0055] The submarine cable management database of the data storage system in the data processing server records a submarine cable burial depth data point every 100 meters, ranging from 0.5 meters to 5 meters, and the water depth data ranges from 10 meters near the coast to 5000 meters in the ocean, from which the submarine cable depth data and water depth data of the first target search range are obtained. The marine environment monitoring system provides environmental data, which at least includes seabed topography (i.e., seabed topography slope (0-45 degrees)) and ocean current data (i.e., ocean current speed (0-2.5 meters / second) data). The geographic information platform uses UTM projection to convert all the above data into a 10 meter × 10 meter grid. The decision tree algorithm is implemented using C4.5, and the input variables include submarine cable depth data, water depth data, and environmental data, and the output is the failure probability (0-100%) of each routing segment. During the growth of the decision tree, the splitting stops when the number of node samples is less than 100 or the depth reaches 5. The information gain ratio threshold is set to 0.01, and features below this value no longer participate in the splitting. The generated failure probability distribution map is represented by a heat map at 0.1% intervals.

[0056] The failure probability of each routing segment is sorted in descending order to obtain the first routing sequence. If the first routing segment does not exist in the first routing sequence (i.e., a high-risk point (failure probability>80%)), the patrol ship is dispatched based on the first routing sequence, and the AIS data is updated every 30 seconds to record the position, heading and speed of the patrol ship. The anchor dragging risk assessment tool takes into account the patrol ship tonnage (100-500,000 tons), speed (0-30 knots), water depth (10-200 meters) and seabed substrate (mud, sand, rock). The routing segment with a greater probability of failure dispatches more patrol ships that are closest to the fault detection and the faster the speed, and executes the submarine cable repair strategy after the patrol ship finds the exact fault location. If the first routing segment exists in the first routing sequence, determine the total number of first routing segments. When the total number of the first route segments is less than the fourth preset threshold (for example, 5), the patrol ship is dispatched for fault detection based on the first route sequence; when the total number of the first route segments is greater than or equal to the fourth preset threshold, all the first route segments are clustered into high-risk areas, and patrol ships are dispatched for fault detection based on the high-risk areas and the second route sequence. The fault detection priority of the high-risk area is higher than the fault detection priority of the second route sequence, and the fault detection of the high-risk area is prioritized. For example: the neighborhood radius of the density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, referred to as DBSCAN) is set to 500 meters, that is, the high-risk points within this range (failure probability>80%) are considered connected, and the minimum number of samples is 5, indicating that at least 5 (i.e., the fourth preset threshold) connected points are required to form a cluster (i.e., the above-mentioned high-risk area). In addition, the weighted sum method can also be used to calculate the risk probability. When the risk probability exceeds 60%, the corresponding 500m×500m area will be further increased by 10%. Finally, by calculating the area ratio of the troubleshooting range before and after optimization (i.e., the area ratio of each routing segment of the submarine cable in the high-risk area and the first target search range), if the reduction is less than 20%, the number of samples of the minimum leaf node of the decision tree is reduced by 10%, the DBSCAN neighborhood radius is increased by 50 meters, and the whole process is re-executed until the expected effect is achieved (the area ratio of the troubleshooting range is reduced by 20%) or it is iterated 10 times.

[0057] In order to monitor the status of submarine cables in real time, predict potential faults and quickly locate fault points. Improve the maintenance efficiency of submarine cables, optimize patrol ship scheduling, reduce maintenance costs, and reduce information transmission delays, this application adopts a long short-term memory neural network. The long short-term memory network contains a 2-layer long short-term memory unit (Long Short-Term Memory, referred to as LSTM) algorithm, combined with the historical fault data of submarine cables, routing space distribution data, and the maneuvering radius and scheduling frequency of AIS patrol ships, to establish a prediction model, and obtain the data to be predicted at intervals of the second preset time period, wherein the data to be predicted includes the submarine cable status update frequency, the submarine cable routing information processing time, the submarine cable status data, and the patrol ship's location information, communication capability data, and the submarine cable status data includes at least the optical signal strength, temperature, and stress of the submarine cable; the prediction model is used to predict the data to be predicted to obtain a prediction result, wherein the prediction result is used to predict the change of the submarine cable status within the preset time in the future.

[0058] When the prediction result indicates that the predicted signal attenuation exceeds the first preset risk threshold, a first-level alarm is activated, and a first-level alarm message is generated and sent to the user terminal of the corresponding level; when the prediction result indicates that the predicted signal attenuation exceeds the second preset risk threshold, a second-level alarm is activated, and a second-level alarm message is generated and sent to the user terminal of the corresponding level; when the prediction result indicates that the predicted signal attenuation exceeds the third preset risk threshold, a third-level alarm is activated, and a third-level alarm message is generated and sent to the user terminal of the corresponding level, wherein the values ​​of the first preset risk threshold, the second preset risk threshold, and the third preset risk threshold gradually increase; the cruise ship density and the submarine cable bandwidth in the predicted abnormal area indicated in the first-level alarm information, the second-level alarm information, and the third-level alarm information are adjusted respectively, wherein the priorities of the first-level alarm information, the second-level alarm information, and the third-level alarm information gradually increase.

[0059] The following is a specific implementation example: For the establishment and training of the prediction model: According to the submarine cable status data and AIS data, a long short-term memory neural network algorithm is used, combined with the magnitude of the submarine cable historical fault data, the accuracy of the submarine cable routing spatial distribution data, and the maneuvering radius and scheduling frequency of the patrol ship mobile base station, to establish an initial prediction model, dynamically adjust the model complexity, and improve the accuracy and adaptability of the prediction. The prediction model is obtained by training the initial prediction model in the following way: the submarine cable status update data (including the submarine cable status data and AIS data) is obtained from the submarine cable monitoring database. The submarine cable update data at least includes the optical signal strength, temperature, and stress of the submarine cable. The data is preprocessed, including outlier removal, missing value interpolation, and data standardization. Then, time series features are extracted from it, such as the submarine cable signal strength, temperature change rate, etc. The monitored sea area is divided into grids of 1 square kilometer, and the number of patrol ships in each grid is calculated as the AIS ship density feature. According to the preprocessed data, the input layer, hidden layer and output layer of the long short-term memory neural network are constructed. The number of nodes in the input layer is determined according to the number of extracted features. The hidden layer adopts a three-layer structure, and the number of nodes in each layer is 2 times, 1.5 times and 1 times the number of nodes in the input layer respectively. The number of nodes in the output layer corresponds to the number of predicted submarine cable state parameters. Using the historical fault data magnitude, the accuracy of the spatial distribution data of the submarine cable route, the maneuvering radius and dispatch frequency of the mobile base station of the AIS patrol ship, an adaptive learning rate adjustment algorithm based on gradient descent is designed. The initial learning rate is set to 0.001. After every 500 iterations, the learning rate is adjusted according to the trend of the loss function on the validation set. If the loss function decreases slowly, the learning rate is reduced to 0.8 times the original. The prediction model is continuously evaluated by the sliding window method. The model performance is evaluated every 1000 iterations. If the prediction error of the prediction result exceeds 5%, the structural adjustment is triggered. The adjustment methods include: increasing the number of neurons at the time step with large errors, or adding a convolutional layer between the input layer and the first hidden layer to extract local features, thereby optimizing the model complexity and improving the prediction accuracy. According to the accuracy of the spatial distribution data of the submarine cable route, the prediction results are spatially interpolated to generate a continuous submarine cable status prediction distribution map. The interpolation method is used, and the interpolation grid size is set to 1 / 10 of the accuracy of the submarine cable route data. Specifically: The submarine cable monitoring database obtains the submarine cable status data every 5 minutes, including the optical signal strength (ranging from -20dBm to 0dBm), temperature (ranging from 0℃ to 40℃) and stress (ranging from 0MPa to 100MPa). The AIS data records the position of the patrol ship at intervals of 1 minute. In data preprocessing, the 3 times standard deviation method is used to remove outliers, the linear interpolation method is used to fill the missing values, and then the Z-score is used for standardization. In the feature extraction process, the mean of the submarine cable signal strength, the temperature change rate and the stress standard deviation within the 30-minute sliding window are calculated. The monitoring sea area is divided into 1km×1km grids, and the number of ships in the grid is counted every 15 minutes as the AIS ship density feature.The structure of the long short-term memory neural network is designed as follows: 100 nodes in the input layer (corresponding to the number of extracted features), 200, 150 and 100 nodes in the three hidden layers respectively, and 10 nodes in the output layer (predicting the five key state parameters in the next two hours, namely, the update frequency of the submarine cable status, the processing time of the submarine cable routing information, the submarine cable status data, and the location information and communication capability data of the patrol ship). The initial learning rate of the adaptive learning rate adjustment algorithm is 0.001, and the validation set loss function is evaluated after every 500 iterations. If the loss decrease rate is less than 1% for three consecutive evaluations, the learning rate is multiplied by 0.8. The model evaluation uses a 30-minute sliding window and is performed every 1,000 iterations. If the prediction error of the prediction result exceeds 5%, 10% of the neurons are added at the time step with the largest error, or 16 3×3 convolution kernels are added between the input layer and the first hidden layer. Finally, the prediction results are spatially interpolated using the Kriging interpolation method, with the interpolation grid size set to 100m×100m (assuming the original submarine cable route data accuracy is 1km) to generate a high-precision continuous submarine cable status prediction distribution map. The model parameters are updated every 6 hours to continuously optimize the prediction performance.

[0060] Then the submarine cable status data is obtained through the submarine cable monitoring system, such as Figure 3As shown, it is a flowchart of a submarine cable status prediction provided according to an embodiment of the present application. Periodically obtain submarine cable status update data: including the submarine cable status update frequency and the submarine cable routing information processing time. Real-time acquisition of patrol ship position and communication data: obtain the deployment density and communication capability data of the AIS patrol ship mobile base station. The above data is used as input for predicting future state changes of the submarine cable (i.e., changes in the submarine cable state within the above-mentioned future preset time). The submarine cable status update frequency data and the submarine cable routing information processing time, the patrol ship's position information, and communication capability data are obtained from the submarine cable monitoring system every 10 minutes (i.e., the above-mentioned second preset time period) (the patrol ship position and communication capability data, i.e., the communication status, are obtained in real time from the patrol ship automatic identification system). Aggregate the data to the processing center for cleaning: these data are cleaned and standardized by the data processing center to remove outliers and noise. For the cleaned data extraction features, the sliding window method is used to extract the submarine cable features: a 60-minute sliding window is used to calculate the statistical characteristics of the submarine cable signal strength, such as the mean -15dBm, variance 0.5dB2, and peak -13dBm. Apply Fourier transform frequency domain analysis: Fast Fourier transform converts time domain signals into frequency domain and analyzes the main frequency components in the range of 0.1Hz to 10Hz. Construct time series features and models, and train models to predict changes in submarine cable status: The autoregressive integrated moving average model uses historical data from the past 30 days to predict the submarine cable status trend in the next 24 hours. When training the gradient boosting tree model, the submarine cable status update frequency (every 10 minutes), routing information processing time (average 200ms), patrol ship location (latitude and longitude coordinates) and density (3 ships per 100 square kilometers) are used as input features, and the trained prediction model is used to output the possible status changes of the submarine cable in the future (for example, 6 hours) (that is, the changes in the submarine cable status within the above-mentioned future preset time). According to the prediction results of the prediction model, multi-level warning thresholds are set. For example, the warning mechanism sets three thresholds: when the predicted signal attenuation exceeds 3dB (i.e., the first preset risk threshold), it is a first-level alarm, 5dB (i.e., the second preset risk threshold) is a second-level alarm, and 7dB (i.e., the third preset risk threshold) is a third-level alarm. When the predicted abnormality of the submarine cable status exceeds different levels, an alarm is automatically sent to the corresponding level of management personnel (sent to the corresponding level of user terminals), and the alarm information is sent to the user terminals of the corresponding level of management personnel via SMS and email. The prediction results are also fed back to the submarine cable monitoring system and patrol ship automatic identification system of the data processing server for real-time adjustment of patrol strategies. The heuristic algorithm dynamically plans the patrol ship route according to the predicted high-risk areas, for example, adjusting the originally evenly distributed cruise mode to increase the cruise density by 50% in the abnormal area indicated by the prediction results. The allocation of communication resources is also adjusted accordingly, and the bandwidth allocation is increased by 20% in the high-risk area indicated by the prediction results to ensure timely response and data transmission in abnormal situations.This series of measures forms a closed-loop system to continuously optimize submarine cable monitoring and maintenance strategies, ensuring timely response when the submarine cable status is abnormal.

[0061] In addition, in order to minimize the maintenance cost of submarine cables and ensure that the communication needs of submarine cables are met, the spatial distribution data accuracy, fault frequency and impact range of submarine cable routes are combined with the deployment density and scheduling frequency of patrol ship mobile base stations, and genetic algorithms are used to optimize submarine cable asset planning and patrol ship scheduling schemes: the spatial distribution data accuracy, historical fault frequency and impact range data of submarine cable routes are obtained from the submarine cable management database, and the deployment density and scheduling frequency information of patrol ships are obtained from the AIS system, and these data are integrated into a unified geographic information platform. The acquired data is standardized, the spatial distribution data accuracy is unified to 10 meters, the fault frequency is converted to the number of faults per kilometer per year, and the impact range is quantified as the length of the affected submarine cable. An optimization model for submarine cable asset planning and patrol ship scheduling is constructed, with the submarine cable maintenance cost and communication demand satisfaction as optimization targets, and the spatial distribution of submarine cable routes, fault characteristics and patrol ship resources as constraints, forming a multi-objective optimization problem. The average utilization rate of each submarine cable is calculated through network traffic monitoring data, which is used as an indicator of communication demand satisfaction. The genetic algorithm is used to solve the optimization model, and a binary chromosome coding scheme is designed. The layout of the submarine cable assets is encoded as a 0 / 1 sequence, and the patrol ship scheduling scheme is encoded as an integer sequence. The fitness function is designed as the weighted sum of the inverse of the maintenance cost and the satisfaction of the communication demand. The genetic algorithm is iteratively executed, and the termination condition is set as follows: the maximum number of iterations is 1000, or the improvement of the optimal solution for 50 consecutive generations is less than 0.1%. 20% of the elite individuals are retained in each iteration, the crossover probability is set to 0.8, the mutation probability is 0.1, and the optimal submarine cable asset planning and patrol ship scheduling scheme are output. The annual maintenance costs before and after optimization are compared, and the cost reduction percentage is calculated. If the cost reduction is less than 10%, the genetic algorithm parameters are adjusted, the population size is increased or the mutation probability is increased, and the optimization process is re-executed until the expected cost reduction effect is achieved.

[0062] The following is a specific embodiment: The submarine cable management database records the spatial distribution data of each submarine cable with an accuracy of 1 meter, the historical fault frequency is an average of 0.5 times / year / kilometer, and the impact range is usually 5 kilometers around the fault point. Patrol ships are deployed on average every 100 square kilometers, and the dispatch frequency is once every 6 hours. During the data standardization process, the spatial accuracy is unified to 10 meters, the fault frequency is converted to 0.0001370 times / day / meter, and the impact range is quantified to 5000 meters. Network traffic monitoring shows that the average utilization rate of submarine cables is 65%. In the optimization model, the maintenance cost target is set to 80% of the annual budget, and the communication demand satisfaction target is set to 90%. The genetic algorithm uses 100-bit binary code to represent the layout of submarine cable assets, with each 10 bits representing a sea area segment and 1 representing deployment; an 8-bit integer code is used to represent the patrol ship dispatch frequency, ranging from 0 to 255 hours. The initial population size is set to 200, and the fitness function weight ratio is the maintenance cost. During the execution of the algorithm, the improvement of the optimal solution is calculated every 50 generations, and it is terminated early when the improvement is less than 0.1% for three consecutive times. The final optimal solution output shows that after the optimization of the submarine cable asset layout, the coverage rate increased by 5%, and the average dispatch frequency of patrol ships was adjusted to once every 4.5 hours. After the optimization, the annual maintenance cost was reduced by 12%, achieving the expected goal, without adjusting the algorithm parameters and re-executing. The entire optimization process took about 30 minutes and a total of 783 iterations.

[0063] In order to verify the accuracy of the prediction results, the cable status change trend and AIS data characteristics are analyzed through data mining algorithms, and the prediction results are compared with the actual monitoring data. The cable status data transmission delay and AIS data satellite transmission delay are dynamically adjusted to minimize the time difference between the displayed information and the actual status, thereby improving the real-time performance of the system.

[0064] Specifically: Figure 4As shown in the figure, a flowchart for comparing the prediction results with the actual monitoring data is used to obtain the historical data of the submarine cable and the ship: the historical data of the submarine cable status is obtained from the submarine cable monitoring system, and the historical data of the patrol ship position is obtained based on AIS. Preprocessing data: denoising, normalization, alignment: the above data are preprocessed, including denoising, normalization and time series alignment. Forming a standard data set: linear interpolation is used to align data from different sources to a unified timestamp, and the sampling interval is set to 1 minute to form a standardized data set. Using LSTM network to mine data: a long short-term memory neural network (LSTM network) is used to mine the processed data, and the input window is set to the data of the past 24 hours, the submarine cable status change trend and AIS data features are extracted, a prediction model is constructed, and the prediction results for the next 6 hours are output: based on the above prediction model, the prediction results of the submarine cable status and patrol ship position for the next 6 hours are output. Compare predictions with real-time data and adjust transmission strategies: Compare prediction results with real-time collected monitoring data, calculate prediction errors and time differences between displayed information and actual status, prediction error refers to the error between predicted cable status and actual status, time difference refers to the error between predicted cable status change time and actual cable status change time, when the error (prediction error or time difference) exceeds a preset ratio (e.g., 10%) of a preset threshold, double the data sampling frequency in the area, increase the transmission priority to the highest level, dynamically adjust the data transmission frequency according to the error size, and increase the sampling frequency and transmission priority for areas with large errors. Based on the adjusted transmission strategy, edge computing nodes are deployed at each monitoring station, wavelet transform is used for data noise reduction and compression, the compression ratio is set to 5:1, and a dynamic routing algorithm is used to select the optimal transmission path, comprehensively consider network delay and bandwidth occupancy, optimize the transmission route of cable status data and AIS data, reduce transmission delay and bandwidth occupancy, and realize real-time information display. Continuously monitor the time difference between the displayed information and the actual status, calculate the average time difference and the maximum time difference. If the average time difference exceeds 2 seconds or the maximum time difference exceeds 5 seconds, the system parameter self-optimization process is triggered to adjust the prediction model parameters and transmission strategy to minimize the time difference between the displayed information and the actual status.

[0065] The following are specific embodiments:

[0066] The submarine cable monitoring system collects status data every 5 seconds, including optical power (-30dBm to 0dBm), temperature (0℃ to 40℃) and stress (0MPa to 100MPa). The patrol ship position data is updated every 30 seconds with an accuracy of 0.0001°. In data preprocessing, median filtering is used to remove outliers, and then the data is mapped to the 0-1 interval through minimum-maximum normalization. Linear interpolation aligns the two data to one sampling point per minute. The long short-term memory neural network (LSTM) has a 2-layer structure with 128 neurons in each layer. It uses the data of the past 1440 time points (24 hours) to predict the next 360 time points (6 hours) based on the constructed prediction model. The prediction results are compared with the real-time data. When the error exceeds 10%, the sampling frequency of the area is increased to once every 2.5 seconds, and the transmission priority is set to 1 (highest). The edge computing node uses Daubechies 4 wavelets (an orthogonal wavelet transform basis function) for 3-level decomposition, retaining low-frequency coefficients and a small number of high-frequency coefficients to achieve a compression ratio of 5:1. The dynamic routing algorithm is based on the Dijkstra algorithm, which comprehensively considers link delay (weight 0.7) and available bandwidth (weight 0.3) to select the optimal path. The time difference between the displayed information and the actual state is continuously calculated, and the average time difference is calculated using the exponentially weighted moving average method with a window size of 1000 sampling points. When the average time difference exceeds 2 seconds or the time difference of any sampling point exceeds 5 seconds, the self-optimization process is triggered to adjust the neural network learning rate (initial value 0.001, multiplied by 0.8 each time adjustment) and data compression ratio (adjusted between 3:1 and 7:1). Through these measures, the system achieves millisecond-level display delay, and the average time difference is controlled within 1.5 seconds.

[0067] If the time difference between the above display information and the actual status exceeds the preset threshold, the optimization process of the prediction model and the monitoring system is triggered. By analyzing the impact of factors such as the submarine cable status update frequency and the AIS data update cycle on the time difference, the data transmission and processing process is optimized, the submarine cable fault information transmission time and the fault location response speed are improved, and the time difference between the display information and the actual status is shortened. Specifically: real-time monitoring of the time difference between the display information and the actual status, using timestamp comparison, calculate the difference between the display information timestamp and the actual status timestamp, accurate to milliseconds, when the time difference exceeds the preset threshold of 2 seconds, the optimization process is automatically triggered, and the system parameters at the triggering time are recorded, including the submarine cable status update frequency, AIS data update cycle, network delay, etc. The random forest regression model is used to analyze the degree of influence of each factor on the time difference. Taking into account the possible nonlinear relationship, the feature importance score is used to identify the key factors that have the greatest impact on the time difference. According to the feature importance of the random forest model, an adaptive sampling strategy is designed. For factors with importance higher than 0.1, the sampling frequency is increased by 50%, and for factors below the threshold, the sampling frequency is reduced by 25%. At the same time, an autoencoder is used for data compression. The compression rate is dynamically adjusted according to the network bandwidth, the data compression algorithm is optimized, and the network transmission route is adjusted to balance the utilization of system resources and minimize the time difference. The optimized system performance is continuously evaluated, the average time difference and fluctuation range are calculated, and if the optimization effect is not obvious, the retraining process of the deep learning model is triggered. The long short-term memory network is used as the deep learning model, and the sliding window method is used for incremental learning. The model is updated with the latest 1000 data points each time, the learning rate is set to 0.001, and 50 cycles are trained each time to improve the prediction accuracy and response speed. A fast fault response mechanism is designed. When a potential fault is detected (such as a sudden drop in signal strength by 10%), the sampling frequency of the area is immediately increased to 10 times per second, and the emergency communication channel is activated to give priority to the transmission of fault-related data, thereby improving the transmission time of submarine cable fault information and the fault location response speed.

[0068] The following are specific embodiments:

[0069] The time difference is calculated every 100 milliseconds, using a 64-bit timestamp with nanosecond accuracy. When 20 consecutive time differences exceeding 2 seconds are detected, the optimization process is triggered. The recorded system parameters include the cable status update frequency (range 1-10Hz), AIS data update cycle (range 10-60 seconds) and network latency (range 0-500 milliseconds). The random forest model uses 100 decision trees with a maximum depth of 10 and uses Gini impurity (in the decision tree algorithm, Gini impurity is used to measure the uncertainty or impurity of samples in a node) as the splitting criterion. The feature importance threshold is set to 0.1. The sampling frequency of factors above this value is increased by 50%, and that below this value is reduced by 25%. The autoencoder adopts a 3-layer structure. The number of neurons in the input and output layers is the same as the original data dimension. The hidden layer is 1 / 2 of the input layer. The rectified linear unit (ReLU) activation function is used, which is a nonlinear activation function. The data compression ratio is dynamically adjusted between 2:1 and 10:1 according to the network bandwidth. The LSTM network contains two layers of LSTM units, each with 128 neurons. The input is the data of the past 24 hours, and the output is the forecast of the next hour. The Adaptive Moment Estimation optimizer (Adam optimizer) is used, with a learning rate of 0.001, which is reduced by 10% every 50 training cycles (epochs). The sliding window size is 1000 data points with a step size of 100. The fault detection threshold is set to a mutation of 10% of the signal strength. After the trigger, the sampling frequency is increased to 10Hz, and an independent 5G emergency communication channel is enabled, with a bandwidth guaranteed to be above 100Mbps. Through these measures, the average time difference is reduced to less than 500 milliseconds.

[0070] The parameters and algorithms of the above prediction model can also be dynamically adjusted according to the optimization cycle of submarine cable asset planning and the timeliness of submarine cable maintenance scheduling decisions, so as to balance the prediction accuracy and computational efficiency, provide more real-time and reliable decision support for submarine cable monitoring and maintenance, and finally realize the intelligent management of the entire life cycle of the submarine cable network. Specifically: according to the optimization cycle of submarine cable asset planning and the timeliness of maintenance scheduling decisions, a dynamic threshold trigger mechanism is set, and an adaptive threshold algorithm is used. Based on the mean and standard deviation of the prediction error in the past 30 days, the threshold is set to the mean plus two times the standard deviation, and the calculation time limit is set to 1.5 times the current average calculation time. When the prediction error exceeds the threshold or the calculation time exceeds the preset limit, the parameter adjustment process of the submarine cable status prediction model is automatically started. The Bayesian optimization algorithm is used to automatically tune the hyperparameters of the prediction model, including the learning rate, the number of hidden layers, the number of neurons, etc. Gaussian process regression is used as the proxy model, and the expected improvement is used as the acquisition function. 50 iterations are set, and 5 sets of hyperparameter combinations are evaluated each time. Through multiple iterative optimizations, the best parameter combination that balances prediction accuracy and computational efficiency is found. Based on the optimized prediction model, combined with historical maintenance data and current submarine cable status, the intelligent scheduling agent is trained using a reinforcement learning algorithm. The state space includes the submarine cable status, maintenance history and resource availability, and the action space includes inspection route selection and maintenance priority allocation. The exploration strategy is used for learning, and the exploration value decays linearly from 0.9 to 0.1. The submarine cable maintenance scheduling decision is automatically generated, including inspection route planning, maintenance priority sorting, etc. A digital twin of the submarine cable network based on a graph database is constructed, and the topology structure is stored in a graph database. The real-time data synchronization between the physical network and the digital twin is achieved through a message queue, and the delay is controlled within 100 milliseconds. The status of the physical submarine cable network is synchronized in real time, and the effectiveness of the prediction model and scheduling decision is verified through simulation, and the strategy is optimized in a virtual environment. A submarine cable asset life cycle database is established to record the data of the entire process from planning, installation to decommissioning. Combined with maintenance costs and performance indicators, the optimal asset renewal plan is formulated to continuously improve the intelligent management level of the submarine cable network throughout its life cycle.

[0071] The following are specific embodiments:

[0072] The prediction model runs once an hour, and the prediction error is calculated based on the data of the past 720 hours (30 days). The current mean is 0.05 and the standard deviation is 0.02, so the dynamic threshold is set to 0.09. The calculation time limit is adjusted from the original 5 minutes to 7.5 minutes. During the Bayesian optimization process, the learning rate range is set to 0.0001 to 0.1, the number of hidden layers is 1 to 5, and the number of neurons in each layer is 32 to 256. Gaussian process regression uses a radial basis function kernel, and the initial value of the length scale is set to 1.0. The expected improvement threshold is set to 0.001, and it is terminated early if it is lower than this value for 10 consecutive iterations. The state space of the reinforcement learning algorithm contains 50 features, and the action space is discretized into 100 options. The reward function is designed based on maintenance cost savings and network reliability improvement, and the discount factor γ is set to 0.95. The graph database contains 10,000 nodes and 50,000 relationships, representing the physical topology and logical connections of the submarine cable network. The simulation frequency of the digital twin is 10Hz, and the state synchronization delay with the physical network is controlled within 100ms. The submarine cable asset life cycle database is stored in a time series database, and the data retention policy is set to 5 years. The time series prediction model uses an autoregressive integrated moving average model (2nd-order autoregression, 1st-order difference, 2nd-order moving average, referred to as ARIMA (2, 1, 2)) to predict the remaining service life in the next 2 years based on the monthly performance data of the past 5 years. The asset renewal plan optimization adopts mixed integer programming. The objective function comprehensively considers the renewal cost, maintenance cost and network performance improvement. The constraints include budget constraints and minimum performance requirements. Based on the above process, the average failure interval of the submarine cable network has increased by 20%, the maintenance cost has decreased by 15%, and the asset utilization rate has increased by 10%.

[0073] It should be noted that in the technical solution provided in step S202, when a submarine cable fault is detected in the event of a submarine earthquake, optical polarization data (at least including polarization amplitude, polarization angle change, and continuous distribution of polarization state) and seismic data (at least including: epicenter location, magnitude, and relative distance between the epicenter location and the submarine cable) are obtained, and based on the optical polarization data, seismic data, and a large model, a high-correlation earthquake area is determined, and post-earthquake seabed topography data (at least including seabed images, sonar data, terrain height, etc.) of the high-correlation earthquake area is obtained, and key inspection areas are determined based on the post-earthquake seabed topography data and the large model, wherein the large model is used to determine the scope of earthquake impact and predict key inspection areas, and patrol ships are dispatched for fault detection based on the key inspection areas.

[0074] The following are specific embodiments:

[0075] In the event of an undersea earthquake, light polarization data (including at least polarization amplitude, polarization angle change, and continuous distribution of polarization states) is obtained based on distributed optical fiber vibration sensors, and earthquake data (including at least: epicenter location, magnitude, and relative distance between the epicenter location and the submarine cable) is obtained based on real-time earthquake detection equipment. The light polarization data and earthquake data are input into a large model (for example, a large terrain model (LandGPT), an advanced deep learning model for processing and analyzing geospatial data), and a retrieval is constructed for all earthquake data (for example, a fast similarity search library (Facebook AI SimilaritySearch, referred to as FAISS index)). The key data features of earthquake data include the epicenter location (latitude and longitude, depth), magnitude (moment magnitude (Mw), used to reflect earthquake energy), the relative distance between the epicenter location and the submarine cable (calculated from the epicenter coordinates and the submarine cable route), and the source mechanism (fault type, vibration direction). The above key features are vectorized to form an earthquake vector. The structure of earthquake vector is: [epicenter longitude, epicenter latitude, focal depth, magnitude, distance between epicenter and submarine cable]. The dimension of earthquake vector depends on the number of features of earthquake and submarine cable. At the same time, a submarine cable vector library is constructed. The structure of submarine cable vector in the submarine cable vector library is: [node coordinates (determined by obtaining the geometric path point set (longitude and latitude) of the submarine cable), burial depth (determined by the burial depth of the submarine cable), surrounding geological information (i.e. the location of the submarine cable that failed after the historical earthquake and related features (such as high stress area)) and historical failure probability]. According to the amount and dimension of data, the appropriate FAISS index type is selected, and the earthquake vector and submarine cable vector are stored in the FAISS index library for index construction for subsequent efficient retrieval.

[0076] Through the large model, FAISS search is performed to retrieve and return the closest submarine cable vector, and the high-correlation earthquake area is determined. For example, the high-correlation earthquake area is determined in the following way: the probability value of earthquake is detected for each submarine cable segment in the set of geometric path points of the submarine cable indicated by the closest submarine cable vector: the probability value of earthquake for each submarine cable segment in the set of geometric path points of the submarine cable is determined based on the magnitude, focal depth, submarine cable distance, and historical failure probability, and the area where the submarine cable segment with high correlation (the probability value of earthquake is greater than the preset earthquake failure probability threshold, for example, 0.8) is located is a high-correlation earthquake area, and a risk report is generated, and the early warning mechanism is automatically triggered. The risk report includes at least the high-correlation earthquake area and the earthquake impact range (the earthquake impact range is quantified as the affected submarine cable length, that is, the submarine cable segment in the above-mentioned high-correlation earthquake area, in meters, and the area corresponding to the high correlation is given a higher weight). After the high-correlation earthquake area is determined, a robot (for example, a remotely operated submersible) is dispatched based on AIS. The ROV (Remote Control Vehicle, referred to as ROV) obtains the post-earthquake seabed topography data (including at least seabed images, sonar data, terrain height, etc.) in the high-correlation earthquake area. The ROV is equipped with a high-precision camera (used to obtain high-resolution seabed images, identify the status of the submarine cable and terrain changes), sonar equipment (used to draw a three-dimensional model of the seabed terrain after the earthquake, expand the area that is difficult to observe with the camera, and obtain sonar data), a laser rangefinder (used to measure the terrain height, the distance between the submarine cable and the seabed, and the change in the bending angle, etc.), and a water quality sensor (optional): monitors changes in the seabed environment (such as sediment disturbance). The ROV cruises in the earthquake location range and its surrounding areas, uses path planning technology to efficiently cover the range that may be affected by the submarine cable, and automatically inspects the cable laying path. The earthquake location range is scanned in detail, and the collected seabed topography data (including at least seabed images, sonar data, terrain height, etc.) is transmitted back to the command center in real time through the communication link between the ROV and the mother ship and stored in a high-performance computing platform for subsequent analysis.

[0077] The collected seabed topography data is input into the large model, and the status of each section of the submarine cable in the high-correlation earthquake area is evaluated (for example, the status evaluation at least includes the evaluation of the bending, exposure, and fracture status of the submarine cable), and whether the submarine topography changes based on the submarine topography data to obtain the status evaluation prediction results. The key inspection area is determined based on the status evaluation prediction results. Specifically: the status evaluation results are divided into normal state (i.e., it is predicted that no submarine topography changes have occurred), potential risk state (the change of the submarine topography is greater than the first preset change threshold), and severe damage state (the change of the submarine topography is greater than the second preset change threshold, and the second preset change threshold is greater than the first preset change threshold). The status of the submarine cable is evaluated as a potential risk state, and the area where the submarine cable is located in the severe damage state is determined as a key inspection area, and patrol ships are dispatched to perform fault detection on the key inspection area. When dispatching patrol ships, the priority of the area where the submarine cable is located in the severe damage state is higher than the area where the submarine cable is located in the status evaluation as a potential risk state. The status evaluation results also include the predicted potential risk state and the time point when the submarine topography change occurs in the severe damage state. The initial large model is based on historical seabed topography data, historical pre-earthquake seabed data (for example, pre-earthquake seabed height field (seabed topography benchmark), sediment distribution map). As well as historical post-earthquake topography data (seabed sonar images, camera images and laser ranging data in historical earthquake events, post-earthquake height field, terrain change data (such as collapse, uplift areas)), and fault sample library (submarine cable maintenance records and event data, including characteristic samples of submarine cable problems caused by different types of terrain changes (such as bending, exposure, and fracture)). The collected historical seabed topography data is annotated to generate training samples: the uplift, collapse, slope avalanche and other change areas indicated in the terrain change data in the post-earthquake topographic map are annotated. The submarine cables in the area where the terrain change area is located are trained by annotating the cable status (annotated as normal, bending, exposure, fracture, etc.), and the training is stopped after reaching the preset number of training iterations to obtain the large model.

[0078] In order to ensure the accuracy of the predicted key inspection areas and realize continuous monitoring of the key inspection areas, the time difference between the predicted potential risk state indicated by the status assessment result, the time point when the seabed topography changes in the severe damage state and the actual potential risk state, the time when the seabed topography changes in the severe damage state occur is obtained at preset detection period intervals. When the time difference exceeds a first preset time threshold, the optical polarization data of the area where the seabed topography changes occur within the time difference is obtained, and the optical polarization data is input into the large model to obtain the abnormal probability value. When the abnormal probability value is greater than the preset abnormal probability threshold (for example, 0.8), the area where the seabed topography changes occur is regarded as an abnormal area, indicating that the optical fiber transmission in this area is affected by the earthquake. When the area is an abnormal area in a preset detection cycle for a preset number of consecutive times, the future state of the submarine cable in the area and its damage probability in the earthquake are predicted based on the large model. Specifically, the input submarine cable structural characteristics and earthquake data are input into the earthquake simulation module of the large model, and the submarine cable structural characteristics and earthquake data include: 1. Earthquake parameters: focal depth: {focal depth value}, magnitude: {magnitude value}, epicenter distance: {epicenter distance value}, earthquake occurrence time: {timestamp} 2. Submarine cable structural parameters: submarine cable material: {material name}, submarine cable diameter: {diameter value}, submarine cable length: {length value}, submarine cable aging status: {aging status value}, submarine cable historical fatigue data: {fatigue data set}; 3. Seismic wave propagation characteristics: seismic wave type: {wave type}, vibration intensity: {vibration intensity value}, propagation path: {path information}; 4. Submarine cable status and seismic activity data in the past 30 days: prediction error: {error data}, cumulative stress: {stress data}, vibration history: {vibration history data}. Then, dynamic modeling technology is used to evaluate the damage probability of the submarine cable under different earthquake impacts, predict the cumulative damage probability of the submarine cable under multiple earthquakes, calculate the possible damage risk after the next earthquake, calculate the remaining service life of the submarine cable, and predict the future state of the submarine cable in an earthquake (one of the normal state (i.e., it is predicted that no seabed topography changes have occurred), potential risk state (the change in seabed topography is greater than a first preset change threshold), and severe damage state (the change in seabed topography is greater than a second preset change threshold, and the second preset change threshold is greater than the first preset change threshold)). For example, input data: earthquake parameters: focal depth: 10 kilometers, magnitude: 7.2, epicenter distance: 50 kilometers, earthquake occurrence time: xx year xx day xx minutes xx seconds; submarine cable structure parameters: submarine cable material: aluminum-clad steel armored optical fiber composite submarine cable, submarine cable diameter: 20 mm, submarine cable length: 1500 meters, submarine cable aging status: slightly aged, submarine cable historical fatigue data: the cumulative number of bending times in the past five years exceeds 10,000 times; seismic wave propagation characteristics: seismic wave type: xx wave, vibration intensity: peak ground acceleration is 0.5g, propagation path: propagates from the epicenter to the northeast, through the deep sea plain to the edge of the continental shelf.4. Cable status and seismic activity data for the past 30 days: Prediction error: mean absolute error (MAE) is ±0.03g, cumulative stress: maximum cumulative stress reaches 120MPa, vibration history: a total of 25 small vibration events were recorded. The large model outputs that the future state of the cable in the earthquake is a severely damaged state, the cumulative damage probability of the cable under multiple earthquakes is 0.8, and the possible damage risk after the next earthquake is high risk. The earthquake prediction module of the large model runs once when it recognizes that the same area is an abnormal area in the preset detection cycle for a preset number of consecutive times. Based on the predicted future state of the cable in the earthquake and its damage probability, a strong reminder is given. The warning information of the strong reminder includes: the optical fiber area affected by the earthquake, the affected time range, the probability of failure, etc. Through the above steps, continuous prediction of key monitoring areas and avoidance of the risk of submarine cable failure with time lag are achieved.

[0079] The present application also provides a flowchart of a submarine cable intelligent maintenance and monitoring process, such as Figure 5As shown, the method steps in each embodiment of the above-mentioned steps S202-S208 are shown. S502, obtaining the submarine cable status data through the submarine cable monitoring system, including the submarine cable status update frequency and the submarine cable route information processing time, and obtaining the deployment density and communication capability data of the AIS patrol ship mobile base station as input for predicting the future state change of the submarine cable; S504, according to the submarine cable status data and AIS data, using the long short-term memory neural network algorithm, combined with the magnitude of the submarine cable historical fault data, the accuracy of the submarine cable route spatial distribution data, and the maneuvering radius and scheduling frequency of the AIS patrol ship mobile base station, to establish a submarine cable status prediction model, dynamically adjust the model complexity, and improve the accuracy of the prediction. and adaptability; S506, if the submarine cable monitoring system detects that a submarine cable has failed, the fault location process is triggered, and the fault location response speed of the submarine cable monitoring system is used to obtain the precise location of the fault point, and the search range along the coastal cable route to both ends is determined according to the processing time of the submarine cable route information. At the same time, the communication capability of the mobile base station of the AIS patrol ship is used to quickly transmit the submarine cable fault information to the command center, thereby shortening the fault processing time; S508, the submarine cable burial depth and water depth data within the faulty submarine cable route are obtained, and the possibility of failure of each route segment is analyzed through the decision tree algorithm in combination with environmental factors such as the seabed topography and ocean currents, thereby further narrowing the scope of fault investigation and using the update of AIS data cycle, dynamically verify the fault analysis results and improve the accuracy of fault location; S510, according to the spatial distribution data accuracy of the submarine cable route, the frequency of faults and the impact range, combined with the deployment density and dispatch frequency of the mobile base stations of the AIS patrol ships, use genetic algorithms to optimize the submarine cable asset planning and patrol ship dispatching plan, minimize the maintenance cost of the submarine cable, and ensure that the communication needs of the submarine cable are met; S512, analyze the trend of submarine cable status changes and AIS data characteristics through data mining algorithms, and compare the predicted results with the actual monitoring data, dynamically adjust the submarine cable status data transmission delay and AIS data satellite transmission delay, minimize the time difference between the displayed information and the actual status, and improve the real-time performance of the system. ; S514, if the time difference between the displayed information and the actual status exceeds the preset threshold, the optimization process of the prediction model and the monitoring system is triggered, and the data transmission and processing process is optimized by analyzing the influence of factors such as the submarine cable status update frequency and the AIS data update cycle on the time difference, so as to improve the transmission time of the submarine cable fault information and the fault location response speed, and shorten the time difference between the displayed information and the actual status; S516, according to the submarine cable asset planning optimization cycle and the timeliness of the submarine cable maintenance scheduling decision, the parameters and algorithms of the submarine cable status prediction model are dynamically adjusted to balance the prediction accuracy and calculation efficiency, so as to provide more real-time and reliable decision support for submarine cable monitoring and maintenance, and finally realize the intelligent management of the submarine cable network throughout its life cycle. The specific implementation methods of the above steps S502-S516 have been described in detail in the above embodiments, and will not be repeated here.

[0080] The present application embodiment provides a schematic diagram of the structure of a submarine cable detection device, such as Figure 6 As shown, including:

[0081] The acquisition module 602 is used to acquire the location of the fault point when a fault is detected in the submarine cable.

[0082] The first determination module 604 is used to determine a first target search range corresponding to the fault point location based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain routing information of the fault point location.

[0083] The second determination module 606 is used to determine the failure probability of each routing segment of the submarine cable in the first target search range based on the submarine cable depth data, water depth data and environmental data in the first target search range, wherein the environmental data at least includes the seabed topography and ocean current data in the first target search range.

[0084] The sorting module 608 is used to sort the fault probabilities of the various route segments to obtain a route segment sequence, and schedule patrol ships to perform fault detection based on the route segment sequence.

[0085] It should be noted that Figure 6 The submarine cable detection device shown is used to perform Figure 2 The detection method of the submarine cable shown in FIG. Figure 2 The relevant explanations in the detection method of the submarine cable in are also applicable to the detection device of the submarine cable and will not be repeated here.

[0086] It should be noted that the various modules in the above-mentioned submarine cable detection device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0087] The embodiment of the present application also provides a non-volatile storage medium, the non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above submarine cable detection method. For example, in the case of detecting a submarine cable fault, the fault point location is obtained; based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, the first target search range corresponding to the fault point location is determined, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain the routing information of the fault point location; based on the submarine cable depth data, water depth data and environmental data of the first target search range, the fault probability of each routing segment of the submarine cable in the first target search range is determined, wherein the environmental data at least includes the seabed topography and ocean current data of the first target search range; the fault probability of each routing segment is sorted to obtain a routing segment sequence, and a patrol ship is dispatched to perform fault detection based on the routing segment sequence.

[0088] The embodiment of the present application also provides an electronic device, the electronic device includes a processor, the processor is used to run a program, wherein the above submarine cable detection method is executed when the program is running. For example, in the case of detecting a fault in the submarine cable, the fault point location is obtained; based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, the first target search range corresponding to the fault point location is determined, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain the routing information of the fault point location; based on the submarine cable depth data, water depth data and environmental data of the first target search range, the fault probability of each routing segment of the submarine cable in the first target search range is determined, wherein the environmental data at least includes the seabed topography and ocean current data of the first target search range; the fault probability of each routing segment is sorted to obtain a routing segment sequence, and a patrol ship is dispatched to perform fault detection based on the routing segment sequence.

[0089] According to another aspect of the embodiment of the present application, a computer program product is also provided, including a computer program, which implements the above submarine cable detection method when executed by a processor. For example, in the case of detecting a submarine cable fault, the fault point location is obtained; based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, the first target search range corresponding to the fault point location is determined, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain the routing information of the fault point location; based on the submarine cable depth data, water depth data and environmental data of the first target search range, the fault probability of each routing segment of the submarine cable in the first target search range is determined, wherein the environmental data at least includes the seabed topography and ocean current data of the first target search range; the fault probability of each routing segment is sorted to obtain a routing segment sequence, and a patrol ship is dispatched for fault detection based on the routing segment sequence.

[0090] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0095] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting a submarine cable, characterized in that: include: When a submarine cable fault is detected, the fault point location is obtained; Determine a first target search range corresponding to the fault point location based on the fault location response time, the submarine cable routing information processing time and the ocean current speed, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain the routing information of the fault point location; Determine the failure probability of each routing segment of the submarine cable in the first target search range based on the submarine cable depth data, water depth data and environmental data in the first target search range, wherein the environmental data at least includes the seabed topography and ocean current data in the first target search range; The fault probabilities of the respective route segments are sorted to obtain a route segment sequence, and patrol ships are dispatched to perform fault detection based on the route segment sequence.

2. The method according to claim 1, characterized in that When a submarine cable failure is detected, obtaining the location of the fault point includes: Forming a mesh communication network based on all the patrol ships, wherein each node in the mesh communication network represents one of the patrol ships; determining a shortest communication path of the mesh communication network; The fault point location is acquired based on the shortest communication path.

3. The method according to claim 1, characterized in that The determining of the first target search range corresponding to the fault point location based on the fault location response time, the submarine cable routing information processing time and the ocean current speed comprises: Determine the sum of the fault location response time and the submarine cable routing information processing time as the fault propagation duration; Determine the product of the fault propagation time and the ocean current speed as the fault propagation length; Taking the fault point location as a starting point, the routing line indicated by the fault point location is extended to both ends to the fault propagation length respectively, to obtain the first target search range.

4. The method according to claim 1, characterized in that: The method further comprises: Acquire submarine cable status data at intervals of a first preset time period, wherein the submarine cable status data at least includes optical signal strength, temperature, and stress of the submarine cable; When the submarine cable status data obtained in any first preset time period satisfies at least one of the following, it is determined that the submarine cable fails: The change in the intensity of the optical signal exceeds a first preset threshold; The temperature change exceeds a second preset threshold; The change in stress exceeds a third preset threshold.

5. The method according to claim 1, characterized in that The method of sorting the failure probabilities of the respective route segments to obtain a route segment sequence, and scheduling patrol ships to perform failure detection based on the route segment sequence, includes: Sorting the failure probabilities of the routing segments in descending order to obtain a first routing sequence; Determine the routing segment whose failure probability is greater than a preset probability threshold as the first routing segment; In a case where the first routing segment does not exist in the first routing sequence, the patrol ship is scheduled to perform fault detection based on the first routing sequence.

6. The method according to claim 5, characterized in that In a case where the first routing segment exists in the first routing sequence, the method further includes: Determining a total number of the first routing segments; When the total number of the first routing segments is less than a fourth preset threshold, scheduling the patrol ship to perform fault detection based on the first routing sequence; When the total number of the first routing segments is greater than or equal to a fourth preset threshold, clustering all the first routing segments into a high-risk area, and sorting the routing segments other than the first routing segments in descending order of the failure probability to obtain a second routing sequence; The patrol ship is scheduled to perform fault detection based on the high-risk area and the second routing sequence, wherein the fault detection priority of the high-risk area is higher than the fault detection priority of the second routing sequence.

7. The method according to claim 1, characterized in that After determining the first target search range corresponding to the fault point location, the method further includes: Acquire real-time sea condition data and real-time weather data and historical fault data corresponding to the first target search range, wherein the real-time sea condition data at least includes the wave height and wind speed at the acquisition time, and the real-time weather data at least includes the visibility and rainfall at the acquisition time; A submarine cable repair plan is determined based on the real-time sea condition data, the real-time weather data and the historical fault data.

8. The method according to claim 1, characterized in that The method further comprises: Acquire the data to be predicted at intervals of a second preset time period, wherein the data to be predicted includes the submarine cable status update frequency, the submarine cable routing information processing time, the submarine cable status data, and the position information and communication capability data of the patrol ship, and the submarine cable status data includes at least the optical signal strength, temperature, and stress of the submarine cable; The prediction model is used to predict the data to be predicted to obtain a prediction result, wherein the prediction result is used to predict the change of the submarine cable state within a preset time in the future.

9. The method according to claim 8, characterized in that When the prediction result indicates that the predicted signal attenuation exceeds the first preset risk threshold, a first-level alarm is activated, and a first-level alarm message is generated and sent to a user terminal of a corresponding level; when the prediction result indicates that the predicted signal attenuation exceeds the second preset risk threshold, a second-level alarm is activated, and a second-level alarm message is generated and sent to a user terminal of a corresponding level; when the prediction result indicates that the predicted signal attenuation exceeds the third preset risk threshold, a third-level alarm is activated, and a third-level alarm message is generated and sent to a user terminal of a corresponding level, wherein the values ​​of the first preset risk threshold, the second preset risk threshold, and the third preset risk threshold gradually increase; The cruise ship density and the submarine cable bandwidth in the predicted abnormal area indicated in the first-level alarm information, the second-level alarm information, and the third-level alarm information are adjusted respectively, wherein the priorities of the first-level alarm information, the second-level alarm information, and the third-level alarm information gradually increase.

10. A submarine cable detection device, characterized in that: include: An acquisition module is used to acquire the location of a fault point when a fault is detected in the submarine cable; A first determination module is used to determine a first target search range corresponding to the fault point location based on the fault location response time and the submarine cable routing information processing time and the ocean current speed, wherein the fault location response time is used to indicate the time required to determine the fault point location, and the submarine cable routing information processing time is used to indicate the time required to obtain the routing information of the fault point location; A second determination module is used to determine the failure probability of each routing segment of the submarine cable in the first target search range based on the submarine cable depth data, water depth data and environmental data in the first target search range, wherein the environmental data at least includes the seabed topography and ocean current data in the first target search range; The sorting module is used to sort the fault probabilities of the various route segments to obtain a route segment sequence, and dispatch patrol ships to perform fault detection based on the route segment sequence.

11. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the submarine cable detection method according to any one of claims 1 to 9.

12. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes the submarine cable detection method according to any one of claims 1 to 9 when running.

13. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the submarine cable detection method according to any one of claims 1 to 9 is implemented.

Images