Navigation aid information real-time transmission and analysis system based on navigation mark

Abstract

The invention discloses a navigation aid information real-time transmission and analysis system based on a navigation mark, and relates to the field of navigation mark telemetering, the system is composed of a plurality of functional modules, and the system comprises a data acquisition module for acquiring dynamic data, meteorological data and hydrological data of ships near the navigation mark; the edge calculation module is used for generating a ship real-time track according to the ship dynamic data, obtaining a ship prediction track based on the ship real-time track and the hydrological data, and calculating a deviation degree based on a preset ship channel and the ship prediction track; the risk prediction module carries out risk analysis on the deviation degree according to meteorological data and carries out route adjustment according to a risk analysis result, and the route adjustment module generates an optimized route by applying an A * algorithm and considering ship dynamic constraint and channel limitation and then sends an instruction in time through the VHF radio module, so that risks of ship deviation from a channel, collision and the like are effectively avoided; the safety of sailors, ships and goods is greatly guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of beacon telemetry, in particular to a beacon navigation information real-time transmission and analysis system. BACKGROUND

[0002] Since the 20th century, with the rapid development of electronic technology, computer technology and communication technology, beacon navigation information analysis has entered a new stage; the emergence of radar, global positioning system (GPS) and other advanced devices has greatly improved the accuracy of ship positioning and navigation; the automatic identification system (AIS) can transmit the position, speed, heading and other information of the ship in real time, so that the port management department and other ships can timely understand the dynamic of the surrounding ships; meteorological satellites, ocean monitoring equipment and other developments can obtain a large amount of meteorological and hydrological data in real time; with the powerful computing power of computers, people can comprehensively analyze these massive beacon navigation information, and establish complex mathematical models to predict the ship's sailing trajectory and assess the sailing risk.

[0003] The traditional beacon navigation system is mostly static facilities, which can only provide basic channel identification function, and lacks effective collection, transmission and analysis capability of real-time information such as ship dynamic, weather and hydrology; in terms of ship navigation safety, the previous system is difficult to monitor the motion state of the ship in real time, and also cannot accurately combine meteorological and hydrological factors to give early warning and classification of the risk of ship deviating from the channel; when the ship faces complex weather or hydrological conditions, it often can only rely on the experience of the crew, which has a great safety hazard and is prone to accidents such as ship deviating from the channel and collision, which threatens the safety of the crew, the ship and the cargo; in the data transmission and processing link, the data transmission mode of the traditional system is prone to high transmission delay and poor stability in remote sea areas, and the integrity and reliability of the data are difficult to guarantee, which cannot provide timely and accurate basis for the analysis and decision of ship navigation. SUMMARY

[0004] (I) Technical problems solved

[0005] In view of the deficiencies of the prior art, the present application provides a beacon navigation information real-time transmission and analysis system, which solves the problems raised in the background art.

[0006] (II) Technical solutions

[0007] In order to achieve the above purpose, the present application is realized by the following technical solutions:

[0008] The beacon navigation information real-time transmission and analysis system comprises:

[0009] A data acquisition module acquires ship dynamic data, weather data and hydrological data near the beacon;

[0010] An edge computing module generates a real-time trajectory of the ship according to the ship dynamic data, obtains a predicted trajectory of the ship based on the real-time trajectory of the ship and the hydrological data, and calculates a deviation degree based on a preset ship channel and the predicted trajectory of the ship.

[0011] A risk prediction module performs risk analysis on the deviation degree according to the meteorological data, and makes a route adjustment according to a result of the risk analysis.

[0012] Further, the human collection image data and thermal imaging data specifically include:

[0013] S101: The PLC synchronously triggers the camera and the thermal imager;

[0014] S102: The camera irradiates the surface of the PVC through multi-angle light sources under the triggering of the PLC, captures multi-view images, and measures the temperature distribution of the surface of the PVC hard sheet in real time;

[0015] S103: The edge computing data is used to pre-process the image data and the thermal data.

[0016] Further, the data collection module includes:

[0017] A ship dynamic collection unit is configured to collect longitude and latitude, speed, heading, and ship type data of the ship in real time through an AIS receiver and a radar sensor;

[0018] A meteorological collection unit is configured to integrate an anemometer, a barometer, and a visibility sensor, collect meteorological parameters such as wind speed, wind direction, air pressure, rainfall, and visibility, and upload the data to the edge computing module in a low-power consumption manner through a LoRa wireless communication module;

[0019] A hydrological collection unit is configured to deploy a water level sensor, a tidal current meter, and a wave sensor on a navigation mark, collect water level, tidal current speed, tidal current direction, and wave height data, and use an encryption transmission protocol to ensure data integrity.

[0020] Further, the edge computing module includes:

[0021] A trajectory generation submodule fuses AIS and radar data using a Kalman filtering algorithm to generate a real-time trajectory of the ship, and removes noise interference through time series analysis;

[0022] A predicted trajectory calculation submodule predicts a trajectory path of the ship in the next 5-30 minutes based on an LSTM neural network model and in combination with a tidal influence factor in the hydrological data, and outputs a confidence interval to quantify uncertainty;

[0023] The deviation calculation sub-module presets a plurality of parallel buffer zones as a ship channel, calculates a deviation according to a Euclidean distance between a predicted trajectory of the ship and a center line of the channel, and triggers an alarm signal when the deviation exceeds a threshold value.

[0024] Further, the risk prediction module comprises:

[0025] The risk assessment sub-module adopts a Bayesian network model, inputs meteorological data as a conditional probability, performs multi-level risk grading on the deviation, including low risk: deviation < 10%, medium risk: 10%-30%, and high risk: > 30%, and generates a risk heat map;

[0026] The route adjustment sub-module automatically generates an optimized route suggestion according to the risk analysis result, considers ship dynamic constraints and channel restrictions, and sends adjustment instructions to the ship through a VHF radio module, supporting voice and text dual-mode transmission.

[0027] Further, it further comprises a communication transmission module configured to:

[0028] A 5G or satellite communication link is adopted to realize data relay between beacons, form a distributed mesh network, and make the real-time transmission delay of remote sea areas less than 100ms;

[0029] Block chain technology is integrated to timestamp and hash verify the collected data and support a consensus mechanism between multiple beacon nodes.

[0030] Further, it further comprises a cloud analysis module connected with the edge computing module through an API interface and configured to:

[0031] Multiple beacon data are aggregated for global risk modeling, a reinforcement learning algorithm is used to optimize system parameters, and a historical trajectory database is generated to support offline simulation training;

[0032] The anomaly detection sub-module uses an isolation forest algorithm to identify potential collision or equipment failure events and automatically notifies the shore-based command center.

[0033] Further, it further comprises a user interaction module configured to:

[0034] A mobile APP interface displays a ship trajectory superimposed on a risk heat map in real time, supports AR mode visual channel adjustment suggestion, and supports AR mode visual channel adjustment suggestion.

[0035] The permission management unit ensures different data access levels of the captain, dispatcher and administrator based on a role-based access control model, and records all operation logs to meet IMO safety standards.

[0036] (Three) beneficial effects

[0037] The application provides a beacon-based real-time navigation information transmission and analysis system, which has the following beneficial effects:

[0038] (1) The system of the application can comprehensively monitor and analyze real-time ship trajectory, meteorological and hydrological data through multi-module cooperation; the risk prediction module can make multi-level risk classification of ship deviation degree by combining meteorological data with the aid of a Bayesian network model and generate a risk heat map, so as to perceive potential risks in advance; the route adjustment module can generate an optimized route by considering ship dynamic constraints and channel restrictions by using an A* algorithm, and then timely send instructions through a VHF radio module, so as to effectively avoid ship deviation from the channel, collision and other dangers, and greatly ensure the safety of crew, ships and goods.

[0039] (2) The edge computing module of the application can predict the ship trajectory in the next 5-30 minutes by using an LSTM neural network model combined with hydrological data, so as to provide an advance for ship navigation planning; the risk analysis and route adjustment mechanism can make the ship avoid adverse weather and hydrological conditions, and reduce the navigation delay caused by adverse environment; for example, the ship can avoid strong storm areas, although the navigation distance may be increased, but the low-speed navigation or stagnation caused by the storm can be avoided, so as to ensure the timely completion of the shipping task and improve the operation efficiency and economic benefit of the shipping enterprise; at the same time, the cloud analysis module aggregates multiple beacon data to model the global risk, uses a reinforcement learning algorithm to optimize system parameters, and also generates a historical trajectory database to support offline simulation training, so as to control the shipping risk from a more macro perspective and continuously optimize the system; the anomaly detection submodule uses an isolation forest algorithm to identify potential collision or equipment failure events, automatically notifies the shore-based command center, and realizes the timely early warning and disposal of shipping abnormal conditions. BRIEF DESCRIPTION OF DRAWINGS

[0040] Fig. 1 is a schematic diagram of the system of the application;

[0041] Fig. 2 is a schematic diagram of the prediction trajectory process of the application. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the application will be described clearly and completely in combination with the drawings of the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the application.

[0043] Embodiment 1:

[0044] Please refer to Figs. 1-2 The embodiment provides a beacon-based real-time navigation information transmission and analysis system, which comprises:

[0045] The data acquisition module collects dynamic data of ships, meteorological data, and hydrological data near the navigation mark;

[0046] It employs a multi-functional device integrating AIS receiver, millimeter-wave radar, and Doppler current meter (ADCP). The AIS receiving antenna acquires basic ship information in real time, while the millimeter-wave radar, scanning at a frequency of 1-2 seconds per revolution, dynamically monitors ship speed and heading angle within 5km through Doppler frequency shift. Simultaneously, the ADCP is deployed 2-3 meters underwater at the bottom of the buoy, emitting 300-600kHz sound waves to monitor the surface, middle, and bottom current velocities of the water area, providing data for ship speed correction.

[0047] A composite sensor system combining a three-dimensional ultrasonic anemometer and an ultrasonic water level gauge is employed. The three-dimensional ultrasonic anemometer, with no mechanical parts, can accurately measure wind speed and direction using the time difference of ultrasonic propagation in extreme temperature and humidity environments. The ultrasonic water level gauge, installed on the navigation beacon, utilizes a redundant design with a pressure-type water level sensor to achieve a water level measurement accuracy of ±0.02m. Furthermore, a built-in laser visibility meter, based on the Lambert-Beer law, effectively monitors visibility in both dense fog and clear weather conditions. An accelerometer at the bottom of the navigation beacon continuously samples for 30 seconds to calculate the significant wave height with an accuracy of ±0.1m, providing a basis for ship maneuverability assessment.

[0048] The edge computing module generates a real-time trajectory of the ship based on the ship dynamic data, obtains a predicted trajectory of the ship based on the real-time trajectory and the hydrological data, and calculates the deviation between the ship's predicted trajectory and the preset ship channel.

[0049] The process of generating a ship's real-time trajectory is as follows:

[0050] The edge computing module is used for data processing and trajectory analysis. Continuous and accurate real-time ship trajectories are generated through multi-step operations, including data coordinate system, single-point data error correction, and trajectory continuity.

[0051] Based on ship dynamic data, a ship state vector is defined, including position coordinates, velocity components, and acceleration components. Simultaneously, an observation vector is defined, including directly observable parameters such as position, speed, and heading. A state transition equation is established based on the ship's motion laws to describe the relationship between the ship's state and time, considering process noise such as errors caused by fluctuations in the ship's propulsion system. An observation equation is also established based on the characteristics of the observation equipment to describe the correspondence between observed values ​​and the ship's actual state, also considering observation noise such as GPS positioning errors.

[0052] Kalman filtering is divided into prediction and update. In the prediction stage, the ship's state and state covariance at the current moment are predicted based on the state transition equation and the optimal state estimate at the previous moment, reflecting the uncertainty of the predicted value.

[0053] In the update phase, the Kalman gain is calculated by combining the observations at the current moment, the reliability of the predicted value and the observation value is weighed, and the predicted state is corrected according to the Kalman gain to obtain the optimal state estimate at the current moment. Finally, the real-time trajectory of the ship is generated based on the optimal state estimate.

[0054] The process of predicting a ship's trajectory is as follows:

[0055] The process of generating ship predicted trajectories involves a complex technical step that deeply integrates multi-source data-driven approaches with intelligent algorithm modeling to accurately predict the future motion of ships. This can be achieved through the following progressive technical steps:

[0056] First, through preliminary motion state extrapolation, based on the motion parameters contained in the ship's real-time trajectory, such as current speed and heading angle, a preliminary inference is made about the ship's subsequent motion state. For example, when the ship is in a uniform straight-line state, its short-term position change trend can be preliminarily estimated based on the current velocity vector. It should be noted that the inference at this stage is only a simple extrapolation based on the ship's own motion state and has not yet introduced interference from environmental factors. It is a preliminary basic operation for subsequent accurate prediction.

[0057] Secondly, hydrological environmental factors are introduced for correction. Water flow, as a key environmental load affecting ship navigation, directly influences the ship's actual ground speed and heading through its velocity and direction. The system uses a hydrodynamic calculation model to quantitatively analyze the coupled effects of water flow velocity and direction vectors on the ship's actual speed vector and heading angle, and corrects the previous motion state predictions. For example, in downstream navigation, the water flow adds a downstream velocity component to the ship's own speed, thus changing the ship's actual ground speed; while in cross-current conditions, the water flow not only causes a change in the vector composition of the ship's speed but also induces a shift in the heading angle.

[0058] Then, an artificial intelligence algorithm integrating time-series prediction and environmental impact modeling is used to extract time-series features from the real-time trajectory data of ships. The motion of ships exhibits significant temporal dynamics, and their historical motion data contains specific behavioral patterns, such as speed change gradients during turning maneuvers and speed stability characteristics during constant-speed navigation. Through deep learning networks such as Long Short-Term Memory (LSTM), time-series features are extracted from the real-time trajectory data to uncover historical behavioral patterns of ship motion and construct a time-series prediction model of the ship's own motion. This model can accurately capture the motion characteristics of ships under different operating conditions, such as acceleration / deceleration, turning, and constant-speed cruising, providing a benchmark model for subsequent comprehensive predictions incorporating environmental factors.

[0059] Simultaneously, hydrological data is transformed into a quantified set of environmental impact factors. Different combinations of water flow velocity and direction significantly affect ship speed and heading. The system uses a trained weight matrix, generated from a large amount of historical ship-current interaction data, to quantitatively calculate the specific impact weights of flow velocity and direction parameters on changes in ship speed and heading angle under different flow conditions, thereby constructing a correlation model between "environmental loads and ship motion response".

[0060] Finally, the system integrates the ship's motion time-series prediction model with the "environment-motion" correlation model to generate the ship's predicted trajectory. In this step, the system performs vector synthesis of the coupled effects of the ship's own motion trend and environmental loads, and outputs the predicted trajectory curve of the ship over a future period through a multi-model fusion algorithm. The generated predicted trajectory not only includes the ship's own motion characteristics but also fully considers the dynamic interference of environmental factors. This provides accurate data for subsequent key stages such as ship deviation calculation, navigation risk assessment, and intelligent route optimization, thereby ensuring the safety and energy efficiency of ship navigation.

[0061] Real-time ship trajectories contain information about a ship's current motion status, including key parameters such as position, speed, and heading. By analyzing real-time data, preliminary inferences about the ship's motion can be made. For example, when a ship is traveling at a constant speed in a straight line, its approximate position 10 minutes from now can be estimated. Hydrological data elements such as water flow velocity and direction have a significant impact on ship navigation. With the current, the water flow propels the ship, causing its actual speed to exceed its own power-driven speed; against the current, the water flow obstructs the ship, reducing its speed; lateral currents can also cause the ship to deviate from its original course. Furthermore, water depth is crucial; insufficient water depth can prevent a ship from maintaining normal speed and may even lead to grounding.

[0062] Based on the "environment-motion" correlation model, the time-series prediction results of real-time trajectories need to be integrated with the environmental impact results of hydrological data. Taking the prediction of a ship's position 10 minutes later as an example, the ship's original position 10 minutes later is first predicted based on the real-time trajectory. Then, the coordinates and speed of this position are corrected by combining water flow data. If the ship is in a downstream environment, its actual position will be further forward and its speed will be faster than originally predicted; if it is upstream, its position will be further back and its speed will be slower; if there is a lateral current, its position will shift in the direction of the current. At the same time, water depth data is used to determine whether the ship can maintain normal navigation in this area. If the water depth changes, the prediction results such as the ship's speed need to be adjusted.

[0063] The AI ​​model continuously receives new real-time trajectory and hydrological data, dynamically updating its predictions. Because the ship's motion and the hydrological environment are constantly changing, new real-time trajectory data reflects the ship's latest motion adjustments, while new hydrological data shows the latest conditions of water flow, depth, and other parameters. Based on this new data, the model re-performs time-series predictions and environmental impact analyses, then integrates them to obtain a new predicted trajectory. This ensures the timeliness and accuracy of the trajectory, ultimately outputting the ship's continuous position points over a future period, forming a complete predicted trajectory.

[0064] The specific process for calculating the deviation is as follows:

[0065] The deviation is calculated by quantifying the difference between the preset waterway and the predicted ship trajectory, providing data basis for risk warning. The deviation is calculated from the two dimensions of position and heading by digital modeling of the preset waterway and standardization of the predicted ship trajectory. The comprehensive deviation is obtained by dynamic weight fusion and corrected in combination with the real-time environment.

[0066] The preset waterway is transformed into a digital model. Based on the official waterway data delineated by the maritime authorities, such as the coordinates of the waterway centerline, the width of the waterway, and the location of turning points, the digital model of the waterway is constructed using the "segmented curve fitting" method. For example, for a straight section of the waterway, the latitude and longitude coordinates of multiple feature points on the centerline of the waterway are collected, and a continuous centerline trajectory is generated using linear interpolation.

[0067] Ship prediction trajectories are sequences of ship positions over a future period generated by AI models. Through "time axis alignment," the preset channel model typically uses "channel mileage" as a parameter, while the prediction trajectory uses "time" as a parameter. The time series of the prediction trajectory needs to be converted into a "mileage-position" sequence. This is achieved by calculating the distance between adjacent positions in the prediction trajectory, accumulating the "cumulative voyage mileage" for each time point, and then matching it with the mileage parameter of the preset channel to ensure that the two are consistent in "position reference dimension."

[0068] This approach relies on a Bayesian network model. A Bayesian network is a graphical network based on probabilistic reasoning. Meteorological data encompasses numerous parameters, including wind speed, wind direction, air pressure, rainfall, and visibility, all of which are critical factors affecting ship navigation safety. For example, strong winds may cause ships to deviate from their planned routes, dense fog that reduces visibility greatly increases the risk of collisions, and abnormal air pressure changes may indicate the onset of severe weather. In the Bayesian network model, meteorological data serves as conditional probability input. Different combinations of meteorological conditions correspond to different probabilities of ship deviation risk. Through learning and training on a large amount of historical navigation data and meteorological data, the Bayesian network establishes a probabilistic relationship model between meteorological factors and ship deviation.

[0069] Once real-time meteorological data is collected, the probabilistic model calculates the probability of the ship's deviation falling into different risk levels under the current conditions, based on the input data. Specifically, the risk is categorized into three levels: low risk (deviation <10%), medium risk (10%-30%), and high risk (>30%). Simultaneously, a risk heatmap is generated, presenting the abstract risk probability in an intuitive thermal distribution. Different colors represent different risk levels, allowing ship operators and shore-based command personnel to clearly understand the risk situation of the area the ship is currently in or about to enter, providing a clear and intuitive basis for subsequent route adjustment decisions.

[0070] Algorithm and execution mechanism for route adjustment

[0071] After obtaining accurate risk analysis results, the route adjustment module activates the A* path planning algorithm to generate optimized route suggestions. The A* algorithm is an efficient algorithm for finding the shortest path in graph search. In route planning, it comprehensively considers the ship's dynamic constraints and channel limitations. The ship's dynamic constraints include its own speed characteristics, turning ability, and inertia. Different types of ships, such as large cargo ships and small yachts, have significantly different dynamic performance. The A* algorithm incorporates these dynamic constraints into the route planning calculation based on information such as ship type, ensuring that the planned route is one that the ship can actually follow.

[0072] Regarding channel restrictions, factors such as channel width, water depth, and traffic density must be considered. For example, some channels may have shoals or shallow water, preventing large vessels from entering; or the channel width may be limited, requiring vessels to follow specific routes to avoid collisions. The A* algorithm will find the optimal route while satisfying these channel restrictions.

[0073] Ships have various dynamic constraints, and these constraints vary significantly depending on the type of ship. The A* algorithm takes these constraints into full consideration to ensure the feasibility of the planned route.

[0074] Regarding the inherent speed characteristics of ships, large cargo ships, due to their large size and mass, experience relatively slow acceleration and deceleration, resulting in a limited range of speed variations. Smaller yachts, on the other hand, are more agile and can adjust their speed more rapidly. When calculating paths, the A* algorithm presets upper and lower limits for speed variations and acceleration constraints based on the ship type. For example, large cargo ships have relatively low maximum acceleration; therefore, when planning the speed for each segment of the route, the algorithm ensures that speed changes do not exceed the ship's acceleration capabilities, avoiding situations where the ship cannot actually reach high speeds or experience sudden decelerations. Smaller yachts have higher acceleration and more flexible speed adjustments, so the algorithm will correspondingly set a wider but realistic range of speed variations.

[0075] A ship's turning capability is also a key constraint. Large cargo ships have large turning radii, requiring more time and space to turn; small yachts are more agile and can achieve rapid turns with small radii. The A* algorithm sets maximum limits on the turning angle for different types of ships. For example, large cargo ships have smaller maximum turning angles. When planning turning nodes in the route, the algorithm ensures that the turning angles between adjacent path segments do not exceed this limit, allowing the ship to complete the turning operation smoothly. Small yachts have more lenient turning angle restrictions, and the algorithm will plan more flexible turning paths accordingly.

[0076] Furthermore, when ships are sailing in water, they cannot stop or change direction instantly like land vehicles due to inertia. When planning a route, the A* algorithm takes into account the ship's inertia, calculating the braking distance and steering lead at different speeds. This ensures that the spacing between planned route nodes and the setting of turning points are reasonable, giving the ship sufficient space and time to complete speed adjustments and turning maneuvers, thus preventing the ship from deviating from the planned route due to inertia.

[0077] After generating optimized route suggestions, adjustment commands are sent to the vessel via a VHF radio module. VHF radio offers moderate transmission distance and good real-time performance, meeting the communication needs of vessels at sea. It also supports dual-mode voice and text transmission. Voice transmission allows the vessel's navigator to quickly receive key route adjustment points, facilitating rapid response in emergencies; text transmission provides more detailed and accurate route adjustment information, such as specific latitude and longitude coordinates and turning points, enabling precise operation by the navigator.

[0078] When a vessel is about to enter a high-risk area, timely course adjustments can effectively prevent it from deviating too far from its course, reducing the likelihood of collisions with other vessels, or avoiding dangerous situations such as loss of control due to severe weather conditions and complex hydrological environments. This plays an irreplaceable role in ensuring the safety of crew members and protecting the vessel and cargo. Course adjustments allow vessels to avoid unfavorable weather and hydrological conditions, reducing navigation delays caused by adverse environments. For example, when a strong storm is predicted ahead, adjusting the course in advance to avoid the storm area may increase the sailing distance, but the overall sailing time may be reduced by avoiding the slow speed or even stagnation caused by the storm, thus ensuring the timely completion of shipping tasks and improving the operational efficiency and economic benefits of shipping companies.

[0079] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0080] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0081] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A real-time transmission and analysis system for navigation aid information, characterized in that: The system includes: The data acquisition module collects dynamic data of ships, meteorological data, and hydrological data near the navigation mark; The edge computing module generates a real-time trajectory of the ship based on the ship dynamic data, obtains a predicted trajectory of the ship based on the real-time trajectory and the hydrological data, and calculates the deviation between the ship's predicted trajectory and the preset ship channel. The risk prediction module performs risk analysis on the deviation based on the meteorological data, and makes route adjustments based on the risk analysis results.

2. The real-time transmission and analysis system based on navigation aid information according to claim 1, characterized in that: The data acquisition module includes: Ship dynamic data is collected in real time through AIS receivers and radar sensors, including the ship's latitude, longitude, speed, heading, and ship type. Meteorological data is collected through the anemometer, barometer and visibility sensor integrated in the meteorological acquisition unit, which collect meteorological parameters such as wind speed, wind direction, air pressure, rainfall and visibility, and uploads the data to the edge computing module in a low-power manner through the LoRa wireless communication module. The hydrological data acquisition unit is equipped with water level sensors, tidal current meters, and wave sensors deployed on navigation marks to collect data on water level, tidal current velocity, tidal current direction, and wave height, and uses an encrypted transmission protocol to ensure data integrity.

3. The real-time transmission and analysis system based on navigation aid information according to claim 2, characterized in that: The real-time trajectory of the vessel includes: The trajectory generation submodule uses a Kalman filter algorithm to fuse AIS and radar data to generate real-time ship trajectories and removes noise interference through time series analysis. The ship trajectory prediction includes a trajectory calculation submodule, which, based on an LSTM neural network model and combined with tidal current influence factors in hydrological data, predicts the ship's trajectory path for the next 5-30 minutes and outputs a confidence interval to quantify uncertainty. The deviation includes a deviation calculation submodule, which pre-determines that the ship's channel is composed of multiple parallel buffer zones, calculates the deviation based on the Euclidean distance between the ship's predicted trajectory and the centerline of the channel, and triggers an alarm signal when the deviation exceeds a threshold.

4. The real-time transmission and analysis system based on navigation aid information according to claim 1, characterized in that: The risk analysis includes: The risk assessment submodule uses a Bayesian network model, taking meteorological data as conditional probability input, to classify the deviation into multiple levels of risk, including low risk (deviation <10%), medium risk (10%-30%), and high risk (>30%), and generates a risk heat map. Based on the risk analysis results, the A* route planning algorithm is used to automatically generate optimized route suggestions, taking into account ship dynamic constraints and waterway restrictions, and sending adjustment instructions to the ship through a VHF radio module, supporting dual-mode voice and text transmission.

5. The real-time transmission and analysis system based on navigation aid information according to claim 1, characterized in that: It also includes a communication transmission module, configured as follows: Using 5G or satellite communication links to achieve data relay between navigation marks and form a distributed mesh network, the real-time transmission latency in remote sea areas is less than 100ms; It integrates blockchain technology to verify the collected data using timestamp hashing and supports consensus mechanisms among multiple beacon nodes.

6. The real-time transmission and analysis system based on navigation aid information according to claim 1, characterized in that: It also includes a cloud analytics module, which connects to the edge computing module via an API interface, configured as follows: It aggregates multi-marker data for global risk modeling, uses reinforcement learning algorithms to optimize system parameters, and generates a historical trajectory database, supporting offline simulation training; The anomaly detection submodule uses the isolated forest algorithm to identify potential collisions or equipment malfunctions and automatically notifies the shore-based command center.

7. The real-time transmission and analysis system based on navigation aid information according to claim 1, characterized in that: It also includes a user interaction module, configured as follows: The mobile app interface displays real-time ship trajectories overlaid with risk heat maps and supports AR mode for visualizing waterway adjustment suggestions. The access control unit, based on a role-based access control model, ensures different data access levels for captains, dispatchers, and administrators, and records all operation logs to comply with IMO security standards.

Images