A ship navigation risk identification and early warning method and system

Abstract

The application discloses a kind of ship navigation risk identification and early warning method and system, it is related to ship navigation risk identification technical field, the method includes the following steps: collect the navigation data under current ship history static data and dynamic data, construct ship operation situation model, in combination with the static data and dynamic data of current ship, the operation situation of current ship is predicted, obtains predicted trajectory coordinates, obtains the situation of current ship surrounding ship by unmanned aerial vehicle shooting image and is mapped to two-dimensional plane to construct ship risk prediction chart, and the predicted trajectory is projected to ship risk prediction chart in real time;Sensor is deployed in the front of current ship, and the flow data around current ship is collected by sensor, in combination with the distribution of other ships around on ship risk prediction chart.The application realizes the situation prediction and risk effective early warning of surrounding ship by comprehensively static and dynamic data of ship, flow fluctuation information, to improve the safety of inland navigation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ship navigation risk identification, in particular to a ship navigation risk identification and early warning method and system. BACKGROUND

[0002] As an important part of waterway transportation, inland shipping plays a key role in regional economic development due to its low cost and large capacity. However, the inland river channel is narrow and the water flow is complex, and the number of ships is large and the types are various, collision accidents occur from time to time, which seriously threatens the safety of life and property and the order of navigation;

[0003] The traditional ship navigation risk identification and early warning method has many limitations, relying on the visual observation and experience judgment of the crew, which is greatly affected by human factors, and it is difficult to fully grasp the dynamic of surrounding ships, especially in low visibility or densely populated areas, it is easy to make mistakes in judgment. At the same time, in the process of inland shipping, the existing early warning system based on AIS has the problem of incomplete information coverage in the case that most small ships on inland rivers are not equipped with this system, which cannot effectively monitor ships without AIS signals, resulting in a blind area in collision risk identification, and the problems of low practicality and functionality. SUMMARY

[0004] In view of the problems in the related art, the present application proposes a ship navigation risk identification and early warning method and system to overcome the above technical problems existing in the prior art.

[0005] To this end, the specific technical solutions adopted by the present application are as follows:

[0006] A ship navigation risk identification and early warning method, the method comprising the following steps:

[0007] S1, collect the navigation data of the current ship under the historical static data and dynamic data, construct a ship operation situation model, combine the static data and dynamic data of the current ship, predict the operation situation of the current ship, obtain the predicted trajectory coordinates, obtain the surrounding ship situation of the current ship through the image shooting of the unmanned aerial vehicle and map it to a two-dimensional plane to construct a ship risk prediction map, and project the predicted trajectory onto the ship risk prediction map in real time;

[0008] S2, deploy a sensor in the front of the current ship, collect the water flow data around the current ship through the sensor, combine the distribution of other ships around the ship risk prediction map, construct a surrounding ship operation situation prediction model, and determine the risk ship based on the surrounding ship operation situation and the heading of the current ship;

[0009] S3, based on the current ship motion situation model combined with the surrounding risk ships of the current ship, the motion situation of the current ship is risk identified, combined with the running situation prediction result of the surrounding risk ships, the risk in the current ship route process is warned.

[0010] As a preferred embodiment, the S1 comprises the following steps:

[0011] S11, collect the static data and dynamic data in the historical running process of the current ship, based on the neural network, build a ship running situation model, wherein the static data includes the length, width and load of the ship, the dynamic data includes the ship speed, heading, acceleration, water flow speed, flow direction, water level and position information of the ship at different time, collect the historical static data and dynamic data of the current ship, identify and process the abnormal values by Z-score method, divide the data into training set, validation set and test set according to the ratio of 7:2:1, train the ship running situation model by LSTM, wherein the ship navigation data and hydrological data are processed through multiple LSTM layers in turn, and finally a fully connected layer is connected to convert the output of the LSTM layer into the predicted ship position;

[0012] S12, combined with the real-time static data and dynamic data in the current ship route process, the running situation of the current ship is predicted, and the predicted trajectory is obtained.

[0013] As a preferred embodiment, the S12 comprises the following steps:

[0014] S121, obtain the load of the current ship through the ship cargo loading and unloading record, collect the ship speed, heading and acceleration of the current ship in real time through the instrument panel of the current ship, receive the hydrological monitoring station information to obtain the hydrological data of the area where the current ship is located, including the water flow speed, flow direction and water level, record the above data as the navigation static data and dynamic data of the current ship, input the ship running situation model of the current ship, and obtain the predicted trajectory coordinates;

[0015] S122, take an overhead view of the navigation area by a drone, keep a circular area with a radius R centered at the current ship in the overhead view of the navigation area, identify the ship contour in the circular area by Canny edge detection, map the circular area to a two-dimensional plane in proportion, construct a ship risk prediction map, convert the latitude and longitude coordinates to two-dimensional plane coordinates using geographic information system technology, project the predicted trajectory coordinates on the ship risk prediction map, and update the ship risk prediction map in real time according to the fixed shooting interval.

[0016] As a preferred embodiment, the S2 comprises the following steps:

[0017] S21. Using an acoustic Doppler current profiler deployed around the current vessel, continuously collect the velocity vector of the surrounding water flow at different times. Calculate the relative motion using the known position of the vessel itself and the positions of the surrounding vessels, deduce the motion state of the surrounding vessels, and construct a prediction model of the surrounding vessel's operating state to predict the position of the surrounding vessels.

[0018] S22. Based on the current course of the vessel and the operational status of surrounding vessels, mark vessels at risk.

[0019] In a preferred embodiment, S21 includes the following steps:

[0020] S211. Use an acoustic Doppler current profiler to collect vector data of the water velocity around the ship. The water velocity at time t is... Including speed magnitude With direction The current position of the ship is obtained through the ship risk prediction map. and the position of the i-th surrounding ship. Further calculations are performed to obtain the positions of surrounding ships relative to the current ship. Calculate the relative displacement and estimate the relative velocity within adjacent time intervals, where adjacent time intervals are... Relative displacement within relative speed for ;

[0021] S212. The relative velocity under the influence of water flow includes the ship's still water velocity and the water flow velocity. The still water velocity is calculated by eliminating the water flow velocity obtained from the acoustic Doppler current profiler. By analyzing the motion patterns of surrounding vessels in still water, the magnitude and direction of velocity changes are obtained, including the following steps:

[0022] Still water speed Then acceleration ;

[0023] Direction of still water velocity Then angular velocity ,in These represent the northward and eastward components of the still water velocity, respectively.

[0024] S213. Use a polynomial to fit the motion trajectories of surrounding ships in still water, and extract the curvature of the trajectory based on the fitted trajectory. As a feature, the rate of change of speed, the rate of change of speed direction, and the trajectory curvature are taken as features to construct a feature vector, which is classified and predicted by a naive Bayes classifier, the prior probability and conditional probability are calculated according to the historical data, the posterior probability is calculated for the newly obtained feature vector, and the class with the maximum posterior probability is selected as the predicted navigation intention direction.

[0025] S214, according to the navigation intention prediction result and the speed information of the surrounding ships at the current time, the position of the ship at time T is predicted, and for the i th surrounding ship, the position of the ship at future time T is .

[0026] As a preferred embodiment, the S22 comprises the following steps:

[0027] S221, based on the heading of the current ship and the running situation prediction of the surrounding ships to obtain the navigation intention, the included angle between the heading of the current ship and the predicted track intention of the surrounding ships is calculated, comprising the following steps:

[0028] According to the heading vector of the current ship , wherein respectively represent the components of the heading vector of the current ship on the x axis and the y axis, and the predicted track intention direction of the surrounding ships , wherein respectively represent the components of the predicted track intention direction vector of the surrounding ships on the x axis and the y axis, and the included angle , the surrounding ship of is marked as a risk ship, wherein is the included angle threshold.

[0029] As a preferred embodiment, the S3 comprises the following steps:

[0030] S31, for the determined risk ship, according to the navigation intention prediction result and the speed information of the risk ship, the position of the ship at consecutive N time is predicted to obtain consecutive position coordinate points, and the consecutive position coordinate points are recorded in the ship risk prediction map, the intersection position is identified by combining the current ship prediction trajectory in the ship risk prediction map and the consecutive position coordinate points of the risk ship, to determine the risk and alarm.

[0031] As a preferred embodiment, the S31 comprises the following steps:

[0032] S311, according to the navigation intention prediction result and the speed information of the risk ship, the position of the ship at consecutive N time is predicted to obtain consecutive position coordinate points, and the calculated position coordinate of each time is projected in the ship risk prediction map, and the current ship prediction trajectory coordinate under consecutive N time is retained;

[0033] S312, for each continuous position coordinate point obtained by risk ship prediction , find the point closest to the current ship in the predicted trajectory of the current ship , and calculate the distance between the two points , wherein , when , it represents that the current ship and the risk ship will intersect at time A, which has a collision risk, wherein , represents the distance threshold, and an audible and visual alarm is issued to remind the duty personnel, and the current risk ship is marked in the radar.

[0034] A ship navigation risk identification and early warning system, comprising a data acquisition module, a model construction module, a risk identification and early warning module;

[0035] The data acquisition module comprises a unmanned aerial vehicle and an acoustic Doppler current profiler, the navigation area overhead view is shot by the unmanned aerial vehicle, the velocity vector of the water flow around the current ship at different times is continuously acquired by the acoustic Doppler current profiler, the load of the current ship is obtained through the ship cargo loading and unloading record, the ship speed, heading, acceleration of the current ship are acquired in real time through the instrument panel of the current ship, the hydrological data of the area where the current ship is located, including the water flow velocity, flow direction and water level, are obtained by receiving the information of the hydrological monitoring station, and the static data and dynamic data in the historical operation process of the current ship are collected, the ship operation situation model is constructed based on the neural network, wherein the static data includes the length, width and load of the ship, and the dynamic data includes the ship speed, heading, acceleration, water flow velocity, flow direction, water level and position information of the ship at different times;

[0036] The model construction module constructs the ship operation situation model through the navigation data under the historical static data and dynamic data of the current ship based on the data acquired by the data acquisition module, acquires the surrounding ship situation of the current ship through the image shot by the unmanned aerial vehicle and maps it to a two-dimensional plane to construct a ship risk prediction map, and constructs the surrounding ship operation situation prediction model in combination with the distribution of other surrounding ships on the ship risk prediction map based on the water flow data around the current ship acquired by the sensor;

[0037] The risk identification and early warning module predicts the operation situation of the current ship through the ship operation situation model of the current ship, obtains the predicted trajectory coordinates and projects the predicted trajectory on the ship risk prediction map in real time, determines the risk ship based on the operation situation of the surrounding ships and the heading of the current ship, identifies the risk of the operation situation of the current ship based on the ship operation situation model of the current ship in combination with the risk ships around the current ship, and gives a warning to the risk in the navigation process of the current ship in combination with the operation situation prediction results of the surrounding risk ships.

[0038] The beneficial effects of the present application are:

[0039] 1. This invention collects static and dynamic data of the current vessel during navigation, predicts the vessel's navigation route based on the current vessel's load and inertia, draws a risk prediction map based on the situation of other vessels around the current vessel, identifies risky vessels based on water flow fluctuation data around the current vessel, and performs risk identification and early warning based on the predicted trajectory of the current vessel. It can detect situations that may collide with the current vessel in advance, and issue timely warnings when the collision risk is high, giving the crew enough time to take evasive action, thereby reducing the probability of vessel collision accidents.

[0040] 2. This invention predicts the situation of surrounding vessels based on water flow fluctuation data around the hull. It can effectively identify and warn of risks during navigation in inland waterways where there are many small and densely packed vessels and most vessels are not equipped with AIS systems. This helps crew members better plan their navigation routes, reduces the risk of collisions due to lack of information, and enhances functionality.

[0041] 3. By predicting the situation of surrounding vessels, this invention allows crew members to plan their navigation routes and speeds more effectively, avoiding frequent evasive maneuvers and unnecessary deceleration, thus improving the navigation efficiency of inland waterway vessels. Predicting the dynamics of surrounding vessels based on water flow fluctuation data also enables better coordination of the navigation order between the current vessel and other vessels, enhancing its practicality. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart of a method for identifying and warning of ship navigation risks according to an embodiment of the present invention.

[0044] Figure 2 This is a block diagram of a ship navigation risk identification and early warning system according to an embodiment of the present invention. Detailed Implementation

[0045] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0046] According to an embodiment of the present application, a ship navigation risk identification and early warning method and system are provided.

[0047] The present application will be further described in conjunction with the drawings and specific embodiments:

[0048] Embodiment 1: As shown, according to a ship navigation risk identification and early warning method according to an embodiment of the present application, the method comprises the following steps: Figure 1

[0049] S1, collect the navigation data of the current ship under the historical static data and dynamic data, construct a ship operation situation model, combine the static data and dynamic data of the current ship, predict the operation situation of the current ship, obtain the predicted trajectory coordinates, obtain the surrounding ship situation of the current ship through the image shooting of the unmanned aerial vehicle and map it to a two-dimensional plane to construct a ship risk prediction map, and project the predicted trajectory onto the ship risk prediction map in real time;

[0050] S11, collect the static data and dynamic data of the current ship in the historical operation process, construct a ship operation situation model based on a neural network, wherein the static data includes the length, width and load of the ship, and the dynamic data includes the ship speed, heading, acceleration, water flow speed, flow direction, water level and position information of the ship at different times, collect the historical static data and dynamic data of the current ship, identify and process the outliers through the Z-score method, divide the data into a training set, a validation set and a test set according to a ratio of 7:2:1, and train the ship operation situation model through LSTM, wherein the ship navigation data and hydrological data are processed through multiple LSTM layers in sequence, and finally a fully connected layer is connected to convert the output of the LSTM layer into the predicted ship position;

[0051] It should be noted that, wherein the ship navigation data includes ship speed, heading, acceleration, and the hydrological data includes water flow speed, flow direction, and water level, when performing LSTM training, the mean square error is used as the loss function to measure the error between the predicted ship position of the model and the actual historical data of the ship position, the learning rate of each parameter is adaptively adjusted through the Adam optimizer, the training set data is input into the model in batches to calculate the predicted value through forward propagation, the error between the predicted value and the actual value is calculated according to the loss function, the gradient is calculated through back propagation, the parameters of the model are updated using the optimizer, and the iteration is repeated until the preset training number of rounds is reached to obtain the ship operation situation model of the current ship.

[0052] S12, combine the real-time static data and dynamic data in the current ship route process to predict the operation situation of the current ship and obtain the predicted trajectory;

[0053] ​S121, obtain the load of the current ship through the ship cargo handling record, collect the ship speed, heading, acceleration of the current ship in real time through the instrument panel of the current ship, receive the hydrological monitoring station information to obtain the hydrological data of the area where the current ship is located, including the flow velocity, flow direction, water level, record the above data as the static and dynamic data of the current ship's navigation, input the ship operation situation model of the current ship, and obtain the predicted trajectory coordinates;

[0054] S122, take an overhead view of the navigation area by using a drone, reserve a circular area with a radius R in the overhead view of the navigation area with the current ship as the center, identify the ship outline in the circular area by using Canny edge detection, map the circular area to a two-dimensional plane in proportion, construct a ship risk prediction map, convert the latitude and longitude coordinates to two-dimensional plane coordinates using geographic information system technology, project the predicted trajectory coordinates onto the ship risk prediction map, and update the ship risk prediction map in real time according to a fixed shooting interval.

[0055] It should be noted that the radius R needs to be set according to experience based on the parameters of the current drone camera and the size of the navigation area, and the shooting interval is usually set to 10s, which can also be adjusted according to the actual situation. The coordinate conversion is realized by using the pyproj library of Python, a binary mask consistent with the image size is created, a circular area is drawn with the center position coordinates of the current ship in the image as the center and a radius of R, the pixel values in the circular area are set to 1, and the rest are set to 0. The circular area image with the current ship as the center and a radius of R is extracted. According to the range of the mapped two-dimensional circular area plane image, a blank two-dimensional image is created as the basis of the ship risk prediction map. The ship outline corresponding to the two-dimensional plane coordinates and the predicted trajectory are drawn on the blank two-dimensional graph to obtain the ship risk prediction map.

[0056] Embodiment 2: S2, deploy sensors at the front of the current ship, collect water flow data around the current ship through the sensors, construct a surrounding ship operation situation prediction model based on the distribution of other ships around the current ship on the ship risk prediction map, and determine the risk ship based on the surrounding ship operation situation and the heading of the current ship;

[0057] S21, use the acoustic Doppler current profiler deployed around the current ship to continuously collect the velocity vectors of the surrounding water flow at different times, calculate the relative motion through the known position of the current ship and the position of the surrounding ships, deduce the motion situation of the surrounding ships, and construct a surrounding ship operation situation prediction model to predict the position of the surrounding ships;

[0058] S211, use the acoustic Doppler current profiler to collect water flow velocity vector data around the current ship, and the water flow velocity at time t is , including the speed and direction obtain the current ship position by ship risk prediction map and the position of the i-th surrounding ship further calculate the position of the surrounding ship relative to the current ship calculate the relative displacement in the adjacent time and estimate the relative speed, wherein the relative displacement in the adjacent time the relative speed ; ;

[0059] S212, the relative speed under the influence of water flow includes the static water speed of the ship and the water flow speed obtained by eliminating the acoustic Doppler current profiler to calculate the static water speed analyze the motion pattern of the surrounding ship by the static water speed, obtain the speed size change and the speed direction change, including the following steps:

[0060] the static water speed size then the acceleration ;

[0061] the static water speed direction then the angular velocity , wherein respectively represent the north and east components of the static water speed;

[0062] It should be noted that the static water speed size is calculated and analyzed, when continuously increases, it represents that the ship is accelerating, continuously decreases, it represents that the ship is decelerating, and the analysis changes over time, if the change rate is large, it represents that the ship is turning.

[0063] S213, use polynomial fitting to obtain the motion trajectory of the surrounding ship in the static water, and extract the curvature of the trajectory according to the fitted trajectory as a feature, the velocity size change rate, the velocity direction change rate and the trajectory curvature are used as features to construct a feature vector, which is classified and predicted by a naive Bayes classifier, the prior probability and the conditional probability are calculated according to the historical data, the posterior probability is calculated for the newly obtained feature vector, and the class with the maximum posterior probability is selected as the predicted sailing intention direction;

[0064] It should be noted that the position data of the ship is fitted using a quadratic polynomial, the coefficients are solved by the least square method, so that the error sum of squares of the fitted curve and the actual trajectory is minimized, and when the naive Bayes classifier is used for classification and prediction, it is assumed that there are m categories of sailing intention the prior probability and the conditional probability , wherein​ For the feature vector constructed by taking the speed magnitude change rate, the speed direction change rate, and the trajectory curvature as features, for a new feature vector , the posterior probability is calculated according to the Bayes formula .

[0065] S214, according to the navigation intention prediction result and the speed information of the surrounding ships around the current time, the position of the ship at time T is predicted, and for the i th surrounding ship, the ship position at future time T is .

[0066] S22, based on the heading of the current ship and the running situation prediction of the surrounding ships, mark the risk ships;

[0067] S221, based on the heading of the current ship and the running situation prediction of the surrounding ships, obtain the navigation intention, calculate the included angle between the heading of the current ship and the predicted route intention of the surrounding ships, including the following steps:

[0068] According to the heading vector of the current ship , wherein respectively represent the components of the heading vector of the current ship on the x-axis and the y-axis, and the predicted route intention direction of the surrounding ships , wherein respectively represent the components of the predicted route intention direction vector of the surrounding ships on the x-axis and the y-axis, and the included angle , mark the surrounding ship of as a risk ship, wherein is the included angle threshold.

[0069] It should be noted that is the included angle threshold, which is usually set to 30°, and can also be adjusted according to actual needs, when the included angle is less than the included angle threshold, it represents that there is a collision risk between the current ship and the surrounding ship.

[0070] S3, based on the current ship motion situation model and the surrounding risk ships of the current ship, the motion situation of the current ship is risk identified, and the running situation prediction result of the surrounding risk ships is combined to predict the risk of the current ship during navigation;

[0071] S31, for the determined risk ship, according to the navigation intention prediction result and the speed information of the risk ship, the positions of the ship at consecutive N times are predicted to obtain consecutive position coordinate points, and the consecutive position coordinate points are recorded in the ship risk prediction map, and the intersection position is identified to determine the risk and give an alarm by combining the current ship prediction trajectory in the ship risk prediction map and the consecutive position coordinate points of the risk ship.

[0072] S311. Based on the prediction results of the navigation intention and speed information of the risky vessel, predict the position of the vessel at N consecutive time points to obtain continuous position coordinates. Project the calculated position coordinates at each time point onto the vessel risk prediction map and retain the current predicted trajectory coordinates of the vessel at N consecutive time points.

[0073] S312. For each consecutive position coordinate point obtained from the risk vessel prediction Find the point closest to it in the current ship's predicted trajectory. And calculate the distance between the two points. ,in ,when At time A, it indicates that the current vessel and the vessel at risk will meet at a time of collision risk. Representing a distance threshold, it issues an audible and visual alarm to alert on-duty personnel and marks currently at-risk vessels on the radar.

[0074] It should be noted that, This represents the distance threshold, which needs to be set in conjunction with the current navigation area. In narrow waterways, the distance threshold can be set smaller, while in open sea areas, the distance threshold can be appropriately increased.

[0075] Example 3: As Figure 2 As shown, a ship navigation risk identification and early warning system includes a data acquisition module, a model building module, and a risk identification and early warning module.

[0076] The data acquisition module includes a drone and an acoustic Doppler current profiler. The drone captures an overhead view of the navigation area, and the acoustic Doppler current profiler continuously collects the velocity vector of the water flow around the vessel at different times. The vessel's load is obtained from the cargo loading and unloading records. The vessel's speed, heading, and acceleration are collected in real time from the instrument panel. The module receives hydrological data from the hydrological monitoring station, including water flow velocity, direction, and water level. It also collects static and dynamic data from the vessel's historical operation. Based on a neural network, a vessel operation status model is constructed. The static data includes the vessel's length, width, and load, while the dynamic data includes the vessel's speed, heading, acceleration, water flow velocity, direction, water level, and the vessel's position information at different times.

[0077] The model building module, based on the data collected by the data acquisition module, constructs a ship operation status model through the historical static and dynamic navigation data of the current ship, and obtains the situation of ships around the current ship by taking pictures with drones and maps them onto a two-dimensional plane to construct a ship risk prediction map. The water flow data around the current ship collected by sensors, combined with the distribution of other ships around the ship on the ship risk prediction map, constructs a prediction model of the operation status of surrounding ships.

[0078] The risk identification and early warning module predicts the operation situation of the current ship through the current ship operation situation model, obtains the predicted trajectory coordinates and projects the predicted trajectory on the ship risk prediction map in real time, determines the risk ship based on the operation situation of the surrounding ships and the heading of the current ship, identifies the motion situation of the current ship based on the current ship motion situation model and the risk ships around the current ship, and early warns the risks in the navigation process of the current ship in combination with the operation situation prediction results of the surrounding risk ships

[0079] In conclusion, the application collects the static data and dynamic data of the current ship in the navigation process, predicts the ship navigation route based on the load and inertia of the current ship, draws a risk prediction map in combination with the conditions of other ships around the current ship, determines the risk ships based on the water flow fluctuation data around the current ship, and identifies and early warns the risks in combination with the predicted trajectory of the current ship, so that the collision conditions with the current ship can be found in advance, the collision risks can be early warned when the collision risks are high, the crew has enough time to take avoiding measures, and the probability of ship collision accidents is reduced.

[0080] By predicting the situation of the surrounding ships based on the water flow fluctuation data around the ship body, effective risk identification and early warning in the ship navigation process can be realized under the condition that the river is small and there are many ships, and most of the ships are not equipped with AIS systems, which helps the crew to better plan the navigation path, reduces the collision risks caused by information loss, and enhances the functionality.

[0081] By predicting the situation of the surrounding ships, the crew can reasonably plan their own navigation route and speed, avoid frequent avoiding operations and unnecessary speed reduction, improve the navigation efficiency of the inland river ship, predict the dynamics of the surrounding ships according to the water flow fluctuation data, better coordinate the navigation order of the current ship and other ships, and enhance the practicability.

[0082] The above only describes the preferred embodiments of the application and is not used to limit the application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A method for ship navigation risk identification and early warning, characterized in that, The method comprises the following steps: S1, collecting the sailing data of the current ship under the historical static data and dynamic data, constructing a ship operation situation model, combining the static data and dynamic data of the current ship, predicting the operation situation of the current ship, obtaining the predicted trajectory coordinates, obtaining the surrounding ship situation of the current ship through the image shooting of the unmanned aerial vehicle and mapping to a two-dimensional plane to construct a ship risk prediction map, and projecting the predicted trajectory onto the ship risk prediction map in real time; S2, deploying sensors in the front of the current ship, collecting the surrounding water flow data of the current ship through the sensors, combining the distribution of other surrounding ships on the ship risk prediction map, constructing a surrounding ship operation situation prediction model, and determining the risk ship based on the surrounding ship operation situation and the heading of the current ship; S21, using the acoustic Doppler current profiler deployed around the current ship to continuously collect the velocity vector of the surrounding water flow at different times, calculating the relative motion through the known position of the current ship and the position of the surrounding ships, deducing the motion situation of the surrounding ships, and constructing a surrounding ship operation situation prediction model to predict the position of the surrounding ships; S211, using acoustic Doppler current profiler to collect the current velocity vector data around the current ship, the current velocity at time t is , including the velocity size and direction , obtaining the current ship position and the position of the i-th ship around the current ship by the ship risk prediction map , further calculating the position of the surrounding ship relative to the current ship , calculating the relative displacement in the adjacent time and calculating the relative velocity, wherein the relative displacement in the adjacent time , the relative velocity is ; S212, the relative speed under the influence of the water flow contains the static water speed of the ship and the water flow speed, the water flow speed obtained by eliminating the acoustic Doppler current profiler is used to calculate the static water speed , the speed size change and the speed direction change are obtained by analyzing the surrounding ship movement mode through the static water speed, including the following steps: Static water velocity magnitude Then acceleration ; direction of the current velocity then the angular velocity where and represent the north and east components of the current velocity, respectively; S213, using polynomial fitting the trajectory of the surrounding ships in still water, extracting the curvature of the trajectory according to the fitted trajectory As a feature, the rate of change of speed, the rate of change of speed direction, the trajectory curvature are taken as the features to construct the feature vector, the classification prediction is carried out through the naive Bayes classifier, the prior probability and the conditional probability are calculated according to the historical data, the posterior probability is calculated for the newly obtained feature vector, and the class with the maximum posterior probability is selected as the predicted sailing intention direction. S214, according to the sailing intention prediction result and speed information of the surrounding ships around the current time, the position of the ship at time T is predicted, and for the i-th surrounding ship, the ship position at future time T is ; S22, based on the heading of the current ship and the operation situation prediction of the surrounding ships, marking the risk ship; S3, based on the current ship motion situation model and the surrounding risk ships of the current ship, identifying the risk of the current ship motion situation, and warning the risk in the process of the current ship route based on the operation situation prediction result of the surrounding risk ships.

2. The method of claim 1, wherein, The S1 comprises the following steps: S11, collecting the static data and dynamic data of the current ship in the historical operation process, constructing a ship operation situation model based on a neural network, wherein the static data includes the length, width and load of the ship, and the dynamic data includes the ship speed, heading, acceleration, water flow speed, flow direction, water level and position information of the ship at different times, collecting the historical static data and dynamic data of the current ship, identifying and processing abnormal values through the Z-score method, dividing the data into a training set, a validation set and a test set according to a ratio of 7:2:1, and training the ship operation situation model through LSTM, wherein the ship sailing data and hydrological data are processed through multiple LSTM layers in sequence, and finally a fully connected layer is connected to convert the output of the LSTM layer into the predicted ship position; S12, combining the real-time static data and dynamic data in the process of the current ship route, predicting the operation situation of the current ship, and obtaining the predicted trajectory.

3. The method of claim 2, wherein, The S12 comprises the following steps: S121, obtaining the load of the current ship through the ship cargo loading and unloading record, collecting the ship speed, heading and acceleration of the current ship in real time through the instrument panel of the current ship, receiving the hydrological monitoring station information to obtain the hydrological data of the area where the current ship is located, including the water flow speed, flow direction and water level, recording the above data as the sailing static data and dynamic data of the current ship, inputting the ship operation situation model of the current ship, and obtaining the predicted trajectory coordinates; S122, a UAV is used to take an overhead view of the navigation area, a circular area with a radius of R is reserved in the overhead view of the navigation area with the current ship as the center, the ship contour in the circular area is identified through Canny edge detection, the circular area is proportionally mapped to a two-dimensional plane, a ship risk prediction map is constructed, geographic information system technology is used to convert latitude and longitude coordinates into two-dimensional plane coordinates, the predicted trajectory coordinates are projected onto the ship risk prediction map, and the ship risk prediction map is updated in real time at a fixed shooting interval.

4. The method of claim 1, wherein, The S22 includes the following steps: S221, based on the heading of the current ship and the running situation of the surrounding ships, the navigation intention is predicted, the included angle between the heading of the current ship and the predicted navigation intention of the surrounding ships is calculated, and the following steps are included: According to the current vessel heading vector wherein represent the components of the current vessel heading vector on the x- and y-axes, respectively, in combination with the surrounding vessel predicted track intended direction wherein represent the components of the surrounding vessel predicted track intended direction vector on the x- and y-axes, respectively, the included angle is calculated marking the surrounding vessel as a risk vessel if is greater than a threshold value is the included angle threshold value.

5. The method of claim 4, wherein, The S3 includes the following steps: S31, for the determined risk ship, the position of the ship at consecutive N time points is predicted according to the navigation intention prediction result and the speed information of the risk ship to obtain consecutive position coordinate points, and the consecutive position coordinate points are recorded in the ship risk prediction map, the intersection position is identified by combining the predicted trajectory of the current ship in the ship risk prediction map and the consecutive position coordinate points of the risk ship, and the risk is determined and an alarm is given.

6. The method of claim 5, wherein, The S31 includes the following steps: S311, according to the navigation intention prediction result and the speed information of the risk ship, the position of the ship at consecutive N time points is predicted to obtain consecutive position coordinate points, and the position coordinate at each time point calculated is projected in the ship risk prediction map, and the predicted trajectory coordinate of the current ship at consecutive N time points is reserved; S312, for each continuous position coordinate point obtained by the risk ship prediction finding the point closest to the current ship in the predicted trajectory of the current ship and calculating the distance between the two points wherein when , it represents that the current ship and the risk ship will intersect at time A, which has a collision risk, wherein represents the distance threshold, an audible and light alarm is issued to remind the duty personnel, and the current risk ship is marked in the radar.

7. A ship navigation risk identification and early warning system, characterized in that, The system adopts a ship navigation risk identification and early warning method according to any one of claims 1-6, comprising a data acquisition module, a model construction module, a risk identification and early warning module; The data acquisition module comprises a UAV and an acoustic Doppler current profiler, the UAV is used to take an overhead view of the navigation area, the acoustic Doppler current profiler is used to continuously collect the velocity vector of the water flow around the current ship at different time points, the load of the current ship is obtained through the ship cargo loading and unloading record, the ship speed, heading and acceleration of the current ship are collected in real time through the instrument panel of the current ship, the hydrological data of the area where the current ship is located, including the water flow velocity, direction and level, are obtained by receiving the information of the hydrological monitoring station, and the static data and dynamic data in the historical running process of the current ship are collected, the ship running situation model is constructed based on the neural network, wherein the static data includes the length, width and load of the ship, and the dynamic data includes the ship speed, heading, acceleration, water flow velocity, direction and level, and the position information of the ship at different time points; The model construction module is based on the data collected by the data acquisition module, the ship running situation model is constructed through the navigation data under the historical static data and dynamic data of the current ship, the situation of the surrounding ships of the current ship is obtained through the image taken by the UAV and mapped to a two-dimensional plane to construct a ship risk prediction map, and the surrounding ship running situation prediction model is constructed through the water flow data around the current ship collected by the sensor in combination with the distribution of the surrounding ships on the ship risk prediction map. The risk identification and early warning module predicts the operation situation of the current ship through a current ship operation situation model, obtains predicted trajectory coordinates and projects the predicted trajectory onto a ship risk prediction map in real time, determines risk ships based on the operation situation of surrounding ships and the heading of the current ship, identifies the risk of the operation situation of the current ship based on the current ship operation situation model and the risk ships around the current ship, and early warns the risks in the navigation process of the current ship based on the operation situation prediction results of the surrounding risk ships.

Images