Ship intelligent situation awareness prediction method and system

Abstract

The invention discloses an intelligent ship situation awareness prediction method and system, and relates to the technical field of intelligent ship situation awareness and trajectory prediction, and the method comprises the steps: carrying out the time-space synchronization of collected operation environment data of a ship through a timestamp alignment method, and generating a ship situation data set; based on the ship situation data set, the course angle change rate and the Euclidean distance of the obstacle relative to the ship are extracted, and weighted fusion is carried out on the dynamic collision probability and the approaching time of the obstacle to obtain an obstacle threat degree index; inputting the obstacle threat degree index into a ship trajectory prediction model, and outputting the minimum meeting distance between the ship and each obstacle; and carrying out risk grade division on the minimum encounter distance according to an international maritime collision avoidance rule, outputting a graded early warning signal, and formulating a navigation strategy to execute obstacle avoidance and route adjustment. According to the method, the technical problems of risk perception lag, single and rough avoidance action and insufficient trajectory prediction accuracy in the prior art are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent ship situation awareness and trajectory prediction, and particularly to a ship intelligent situation awareness and prediction method and system. Background Art

[0002] The intelligent ship situation awareness technology is mainly used to real-time sense and predict the dynamic changes of the ship and its surrounding environment to support safe navigation decisions. With the continuous development of technologies such as intelligent sensors, data fusion, and machine learning, ship situation awareness has gradually evolved from the monitoring based on a single data source such as traditional radar and AIS (Automatic Identification System) to the stage of integrating multi-source heterogeneous data and realizing the comprehensive perception of the environment and the ship's own state. The existing technologies usually assist ship drivers in making collision avoidance and path optimization decisions through means such as navigation environment perception, obstacle detection, and trajectory prediction, and have played an active role in improving navigation safety and reducing accident risks. However, in the face of the actual marine environment with complex dynamic changes, large amounts of data, and high uncertainty, there are still certain deficiencies in the spatio-temporal synchronous processing of ship operation environment data, obstacle threat measurement, accurate prediction of the minimum encounter distance, and formulation of risk classification and early warning strategies in the existing technologies. It is urgent to further optimize the accuracy of perception and prediction and the timeliness of response. Especially in comprehensively considering the threat degree in terms of dynamic indicators such as the relative course change and approach time of obstacles, the refined processing ability of the existing methods is still insufficient.

[0003] CN118245756B discloses a ship intelligent navigation analysis method and system based on situation awareness. By obtaining navigation environment monitoring information and ship operation monitoring information, it respectively conducts environment perception and ship state assessment, constructs a channel digital model in combination with digital twin technology, and evaluates the channel situation. Finally, it realizes navigation event prediction and obstruction degree assessment, and formulates navigation strategies for collision avoidance and route adjustment. This method can comprehensively perceive the navigation environment and improve the adaptability and safety of the ship to complex navigation conditions. However, in the threat degree assessment of dynamic obstacles, it fails to carefully consider the fusion calculation of dynamic indicators such as the course angle change rate and approach time, resulting in room for improvement in the accuracy of refined threat prediction and classification early warning.

[0004] CN114627363B discloses a panoramic maritime ship situation awareness method based on multi-task learning. By establishing a multi-task learning network model, ship situation prediction and visualization are realized based on a remote sensing image data set. This method effectively improves the overall accuracy of maritime ship situation awareness and solves the problems of isolation between different perception systems and low detection accuracy. However, due to relying mainly on remote sensing images as the perception means, it lacks a dynamic synchronization processing mechanism for the real-time changes in the close-range operation environment and does not comprehensively evaluate multi-factors such as the approach time of obstacles and the dynamic collision probability, which limits its real-time performance and the prediction ability of threat change trends in high-dynamic scenarios. Summary of the Invention

[0005] In view of the problems of insufficient spatio-temporal synchronization accuracy, imperfect obstacle threat assessment, limited trajectory prediction accuracy, and lagging collision avoidance decision response in the existing ship collision avoidance and navigation risk assessment methods, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to achieve high-precision spatio-temporal alignment and fusion of ship operation environment data, accurately evaluate the threat level of obstacles and conduct dynamic risk prediction, issue hierarchical warning signals based on the minimum distance of closest approach, and formulate intelligent navigation adjustment strategies that comply with the International Regulations for Preventing Collisions at Sea, so as to effectively improve the intelligent level of collision avoidance decisions and navigation safety during the ship's navigation process.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a ship intelligent situation awareness and prediction method, which includes,

[0009] Using a timestamp alignment method to perform spatio-temporal synchronization on the collected ship operation environment data to generate a ship situation data set;

[0010] Based on the ship situation data set, extract the course angle change rate and Euclidean distance of the obstacle relative to the ship, and perform weighted fusion on the dynamic collision probability and the approach time of the obstacle to obtain an obstacle threat degree index;

[0011] Input the obstacle threat degree index into a ship trajectory prediction model to output the minimum distance of closest approach between the ship and each obstacle;

[0012] According to the International Regulations for Preventing Collisions at Sea, divide the risk level of the minimum distance of closest approach, output a hierarchical warning signal, and formulate a navigation strategy to execute obstacle avoidance and route adjustment.

[0013] As a preferred solution of the ship intelligent situation awareness and prediction method of the present invention, wherein: the minimum encounter distance is divided into risk levels according to the International Regulations for Preventing Collisions at Sea, and a classification warning signal is displayed through a man-machine interface, including:

[0014] Set a safety distance threshold according to the International Regulations for Preventing Collisions at Sea, compare the minimum encounter distance with the safety distance threshold, and judge the navigation risk level;

[0015] Based on the relative azimuth angle between the own ship and the obstacle, the encounter state is divided into overtaking situation, crossing situation and head-on situation;

[0016] Taking the current course of the own ship as a reference, a new sequence of navigation path points is obtained by combining the obstacle threat degree index, and a route adjustment plan is generated, wherein the sequence of navigation path points satisfies the minimum turning radius constraint of the ship;

[0017] Re-enter the adjusted course into the ship trajectory prediction model, calculate the new minimum encounter distance, and judge whether it meets the safe navigation requirements;

[0018] Record the warning signal, encounter state and course adjustment data, and establish a situation warning database.

[0019] As a preferred solution of the ship intelligent situation awareness and prediction method of the present invention, wherein: the judging of the navigation risk level includes:

[0020] When the minimum encounter distance is less than the first threshold, the navigation risk level is a high risk level; if it is a high risk level, output a red warning signal, trigger an emergency collision avoidance decision-making process, and adjust the course according to the current encounter state;

[0021] When the minimum encounter distance is between the first threshold and the second threshold, the navigation risk level is a medium risk level; if it is a medium risk level, output a yellow warning signal and calculate the yaw angle correction amount;

[0022] When the minimum encounter distance is greater than the second threshold, the navigation risk level is a low risk level; if it is a low risk level, output a green warning signal, maintain the original course and speed, and continuously monitor the change trend of the minimum encounter distance.

[0023] As a preferred solution of the ship intelligent situation awareness and prediction method of the present invention, wherein:

[0024] Adjusting the course according to the current encounter state includes:

[0025] If in an overtaking state, the own ship deflects to the right by a course of not less than the first preset angle;

[0026] If in a crossing state, the own ship deflects to the right by a course of not less than the second preset angle;

[0027] If in a head-on situation, the vessel turns to the right by a course of not less than a third preset angle.

[0028] As a preferred solution of the ship intelligent situation awareness and prediction method described in the present invention, wherein: the method for obtaining the minimum encounter distance is as follows,

[0029] Construct a trajectory prediction model based on a combined recurrent neural network;

[0030] Sample the ship position data and the obstacle position data at a preset time interval to form a trajectory sequence of a number of sampling points, wherein the sampling points include position coordinates, course angle and speed information;

[0031] Combine the trajectory sequence with the obstacle threat degree index to construct a spatio-temporal feature tensor and input it into the bidirectional long short-term memory network layer;

[0032] Extract the temporal dependence relationship of the trajectory sequence through forward propagation and backward propagation, and output a hidden state sequence;

[0033] The spatio-temporal attention layer calculates an attention score matrix based on the hidden state sequence and the obstacle threat degree index;

[0034] Weight-sum the attention score matrix and the hidden state sequence, map it to the prediction space through a fully connected layer, and output a trajectory prediction point sequence;

[0035] Calculate the Euclidean distance between the ship prediction trajectory points and the obstacle prediction trajectory points within the prediction time window to form a relative distance matrix;

[0036] Based on the relative distance matrix, use the dynamic programming algorithm to calculate the minimum encounter distance between the ship and each obstacle within the prediction time window, where the minimum encounter distance includes the turning radius and the acceleration and deceleration ability limit.

[0037] As a preferred solution of the ship intelligent situation awareness and prediction method described in the present invention, wherein: the trajectory prediction model includes a bidirectional long short-term memory network layer and a spatio-temporal attention layer; the bidirectional long short-term memory network layer extracts the historical trajectory features of the ship and the obstacle; the spatio-temporal attention layer assigns weights to the obstacle threat degree index.

[0038] As a preferred solution of the ship intelligent situation awareness and prediction method described in the present invention, wherein: the method for obtaining the obstacle threat degree index is as follows,

[0039] Based on the position data of the ship situation data set and the surrounding obstacle distance data, establish a relative coordinate system of the ship and the obstacle;

[0040] In the relative coordinate system, calculate the course angle of the obstacle relative to the own ship, and obtain a sequence of course angle change rates through differential operations of the course angles within a continuous time window;

[0041] Input the sequence of course angle change rates into a long short-term memory neural network model, where the long short-term memory neural network model includes an input layer, a hidden layer, and an output layer;

[0042] Through the temporal feature learning of the long short-term memory neural network model, output the dynamic collision probability between the obstacle and the own ship;

[0043] Meanwhile, calculate the Euclidean distance using the position coordinates of the ship and the obstacle respectively;

[0044] Based on the Euclidean distance and the relative speed of the obstacle, calculate the approaching time of the obstacle using the dynamic time window method;

[0045] Design an adaptive weight coefficient to perform weighted fusion on the dynamic collision probability and the approaching time to obtain an obstacle threat degree index.

[0046] In a second aspect, an embodiment of the present invention provides a ship intelligent situation awareness and prediction system, which includes:

[0047] An acquisition module, configured to perform spatio-temporal synchronization on the collected operation environment data of the ship using a timestamp alignment method to generate a ship situation data set;

[0048] An extraction module, based on the ship situation data set, extracts the course angle change rate and the Euclidean distance of the obstacle relative to the ship, and performs weighted fusion on the dynamic collision probability and the approaching time of the obstacle to obtain an obstacle threat degree index;

[0049] An output module, inputs the obstacle threat degree index into a ship trajectory prediction model, and outputs the minimum encounter distance between the ship and each obstacle;

[0050] An early warning module, classifies the risk level of the minimum encounter distance according to the International Regulations for Preventing Collisions at Sea, outputs a classified early warning signal, and formulates a navigation strategy to perform obstacle avoidance and route adjustment.

[0051] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the processor executes the computer program, any step of the above-mentioned ship intelligent situation awareness and prediction method is implemented.

[0052] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by a processor, any step of the above-mentioned ship intelligent situation awareness and prediction method is implemented.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0054] 1. By using the timestamp alignment method to synchronize the spatio-temporal data of the operating environment of the collected ship, a ship situation data set is generated, realizing the consistent fusion of multi-source environmental information, effectively avoiding the problem of information distortion caused by the time deviation of data collection, and making the subsequent collision risk assessment and trajectory prediction based on data have a unified and continuous time basis;

[0055] 2. By extracting the rate of change of the heading angle and the Euclidean distance of the obstacle relative to the ship from the ship situation data set, and weighted-fusing the dynamic collision probability and the obstacle approach time, an obstacle threat degree index is obtained, realizing the quantitative characterization of the obstacle threat level. It not only considers the spatial position relationship, but also incorporates the dynamic approach trend, forming a comprehensive spatio-temporal feature evaluation system, reflecting the actual threat change of the obstacle to the ship safety, enhancing the sensitivity and accuracy of risk identification, and achieving rapidness in a complex navigation environment;

[0056] 3. By inputting the obstacle threat degree index into the ship trajectory prediction model and outputting the minimum encounter distance between the ship and each obstacle, realizing the precise risk prediction for future navigation dynamics, avoiding the problem that the traditional static distance judgment fails in a dynamic environment, and improving the accuracy and adaptability of trajectory prediction;

[0057] 4. By classifying the risk level of the minimum encounter distance according to the International Regulations for Preventing Collisions at Sea, outputting a classified early warning signal, and formulating a navigation strategy to execute the avoidance of navigation obstacles and route adjustment, an intelligent navigation decision-making mechanism that is in line with international standards is realized, enabling the system to have a standardized and interpretable risk response ability; Triggering different levels of route adjustment plans based on the risk level not only improves the rationality and compliance of the decision-making, but also effectively takes into account the navigation efficiency and safety, achieving the improvement of the ship's autonomous navigation safety guarantee level and the reduction of the risk of human judgment deviation;

[0058] 5. By adjusting the heading according to the current encounter state, including setting the right-turn yaw angle for collision avoidance decisions in different situations such as overtaking, crossing, and head-on encounters, a differential heading adjustment strategy for specific situation characteristics is realized, overcoming the problems of insufficient avoidance or over-avoidance caused by the one-size-fits-all processing of traditional collision avoidance algorithms. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:

[0060] Figure 1 It is a flowchart of the intelligent situation awareness and prediction method for ships. Specific implementation manners

[0061] To make the above objects, features and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0062] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0063] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that can be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0064] The present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for the convenience of explanation, the cross-sectional views showing the device structures will be enlarged locally out of the general proportion, and the schematic diagrams are only examples and should not limit the protection scope of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width and depth should be included.

[0065] At the same time, in the description of the present invention, it should be noted that the orientation or positional relationships indicated by terms such as "upper, lower, inner and outer" are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0066] Unless otherwise clearly defined and limited in the present invention, the terms "mounted, connected, and connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, and can also be indirectly connected through an intermediate medium, or can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0067] Example 1

[0068] Reference Figure 1 , which is the first embodiment of the present invention. This embodiment provides a method for intelligent situation awareness and prediction of ships, including:

[0069] S1: Use the timestamp alignment method to perform spatio-temporal synchronization on the collected operation environment data of the ship to generate a ship situation data set;

[0070] S2: Based on the ship situation data set, extract the course angle change rate and Euclidean distance of the obstacle relative to the ship, and perform weighted fusion on the dynamic collision probability and the approaching time of the obstacle to obtain the obstacle threat degree index;

[0071] S3: Input the obstacle threat degree index into the ship trajectory prediction model and output the minimum encounter distance between the ship and each obstacle;

[0072] S4: According to the International Regulations for Preventing Collisions at Sea, divide the minimum encounter distance into risk levels, output a graded warning signal, and formulate a navigation strategy to execute the avoidance of obstacles and route adjustment.

[0073] In the embodiment of the present application, the above step S1 includes:

[0074] It should be noted that the operation environment data includes position data, surrounding obstacle distance data, and environmental wind speed data.

[0075] S1.1: Obtain the position data of the ship through the GPS positioning module of the ship;

[0076] It should be noted that the position data includes the longitude, latitude, and course angle information of the ship, and the acquisition frequency is 1 time per second.

[0077] S1.2: At the same time, use a millimeter-wave radar to collect the relative distance data of surrounding obstacles;

[0078] It should be noted that the surrounding obstacle distance data includes the relative distance, relative azimuth angle, and relative speed information of the obstacle, and the acquisition frequency is 2 times per second;

[0079] S1.3: Obtain the current environmental wind speed data through a meteorological sensor, where the environmental wind speed data includes the wind speed magnitude and wind direction angle;

[0080] S1.4: Add a unified timestamp mark to the position data, surrounding obstacle distance data, and environmental wind speed data respectively, and perform alignment processing on the data collected at different frequencies based on the timestamp;

[0081] Specifically, taking 1 second as the reference time unit, interpolate the environmental wind speed data to obtain the wind condition information per second, and downsample the surrounding obstacle distance data to ensure the synchronization of the three types of data in the time dimension.

[0082] S1.5: Integrate the time-aligned data in chronological order to form a ship situation dataset including complete operating environment information.

[0083] In the embodiment of the present application, the above step S2 includes:

[0084] S2.1: Based on the position data of the ship situation dataset and the surrounding obstacle distance data, establish a relative coordinate system between the ship and the obstacle;

[0085] S2.2: In the relative coordinate system, calculate the heading angle of the obstacle relative to the ship, and obtain a sequence of heading angle change rates through differential operations of the heading angles within a continuous time window;

[0086] S2.3: Input the sequence of heading angle change rates into a long short-term memory neural network model, where the long short-term memory neural network model includes an input layer, a hidden layer, and an output layer;

[0087] It should be noted that the hidden layer is set with 64 neurons and uses the tanh activation function.

[0088] S2.4: Through the temporal feature learning of the long short-term memory neural network model, output the dynamic collision probability between the obstacle and the ship;

[0089] Preferably, the specific formula for the dynamic collision probability is as follows:

[0090]

[0091] where h t is the LSTM hidden state; σ is the Sigmoid activation function; W o and b o are the output layer parameters; μ is the heading change rate influence coefficient; γ is the distance influence coefficient; d ref is the reference distance; d(t) is the Euclidean distance.

[0092] S2.5: At the same time, calculate the Euclidean distance using the respective position coordinates of the ship and the obstacle;

[0093] S2.6: Based on the Euclidean distance and the relative speed of the obstacle, calculate the obstacle approach time using the dynamic time window method;

[0094] Preferably, the specific formula for the obstacle approach time is as follows:

[0095]

[0096] where λ is the speed adjustment coefficient; v r (t) represents the speed of the obstacle relative to the ship; θ is the influence coefficient of the course change rate.

[0097] S2.7: Design an adaptive weight coefficient to perform weighted fusion on the dynamic collision probability and the approaching time to obtain the obstacle threat degree index;

[0098] Preferably, the specific formula for the obstacle threat degree index is as follows:

[0099] TI = ω(t)·P col (t)+(1 - ω(t))·φ(t app (t));

[0100] where TI is the obstacle threat degree index; ω(t) is the adaptive weight coefficient, which is used to dynamically adjust the weight ratio of the collision probability P col (t) and the approaching time conversion function φ(*).

[0101] It should be noted that the weight coefficient is dynamically adjusted according to the complexity of the navigation environment.

[0102] In the embodiment of the present application, the above step S3 includes:

[0103] S3.1: Construct a trajectory prediction model based on a combined recurrent neural network;

[0104] In an alternative embodiment, the trajectory prediction model includes a bidirectional long short-term memory network layer and a spatio-temporal attention layer; the bidirectional long short-term memory network layer extracts the historical trajectory features of the ship and the obstacle; the spatio-temporal attention layer assigns weights to the obstacle threat degree index; the trajectory prediction model further includes an input layer, a first gated recurrent unit network, and a second gated recurrent unit network; the input layer receives state parameters such as the obstacle threat degree index, the current course and speed of the ship, the first gated recurrent unit network contains 128 hidden neurons, which are used to extract the temporal features of the ship's movement; the second gated recurrent unit network contains 64 hidden neurons, which are used to predict the sequence of future navigation trajectory points of the ship.

[0105] S3.2: Sample the ship position data and the obstacle position data at a preset time interval to form a trajectory sequence of several sampling points, where the sampling points include position coordinates, course angles, and speed information;

[0106] S3.3: Combine the trajectory sequence with the obstacle threat degree index to construct a spatio-temporal feature tensor and input it into the bidirectional long short-term memory network layer;

[0107] S3.4: Extract the temporal dependence relationship of the trajectory sequence through forward propagation and backward propagation and output the hidden state sequence;

[0108] S3.5: The spatio-temporal attention layer calculates the attention score matrix based on the hidden state sequence and the obstacle threat degree index;

[0109] Preferably, the specific formula of the attention score matrix is as follows:

[0110]

[0111] where, S ij is the attention score of the i-th time step to the j-th time step, is the permutation of the hidden state vector of the i-th time step; h j is the hidden state vector of the j-th time step; W q is the query matrix weight; is the permutation of the key matrix weight; d is the hidden state dimension; n is the time series length; η is the threat degree adjustment coefficient; TI is the obstacle threat degree index.

[0112] It should be noted that the attention score matrix represents the importance of different spatio-temporal positions.

[0113] S3.6: Weightedly sum the attention score matrix and the hidden state sequence, map it to the prediction space through the fully connected layer, and output the sequence of trajectory prediction points;

[0114] S3.7: Calculate the Euclidean distance between the predicted trajectory points of the ship and the predicted trajectory points of the obstacles within the prediction time window to form a relative distance matrix;

[0115] Preferably, the specific formula of the relative distance matrix is as follows:

[0116]

[0117] where, R ij is the element of the relative distance matrix between time point i and time point j; D base is the basic Euclidean distance; is the ship maneuverability coefficient; is the relative course angle change rate between time point i and time point j; ∈ is the standard deviation of the course angle change rate; α is the course influence factor, and the value range is [0,1]; Δψ ij is the relative course difference between the ship and the obstacle.

[0118] S3.8: Based on the relative distance matrix, use the dynamic programming algorithm to calculate the minimum encounter distance between the ship and each obstacle within the prediction time window, where the minimum encounter distance includes the turning radius and the acceleration and deceleration ability limit.

[0119] Preferably, the specific formula of the minimum encounter distance is as follows:

[0120]

[0121] Among them, D[i][j] is the dynamic programming state value from time step i to j; R ij is an element of the relative distance matrix between time point i and time point j; c1, c2, and c3 are all path cost coefficients; η is the threat degree adjustment coefficient; TI is the obstacle threat degree index; Y is the prediction time window length.

[0122] In the embodiment of the present application, the above step S4 includes:

[0123] S4.1: Set a safety distance threshold according to the International Regulations for Preventing Collisions at Sea, compare the minimum encounter distance with the safety distance threshold, and judge the navigation risk level;

[0124] Specifically, it includes:

[0125] When the minimum encounter distance is less than the first threshold, the navigation risk level is a high risk level; if it is a high risk level, output a red warning signal, trigger an emergency collision avoidance decision-making process, and adjust the course according to the current encounter state;

[0126] Illustrated by an example, high risk level (minimum encounter distance < 0.5 nautical miles): In a certain navigation scenario, the ship forms a crossing encounter situation with a ship ahead. The ship situation dataset calculates that the minimum encounter distance is 0.3 nautical miles, which is lower than the preset first threshold (0.5 nautical miles); it is determined that the current navigation risk level is high risk, and a red warning signal is immediately triggered. The warning information is highlighted on the bridge alarm and the electronic nautical chart; at the same time, start the emergency collision avoidance decision-making process, and analyze the current encounter state according to the International Regulations for Preventing Collisions at Sea (COLREGs); since the two ships are in a crossing encounter state and this ship is the give-way ship, the system automatically generates a course adjustment instruction, requiring this ship to turn to the right by no less than 30°; after turning, the system inputs the new course data into the ship trajectory prediction model and recalculates the minimum encounter distance until it is confirmed that the minimum encounter distance has increased to the safe range (≥ 0.5 nautical miles); if the minimum encounter distance after adjustment is still lower than the threshold, the turning angle will be increased or deceleration is recommended to cooperate to ensure the effectiveness of the collision avoidance measures.

[0127] Preferably, if in a overtaking state, the course of this ship deflects to the right by no less than the first preset angle; if in a crossing state, the course of this ship deflects to the right by no less than the second preset angle; if in a head-on state, the course of this ship deflects to the right by no less than the third preset angle.

[0128] When the minimum encounter distance is between the first threshold and the second threshold, the navigation risk level is a medium risk level; if it is a medium risk level, output a yellow warning signal and calculate the yaw angle correction amount;

[0129] Illustrated by an example, medium risk level (0.5 nautical miles ≤ minimum encounter distance < 1.0 nautical mile): When the vessel approaches a ship on the port side, the system calculates that the minimum encounter distance is 0.7 nautical miles, which is between the first threshold (0.5 nautical miles) and the second threshold (1.0 nautical miles); it determines that the navigation risk level is medium risk and outputs a yellow warning signal, which is marked in yellow on the electronic chart to prompt the driver to pay attention to potential risks. At this time, the emergency collision avoidance action will not be triggered. Instead, based on the rate of change of the obstacle's course angle and the approaching speed, a gentle yaw angle correction amount (such as a 10° fine-tuning to the right) is calculated to gradually increase the minimum encounter distance; the driver can manually confirm or adjust this correction amount; continuously monitor the change trend of the corrected minimum encounter distance. If the distance shrinks to the high-risk range, the warning will be immediately upgraded and the emergency collision avoidance process will be started; if the minimum encounter distance stabilizes or increases, the current strategy will be maintained until the risk is lifted.

[0130] When the minimum encounter distance is greater than the second threshold, the navigation risk level is the low-risk level; if it is the low-risk level, a green warning signal will be output, and the original course and speed will be maintained, and the change trend of the minimum encounter distance will be continuously monitored.

[0131] It should be noted that the safety distance thresholds include the first threshold and the second threshold; the first threshold is determined based on the minimum safe encounter distance required by the vessel under emergency collision avoidance conditions; the second threshold is determined based on the minimum safe encounter distance required by the vessel to maintain a navigation safety margin under normal avoidance conditions.

[0132] Illustrated by an example, low risk level (minimum encounter distance ≥ 1.0 nautical mile): When sailing in open waters, the system detects that the minimum encounter distance of the obstacle closest to the vessel is 1.2 nautical miles, exceeding the second threshold (1.0 nautical miles). Therefore, it is determined that the navigation risk level is low risk, and a green warning signal is output, indicating that the current navigation state is safe and no collision avoidance measures need to be taken. The electronic chart normally displays the tracks of the vessel and surrounding ships, and continuously monitors the dynamic change of the minimum encounter distance. If the minimum encounter distance decreases to the medium risk range due to the subsequent acceleration or course change of the obstacle, it will be promptly switched to the yellow warning state, and a course fine-tuning will be recommended in advance to maintain a safe distance; the driver can always grasp the situation change and make efficient and safe navigation decisions with the assistance of the system.

[0133] S4.2: Based on the relative azimuth angle between the vessel and the obstacle, the encounter state is divided into overtaking situation, crossing situation and head-on situation;

[0134] Preferably, when the obstacle is located at the stern of the ship relative to the own ship and its speed is less than that of the own ship, it is judged as an overtaking situation; when the obstacle is located within a preset range on the port or starboard side of the own ship and has an intersecting trend, it is judged as a crossing situation; when the obstacle is located directly ahead of the own ship and the headings are opposite or nearly opposite, it is judged as a meeting situation.

[0135] S4.3: Based on the current heading of the own ship, obtain a new sequence of navigation path points by combining the threat degree index of the obstacle, and generate a route adjustment plan, where the sequence of navigation path points satisfies the minimum turning radius constraint of the ship;

[0136] S4.4: Re-enter the adjusted heading into the ship trajectory prediction model, calculate the new minimum distance of approach, and judge whether it meets the requirements of safe navigation;

[0137] Preferably, when the new minimum distance of approach is still less than the first threshold, it is determined that the emergency collision avoidance strategy does not meet the safety requirements, triggering a secondary collision avoidance decision-making process to further increase the angle of heading adjustment (such as adding a 5° deflection) or collaborative speed reduction measures; when the new minimum distance of approach is increased to between the first threshold and the second threshold, it is determined that the risk level is reduced to medium risk, maintaining the current adjusted heading, continuously outputting a yellow warning signal and monitoring the dynamic threat degree index; when the new minimum distance of approach is greater than the second threshold, it is determined that the risk level is reduced to low risk, outputting a green warning signal and locking the current heading as the safe heading, terminating the collision avoidance action.

[0138] S4.5: Record the warning signal, encounter status and heading adjustment data, and establish a situation warning database.

[0139] In summary, the present invention synchronizes the spatio-temporal data of the ship operation environment by using the timestamp alignment method, ensuring the consistency and timeliness of various data, and improving the accuracy and reliability of the situation data set; by extracting the relative heading angle change rate and Euclidean distance of the obstacle, and weighted fusing the dynamic collision probability and time to approach, constructing a threat degree index, accurately reflecting the real-time threat level of the obstacle to the ship navigation safety; by inputting the threat degree index into the trajectory prediction model and outputting the minimum distance of approach, it can dynamically evaluate the potential risk interval between the ship and the obstacle, and identify dangerous situations in advance; by classifying the risk level of the minimum distance of approach according to the International Regulations for Preventing Collisions at Sea and outputting a classified warning signal, and formulating a navigation strategy at the same time, it realizes the differential disposal and timely avoidance of different risk situations; by displaying the classified warning results in real time through the man-machine interface, and recording the warning signal and adjustment data, establishing a situation warning database, providing historical support for continuously optimizing the collision avoidance decision-making and navigation path adjustment, and significantly improving the accuracy of ship intelligent situation perception, the timeliness of navigation decision-making and the navigation safety as a whole.

[0140] Furthermore, this embodiment also provides a ship intelligent situation awareness and prediction system, including:

[0141] An acquisition module, which is used to perform spatio-temporal synchronization on the collected operation environment data of the ship by using the timestamp alignment method, and generate a ship situation data set;

[0142] An extraction module, based on the ship situation data set, extracts the course angle change rate and Euclidean distance of the obstacle relative to the ship, and performs weighted fusion on the dynamic collision probability and the approaching time of the obstacle to obtain an obstacle threat degree index;

[0143] An output module, which inputs the obstacle threat degree index into a ship trajectory prediction model and outputs the minimum encounter distance between the ship and each obstacle;

[0144] An early warning module, which divides the risk level of the minimum encounter distance according to the International Regulations for Preventing Collisions at Sea, outputs a classified early warning signal, and formulates a navigation strategy to perform obstacle avoidance and route adjustment.

[0145] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication) or other technologies. When the computer program is executed by the processor, it implements a multi-task edge computing resource scheduling method. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the computer device, or an external keyboard, a touchpad or a mouse, etc.

[0146] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method proposed in the above embodiment.

[0147] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0148] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and the necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disc of a computer, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method of the embodiments of the present invention.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0150] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages.

[0151] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0152] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the function specified in one or more of the processes Figure 1 and / or boxes Figure 1 specified in the one or more processes and / or boxes.

[0153] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more of the processes Figure 1 and / or boxes Figure 1 specified in the one or more boxes.

[0154] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

[0155] It is obvious that those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent situation awareness and prediction method for ships, characterized in that: including Performing spatio-temporal synchronization on the operation environment data of the collected ship using a timestamp alignment method to generate a ship situation dataset; Based on the ship situation dataset, extracting the rate of change of the heading angle and the Euclidean distance of the obstacle relative to the ship, and performing weighted fusion on the dynamic collision probability and the approaching time of the obstacle to obtain an obstacle threat degree index; Inputting the obstacle threat degree index into a ship trajectory prediction model to output the minimum encounter distance between the ship and each obstacle; Performing risk level classification on the minimum encounter distance according to the International Regulations for Preventing Collisions at Sea, outputting a classification warning signal, and formulating a navigation strategy to perform obstacle avoidance and route adjustment; 2. The intelligent situation awareness and prediction method for ships according to claim 1, characterized in that: Performing risk level classification on the minimum encounter distance according to the International Regulations for Preventing Collisions at Sea, and displaying the classification warning signal through a man-machine interaction interface, including: Setting a safety distance threshold according to the International Regulations for Preventing Collisions at Sea, comparing the minimum encounter distance with the safety distance threshold, and judging the navigation risk level; Based on the relative azimuth angle between the own ship and the obstacle, dividing the encounter state into an overtaking situation, a crossing situation, and a head-on situation; Taking the current heading of the own ship as a reference, combining with the obstacle threat degree index to obtain a new sequence of navigation path points, and generating a route adjustment plan, where the sequence of navigation path points satisfies the minimum turning radius constraint of the ship; Re-inputting the adjusted heading into the ship trajectory prediction model, calculating the new minimum encounter distance, and judging whether it meets the requirements of safe navigation; Recording warning signals, encounter states, and heading adjustment data, and establishing a situation warning database; 3. The intelligent situation awareness and prediction method for ships according to claim 2, characterized in that: The judging of the navigation risk level includes: When the minimum encounter distance is less than the first threshold, the navigation risk level is a high risk level; if it is a high risk level, output a red warning signal, trigger an emergency collision avoidance decision-making process, and adjust the heading according to the current encounter state; When the minimum encounter distance is between the first threshold and the second threshold, the navigation risk level is a medium risk level; if it is a medium risk level, output a yellow warning signal and calculate the yaw angle correction amount; When the minimum encounter distance is greater than the second threshold, the navigation risk level is a low risk level; if it is a low risk level, output a green warning signal, maintain the original heading and speed, and continuously monitor the change trend of the minimum encounter distance; 4. The ship intelligent situation awareness and prediction method according to claim 3, characterized in that: Adjusting the heading according to the current encounter state includes: If in an overtaking state, the own ship deflects the heading to the right by no less than the first preset angle; If in a crossing state, the own ship deflects the heading to the right by no less than the second preset angle; If in a head-on state, the own ship deflects the heading to the right by no less than the third preset angle; 5. The ship intelligent situation awareness and prediction method according to claim 3, characterized in that: The method for obtaining the minimum encounter distance is Constructing a trajectory prediction model based on a combined recurrent neural network; Sampling the ship position data and the obstacle position data at a preset time interval to form a trajectory sequence of a number of sampling points, where the sampling points include position coordinates, heading angles, and speed information; Combining the trajectory sequence with the obstacle threat degree index to construct a spatio-temporal feature tensor and inputting it into the bidirectional long short-term memory network layer; Extracting the temporal dependence relationship of the trajectory sequence through forward propagation and backward propagation, and outputting a hidden state sequence; The spatio-temporal attention layer calculates an attention score matrix based on the hidden state sequence and the obstacle threat degree index; The attention score matrix is weighted and summed with the hidden state sequence, mapped to the prediction space through a fully connected layer, and a sequence of trajectory prediction points is output; Calculate the Euclidean distance between the predicted trajectory points of the ship and the predicted trajectory points of the obstacle within the prediction time window to form a relative distance matrix; Based on the relative distance matrix, the dynamic programming algorithm is used to calculate the minimum encounter distance between the ship and each obstacle within the prediction time window, where the minimum encounter distance includes the turning radius and the acceleration and deceleration ability limit.

6. The ship intelligent situation awareness and prediction method according to claim 5, wherein: The trajectory prediction model includes a bidirectional long short-term memory network layer and a spatio-temporal attention layer; the bidirectional long short-term memory network layer extracts the historical trajectory features of the ship and the obstacle; the spatio-temporal attention layer assigns weights to the obstacle threat degree index.

7. The intelligent situation awareness and prediction method for ships according to claim 6, characterized in that: The method for obtaining the obstacle threat degree index is as follows: Based on the position data and the surrounding obstacle distance data in the ship situation dataset, a relative coordinate system of the ship and the obstacle is established; In the relative coordinate system, calculate the heading angle of the obstacle relative to the ship, and obtain a sequence of heading angle change rates through the differential operation of the heading angle within a continuous time window; Input the sequence of heading angle change rates into a long short-term memory neural network model, where the long short-term memory neural network model includes an input layer, a hidden layer, and an output layer; Through the temporal feature learning of the long short-term memory neural network model, output the dynamic collision probability between the obstacle and the ship; At the same time, use the position coordinates of the ship and the obstacle respectively to calculate the Euclidean distance; Based on the Euclidean distance and the relative speed of the obstacle, the dynamic time window method is used to calculate the obstacle approach time; Design an adaptive weight coefficient to perform weighted fusion on the dynamic collision probability and the approach time to obtain the obstacle threat degree index.

8. A ship intelligent situation awareness and prediction system, based on the ship intelligent situation awareness and prediction method according to any one of claims 1 to 7, characterized in that: Including: An acquisition module for synchronizing the spatio-temporal data of the operating environment data of the collected ship by using the timestamp alignment method to generate a ship situation dataset; An extraction module, based on the ship situation dataset, extracts the heading angle change rate and the Euclidean distance of the obstacle relative to the ship, and performs weighted fusion on the dynamic collision probability and the approach time of the obstacle to obtain the obstacle threat degree index; An output module, which inputs the obstacle threat degree index into the ship trajectory prediction model and outputs the minimum encounter distance between the ship and each obstacle; An early warning module, which divides the risk level of the minimum encounter distance according to the International Regulations for Preventing Collisions at Sea, outputs a classified early warning signal, and formulates a navigation strategy to execute the avoidance of obstacles and the adjustment of the shipping route.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the ship intelligent situation awareness and prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the ship intelligent situation awareness and prediction method according to any one of claims 1 to 7.

Images