GNSS-based method, system and device for predicting ship route trajectory in dock area
By installing a GNSS site on the central axis of the ship, recording and calculating the ship's motion status and predicting future trajectories, the poor adaptability of ship docking trajectory prediction in the prior art is solved, and efficient and accurate trajectory prediction in the docking area is achieved.
Patent Information
- Application Number
- CN202211290461.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-10-21
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2042-10-21
AI Technical Summary
The prior art is difficult to accurately predict trajectories during ship docking, especially in docking areas. Traditional methods are poorly adaptable and artificial intelligence methods require a lot of data training, which is not suitable for trajectory prediction in smaller seas during single-ship docking.
Using a GNSS-based method, by installing GNSS sites A and B on the central axis of the ship, recording the position time series, calculating the rate and spin velocity, predicting the future position, forming a trajectory prediction line, simplifying the dynamic model, comprehensively considering tugboats, wind and waves, etc. factor.
It realizes efficient prediction of ship trajectory in the docking area, simplifies operations, improves docking efficiency and accuracy, and is suitable for actual sea areas operations.
Smart Images

Figure CN115762236B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of computer engineering technology, and relates to a method, system and device for predicting a ship's route trajectory, and specifically to a method, system and device for predicting a ship's route trajectory in a dock area. Background Art
[0002] When some docks enter the coastal dock, they need to be towed or pushed by a small tugboat, align with the dock at a certain distance, and then enter vertically to ensure safety. Generally, the commander relies on the naked eye to observe the relative spatial relationship between the hull and the dock, and then use the power of the tugboat to change the route of the ship to achieve the purpose of safe docking. Due to the limitations of human visual observation and the difficulty in trajectory prediction, it is difficult for the hull to approach the dock in an optimized route, which greatly reduces the efficiency of ship docking.
[0003] At present, there are also some methods for predicting ship trajectories, such as the traditional method of constructing dynamic equations. This type of method not only requires professional knowledge, but also requires modeling and debugging according to different ship feature data and scenarios. When the ship sails under multiple power sources such as its own propeller, tugboat and wind and waves, this method is difficult to establish a correct power model, so its adaptability and versatility are poor. There are also new methods for training based on artificial intelligence methods. For example, a ship trajectory prediction method based on CNN and BILSTM is published in CN202111349534.1. The navigation data of the target ship, including longitude, latitude, heading and speed, is collected through the ship AIS. These information data are divided into training sets and test sets, and imported into the convolutional neural network CNN for feature extraction, forming the input data for trajectory prediction and imported into the BILSTM neural network model for learning, obtaining the implicit ship motion law model in the trajectory data, and predicting the ship's driving trajectory based on this. It mainly solves the problem of ship trajectory prediction in complex water traffic environments in a large area, and is not suitable for ship route trajectory prediction in the dock area.
[0004] To sum up, the current methods are as follows: hull modeling methods have weak adaptability and cumbersome preparation work; while artificial intelligence methods require a large amount of data training, and are mainly used to solve traffic prediction and planning problems for multiple ships in large waters. They are not suitable for trajectory prediction in a smaller sea area near the dock during the docking process of a single ship. Summary of the invention
[0005] In order to solve the above technical problems, the present invention provides a method, system and device for predicting the trajectory of a ship route in a dock area.
[0006] The technical solution adopted by the method of the present invention is: a method for predicting the trajectory of a ship route in a docking area based on GNSS, wherein GNSS stations A and B are installed along the central axis of the ship to be docked, wherein A is in the middle of the ship and B is in the stern of the ship; the distance from the head O of the ship to the middle A is recorded as L;
[0007] The method comprises the following steps:
[0008] Step 1: Use the GNSS device to continuously record the position time series of A and B during the ship's travel (X A , Y A ) and (X B , Y B );
[0009] Step 2: Take the position data of point B at the current time point and two time points before the fixed time interval Δt in the position time series, and calculate the velocity V of point B B , the spin speed R of point B B and the relative spin speed R at point A A ;
[0010] Step 3: Predict the position of the ship after the future time Δt′, including the position of point B (X B est,Y B est), point A position (X A est,Y A est) and the ship's head position (X O est,Y O est);
[0011] Step 4: The ship position after the predicted time point Δt′, i.e. the position of point A (X A est,Y A est) and point B position (X B est,Y B est) is set as the current position; repeat the above steps 1 to 3 to predict the position of the ship at point A and point B after a certain time interval of Δt′;
[0012] Step 5: The predicted positions of N Δt′, including the position A in the middle of the ship and the position O at the head of the ship, are combined to form a ship predicted position sequence, i.e., a trajectory prediction line.
[0013] The technical solution adopted by the system of the present invention is: a GNSS-based ship route trajectory prediction system in the docking area, GNSS stations A and B are installed along the central axis of the ship to be docked, where A is in the middle of the ship and B is at the stern of the ship; the distance from the head O of the ship to the middle A is recorded as L;
[0014] The system includes the following modules:
[0015] Module 1 is used to use the GNSS device to continuously record the position time series (X) of A and B during the ship's travel. A , Y A ) and (X B , Y B );
[0016] Module 2 is used to obtain the position data of point B at the current time point and two time points before the fixed time interval Δt in the position time series, and calculate the velocity V of point B B , the spin speed R of point B B and the relative spin speed R at point A A ;
[0017] Module 3 is used to predict the position of the ship after the future time Δt′, including the position of point B (X B est,Y B est), point A position (X A est,Y A est) and the ship's head position (X O est,Y O est);
[0018] Module 4 is used to predict the position of the ship after the predicted time point Δt′, that is, the position of point A (X A est,Y A est) and point B position (X B est,Y B est) is set as the current position; repeat the above modules 1 to 3 to predict the position of the ship at point A and point B after a certain time interval of Δt′;
[0019] Module 5 is used to form a ship predicted position sequence, i.e., a trajectory prediction line, by combining the predicted positions of N Δt′, including the ship middle position A and the ship bow position O.
[0020] The technical solution adopted by the device of the present invention is: a GNSS-based ship route trajectory prediction device in the dock area, comprising:
[0021] one or more processors;
[0022] A storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the GNSS-based dock area ship route trajectory prediction method.
[0023] The present invention takes into account the comprehensive superposition of various dynamics such as tugboat wind and waves when the hull is docked in actual sea areas. It uses the movement state of the ship in a period of time obtained by GNSS to predict the ship's trajectory in the future. There is no need to perform complex dynamic modeling for each hull. The present invention grasps the core of the movement trajectory and comprehensively expresses the joint influence of factors such as towing ropes, waves and currents, and hull power. Its concise formula is convenient for software application, very friendly to operators, and convenient and practical. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 is a flow chart of a method according to an embodiment of the present invention;
[0025] Figure 2 This is a schematic diagram of the ship GNSS installation relationship according to an embodiment of the present invention;
[0026] Figure 3 Schematic diagram of geometric relationship of an embodiment of the present invention. DETAILED DESCRIPTION
[0027] In order to facilitate ordinary technicians in the field to understand and implement the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.
[0028] Please see Figure 1 The present invention provides a method for predicting the trajectory of a ship route in a docking area based on GNSS. GNSS stations A and B are installed along the central axis of the ship to be docked, wherein A is located in the middle of the ship and B is located at the stern of the ship. The distance from the head O of the ship to the middle A is denoted as L. Figure 2 As shown, the installation adopts a temporary structure, which can be quickly recovered after use.
[0029] The method of this embodiment includes the following steps:
[0030] Step 1: Use the GNSS device to continuously record the position time series of A and B during the ship's travel (X A , Y A ) and (X B , Y B );
[0031] Step 2: Take the position data of point B at the current time point and two time points before the fixed time interval Δt in the position time series, and calculate the velocity V of point B B , the spin speed R of point B B and the relative spin speed R at point A A ;
[0032] like Figure 3As shown, nowA and nowB represent the positions of GNSS stations A and B on the ship at the current moment, and lastA and lastB represent the positions of A and B on the ship recorded before Δt;
[0033]
[0034] R B =(Arctan((Y B now-Y B last) / (X B now-X B last))-Arctan((Y A last-Y B last) / (X A last-X B last))) / Δt;
[0035] R A =(Arctan((Y A now-Y B now) / (X A now-X B now))-Arctan((Y A last-Y B last) / (X A last-X B last))) / Δt;
[0036] Among them, (X B Now, Y B now) represents the position coordinates of point B at the current time point, (X B last,Y B last) represents the position coordinates of point B at a fixed time interval Δt ago.
[0037] Step 3: Predict the position of the ship after the future time Δt′, including the position of point B (X B est,Y B est), point A position (X A est,Y A est) and the ship's head position (X O est,Y O est);
[0038] X B est=X B now+V B *Δt′*cos(arctan((Y A now-Y B now) / (XA now-X B now))+W ton *R B *Δt′)
[0039] Y B est=Y B now+V B *Δt′*sin(arctan((Y A now-Y B now) / (X A now-X B now))+W ton *R B *Δt′)
[0040] W ton =W1, when tonnage ton∈[0,1],
[0041] W ton =W2, when tonnage ton∈(1,10],
[0042] W ton =W3, when tonnage ton∈(10,100],
[0043] W ton =W4, when tonnage ton∈(100,1000],
[0044] W ton =W5, when tonnage ton∈(1000,10000].
[0045] W1, W2, W3, W4, and W5 are preset values, which are obtained based on the data obtained from the practice of various tonnage ship types. Generally, W1=0.5, W2=0.2, W3=0.1, W14=0.07, and W5=0.05.
[0046] X A est=X B now+|AB|*cos(arctan((Y A now-Y B now) / (X A now-X B now))+R A *Δt′);
[0047] Y A est=Y B now+|AB|*sin(arctan((Y A now-Y B now) / (X A now-X Bnow))+R A *Δt′);
[0048] X O est=X A now+L*cos(arctan((Y A now-Y B now) / (X A now-X B now)));
[0049] Y O est=Y A now+L*sin(arctan((Y A now-Y B now) / (X A now-X B now)));
[0050] Among them, (X B Now, Y B now) represents the position coordinates of point B at the current time point, (X A Now, Y A now) represents the position coordinates of point A at the current time point; |AB| is the distance between points AB, which is a fixed value.
[0051] Step 4: The ship position after the predicted time point Δt′, i.e. the position of point A (X A est,Y A est) and point B position (X B est,Y B est) is set as the current position; repeat the above steps to predict the position of the ship at point A and point B after 2 Δt′ time intervals.
[0052] Step 5: The predicted positions of N Δt′, including the position A in the middle of the ship and the position O at the bow of the ship, are formed into a ship predicted position sequence, i.e., a trajectory prediction line, which is provided to the commander for reference.
[0053] This embodiment has been tested in real sea areas, with a range of 2000m, effectively guiding the commanding personnel in towing, steering, acceleration and deceleration operations, and accurately docking (with an accuracy better than 3cm). The prediction and warning of the heading is significantly ahead of manual observation, generally 5-10 seconds, which greatly improves the predictability. Combined with the use of software, it greatly facilitates the on-site command of the operator.
[0054] It should be understood that the above description of the preferred embodiment is relatively detailed and cannot be regarded as limiting the scope of patent protection of the present invention. Under the enlightenment of the present invention, ordinary technicians in this field can also make substitutions or modifications without departing from the scope of protection of the claims of the present invention, which all fall within the scope of protection of the present invention. The scope of protection requested for the present invention shall be based on the attached claims.
Claims
1. A method for predicting ship route trajectories in a docking area based on GNSS, characterized in that: GNSS stations A and B are installed along the central axis of the ship to be docked, with A at the middle of the ship and B at the stern of the ship. The distance from the bow O to the middle A is denoted as L. The method comprises the following steps: Step 1: Use the GNSS device to continuously record the position time series of A and B during the ship's travel (X A , Y A ) and (X B , Y B ); Step 2: Take the position data of point B at the current time point and two time points before the fixed time interval Δt in the position time series, and calculate the velocity V of point B B , the spin speed R of point B B and the relative spin speed R at point A A ; Step 3: Predict the position of the ship after the future time Δt′, including the position of point B (X B est,Y B est), point A position (X A est,Y A est) and the ship's head position (X O est,Y O est); Step 4: The ship position after the predicted time point Δt′, i.e. the position of point A (X A est,Y A est) and point B position (X B est,Y B est) is set as the current position; repeat the above steps 1 to 3 to predict the position of the ship at point A and point B after a certain time interval of Δt′; Step 5: The predicted positions of N Δt′, including the position A in the middle of the ship and the position O at the head of the ship, are combined to form a ship predicted position sequence, i.e., a trajectory prediction line.
2. The method for predicting the trajectory of a ship route in a docking area based on GNSS according to claim 1, characterized in that: In step 2, Among them, (X B Now, Y B now) represents the position coordinates of point B at the current time point, (X B last,Y B last) represents the position coordinates of point B at a fixed time interval Δt ago.
3. The method for predicting the trajectory of a ship route in a docking area based on GNSS according to claim 1, characterized in that: In step 2, R B =(Arc tan((Y B now-Y B last) / (X B now-X B last))-Arc tan((Y A last-Y B last) / (X A last-X B last))) / Δt; Among them, (X B Now, Y B now) represents the position coordinates of point B at the current time point, (X B last,Y B last) represents the position coordinates of point B at a fixed time interval Δt ago.
4. The method for predicting the trajectory of a ship route in a docking area based on GNSS according to claim 1, characterized in that: In step 2, R A =(Arc tan((Y A now-Y B now) / (X A now-X B now))-Arc tan((Y A last-Y B last) / (X A last-X B last))) / Δt; Among them, (X B Now, Y B now) represents the position coordinates of point B at the current time point, (X B last,Y B last) represents the position coordinates of point B at a fixed time interval Δt ago.
5. The method for predicting the trajectory of a ship route in a docking area based on GNSS according to claim 1, characterized in that: In step 3, X B est=X B now+V B *Δt′*cos(arctan((Y A now-Y B now) / (X A now-X B now))+W ton *R B *Δt′) Y B est = Y B now + V B *Δt′*sin(arctan((Y A now - Y B now) / (X A now - X B now)) + W ton *R B *Δt′) where W ton = W1, when the tonnage ton ∈ [0, 1], W ton =W2, when tonnage ton∈(1,10], W ton =W3, when tonnage ton∈(10,100], W ton =W4, when tonnage ton∈(100,1000], W ton =W5, when tonnage ton∈(1000,10000]; W1, W2, W3, W4, and W5 are preset values.
6. The method for predicting the ship route trajectory in the dock area based on GNSS according to claim 1, characterized in that: In step 3, X A est=X B now+|AB|*cos(arctan((Y A now-Y B now) / (X A now-X B now))+R A *Δt′); Y A est=Y B now+|AB|*sin(arctan((Y A now-Y B now) / (X A now-X B now))+R A *Δt′); Among them, (X B Now, Y B now) represents the position coordinates of point B at the current time point, (X A Now, Y A now) represents the position coordinates of point A at the current time point; |AB| is the distance between points AB, which is a fixed value.
7. The method for predicting the trajectory of a ship route in a docking area based on GNSS according to claim 1, characterized in that: In step 3, X O est=X A now+L*cos(arc tan((Y A now-Y B now) / (X A now-X B now))); Y O est=Y A now+L*sin(arc tan((Y A now-Y B now) / (X A now-X B now))); Among them, (X B Now, Y B now) represents the position coordinates of point B at the current time point, (X A Now, Y A now) represents the position coordinates of point A at the current time.
8. A GNSS-based ship route trajectory prediction system in a docking area, characterized by: GNSS stations A and B are installed along the central axis of the ship to be docked, with A at the middle of the ship and B at the stern of the ship. The distance from the bow O to the middle A is denoted as L. The system includes the following modules: Module 1 is used to use the GNSS device to continuously record the position time series (X) of A and B during the ship's travel. A , Y A ) and (X B , Y B ); Module 2 is used to obtain the position data of point B at the current time point and two time points before the fixed time interval Δt in the position time series, and calculate the velocity V of point B B , the spin speed R of point B B and the relative spin speed R at point A A ; Module 3 is used to predict the position of the ship after the future time Δt′, including the position of point B (X B est,Y B est), point A position (X A est,Y A est) and the ship's head position (X O est,Y O est); Module 4 is used to predict the position of the ship after the predicted time point Δt′, that is, the position of point A (X A est,Y A est) and point B position (X B est,Y B est) is set as the current position; repeat the above modules 1 to 3 to predict the position of the ship at point A and point B after a certain time interval of Δt′; Module 5 is used to form a ship predicted position sequence, i.e., a trajectory prediction line, by combining the predicted positions of N Δt′, including the ship middle position A and the ship bow position O.
9. A GNSS-based ship route trajectory prediction device in a docking area, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the GNSS-based dock area ship route trajectory prediction method as described in any one of claims 1 to 7.
