A ship maneuvering optimization method and system based on machine learning

Abstract

The present invention discloses a ship maneuvering optimization method and system based on machine learning, the method comprising: obtaining historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information comprises: environmental wind speed, environmental wave height and water flow speed, and the historical ship information comprises: the horizontal coordinate of the ship, the vertical coordinate of the ship, the ship speed, the ship acceleration, the heading angle of the ship and the turning rate of the ship; setting a ship maneuvering score model, inputting the historical environmental information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculating the ship maneuvering score under the historical environmental information; under the historical environmental information, using the historical ship information corresponding to the highest ship maneuvering score as the ship maneuvering strategy to complete the optimization of ship maneuvering.

Description

Technical Field

[0001] The present invention belongs to the technical field of ship maneuvering optimization, and more specifically, relates to a ship maneuvering optimization method and system based on machine learning. Background Art

[0002] Ship maneuvering optimization refers to improving the maneuverability and efficiency of ships through technical means and strategies. This includes improving ship maneuverability, reducing energy consumption, improving safety and reducing environmental impact.

[0003] Here are some possible methods and techniques for optimizing ship maneuvering:

[0004] Steering and thruster control optimization: By improving the control systems of steering and thrusters, the maneuverability and agility of the vessel can be improved. This can include the use of advanced automation technology, precise control of steering gear angle and thruster power, and optimization of control algorithms.

[0005] Ship Path Planning: Using ship path planning algorithms, the ship's path can be optimized to achieve objectives such as the best route, shortest time or lowest fuel consumption. This can take into account factors such as ocean currents, wind speed, ship characteristics and environmental requirements.

[0006] Ship stability optimization: By improving the ship's stability design and control systems, the maneuverability and safety of the ship can be improved. This may include improving the hull design, installing automatic stability control systems, optimizing ballast and cargo distribution, etc.

[0007] Ship power system optimization: By improving the ship's power system, the ship's maneuverability and energy efficiency can be improved. This includes using more efficient engines and propellers, optimizing the transmission system, reducing resistance, and improving the interaction between the hull and the water flow.

[0008] Data analysis and predictive models: Utilizing ship sensors and data acquisition systems, combined with data analysis and predictive models, real-time monitoring of ship maneuvers, fault diagnosis and prediction, and decision support for performance optimization can be achieved.

[0009] Human-machine interface improvement: Improve the human-machine interface of the ship's operating system to make it easier for crew members to understand and control the ship's status and operations. This can include improving the design of display and control devices, adding intelligent assistance functions, and providing training and training tools.

[0010] Nautical Training and Skills Upgrading: Provide high-quality marine training and skills upgrading opportunities for crew members, enabling them to better master ship handling techniques and best practices.

[0011] However, there is no technical solution in the prior art that can automatically optimize ship maneuvers based on current environmental information. Summary of the invention

[0012] In order to solve the above technical problems, the present invention proposes a ship maneuvering optimization method based on machine learning, comprising:

[0013] Acquire historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the abscissa of the ship, the ordinate of the ship, the ship speed, the ship acceleration, the heading angle of the ship and the turning rate of the ship;

[0014] Setting a ship maneuvering score model, inputting the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculating the ship maneuvering score under the historical environment information;

[0015] Under the historical environmental information, the historical ship information corresponding to the highest ship maneuvering score is used as a ship maneuvering strategy to optimize the ship maneuvering.

[0016] Furthermore, the ship maneuvering score model is:

[0017] score=f(g(x,y,v,a,θ,ω),h(wv,wh,fw))

[0018] Among them, score is the ship maneuvering score, x is the horizontal coordinate of the ship, y is the vertical coordinate of the ship, v is the ship speed, α is the ship acceleration, θ is the ship's heading angle, ω is the ship's turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow speed, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wh, fw) is the mapping function of the intermediate feature space of environmental information.

[0019] Furthermore, the intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is:

[0020]

[0021] Furthermore, the environmental information intermediate feature space mapping function h(wv, wh, fw) is:

[0022]

[0023] Furthermore, the ship maneuvering score model is specifically:

[0024] score = sigmoid(w1 *g(x,y,v,a,θ,ω)+w 2 *h(wv,wh,fw)+b)

[0025] Among them, w 1 and w 2 is a weight matrix used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model.

[0026] The present invention also proposes a ship maneuvering optimization system based on machine learning, comprising:

[0027] A data acquisition module is used to acquire historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the horizontal coordinate of the ship, the vertical coordinate of the ship, the ship speed, the ship acceleration, the ship heading angle and the ship turning rate;

[0028] A model setting module is used to set a ship maneuvering score model, input the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculate the ship maneuvering score under the historical environment information;

[0029] The optimization module is used to use the historical ship information corresponding to the highest ship maneuvering score as a ship maneuvering strategy under the historical environmental information to optimize the ship maneuvering.

[0030] Furthermore, the ship maneuvering score model is:

[0031] score=f(g(x,y,v,a,θ,ω),h(wv,wh,fw))

[0032] Among them, score is the ship maneuvering score, x is the horizontal coordinate of the ship, y is the vertical coordinate of the ship, v is the ship speed, a is the ship acceleration, θ is the ship's heading angle, ω is the ship's turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow velocity, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wh, fw) is the mapping function of the intermediate feature space of environmental information.

[0033] Furthermore, the intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is:

[0034]

[0035] Furthermore, the environmental information intermediate feature space mapping function h(wv, wh, fw) is:

[0036]

[0037] Furthermore, the ship maneuvering score model is specifically:

[0038] score = sigmoid(w 1 *g(x,y,v,a,θ,ω)+w 2 *h(wv,wh,fw)+b)

[0039] Among them, w 1 and w 2 is a weight matrix used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model.

[0040] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:

[0041] The present invention obtains historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the horizontal coordinate of the ship, the vertical coordinate of the ship, the ship speed, the ship acceleration, the ship's heading angle and the ship's turning rate; sets a ship maneuvering score model, inputs the historical environmental information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculates the ship maneuvering score under the historical environmental information; under the historical environmental information, the historical ship information corresponding to the highest ship maneuvering score is used as a ship maneuvering strategy to complete the optimization of ship maneuvering. Through the above technical scheme, the present invention can give the maneuvering strategy with the highest score according to the historical environmental information and the historical ship information corresponding thereto, and through the ship maneuvering score model, thereby completing the optimization of ship maneuvering. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0043] Figure 2 It is a structural diagram of the system of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0044] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0045] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0046] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0047] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0048] The display screen is used to display the user interface of each application.

[0049] All subscripts in the formulas of the present invention are only used to distinguish parameters and have no actual meaning.

[0050] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0051] Example 1

[0052] like Figure 1 As shown, an embodiment of the present invention provides a ship maneuvering optimization method based on machine learning, comprising:

[0053] Step 101, obtaining historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the abscissa of the ship, the ordinate of the ship, the ship speed, the ship acceleration, the heading angle of the ship and the turning rate of the ship;

[0054] Step 102, setting a ship maneuvering score model, inputting the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculating the ship maneuvering score under the historical environment information;

[0055] Specifically, the ship maneuvering score model is:

[0056] score=f(g(x,y,v,a,θ,ω),h(wv,wh,fw))

[0057] Among them, score is the ship maneuvering score, x is the horizontal coordinate of the ship, y is the vertical coordinate of the ship, v is the ship speed, a is the ship acceleration, θ is the ship's heading angle, ω is the ship's turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow velocity, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wh, fw) is the mapping function of the intermediate feature space of environmental information.

[0058] Specifically, the intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is:

[0059]

[0060] Specifically, the environmental information intermediate feature space mapping function h(wv, wh, fw) is:

[0061]

[0062] Specifically, the ship maneuvering score model is as follows:

[0063] score = sigmoid(w 1 *g(x,y,v,a,θ,ω)+w 2 *h(wv,wh,fw)+b)

[0064] Among them, w 1 and w 2 is a weight matrix used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model.

[0065] Step 103, under the historical environment information, using the historical ship information corresponding to the highest ship maneuvering score as a ship maneuvering strategy to optimize the ship maneuvering.

[0066] Example 2

[0067] like Figure 2 As shown, an embodiment of the present invention further provides a ship maneuvering optimization system based on machine learning, comprising:

[0068] A data acquisition module is used to acquire historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the horizontal coordinate of the ship, the vertical coordinate of the ship, the ship speed, the ship acceleration, the ship heading angle and the ship turning rate;

[0069] A model setting module is used to set a ship maneuvering score model, input the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculate the ship maneuvering score under the historical environment information;

[0070] Specifically, the ship maneuvering score model is:

[0071] score=f(g(x,y,v,a,θ,ω),h(wv,wh,fw))

[0072] Among them, score is the ship maneuvering score, x is the horizontal coordinate of the ship, y is the vertical coordinate of the ship, v is the ship speed, a is the ship acceleration, θ is the ship's heading angle, ω is the ship's turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow speed, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wh, fw) is the mapping function of the intermediate feature space of environmental information.

[0073] Specifically, the intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is:

[0074]

[0075] Specifically, the environmental information intermediate feature space mapping function h(wv, wh, fw) is:

[0076]

[0077] Specifically, the ship maneuvering score model is as follows:

[0078] score = sigmoid(w 1 *g(x,y,v,a,θ,ω)+w 2 *h(wv,wh,fw)+b)

[0079] Among them, w 1 and w 2 is a weight matrix used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model.

[0080] The optimization module is used to use the historical ship information corresponding to the highest ship maneuvering score as a ship maneuvering strategy under the historical environmental information to optimize the ship maneuvering.

[0081] Example 3

[0082] An embodiment of the present invention further proposes a storage medium storing a plurality of instructions, wherein the instructions are used to implement the ship maneuvering optimization method based on machine learning.

[0083] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0084] Optionally, in this embodiment, the storage medium is configured to store a program code for executing the following steps: Step 101, obtaining historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the horizontal coordinate of the ship, the vertical coordinate of the ship, the ship speed, the ship acceleration, the ship heading angle and the ship turning rate;

[0085] Step 102, setting a ship maneuvering score model, inputting the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculating the ship maneuvering score under the historical environment information;

[0086] Specifically, the ship maneuvering score model is:

[0087] score=f(g(x,y,v,a,θ,ω),h(wv,wh,fw))

[0088] Among them, score is the ship maneuvering score, x is the horizontal coordinate of the ship, y is the vertical coordinate of the ship, v is the ship speed, a is the ship acceleration, θ is the ship's heading angle, ω is the ship's turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow velocity, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wg, fw) is the mapping function of the intermediate feature space of environmental information.

[0089] Specifically, the intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is:

[0090]

[0091] Specifically, the environmental information intermediate feature space mapping function h(wv, wh, fw) is:

[0092]

[0093] Specifically, the ship maneuvering score model is as follows:

[0094] score = sigmoid(w 1*g(x,y,v,a,θ,ω)+w 2 *h(wv,wh,fw)+b)

[0095] Among them, w 1 and w 2 is a weight matrix used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model.

[0096] Step 103, under the historical environment information, using the historical ship information corresponding to the highest ship maneuvering score as a ship maneuvering strategy to optimize the ship maneuvering.

[0097] Example 4

[0098] An embodiment of the present invention also proposes an electronic device, comprising a processor and a storage medium connected to the processor, wherein the storage medium stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the ship maneuvering optimization method based on machine learning.

[0099] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.

[0100] Among them, the storage medium can be used to store software programs and modules, such as a ship maneuvering optimization method based on machine learning in an embodiment of the present invention, and corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned ship maneuvering optimization method based on machine learning. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0101] The processor may call the information and application program stored in the storage medium through the transmission system to execute the following steps: Step 101, obtaining historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the horizontal coordinate of the ship, the vertical coordinate of the ship, the ship speed, the ship acceleration, the ship heading angle and the ship turning rate;

[0102] Step 102, setting a ship maneuvering score model, inputting the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculating the ship maneuvering score under the historical environment information;

[0103] Specifically, the ship maneuvering score model is:

[0104] score=f(g(x,y,v,a,θ,ω),h(wv,wh,fw))

[0105] Among them, score is the ship maneuvering score, x is the horizontal coordinate of the ship, t is the vertical coordinate of the ship, v is the ship speed, a is the ship acceleration, θ is the ship's heading angle, ω is the ship's turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow velocity, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wh, fw) is the mapping function of the intermediate feature space of environmental information.

[0106] Specifically, the intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is:

[0107]

[0108] Specifically, the environmental information intermediate feature space mapping function h(wv, wh, fw) is:

[0109]

[0110] Specifically, the ship maneuvering score model is as follows:

[0111] score = sigmoid(w 1 *g(x,y,v,a,θ,ω)+w 2 *h(wv,wh,fw)+b)

[0112] Among them, w 1 and w 2 is a weight matrix used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model.

[0113] Step 103, under the historical environment information, using the historical ship information corresponding to the highest ship maneuvering score as a ship maneuvering strategy to optimize the ship maneuvering.

[0114] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0115] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0120] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A ship maneuvering optimization method based on machine learning, characterized in that: include: Acquire historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the abscissa of the ship, the ordinate of the ship, the ship speed, the ship acceleration, the heading angle of the ship and the turning rate of the ship; Setting a ship maneuvering score model, inputting the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculating the ship maneuvering score under the historical environment information; The ship maneuvering score model is: Score=f(g(x,y,v,a,θ,ω),h(wv,wh,fw)) Wherein, score is the ship maneuvering score, x is the horizontal coordinate of the ship, y is the vertical coordinate of the ship, v is the ship speed, a is the ship acceleration, θ is the ship heading angle, ω is the ship turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow speed, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wh, fw) is the mapping function of the intermediate feature space of environmental information; The intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is: The environmental information intermediate feature space mapping function h(wv, wh, fw) is: The ship maneuvering score model is specifically: score=sigmoid(w1*g(x,y,v,a,θ,ω)+w2*h(wv,wh,fw)+b) Wherein, w1 and w2 are weight matrices used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model; Under the historical environmental information, the historical ship information corresponding to the highest ship maneuvering score is used as a ship maneuvering strategy to optimize the ship maneuvering.

2. A ship maneuvering optimization system based on machine learning, characterized in that: include: A data acquisition module is used to acquire historical environmental information of historical ships and historical ship information corresponding thereto, wherein the historical environmental information includes: environmental wind speed, environmental wave height and water flow speed, and the historical ship information includes: the horizontal coordinate of the ship, the vertical coordinate of the ship, the ship speed, the ship acceleration, the ship heading angle and the ship turning rate; A model setting module is used to set a ship maneuvering score model, input the historical environment information and the historical ship information corresponding thereto into the ship maneuvering score model, and calculate the ship maneuvering score under the historical environment information; The ship maneuvering score model is: SCore=f(g(x,y,v,a,θ,ω),h(wv,wh,fw)) Wherein, score is the ship maneuvering score, x is the horizontal coordinate of the ship, y is the vertical coordinate of the ship, v is the ship speed, a is the ship acceleration, θ is the ship heading angle, ω is the ship turning rate, wv is the ambient wind speed, wh is the ambient wave height, fw is the water flow speed, g(x, y, v, a, θ, ω) is the mapping function of the intermediate feature space of ship information, and h(wv, wh, fw) is the mapping function of the intermediate feature space of environmental information; The intermediate feature space mapping function g(x, y, v, a, θ, ω) of the ship information is: The environmental information intermediate feature space mapping function h(wv, wh, fw) is: The ship maneuvering score model is specifically: score=sigmoid(w1*g(x,y,v,a,θ,ω)+w2*h(wv,wh,fw)+b) Wherein, w1 and w2 are weight matrices used to adjust the importance of the intermediate feature space, and b is a bias term used to balance the output of the ship maneuvering score model; The optimization module is used to use the historical ship information corresponding to the highest ship maneuvering score as a ship maneuvering strategy under the historical environmental information to optimize the ship maneuvering.

Images