Unmanned ship control method and system based on real-time environmental parameters

Abstract

The invention discloses an unmanned ship control method and system based on real-time environmental parameters. The method comprises the following steps: acquiring real-time paddle parameters and real-time environmental parameters of a target unmanned ship; inputting the real-time paddle parameters and the real-time environment parameters of the target unmanned ship into a ship power regulation and control model, so that the ship power regulation and control model generates a real-time environment parameter vector matrix according to the real-time environment parameters, and generates a weight vector matrix of the real-time power of the target unmanned ship according to the real-time paddle parameters, adjusting the weight vector matrix of the real-time power of the target unmanned ship according to the real-time environment parameter vector matrix to obtain an adjusted vector matrix of the power of the target unmanned ship, and outputting a corrected power value of each paddle of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; and regulating and controlling the power of each paddle of the unmanned ship according to the corrected power value of each paddle of the target unmanned ship. According to the invention, the unmanned ship can flexibly adapt to the changeable marine environment, and the practicability and application range of the unmanned ship are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned ship control, and in particular to an unmanned ship control method and system based on real-time environmental parameters. Background Art

[0002] The control of unmanned ships in complex marine environments requires consideration of multiple factors, such as ship dynamics limitations, ship kinematic limitations, channel navigation conditions, and meteorological and sea conditions. When an unmanned ship is sailing at sea, its heading and propeller power are mainly affected by natural environmental parameters such as wind, waves, and ocean currents. For example, when an unmanned ship is sailing, strong winds will affect the speed and heading of the unmanned ship, causing the unmanned ship to drift and deflect. From the above examples, it can be seen that real-time control of unmanned ships based on environmental parameters is of great significance to the development of unmanned ship navigation technology.

[0003] The existing unmanned ship control is mainly based on the weather conditions of the meteorological forecast, and the control logic of the unmanned ship during navigation is planned before sailing. However, the marine environment has a large mutation in the actual process, and the single control logic of the existing unmanned ship cannot adapt to the mutation of the marine environment, and cannot adjust the unmanned ship in real time according to the changing environmental parameters. Summary of the invention

[0004] The embodiments of the present invention provide an unmanned ship control method and system based on real-time environmental parameters, which can enable the unmanned ship to adjust the power value of each propeller according to real-time data, flexibly respond to the changing environment at sea, and improve the practicality and applicability of the unmanned ship.

[0005] An embodiment of the present invention provides an unmanned ship control method based on real-time environmental parameters, comprising: Acquire the real-time propeller parameters and real-time environmental parameters of the target unmanned ship; wherein the target unmanned ship is a multi-propeller unmanned ship, and the propeller parameters include: the number of operating propellers, the real-time power value of each propeller, the upper limit of the power of each propeller, and the power constraint relationship between each propeller; the real-time environmental parameters include: wind volume, wind direction, wave height, and ocean current intensity; The real-time propeller parameters and real-time environmental parameters of the target unmanned ship are input into the ship power control model, so that the ship power control model generates a real-time environmental parameter vector matrix according to the real-time environmental parameters, generates a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters, adjusts the weight vector matrix of the real-time power of the target unmanned ship with the real-time environmental parameter vector matrix, obtains an adjusted vector matrix of the power of the target unmanned ship, and outputs a corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; The power of each propeller of the target unmanned ship is regulated by the corrected power value of each propeller of the target unmanned ship.

[0006] Furthermore, the construction of the ship power control model includes: Obtaining a number of environmental parameter samples and a number of paddle parameter samples; Combining each environmental parameter sample and each propeller parameter sample in pairs to obtain a number of data to be simulated; Perform simulation based on each to-be-simulated data to obtain a corrected power value of each propeller under the simulation corresponding to each to-be-simulated data; Generate a number of training samples according to each to-be-simulated data and the corrected power value of each propeller under the simulation corresponding to each to-be-simulated data; An initial ship power control model is constructed, with the data to be simulated as input and the corrected power value of each propeller under the simulation corresponding to the data to be simulated as output, and the initial ship power control model is iteratively trained until the initial ship power control model reaches a preset convergence condition, thereby generating the ship power control model.

[0007] Furthermore, the step of generating a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters includes: The initial weight vector matrix of the real-time power of the target unmanned ship is constructed according to the number of operating propellers, the real-time power value of each propeller and the upper limit of the power of each propeller; For each propeller of the target unmanned ship, three propellers with the strongest power constraint relationship with the current propeller are selected according to the power constraint relationship between the propellers; Generate a constraint triangle of the current oar power according to the eigenvector of the oar real-time power value corresponding to the current oar and the eigenvectors of the oar real-time power values ​​corresponding to the three selected oars; The initial weights of the initial weight vector matrix are adjusted according to the constraint triangles of each propeller power to obtain the weight vector matrix of the real-time power of the target unmanned ship.

[0008] Further, generating a real-time environment parameter vector matrix according to the real-time environment parameter includes: Generate wind volume vector, wind direction vector, wave height vector and ocean current intensity vector according to wind volume, wind direction, wave height and ocean current intensity respectively; The wind volume vector and wind direction vector are integrated to obtain the wind factor influence vector; A real-time environmental parameter vector matrix is ​​generated according to the wave height vector, the ocean current intensity vector and the wind factor influence vector.

[0009] Furthermore, the weight vector matrix of the target unmanned ship's real-time power is adjusted by using the real-time environmental parameter vector matrix to obtain the adjusted vector matrix of the target unmanned ship's power, including: The weight vector matrix of the real-time power of the target unmanned ship is adjusted by the wind factor influence vector, the wave height vector and the ocean current intensity vector respectively to obtain a first adjustment result, a second adjustment result and a third adjustment result; The weight vector matrix of the real-time power of the target unmanned ship is adjusted by using the wind factor influence vector, the wave height vector, and the ocean current intensity vector to obtain a fourth adjustment result; A spatial rectangular coordinate system is established based on the real-time environmental parameter vector matrix, with the wind factor influence vector, wave height vector and ocean current intensity vector as the horizontal axis, vertical axis and vertical axis respectively; Respectively projecting the first adjustment result, the second adjustment result, and the third adjustment result onto a first coordinate plane formed by the longitudinal axis and the vertical axis, onto a second coordinate plane formed by the transverse axis and the vertical axis, and onto a third coordinate plane formed by the transverse axis and the longitudinal axis, to obtain a first projection of a weight vector matrix of the real-time power of the target unmanned ship on the first coordinate plane, a second projection on the second coordinate plane, and a third projection on the third coordinate plane; The first projection, the second projection and the third projection are superimposed to obtain a superimposed projection, and the superimposed projection is converted into a superimposed projection vector, and the fourth adjustment result is adjusted with the superimposed projection vector to obtain an adjusted vector matrix of the target unmanned ship power.

[0010] Furthermore, the outputting of the corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the target unmanned ship power includes: Determine the initial corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; For each propeller of the target unmanned ship, three propellers with the strongest power constraint relationship with the current propeller are selected according to the power constraint relationship between the propellers; Generate a constraint triangle of the current oar correction power value according to the characteristic vector of the initial correction power value of the oar corresponding to the current oar and the characteristic vectors of the initial correction power values ​​of the oar corresponding to the three selected oars; Compare the constraint triangle of the current propeller correction power value with the constraint triangle of the current propeller power; If the deviation of any angle between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power is greater than a preset threshold, adjust the initial correction power value of the paddle corresponding to the angle greater than the preset threshold and regenerate the constraint triangle of the current paddle correction power value, until the deviations of each angle between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power are no greater than the preset threshold, and use the initial correction power value of the paddle corresponding to the current paddle as the correction power value of the current paddle; If the angle deviations between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power are not greater than the preset threshold; the initial paddle correction power value corresponding to the current paddle is used as the correction power value of the current paddle.

[0011] Furthermore, the step of comparing the constraint triangle of the current propeller correction power value with the constraint triangle of the current propeller power includes: Obtaining a first centroid of a constraint triangle of a current paddle correction power value and a second centroid of a constraint triangle of the current paddle power, and aligning the constraint triangle of the current paddle correction power value with the constraint triangle of the current paddle power based on the first centroid and the second centroid; Taking the first centroid as the fixed point, the constraint triangle of the current paddle correction power value is adjusted by scaling and aligning, so that the constraint triangle of the adjusted current paddle correction power value is completely wrapped by the constraint triangle of the current paddle power; The constraint triangle of the adjusted current propeller correction power value is compared with the angles of the constraint triangle of the current propeller power.

[0012] Based on the above method embodiment, the present invention provides a corresponding system embodiment; An embodiment of the present invention provides an unmanned ship control system based on real-time environmental parameters, including: a parameter acquisition module, a power value output module and a control module; The parameter acquisition module is used to acquire the real-time propeller parameters and real-time environmental parameters of the target unmanned ship; wherein the target unmanned ship is a multi-propeller unmanned ship, and the propeller parameters include: the number of operating propellers, the real-time power value of each propeller, the power upper limit of each propeller, and the power constraint relationship between each propeller; the real-time environmental parameters include: wind volume, wind direction, wave height, and ocean current intensity; The power value output module is used to input the real-time propeller parameters and real-time environmental parameters of the target unmanned ship into the ship power control model, so that the ship power control model generates a real-time environmental parameter vector matrix according to the real-time environmental parameters, generates a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters, adjusts the weight vector matrix of the real-time power of the target unmanned ship with the real-time environmental parameter vector matrix, obtains the adjusted vector matrix of the power of the target unmanned ship, and outputs the corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; The control module is used to control the power of each propeller of the unmanned ship according to the corrected power value of each propeller of the target unmanned ship.

[0013] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the unmanned ship control method based on real-time environmental parameters described in the above-mentioned embodiment of the invention.

[0014] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the unmanned ship control method based on real-time environmental parameters described in the above-mentioned invention embodiment.

[0015] The following beneficial effects are achieved by implementing the present invention: The present invention provides an unmanned ship control method and system based on real-time environmental parameters. The unmanned ship control method obtains the real-time propeller parameters and real-time environmental parameters of the target unmanned ship, and then inputs the real-time propeller parameters and real-time environmental parameters of the target unmanned ship into the ship power control model, so that the ship power control model outputs the corrected power value of each propeller of the target unmanned ship according to the real-time environmental parameters and the real-time propeller parameters. After obtaining the corrected power value of each propeller of the target unmanned ship by combining the real-time propeller parameters with the real-time environmental parameters, the power of each propeller of the unmanned ship is regulated by the corrected power value of each propeller of the target unmanned ship, so that the unmanned ship can adjust the power value of each propeller according to the real-time data, flexibly respond to the changing environment at sea, and improve the practicality and applicability of the unmanned ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of an unmanned ship control method based on real-time environmental parameters provided by an embodiment of the present invention.

[0017] Figure 2 It is a structural schematic diagram of an unmanned ship control system based on real-time environmental parameters provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. Unless otherwise defined, all technical and scientific terms used in this article have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in this article are only for the purpose of describing specific embodiments, not intended to limit the present application; the terms "including" and "having" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusion. In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined. The reference to "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appearing in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of the associated objects, indicating that three relationships may exist, such as A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two), and similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces). In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0020] like Figure 1 As shown, an unmanned ship control method based on real-time environmental parameters is provided in one embodiment of the present invention, comprising: Step S1: obtaining real-time propeller parameters and real-time environmental parameters of the target unmanned ship; wherein the target unmanned ship is a multi-propeller unmanned ship, the propeller parameters include: the number of operating propellers, the real-time power value of each propeller, the upper limit of the power of each propeller, and the power constraint relationship between each propeller; the real-time environmental parameters include: wind volume, wind direction, wave height and ocean current intensity; Step S2: input the real-time propeller parameters and real-time environmental parameters of the target unmanned ship into the ship power control model, so that the ship power control model generates a real-time environmental parameter vector matrix according to the real-time environmental parameters, generates a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters, adjusts the weight vector matrix of the real-time power of the target unmanned ship with the real-time environmental parameter vector matrix, obtains an adjusted vector matrix of the power of the target unmanned ship, and outputs a corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; Step S3: regulating the power of each propeller of the target unmanned ship according to the corrected power value of each propeller of the target unmanned ship.

[0021] For step S1, the real-time propeller parameters and real-time environmental parameters of the target unmanned ship are obtained. The real-time propeller parameters include the number of propellers in operation of the target unmanned ship, the real-time power value of each propeller, the upper limit of the power of each propeller, and the power constraint relationship between each propeller. Among them, the upper limit of the power of each propeller is used to limit the maximum value of the power value of each propeller, and the lower limit of the power of each propeller is taken as 0 in the present invention. The power constraint relationship between each propeller refers to the power value of each propeller in the target unmanned ship must satisfy the mutual constraint relationship, so that the overall power or driving direction of the target unmanned ship is coordinated. Real-time environmental parameters include: wind volume, wind direction, wave height and ocean current intensity. In addition, in the present invention, the environment mainly refers to the marine environment.

[0022] In step S2, the real-time propeller parameters and real-time environmental parameters of the target unmanned ship are input into the ship power control model. After receiving the real-time propeller parameters and real-time environmental parameters, the ship power control model first normalizes the real-time propagation parameters and real-time environmental parameters. After the normalization is completed, a real-time environmental parameter vector matrix is ​​generated according to the real-time environmental parameters.

[0023] In a preferred embodiment, the real-time environmental parameter vector matrix is ​​generated according to the real-time environmental parameters, including: generating a wind volume vector, a wind direction vector, a wave height vector and an ocean current intensity vector according to wind volume, wind direction, wave height and ocean current intensity, respectively; fusing the wind volume vector and the wind direction vector to obtain a wind factor influence vector; generating a real-time environmental parameter vector matrix according to the wave height vector, the ocean current intensity vector and the wind factor influence vector.

[0024] Specifically, a wind volume vector is generated according to wind volume, a wind direction vector is generated according to wind direction, a wave height vector is generated according to wave height, and an ocean current intensity vector is generated according to ocean current intensity. Since both the wind volume vector and the wind direction vector are influence vectors generated by wind factors, the wind volume vector and the wind direction vector can be fused to obtain a wind factor influence vector to reduce the complexity of subsequent calculations. A real-time environmental parameter vector matrix is ​​generated according to the wave height vector, the ocean current intensity vector, and the wind factor influence vector.

[0025] Furthermore, a weight vector matrix of the real-time power of the target unmanned ship is generated according to the real-time propeller parameters.

[0026] In a preferred embodiment, the method of generating a weight vector matrix of the real-time power of the target unmanned ship based on the real-time propeller parameters includes: constructing an initial weight vector matrix of the real-time power of the target unmanned ship based on the number of running propellers, the real-time power value of each propeller and the upper limit of the power of each propeller; for each propeller of the target unmanned ship, selecting three propellers with the strongest power constraint relationship with the current propeller based on the power constraint relationship between the propellers; generating a constraint triangle of the current propeller power based on the eigenvector of the real-time power value of the propeller corresponding to the current propeller and the eigenvectors of the real-time power values ​​of the propeller corresponding to the selected three propellers; adjusting the initial weights of the initial weight vector matrix based on the constraint triangles of each propeller power to obtain the weight vector matrix of the real-time power of the target unmanned ship.

[0027] Specifically, after determining the number of operating oars, the real-time power value of each oar and the upper limit of the power of each oar are converted into vector representations to obtain the real-time power value vector of each oar and the upper limit vector of the power of each oar, and then the initial weight vector matrix of the real-time power of the target unmanned ship is constructed through the real-time power value vector of each oar and the upper limit vector of each oar. Further, the power constraint relationship between each oar is obtained. It should be noted that if all the oars of the target unmanned ship are exactly the same, the power constraint relationship between each oar can be determined only based on the shortest distance between each oar. The shorter the straight-line distance, the stronger the constraint relationship. If the oars of the target unmanned ship are not all exactly the same, in addition to considering the straight-line distance, it is also necessary to combine the importance of each oar, the main power oar, the secondary power oar and the spare oar to determine it comprehensively.

[0028] Next, it is necessary to construct the constraint triangle of each oar power based on the power constraint relationship between each oar. Specifically, for each oar, select the three oars with the strongest power constraint relationship with the current oar from the power constraint relationship between each oar. Obtain the real-time power value of the current oar and the real-time power values ​​of the three selected oars, convert the real-time power value of the current oar into a feature vector representation, and convert the real-time power values ​​of the three selected oars into a feature vector representation. After the conversion is completed, four feature vectors are obtained. By translating these four feature vectors, the four feature vectors are made to intersect without changing their own vector characteristics, and the constraint triangle of the current oar power is constructed. The constraint triangle of the current oar power generated can be used as a constraint when the current oar power value is adjusted. After completing the construction of the constraint triangle of each propeller power, the initial weights of the initial weight vector matrix are adjusted according to the constraint triangle of each propeller power. For each propeller power constraint triangle, the weights of the eigenvectors of the propeller real-time power values ​​of each propeller associated with the current propeller power constraint triangle are adjusted through the ratio between the eigenvectors of the propeller power constraint triangle. When the eigenvector of the same propeller real-time power value is affected by multiple weights, after fusing the influencing weights, the overall weight of the weight vector matrix is ​​adjusted to finally obtain the weight vector matrix of the real-time power of the target unmanned ship.

[0029] Furthermore, the weight vector matrix of the target unmanned ship's real-time power is adjusted using the real-time environmental parameter vector matrix to obtain an adjusted vector matrix of the target unmanned ship's power.

[0030] In a preferred embodiment, the method of adjusting the weight vector matrix of the real-time power of the target unmanned ship with the real-time environmental parameter vector matrix to obtain the adjusted vector matrix of the target unmanned ship power includes: adjusting the weight vector matrix of the real-time power of the target unmanned ship with the wind factor influence vector, the wave height vector and the ocean current intensity vector respectively to obtain a first adjustment result, a second adjustment result and a third adjustment result; adjusting the weight vector matrix of the real-time power of the target unmanned ship with the wind factor influence vector, the wave height vector and the ocean current intensity vector to obtain a fourth adjustment result; A spatial rectangular coordinate system is established based on the real-time environmental parameter vector matrix, with the wind factor influence vector, wave height vector and ocean current intensity vector as the horizontal axis, vertical axis and vertical axis respectively; the first adjustment result, the second adjustment result and the third adjustment result are projected on a first coordinate plane formed by the vertical axis and the vertical axis, on a second coordinate plane formed by the horizontal axis and the vertical axis, and on a third coordinate plane formed by the horizontal axis and the vertical axis respectively, to obtain a first projection of the weight vector matrix of the real-time power of the target unmanned ship on the first coordinate plane, a second projection on the second coordinate plane, and a third projection on the third coordinate plane; the first projection, the second projection and the third projection are superimposed to obtain a superimposed projection, and the superimposed projection is converted into a superimposed projection vector, and the fourth adjustment result is adjusted with the superimposed projection vector to obtain an adjusted vector matrix of the power of the target unmanned ship.

[0031] Specifically, the weight vector matrix of the real-time power of the target unmanned ship is adjusted with a single factor in the real-time environmental parameters, that is, the weight vector matrix of the real-time power of the target unmanned ship is adjusted with the wind factor influence vector, the wave height vector and the ocean current intensity vector, to obtain the first adjustment result, the second adjustment result and the third adjustment result. In addition, the weight vector matrix of the real-time power of the target unmanned ship is adjusted with all the factors in the real-time environmental parameters, that is, the weight vector matrix of the real-time power of the target unmanned ship is adjusted with the wind factor influence vector, the wave height vector and the ocean current intensity vector, to obtain the fourth adjustment result. A spatial rectangular coordinate system is established based on the real-time environmental parameter vector matrix, with the wind factor influence vector, wave height vector and ocean current intensity vector as the horizontal axis, vertical axis and vertical axis respectively. After the construction of the spatial rectangular coordinate system is completed, the first adjustment result, the second adjustment result and the third adjustment result are projected on the first coordinate plane formed by the vertical axis and the vertical axis, the second coordinate plane formed by the horizontal axis and the vertical axis, and the third coordinate plane formed by the horizontal axis and the vertical axis, to obtain the first projection of the weight vector matrix of the real-time power of the target unmanned ship on the first coordinate plane, the second projection on the second coordinate plane, and the third projection on the third coordinate plane. The first projection, the second projection and the third projection are superimposed to obtain a superimposed projection, and the superimposed projection is converted into a superimposed projection vector, that is, a superimposed projection vector that is processed according to a single factor and then summarized is obtained, and then the superimposed projection vector and the fourth adjustment result are compared, and the fourth adjustment result is adjusted according to the comparison difference with the superimposed projection vector.

[0032] Furthermore, the corrected power value of each propeller of the target unmanned ship is output according to the adjusted vector matrix of the target unmanned ship power.

[0033] In a preferred embodiment, the method outputs the corrected power values ​​of each propeller of the target unmanned ship according to the adjusted vector matrix of the target unmanned ship power, including: determining the initial corrected power values ​​of each propeller of the target unmanned ship according to the adjusted vector matrix of the target unmanned ship power; for each propeller of the target unmanned ship, selecting three propellers with the strongest power constraint relationship with the current propeller according to the power constraint relationship between the propellers; generating a constraint triangle of the current propeller corrected power value according to the characteristic vector of the initial corrected power value of the propeller corresponding to the current propeller and the characteristic vectors of the initial corrected power values ​​of the propeller corresponding to the three selected propellers; comparing the constraint triangle of the current propeller corrected power value with the constraint triangle of the current propeller power; If the deviation of any angle between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power is greater than a preset threshold, adjust the initial correction power value of the paddle corresponding to the angle greater than the preset threshold and regenerate the constraint triangle of the current paddle correction power value, until the deviations of each angle between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power are no greater than the preset threshold, and use the initial correction power value of the paddle corresponding to the current paddle as the correction power value of the current paddle; If the angle deviations between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power are not greater than the preset threshold; the initial paddle correction power value corresponding to the current paddle is used as the correction power value of the current paddle.

[0034] In a preferred embodiment, the comparison of the constraint triangle of the current paddle correction power value with the constraint triangle of the current paddle power includes: obtaining the first centroid of the constraint triangle of the current paddle correction power value and the second centroid of the constraint triangle of the current paddle power, and aligning the constraint triangle of the current paddle correction power value with the constraint triangle of the current paddle power based on the first centroid and the second centroid; taking the first centroid as a fixed point, adjusting the constraint triangle of the current paddle correction power value by scaling and aligning, so that the adjusted constraint triangle of the current paddle correction power value is completely wrapped by the constraint triangle of the current paddle power; comparing the angles of the constraint triangle of the adjusted current paddle correction power value with the constraint triangle of the current paddle power.

[0035] Specifically, when comparing the constraint triangle of the current paddle correction power value with the constraint triangle of the current paddle power, first align the first centroid of the constraint triangle of the current paddle correction power value with the second centroid of the constraint triangle of the current paddle power, and align any vertices or edges of the two constraint triangles that belong to the same paddle. With the first centroid as the fixed point, adjust the constraint triangle of the current paddle correction power value by scaling, so that the adjusted constraint triangle of the current paddle correction power value is completely wrapped by the constraint triangle of the current paddle power, and compare the angles of the constraint triangle of the current paddle correction power value with the constraint triangle of the current paddle power.

[0036] In a preferred embodiment, the construction of the ship power control model includes: obtaining a number of environmental parameter samples and a number of propeller parameter samples; combining each environmental parameter sample and each propeller parameter sample in pairs to obtain a number of data to be simulated; performing simulation based on each data to be simulated to obtain the corrected power value of each propeller under the simulation corresponding to each data to be simulated; generating a number of training samples according to each data to be simulated and the corrected power value of each propeller under the simulation corresponding to each data to be simulated; constructing an initial ship power control model, taking the data to be simulated as input and the corrected power value of each propeller under the simulation corresponding to the data to be simulated as output, and iteratively training the initial ship power control model until the initial ship power control model reaches a preset convergence condition, and then generating the ship power control model.

[0037] Specifically, since the marine environment is difficult to obtain directly, it is mainly obtained through simulation when constructing training data. First, a number of environmental parameter samples and a number of propeller parameter samples are obtained, and then each environmental parameter sample and each propeller parameter sample are combined in pairs to obtain a number of data to be simulated, and each data to be simulated represents a combination of an environmental parameter sample and a propeller parameter sample. Each combination is simulated on the simulation system to obtain the corrected power value of each propeller under the simulation corresponding to each data to be simulated. According to each data to be simulated and the corrected power value of each propeller under the simulation corresponding to each data to be simulated, a number of training samples are generated, and each training sample is marked with the corrected power value of each propeller under the simulation corresponding to each data to be simulated. Then, a neural network model is constructed as the initial ship power control model, with the data to be simulated as input and the corrected power value of each propeller under the simulation corresponding to the data to be simulated as output, and the initial ship power control model is iteratively trained until the initial ship power control model converges or reaches the maximum number of iterations, and the ship power control model is generated.

[0038] In step S3, the power of each propeller of the target unmanned ship is regulated by the corrected power value of each propeller of the target unmanned ship, so that each propeller of the target unmanned ship outputs a power value that is the same as the corrected power value of each propeller.

[0039] Based on the above method embodiments, the present invention provides corresponding system embodiments.

[0040] like Figure 2 As shown, an embodiment of the present invention provides an unmanned ship control system based on real-time environmental parameters, including: a parameter acquisition module, a power value output module and a control module; The parameter acquisition module is used to acquire the real-time propeller parameters and real-time environmental parameters of the target unmanned ship; wherein the target unmanned ship is a multi-propeller unmanned ship, and the propeller parameters include: the number of operating propellers, the real-time power value of each propeller, the power upper limit of each propeller, and the power constraint relationship between each propeller; the real-time environmental parameters include: wind volume, wind direction, wave height, and ocean current intensity; The power value output module is used to input the real-time propeller parameters and real-time environmental parameters of the target unmanned ship into the ship power control model, so that the ship power control model generates a real-time environmental parameter vector matrix according to the real-time environmental parameters, generates a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters, adjusts the weight vector matrix of the real-time power of the target unmanned ship with the real-time environmental parameter vector matrix, obtains the adjusted vector matrix of the power of the target unmanned ship, and outputs the corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; The control module is used to control the power of each propeller of the unmanned ship according to the corrected power value of each propeller of the target unmanned ship.

[0041] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0042] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0043] Based on the above method item embodiments, the present invention provides corresponding terminal device item embodiments.

[0044] An embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, an unmanned ship control method based on real-time environmental parameters as described in any one of the present invention is implemented.

[0045] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0046] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0047] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0048] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0049] An embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute an unmanned ship control method based on real-time environmental parameters as described in any one of the present inventions.

[0050] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0051] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for controlling an unmanned ship based on real-time environmental parameters, characterized in that: include: Acquire the real-time propeller parameters and real-time environmental parameters of the target unmanned ship; wherein the target unmanned ship is a multi-propeller unmanned ship, and the propeller parameters include: the number of operating propellers, the real-time power value of each propeller, the upper limit of the power of each propeller, and the power constraint relationship between each propeller; the real-time environmental parameters include: wind volume, wind direction, wave height, and ocean current intensity; The real-time propeller parameters and real-time environmental parameters of the target unmanned ship are input into the ship power control model, so that the ship power control model generates a real-time environmental parameter vector matrix according to the real-time environmental parameters, generates a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters, adjusts the weight vector matrix of the real-time power of the target unmanned ship with the real-time environmental parameter vector matrix, obtains an adjusted vector matrix of the power of the target unmanned ship, and outputs a corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; The power of each propeller of the target unmanned ship is regulated by the corrected power value of each propeller of the target unmanned ship.

2. The unmanned ship control method based on real-time environmental parameters as claimed in claim 1, characterized in that: The construction of the ship power control model includes: Obtaining a number of environmental parameter samples and a number of paddle parameter samples; Combining each environmental parameter sample and each propeller parameter sample in pairs to obtain a number of data to be simulated; Perform simulation based on each to-be-simulated data to obtain a corrected power value of each propeller under the simulation corresponding to each to-be-simulated data; Generate a number of training samples according to each to-be-simulated data and the corrected power value of each propeller under the simulation corresponding to each to-be-simulated data; An initial ship power control model is constructed, with the data to be simulated as input and the corrected power value of each propeller under the simulation corresponding to the data to be simulated as output, and the initial ship power control model is iteratively trained until the initial ship power control model reaches a preset convergence condition, thereby generating the ship power control model.

3. The unmanned ship control method based on real-time environmental parameters as claimed in claim 1, characterized in that: The method of generating a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters includes: The initial weight vector matrix of the real-time power of the target unmanned ship is constructed according to the number of operating propellers, the real-time power value of each propeller and the upper limit of the power of each propeller; For each propeller of the target unmanned ship, three propellers with the strongest power constraint relationship with the current propeller are selected according to the power constraint relationship between the propellers; Generate a constraint triangle of the current oar power according to the eigenvector of the oar real-time power value corresponding to the current oar and the eigenvectors of the oar real-time power values ​​corresponding to the three selected oars; The initial weights of the initial weight vector matrix are adjusted according to the constraint triangles of each propeller power to obtain the weight vector matrix of the real-time power of the target unmanned ship.

4. The unmanned ship control method based on real-time environmental parameters as claimed in claim 3, characterized in that: The step of generating a real-time environment parameter vector matrix according to the real-time environment parameter comprises: Generate wind volume vector, wind direction vector, wave height vector and ocean current intensity vector according to wind volume, wind direction, wave height and ocean current intensity respectively; The wind volume vector and wind direction vector are integrated to obtain the wind factor influence vector; A real-time environmental parameter vector matrix is ​​generated according to the wave height vector, the ocean current intensity vector and the wind factor influence vector.

5. The unmanned ship control method based on real-time environmental parameters as claimed in claim 4, characterized in that: The method of adjusting the weight vector matrix of the real-time power of the target unmanned ship by using the real-time environmental parameter vector matrix to obtain the adjusted vector matrix of the power of the target unmanned ship includes: The weight vector matrix of the real-time power of the target unmanned ship is adjusted by the wind factor influence vector, the wave height vector and the ocean current intensity vector respectively to obtain a first adjustment result, a second adjustment result and a third adjustment result; The weight vector matrix of the real-time power of the target unmanned ship is adjusted by using the wind factor influence vector, the wave height vector, and the ocean current intensity vector to obtain a fourth adjustment result; A spatial rectangular coordinate system is established based on the real-time environmental parameter vector matrix, with the wind factor influence vector, wave height vector and ocean current intensity vector as the horizontal axis, vertical axis and vertical axis respectively; Respectively projecting the first adjustment result, the second adjustment result, and the third adjustment result onto a first coordinate plane formed by the longitudinal axis and the vertical axis, onto a second coordinate plane formed by the transverse axis and the vertical axis, and onto a third coordinate plane formed by the transverse axis and the longitudinal axis, to obtain a first projection of a weight vector matrix of the real-time power of the target unmanned ship on the first coordinate plane, a second projection on the second coordinate plane, and a third projection on the third coordinate plane; The first projection, the second projection and the third projection are superimposed to obtain a superimposed projection, and the superimposed projection is converted into a superimposed projection vector, and the fourth adjustment result is adjusted with the superimposed projection vector to obtain an adjusted vector matrix of the target unmanned ship power.

6. The unmanned ship control method based on real-time environmental parameters as claimed in claim 5, characterized in that: Outputting the corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the target unmanned ship power includes: Determine the initial corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; For each propeller of the target unmanned ship, three propellers with the strongest power constraint relationship with the current propeller are selected according to the power constraint relationship between the propellers; Generate a constraint triangle of the current oar correction power value according to the characteristic vector of the initial correction power value of the oar corresponding to the current oar and the characteristic vectors of the initial correction power values ​​of the oar corresponding to the three selected oars; Compare the constraint triangle of the current propeller correction power value with the constraint triangle of the current propeller power; If the deviation of any angle between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power is greater than a preset threshold, adjust the initial correction power value of the paddle corresponding to the angle greater than the preset threshold and regenerate the constraint triangle of the current paddle correction power value, until the deviations of each angle between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power are no greater than the preset threshold, and use the initial correction power value of the paddle corresponding to the current paddle as the correction power value of the current paddle; If the angle deviations between the constraint triangle of the current paddle correction power value and the constraint triangle of the current paddle power are not greater than the preset threshold; the initial paddle correction power value corresponding to the current paddle is used as the correction power value of the current paddle.

7. The unmanned ship control method based on real-time environmental parameters as claimed in claim 6, characterized in that: The comparing the constraint triangle of the current propeller correction power value with the constraint triangle of the current propeller power includes: Obtaining a first centroid of a constraint triangle of a current paddle correction power value and a second centroid of a constraint triangle of the current paddle power, and aligning the constraint triangle of the current paddle correction power value with the constraint triangle of the current paddle power based on the first centroid and the second centroid; Taking the first centroid as the fixed point, the constraint triangle of the current paddle correction power value is adjusted by scaling and aligning, so that the constraint triangle of the adjusted current paddle correction power value is completely wrapped by the constraint triangle of the current paddle power; The constraint triangle of the adjusted current propeller correction power value is compared with the angles of the constraint triangle of the current propeller power.

8. An unmanned ship control system based on real-time environmental parameters, characterized in that: include: Parameter acquisition module, power value output module and control module; The parameter acquisition module is used to acquire the real-time propeller parameters and real-time environmental parameters of the target unmanned ship; wherein the target unmanned ship is a multi-propeller unmanned ship, and the propeller parameters include: the number of operating propellers, the real-time power value of each propeller, the power upper limit of each propeller, and the power constraint relationship between each propeller; the real-time environmental parameters include: wind volume, wind direction, wave height, and ocean current intensity; The power value output module is used to input the real-time propeller parameters and real-time environmental parameters of the target unmanned ship into the ship power control model, so that the ship power control model generates a real-time environmental parameter vector matrix according to the real-time environmental parameters, generates a weight vector matrix of the real-time power of the target unmanned ship according to the real-time propeller parameters, adjusts the weight vector matrix of the real-time power of the target unmanned ship with the real-time environmental parameter vector matrix, obtains the adjusted vector matrix of the power of the target unmanned ship, and outputs the corrected power value of each propeller of the target unmanned ship according to the adjusted vector matrix of the power of the target unmanned ship; The control module is used to control the power of each propeller of the unmanned ship according to the corrected power value of each propeller of the target unmanned ship.

9. A terminal device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, an unmanned ship control method based on real-time environmental parameters as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute an unmanned ship control method based on real-time environmental parameters as described in any one of claims 1 to 7.

Images