A method, system and device for positioning and controlling underwater vehicles in a strong interference environment

Abstract

The present invention relates to the technical field of underwater vehicle motion control, and provides a method, system, and device for positioning and controlling underwater vehicles in a strong interference environment. The method comprises the following steps: establishing a training data set based on the navigation data of the vehicle under strong interference; training a convolutional neural network model based on the training data set; inputting the navigation data of the vehicle at the current moment into the trained convolutional neural network model, and outputting the predicted value of the vehicle; and designing an underwater vehicle positioning and control algorithm, using the predicted value of the vehicle as input to obtain the thrust and direction angle of the propeller. The present invention improves prediction accuracy by combining the prediction of the convolutional neural network model with the positioning and control algorithm, thereby enabling the controller to have environmental perception capabilities and improving the positioning and control accuracy of the vehicle under strong interference.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater vehicle motion control, and provides a method, system and device for positioning control of an underwater vehicle in a strong interference environment. Background Art

[0002] Precise positioning and control of underwater vehicles (AUVs) is a core challenge in fields such as marine resource exploration and underwater engineering operations. Traditional AUV control methods have significant limitations in environments with strong interference (such as wind, waves, and currents). Because they lack the ability to anticipate the impact of environmental interference on the vehicle, actuators are unable to proactively counteract the interference, resulting in a significant decrease in positioning and control accuracy under strong interference.

[0003] Currently, the Sequential Quadratic Programming (SQP) algorithm is commonly used to allocate the speed and azimuth of auxiliary thrusters. This method requires separate designs for the motion controller and the auxiliary thruster thrust allocation algorithm, resulting in poor synergy and potentially causing SQP algorithm allocation failures. Furthermore, the SQP algorithm requires real-time iteration through all possible scenarios to find the optimal solution when allocating thrust, which is computationally intensive and difficult to perform. This results in poor real-time performance and consumes a large amount of storage space, making it inconvenient for practical applications. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention provides a method, system, and device for positioning and controlling an underwater vehicle in a strong interference environment, thereby enabling the controller to have environmental perception capabilities and improving the positioning and control accuracy of the vehicle under strong interference.

[0005] The present invention provides a positioning control method for an underwater vehicle in a strong interference environment, comprising:

[0006] S1: Establish a training dataset based on the navigation data of the aircraft under strong interference;

[0007] S2: Training a convolutional neural network model based on the training data set;

[0008] S3: Input the current navigation data of the aircraft into the trained convolutional neural network model and output the predicted value of the aircraft;

[0009] S4: Design an underwater vehicle positioning control algorithm, using the predicted value of the vehicle as input to obtain the thrust command and direction angle of the propeller.

[0010] According to a method for positioning and controlling an underwater vehicle in a strong interference environment provided by the present invention, step S1 includes:

[0011] S11: The navigation data is formed into The training data set is is the number of navigation data elements;

[0012] S12: Setting the front of the training data The elements are training samples, and the back of the training data is set The element is a tag, where is the number of training sample elements.

[0013] According to a positioning control method for an underwater vehicle in a strong interference environment provided by the present invention, the navigation data includes: actual positioning state data and predicted state data;

[0014] The actual positioning state data includes: longitudinal velocity, lateral velocity, bow angular velocity, heel angle, heading, eastward displacement, northward displacement, front auxiliary propeller thrust, front propeller angle, rear propeller thrust and rear propeller angle of the vehicle during the process of moving from the initial position to the target position;

[0015] The predicted state data includes the predicted heading of the aircraft, the predicted north displacement, the predicted east displacement, the predicted bow angular velocity, the predicted longitudinal velocity, and the predicted lateral velocity.

[0016] According to a positioning control method for an underwater vehicle in a strong interference environment provided by the present invention, the structure of the convolutional neural network model includes three convolutional layers connected in sequence and one fully connected layer.

[0017] According to a positioning control method for underwater vehicles in a strong interference environment provided by the present invention, the three convolutional layers are respectively a first convolutional layer, a second convolutional layer and a third convolutional layer, and the convolution kernel of the first convolutional layer is , the convolution kernel of the second convolutional layer is , the convolution kernel of the third convolutional layer is , the convolutional layer and the fully connected layer are both provided with a pReLU activation function.

[0018] According to the positioning control method for underwater vehicles in a strong interference environment provided by the present invention, the loss function of the convolutional neural network model is for:

[0019]

[0020] in, is the heading loss weight, is the heading loss function, is the northbound loss weight, is the northbound loss function, is the eastward loss weight, is the eastward loss function.

[0021] According to a positioning control method for underwater vehicles in a strong interference environment provided by the present invention, the , , The formulas are:

[0022]

[0023] in, is the number of heading data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the heading state quantity, is the convolution operator, For the The normalized prediction error of the heading, For the The true state of the heading, For the A heading prediction state quantity, For the The standard deviation of the heading state quantity, ;

[0024]

[0025] in, is the number of northward displacement data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the northward displacement is For the The normalized prediction error of the northward displacement is For the The true state quantity of the northward displacement, For the The predicted state quantity of northward displacement, For the The standard deviation of the northward displacement, ;

[0026]

[0027] in, is the number of eastward displacement data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the eastward displacement is For the The normalized prediction error of the eastward displacement is For the The true state quantity of the eastward displacement, For the The predicted state quantity of the eastward displacement, For the The standard deviation of the eastward displacement, .

[0028] According to a method for positioning and controlling an underwater vehicle in a strong interference environment provided by the present invention, step S4 includes:

[0029] S41: Using the predicted value of the model output as input, the state space expression is constructed as follows:

[0030]

[0031]

[0032]

[0033] in, represents the predicted longitudinal velocity, represents the predicted value of lateral velocity, represents the predicted value of the bow angular velocity, Represents the heading prediction value, represents the predicted value of northward displacement, represents the predicted value of eastward displacement, express The time derivative, express The time derivative, express The time derivative, express The time derivative, express The time derivative, express The time derivative, is the first heading state space expression coefficient, is the second heading state space expression coefficient, is the spatial expression coefficient of the first northward displacement state, is the spatial expression coefficient of the second northward displacement state, is the state space expression coefficient of the first eastward displacement, is the state space expression coefficient of the second eastward displacement, is the front thruster thrust, is the front thruster angle, is the rear thruster thrust, is the rear thruster angle, is the distance from the front thruster to the center of the spacecraft, is the distance from the rear thruster to the center of the spacecraft;

[0034] S42: Based on the output auxiliary thruster command thrust and command direction angle, the output expression is constructed as follows:

[0035]

[0036] in, is the command thrust for the front thruster, is the front thruster command angle, Command thrust for the rear thrusters, is the rear thruster command angle, is the first controller coefficient, is the second controller coefficient, is the third controller coefficient, is the fourth controller coefficient, is the fifth controller coefficient, is the sixth controller coefficient, is the seventh controller coefficient, is the eighth controller coefficient, is the ninth controller coefficient, for The bow angular velocity after seconds is for The heading after seconds, is the heading command value, for The longitudinal velocity after seconds, for The northward displacement after seconds, is the north displacement instruction value, for The horizontal speed after seconds, for The eastward displacement after seconds, is the eastward displacement command value, To predict the duration, For time;

[0037] S43: Based on the state space expression and output expression, construct the Riccati equation to solve ;

[0038] S44: According to The sequential quadratic programming method is used to distribute the thrust and azimuth of the front and rear auxiliary thrusters to obtain the thruster command thrust and command azimuth.

[0039] The present invention also provides a positioning control system for an underwater vehicle in a strong interference environment, comprising:

[0040] Dataset construction module: used to build training datasets based on the navigation data of the aircraft under strong interference;

[0041] Model training module: used for the training data set to train the convolutional neural network model;

[0042] Numerical prediction module: used to input the current navigation data of the aircraft into the trained convolutional neural network model and output the predicted value of the aircraft;

[0043] Command calculation module: used to design the underwater vehicle positioning control algorithm, using the predicted value of the vehicle as input to obtain the thrust and direction angle of the propeller.

[0044] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, the steps of a method for positioning and controlling an underwater vehicle in a strong interference environment as described above are implemented.

[0045] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects:

[0046] The present invention provides a method, system, and device for positioning and controlling underwater vehicles in a high-interference environment. By combining a convolutional neural network with modern control methods to address these issues, the predicted state output by the convolutional neural network is used as the controller input, enabling the controller to perceive the environment and achieve proactive action. Pre-training the network model using a training set based on the underwater vehicle's navigation data under interference improves the algorithm's real-time performance and further enhances the underwater vehicle's positioning and control accuracy.

[0047] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a flow chart of a positioning control method for an underwater vehicle in a strong interference environment provided by the present invention.

[0050] Figure 2 Schematic diagram of the convolutional neural network structure provided by an embodiment of the present invention.

[0051] Figure 3A comparison chart of the heading control results provided by an embodiment of the present invention and the results of a conventional solution.

[0052] Figure 4 A comparison chart of the northward displacement control results provided by an embodiment of the present invention and the results of a conventional solution.

[0053] Figure 5 A comparison chart of the eastward displacement control results provided by an embodiment of the present invention and the results of a conventional solution.

[0054] Figure 6 This is a structural block diagram of a positioning control system for an underwater vehicle in a strong interference environment provided by the present invention.

[0055] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention.

[0056] Reference numerals:

[0057] 101. Dataset construction module; 102. Model training module; 103. Numerical prediction module; 104. Instruction calculation module; 810. Processor; 820. Communication interface; 830. Memory; 840. Communication bus. DETAILED DESCRIPTION

[0058] To make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below. Obviously, the embodiments described are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0059] In the description of the embodiments of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore should not be understood as limiting the embodiments of the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0060] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0061] The following combination Figures 1 to 7 The present invention is described.

[0062] Example

[0063] like Figure 1 As shown, the present invention provides a positioning control method for an underwater vehicle in a strong interference environment, comprising the following steps:

[0064] S1: Establish a training dataset based on the navigation data of the aircraft under strong interference;

[0065] S2: Training a convolutional neural network model based on the training data set;

[0066] S3: Input the current navigation data of the aircraft into the trained convolutional neural network model and output the predicted value of the aircraft;

[0067] S4: Design an underwater vehicle positioning control algorithm, using the predicted value of the vehicle as input to obtain the thrust command and direction angle of the propeller.

[0068] Specifically, step S1 includes:

[0069] S11: The navigation data is formed into The training data set is is the number of navigation data elements;

[0070] S12: Setting the front of the training data The elements are training samples, and the back of the training data is set The element is a tag, where is the number of training sample elements.

[0071] Specifically, the navigation data includes: actual positioning state data and predicted state data;

[0072] The actual positioning state data includes: longitudinal velocity, lateral velocity, bow angular velocity, heel angle, heading, eastward displacement, northward displacement, front auxiliary propeller thrust, front propeller angle, rear propeller thrust and rear propeller angle of the vehicle during the process of moving from the initial position to the target position;

[0073] The predicted state data includes the predicted heading of the aircraft, the predicted north displacement, the predicted east displacement, the predicted bow angular velocity, the predicted longitudinal velocity, and the predicted lateral velocity.

[0074] The data acquisition method used in the embodiment of the present invention is as follows: setting the target heading and target position of the aircraft, recording the longitudinal speed, lateral speed, bow angular velocity, heading, eastward displacement, northward displacement, auxiliary propeller thrust, auxiliary propeller speed and other data of the aircraft from the initial position to the target position; combining the target value of the aircraft and the recorded actual data into a data set; The training data is in the following form:

[0075]

[0076] in, is the training sample, For label.

[0077] in, is the longitudinal velocity, is the lateral velocity, Bow angular speed, is the heel angle, For the heading, is the northward displacement, is the eastward displacement, is the front thruster thrust, is the front thruster angle, is the rear thruster thrust, is the rear thruster angle, For the target heading, is the target northward displacement, is the eastward displacement of the target, for The longitudinal velocity after seconds, for The horizontal speed after seconds, for The bow angular velocity after seconds is for The heading after seconds, for The northward displacement after seconds, for Eastward displacement after seconds.

[0078] Specifically, step S2 includes:

[0079] like Figure 2 As shown in Figure 1, the structure of the convolutional neural network model includes three convolutional layers connected in sequence and one fully connected layer. The three convolutional layers are the first convolutional layer, the second convolutional layer and the third convolutional layer, and the convolution kernel of the first convolutional layer is , the convolution kernel of the second convolutional layer is , the convolution kernel of the third convolutional layer is , the convolutional layer and the fully connected layer are both provided with a pReLU activation function.

[0080] Specifically, based on the training data set, the convolutional neural network model is trained; in this embodiment, the training samples are converted into The matrix is ​​then fed into the convolutional neural network, and the prediction time is set to 10 seconds. The specific form is as follows;

[0081] Training samples: ;

[0082] Training Label: ;

[0083] in, is the longitudinal velocity of the spacecraft 10 seconds later, is the lateral speed of the spacecraft after 10 seconds, is the bow angular velocity of the vehicle 10 seconds later, is the heading of the vehicle 10 seconds later, is the northward displacement of the spacecraft after 10 seconds, is the eastward displacement of the spacecraft after 10 seconds.

[0084] Calculate the loss between the network output and the training labels as follows:

[0085] Loss function of convolutional neural network model for:

[0086]

[0087] in, is the heading loss weight, is the heading loss function, is the northbound loss weight, is the northbound loss function, is the eastward loss weight, is the eastward loss function.

[0088] In the embodiment of the present invention, , .

[0089] Specifically, the , , The formulas are:

[0090]

[0091] in, is the number of heading data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the heading state quantity, is the convolution operator, For the The normalized prediction error of the heading, For the The true state of the heading, For the A heading prediction state quantity, For the The standard deviation of the heading state quantity, ;

[0092]

[0093] in, is the number of northward displacement data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the northward displacement is For the The normalized prediction error of the northward displacement is For the The true state quantity of the northward displacement, For the The predicted state quantity of northward displacement, For the The standard deviation of the northward displacement, ;

[0094]

[0095] in, is the number of eastward displacement data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the eastward displacement is For the The normalized prediction error of the eastward displacement is For the The true state quantity of the eastward displacement, For the The predicted state quantity of the eastward displacement, For the The standard deviation of the eastward displacement, .

[0096] In the embodiment of the present invention, , .

[0097] In this embodiment, the stochastic gradient descent optimizer (SGD) is selected as the network optimizer.

[0098] Specifically, step S3 includes: setting the size of the convolutional neural network input to be consistent with the label format in order to make the convolutional neural network output consistent with the label format. :

[0099] ;

[0100] in, represents the predicted longitudinal velocity; represents the predicted value of lateral velocity; represents the predicted value of the bow angular velocity; Represents the heading prediction value, represents the predicted value of northward displacement, Represents the predicted eastward displacement.

[0101] Specifically, step S4 includes: S41: using the predicted value output by the model as input, constructing the state space expression as follows:

[0102]

[0103]

[0104]

[0105] in, represents the predicted longitudinal velocity, represents the predicted value of lateral velocity, represents the predicted value of the bow angular velocity, Represents the heading prediction value, represents the predicted value of northward displacement, represents the predicted value of eastward displacement, express The time derivative, express The time derivative, express The time derivative, express The time derivative, express The time derivative, express The time derivative, is the first heading state space expression coefficient, is the second heading state space expression coefficient, is the spatial expression coefficient of the first northward displacement state, is the spatial expression coefficient of the second northward displacement state, is the state space expression coefficient of the first eastward displacement, is the state space expression coefficient of the second eastward displacement, is the front thruster thrust, is the front thruster angle, is the rear thruster thrust, is the rear thruster angle, is the distance from the front thruster to the center of the spacecraft, is the distance from the rear thruster to the center of the spacecraft;

[0106] S42: Based on the output auxiliary thruster command thrust and command direction angle, the output expression is constructed as follows:

[0107]

[0108] in, is the command thrust for the front thruster, is the front thruster command angle, Command thrust for the rear thrusters, is the rear thruster command angle, is the first controller coefficient, is the second controller coefficient, is the third controller coefficient, is the fourth controller coefficient, is the fifth controller coefficient, is the sixth controller coefficient, is the seventh controller coefficient, is the eighth controller coefficient, is the ninth controller coefficient, for The bow angular velocity after seconds is for The heading after seconds, is the heading command value, for The longitudinal velocity after seconds, for The northward displacement after seconds, is the north displacement instruction value, for The horizontal speed after seconds, for The eastward displacement after seconds, is the eastward displacement command value, To predict the duration, For time;

[0109] S43: Based on the state space expression and output expression, construct the Riccati equation to solve ;

[0110] S44: According to The sequential quadratic programming method is used to distribute the thrust and azimuth of the front and rear auxiliary thrusters to obtain the thruster command thrust and command azimuth.

[0111] In summary, the present invention uses a convolutional neural network to predict the future state of an underwater vehicle and designs a positioning controller based on the prediction results of the convolutional neural network. This can enable the controller to have environmental perception capabilities and improve the positioning control accuracy of the vehicle under strong interference.

[0112] like Figure 3 、 Figure 4 、 Figure 5 As shown, Figure 3 A comparison chart of the heading control results provided by an embodiment of the present invention and the results of a conventional solution; Figure 4 A comparison chart of the northward displacement control results provided by an embodiment of the present invention and the results of a conventional solution; Figure 5 Comparison chart of the eastward displacement control results provided by the embodiment of the present invention and the results of the conventional solution

[0113] As shown in the figure above, the method proposed in the present invention improves the prediction accuracy by combining the convolutional neural network model prediction and the positioning control algorithm, enables the controller to have environmental perception capabilities, and improves the positioning control accuracy of the aircraft under strong interference.

[0114] like Figure 6 As shown, an embodiment of the present invention further provides a positioning control system for an underwater vehicle in a strong interference environment, comprising the following modules:

[0115] Dataset construction module 101: used to establish a training data set based on the navigation data of the aircraft under strong interference;

[0116] Model training module 102: used for training the convolutional neural network model using the training data set;

[0117] Numerical prediction module 103: used to input the current navigation data of the aircraft into the trained convolutional neural network model and output the predicted value of the aircraft;

[0118] The command calculation module 104 is used to design an underwater vehicle positioning control algorithm, using the predicted value of the vehicle as input to obtain the thrust command and direction angle of the propeller.

[0119] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute a positioning control method for an underwater vehicle in a strong interference environment, the method comprising:

[0120] S1: Establish a training dataset based on the navigation data of the aircraft under strong interference;

[0121] S2: Training a convolutional neural network model based on the training data set;

[0122] S3: Input the current navigation data of the aircraft into the trained convolutional neural network model and output the predicted value of the aircraft;

[0123] S4: Design an underwater vehicle positioning control algorithm, using the predicted value of the vehicle as input to obtain the thrust command and direction angle of the propeller.

[0124] Furthermore, the logic instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0125] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0126] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

[0128] It should be noted that the embodiments of the present disclosure can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-mentioned devices and methods can be implemented using computer-executable instructions and / or contained in processor control code, for example, such code is provided on a programmable memory or a data carrier such as an optical or electronic signal carrier.

[0129] In addition, although the operations of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flow chart can change the order of execution. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps. It should also be noted that the features and functions of two or more devices according to the present disclosure can be embodied in one device. Conversely, the features and functions of a device described above can be further divided into being embodied by multiple devices.

[0130] Although the present disclosure has been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the specific embodiments disclosed. The present disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A positioning control method for underwater vehicles in a strong interference environment, characterized in that: include: S1: Establish a training dataset based on the navigation data of the aircraft under strong interference; S2: Based on the training data set, the convolutional neural network model is trained; the structure of the convolutional neural network model includes three convolutional layers connected in sequence and one fully connected layer, the three convolutional layers are the first convolutional layer, the second convolutional layer and the third convolutional layer, and the convolution kernel of the first convolutional layer is , the convolution kernel of the second convolutional layer is , the convolution kernel of the third convolutional layer is , the convolutional layer and the fully connected layer are both provided with a pReLU activation function; the loss function of the convolutional neural network model is for: in, is the heading loss weight, is the heading loss function, is the northbound loss weight, is the northbound loss function, is the eastward loss weight, is the eastward loss function; described , , The formulas are: in, is the number of heading data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the heading state quantity, is the convolution operator, For the The normalized prediction error of the heading, For the The true heading state quantity, For the A heading prediction state variable, For the The standard deviation of the heading state quantity, ; in, is the number of northward displacement data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the northward displacement, For the The normalized prediction error of the northward displacement is For the The true state quantity of the northward displacement, For the The predicted state quantity of northward displacement, For the The standard deviation of the northward displacement, ; in, is the number of eastward displacement data within each weight update time interval of the convolutional neural network, For the The weight coefficient of the eastward displacement is For the The normalized prediction error of the eastward displacement is For the The true state quantity of the eastward displacement, For the The predicted state quantity of the eastward displacement, For the The standard deviation of the eastward displacement, ; S3: Input the current navigation data of the aircraft into the trained convolutional neural network model and output the predicted value of the aircraft; S4: Design an underwater vehicle positioning control algorithm, using the predicted value of the vehicle as input to obtain the thrust command and direction angle of the propeller.

2. The method for positioning and controlling an underwater vehicle in a strong interference environment according to claim 1, characterized in that: Step S1 includes: S11: The navigation data is formed into The training data set is is the number of navigation data elements; S12: Setting the front of the training data The elements are training samples, and the back of the training data is set The element is a tag, where is the number of training sample elements.

3. The method for positioning and controlling an underwater vehicle in a strong interference environment according to claim 2, characterized in that: Said navigation data includes: actual positioning state data and predicted positioning state data; The actual positioning state data includes: longitudinal velocity, lateral velocity, bow angular velocity, heel angle, heading, eastward displacement, northward displacement, front auxiliary propeller thrust, front propeller angle, rear propeller thrust and rear propeller angle of the vehicle during the process of moving from the initial position to the target position; The predicted state data includes the predicted heading of the aircraft, the predicted north displacement, the predicted east displacement, the predicted bow angular velocity, the predicted longitudinal velocity, and the predicted lateral velocity.

4. The method for positioning and controlling an underwater vehicle in a strong interference environment according to claim 1, characterized in that: Step S4 includes: S41: Using the predicted value of the model output as input, the state space expression is constructed as follows: in, represents the predicted longitudinal velocity, represents the predicted value of lateral velocity, represents the predicted value of the bow angular velocity, Represents the heading prediction value, represents the predicted value of northward displacement, represents the predicted value of eastward displacement, express The time derivative, express The time derivative, express The time derivative, express The time derivative, express The time derivative, express The time derivative, is the first heading state space expression coefficient, is the second heading state space expression coefficient, is the spatial expression coefficient of the first northward displacement state, is the spatial expression coefficient of the second northward displacement state, is the state space expression coefficient of the first eastward displacement, is the state space expression coefficient of the second eastward displacement, is the front thruster thrust, is the front thruster angle, is the rear thruster thrust, is the rear thruster angle, is the distance from the front thruster to the center of the spacecraft, is the distance from the rear thruster to the center of the spacecraft; S42: Based on the output auxiliary thruster command thrust and command direction angle, the output expression is constructed as follows: in, is the command thrust for the front thruster, is the front thruster command angle, is the thrust command for the rear thrusters, is the rear thruster command angle, is the first controller coefficient, is the second controller coefficient, is the third controller coefficient, is the fourth controller coefficient, is the fifth controller coefficient, is the sixth controller coefficient, is the seventh controller coefficient, is the eighth controller coefficient, is the ninth controller coefficient, for The bow angular velocity after seconds is for The heading after seconds, is the heading command value, for The longitudinal velocity after seconds, for The northward displacement after seconds, is the north displacement instruction value, for The horizontal speed after seconds, for The eastward displacement after seconds, is the eastward displacement command value, To predict the duration, For time; S43: Based on the state space expression and output expression, construct the Riccati equation to solve ; S44: According to The thrust and azimuth of the front and rear auxiliary thrusters are distributed using the sequential quadratic programming method to obtain the thrust and azimuth of the thrusters.

5. A strong interference environment underwater vehicle positioning control system, used to implement the strong interference environment underwater vehicle positioning control method according to any one of claims 1 to 4, characterized in that: include: Dataset construction module: used to build training datasets based on the navigation data of the aircraft under strong interference; Model training module: used for the training data set to train the convolutional neural network model; Numerical prediction module: used to input the current navigation data of the aircraft into the trained convolutional neural network model and output the predicted value of the aircraft; Command calculation module: used to design the underwater vehicle positioning control algorithm, using the predicted value of the vehicle as input to obtain the thrust and direction angle of the propeller.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for positioning and controlling an underwater vehicle in a strong interference environment as described in any one of claims 1 to 4 are implemented.

Images