Unmanned ship safety control method and system based on adaptive neural network observer

Abstract

The invention discloses an unmanned ship safety control method and system based on an adaptive neural network observer, and relates to the technical field of unmanned ship control, and the method comprises the steps: building a second-order dynamic model of an unmanned ship through a kinetic equation, and obtaining the actual position and speed state of the unmanned ship; designing an adaptive observer based on a neural network by using a neural network approximate nonlinear dynamic state so as to estimate a first-order system position state and a second-order system speed state under DoS attack and external interference; determining an actual and estimated position tracking error of the unmanned ship according to a preset expected trajectory in combination with the actual and estimated position states, and constructing a virtual controller; designing a nonlinear filter according to the virtual control signal to obtain a trajectory tracking signal of a second-order speed system, and constructing an adaptive controller in combination with the estimated speed state; based on a virtual controller and an adaptive controller, expected trajectory tracking of the unmanned ship under DoS attack and disturbance is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned boat control, and in particular to an unmanned boat safety control method and system based on an adaptive neural network observer. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Unmanned surface vehicles (USVs), also known as unmanned surface vessels (USVs), are a type of nonlinear motion control system operating on the water surface. They are widely used in surface transportation, reconnaissance, exploration, and rescue. In practice, the navigation control task of an USV is typically achieved by moving the USV along a given reference trajectory. In other words, the control objective is to ensure the predetermined trajectory is tracked. However, due to the complexity of the operating environment, the USV system is inevitably affected by external interference. The communication process of transmitting the USV's motion status to the control center is also vulnerable to malicious attacks, raising security concerns for the USV. Therefore, ensuring that the USV maintains trajectory tracking despite external disturbances and malicious communications attacks is of great significance.

[0004] To address the security issues of the aforementioned unmanned vehicle systems, three common attack behaviors are: denial of service (DoS) attacks, data injection, and spoofing attacks. A DoS attack involves an attacker sending a large amount of useless data to block the channel from transmitting system data in real time, causing the system to malfunction. This attack is one of the most harmful attacks affecting data transmission. Among existing unmanned vehicle safety control methods that consider DoS attacks, one of the mainstream approaches to safety control is to design an observer to estimate the missing state caused by DoS attacks to ensure effective data transmission. However, accurately estimating the missing information in the system is difficult, especially when interfered with by external disturbances. Existing observers are even less able to accurately estimate the missing information.

[0005] On the other hand, due to the cascaded nonlinear characteristics of the position and velocity states of unmanned vehicles, backstepping control is an effective control method for ensuring their safe operation. However, the backstepping control process often involves repeated state differentiation, leading to an explosion in computational complexity. While the complexity explosion in backstepping control can be addressed by designing auxiliary variables using filtering operators, such as the proposed design of linear filters to address the repeated differentiation problem in backstepping safety control processes with DoS attacks, existing linear filter designs lack general applicability and exhibit certain filtering errors, resulting in inaccurate filtered signals and, in turn, affecting the accuracy of tracking control strategies.

[0006] Furthermore, in practical applications, various unexpected factors can affect the stable operation of unmanned boats. For example, in complex environments, external disturbances to the system, such as strong winds, surges, and ocean currents, can affect the performance of unmanned boats. Due to the suddenness and persistence of external disturbances, compensating for them is a key challenge for the stable operation of control systems. However, existing unmanned boat control schemes for external disturbances have relatively strict assumptions, such as constraints such as the differentiability of disturbances and bounded derivatives. These constraints limit them to a very small number of continuous and slowly varying external disturbances, resulting in poor applicability and accuracy of these control schemes. Summary of the Invention

[0007] To address the deficiencies of the above-mentioned prior art, the present invention provides a safety control method and system for an unmanned boat based on an adaptive neural network observer. An observer based on an adaptive neural network is designed to reconstruct the state of the system. Utilizing the backstepping control concept, a step-by-step virtual control signal is designed. A nonlinear filter with filtering error suppression is designed to associate the virtual control signal, thereby providing an accurate auxiliary reference signal. A safety controller is then constructed based on the observer and the filter to ensure the boundedness of each signal in the system. Through the above adaptive control strategy, the negative impact of DoS attacks and external disturbances on the operation of the unmanned boat during actual operation is suppressed, thereby solving the problems of poor applicability and poor accuracy of trajectory tracking control of unmanned boats subjected to DoS attacks and interference.

[0008] In a first aspect, the present invention provides a safety control method for an unmanned boat based on an adaptive neural network observer.

[0009] A safety control method for an unmanned boat based on an adaptive neural network observer comprises:

[0010] Using the dynamic equations, the second-order dynamic model of the unmanned boat is constructed, and the actual position and speed state of the unmanned boat is obtained;

[0011] By using neural networks to approximate the online nonlinear dynamics of position and velocity states in a second-order dynamic model, a neural network-based adaptive observer is designed to estimate the first-order system position state and the second-order system velocity state under DoS attacks and external disturbances.

[0012] According to the preset desired trajectory, combined with the actual and estimated position states, the actual and estimated position tracking errors of the unmanned vehicle are determined, thereby constructing a virtual controller for the first-order position system of the unmanned vehicle;

[0013] According to the virtual control signal output by the virtual controller, a nonlinear filter is designed to obtain the trajectory tracking signal of the second-order velocity system. Then, combined with the estimated velocity state, an adaptive controller for the second-order velocity system is constructed.

[0014] Based on the virtual controller and adaptive controller, the desired trajectory of the unmanned boat is tracked under DoS attack and disturbance.

[0015] In a second aspect, the present invention provides an unmanned boat safety control system based on an adaptive neural network observer.

[0016] An unmanned boat safety control system based on an adaptive neural network observer comprises:

[0017] The data acquisition and model building module is used to build a second-order dynamic model of the unmanned boat using the dynamic equations and obtain the actual position and speed state of the unmanned boat;

[0018] The state estimation module is used to use neural networks to approximate the online nonlinear dynamics of the position and velocity states in the second-order dynamic model, and to design a neural network-based adaptive observer to estimate the first-order system position state and the second-order system velocity state under DoS attacks and external disturbances;

[0019] The virtual controller construction module is used to determine the actual and estimated position tracking errors of the unmanned vehicle based on the preset desired trajectory and the actual and estimated position states, thereby constructing a virtual controller for the unmanned vehicle's first-order position system;

[0020] An adaptive controller building module is used to design a nonlinear filter based on the virtual control signal output by the virtual controller to obtain the trajectory tracking signal of the second-order velocity system. The module then combines the estimated velocity state to build an adaptive controller for the second-order velocity system.

[0021] The tracking control module is used to track the desired trajectory of the unmanned boat under DoS attacks and disturbances based on a virtual controller and an adaptive controller.

[0022] In a third aspect, the present invention also provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing the above-mentioned unmanned boat safety control method based on an adaptive neural network observer when executing the executable instructions stored in the memory.

[0023] In a fourth aspect, the present invention further provides a computer-readable storage medium storing executable instructions for causing a processor to execute the executable instructions to implement the above-mentioned unmanned boat safety control method based on the adaptive neural network observer.

[0024] In a fifth aspect, the present invention also provides a computer program product, which includes executable instructions, and the executable instructions are stored in a computer-readable storage medium; wherein, when the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the above-mentioned unmanned boat safety control method based on the adaptive neural network observer is implemented.

[0025] One or more of the above technical solutions have the following beneficial effects:

[0026] 1. The present invention provides an unmanned boat safety control method and system based on an adaptive neural network observer. An observer based on an adaptive neural network is designed to reconstruct the state of the system. Using the backstepping control concept, a step-by-step virtual control signal is designed. A nonlinear filter with filtering error suppression is designed to associate the virtual control signal to provide an accurate auxiliary reference signal. A safety controller is then constructed based on the observer and the filter to ensure the boundedness of each signal in the system. The above adaptive control strategy suppresses the negative impact of DoS attacks and external disturbances on the operation of the unmanned boat during actual operation, thereby solving the problem of poor applicability and poor accuracy of trajectory tracking control of unmanned boats subjected to DoS attacks and interference.

[0027] 2. In the present invention, the nonlinear characteristics of the unmanned boat are taken into consideration, the neural network approximation technology is integrated to effectively deal with nonlinear dynamics, and a neural network-based observer is designed to enhance the processing capability of estimating missing information of the unmanned boat system under DoS attacks. On this basis, an adaptive observation function is introduced, and the state of the system during the attack is approximated by an adaptive observer based on a neural network, and the influence of interference is suppressed by the adaptive observation function to ensure the accuracy of trajectory tracking; in addition, an adaptive safety controller based on the observer is designed to ensure bounded output tracking of the unmanned boat system under DoS attacks and interference, thereby ensuring the effectiveness and applicability of trajectory tracking.

[0028] 3. The method designed in the present invention has strong stability and robustness, can handle the negative impact of DoS attacks and external disturbances, and enable the unmanned boat system to navigate according to the predetermined trajectory, which is of practical significance.

[0029] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0031] Figure 1This is a flow chart of the unmanned boat safety control method based on the adaptive neural network observer according to an embodiment of the present invention;

[0032] Figure 2 This is a structural diagram of an unmanned boat in an embodiment of the present invention;

[0033] Figure 3 This is a diagram of the position tracking error of the unmanned boat in an embodiment of the present invention;

[0034] Figure 4 The expected trajectory and actual position trajectory of the unmanned boat in the embodiment of the present invention;

[0035] Figure 5 This is a diagram showing the actual speed trajectory of the unmanned boat in an embodiment of the present invention;

[0036] Figure 6 Schematic diagram of the state response curve of the filter of the unmanned boat in an embodiment of the present invention;

[0037] Figure 7 This is a position estimation diagram of the unmanned boat observer in an embodiment of the present invention;

[0038] Figure 8 This is a speed estimation diagram of the unmanned boat observer in an embodiment of the present invention;

[0039] Figure 9 Schematic diagram of the adaptive estimation value of the unmanned vehicle observer in an embodiment of the present invention;

[0040] Figure 10 Schematic diagram of the adaptive estimation value of the neural network weight of the unmanned boat in an embodiment of the present invention;

[0041] Figure 11 Schematic diagram of a virtual control input response curve of the first-order system of an unmanned boat in an embodiment of the present invention;

[0042] Figure 12 Schematic diagram of the actual control input response curve of the unmanned boat in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] It should be noted that the following detailed descriptions are exemplary only and are intended to describe specific embodiments and provide further explanation of the present invention, and are not intended to limit the exemplary embodiments according to the present invention. Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as those commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0044] Explanation of terms

[0045] (1) An unmanned boat is an unmanned surface vessel.

[0046] (2) Adaptive control refers to the process of online estimation and adjustment of system control parameters so that the control system can adapt to changes in the system's internal dynamics or external disturbances.

[0047] (3) Denial of service attack, or DoS attack, is when the attacker sends a large amount of useless data to block the channel from transmitting system data in real time, causing the system to be unable to work properly.

[0048] (4) A neural network is a computational model consisting of a large number of interconnected nodes (or neurons). Through multi-layer combination and stacking, the neural network can well approximate complex nonlinear functions.

[0049] (5) External disturbance refers to the disturbance of the external environment of the control system, such as strong wind, surge, ocean current, etc., which will affect the performance of the unmanned boat system.

[0050] Example 1

[0051] This embodiment provides a safety control method for an unmanned boat based on an adaptive neural network observer. Figure 1 As shown in the figure, when the unmanned boat system operates in an environment with DoS attack and external disturbance conditions, an adaptive observer and a safety controller are established through system error and neural network to enable the unmanned boat to track the preset target trajectory. The method specifically includes the following steps:

[0052] Step S1: Use the dynamic equation to construct a second-order dynamic model of the unmanned boat and obtain the actual position and speed state of the unmanned boat.

[0053] First, the unmanned boat dynamics model and the second-order system model are established.

[0054] Step S101: Establish the unmanned boat dynamics model through the Euler-Lagrange dynamics equation. Figure 2 As shown, set the ground coordinate system X e O e Y e and the ship coordinate system X v O v Y v , define x s and y s Unmanned Boat X e Axis, Y e Axis direction position state, φ is the yaw angle of the unmanned boat; accordingly, define u s ,v s ,r s Unmanned Boat X v Axis, Y vThe velocity state in the axial direction and the yaw angular velocity. Through the Euler-Lagrange dynamics equation, the unmanned boat dynamics model is established as:

[0055]

[0056] Among them, x1:=(x s ,y s ,φ) T and v:=(u s ,v s ,r s ) T Respectively represent the position and velocity state vectors of the unmanned boat, := is the definition symbol, T represents the transposition of the vector, is the rotation matrix of the transformation variables between the earth-fixed inertial reference frame and the unmanned vehicle fixed reference frame; M is the positive definite symmetric inertia matrix; C(v) represents the Coriolis force and centrifugal force vector; D(v) is the fluid dynamics damping parameter matrix; d is the unknown bounded external disturbance; τ is the generalized control force vector of external input.

[0057] Step S102: Define the position and velocity state vectors of the UAV and convert the UAV dynamic model into a second-order dynamic model. Specifically, define x2 = J(φ)v and convert the UAV dynamic model into a second-order dynamic model, which can be expressed as a first-order position system dynamic model and a second-order velocity system dynamic model, as follows:

[0058]

[0059] Where y(t) is the position output of the unmanned boat, u(t)=J(φ)M -1 τ represents the control input, ω(t)=J(φ)M -1 d is a bounded external disturbance that satisfies is an unknown constant, is a nonlinear dynamic that can be represented by a continuous smooth function.

[0060] Step S2: Using a neural network to approximate the online nonlinear dynamics of the position and velocity states in the second-order dynamic model, a neural network-based adaptive observer is designed to estimate the first-order system position state and the second-order system velocity state under DoS attacks and external interference.

[0061] To accurately estimate missing information in the system, this embodiment utilizes the online parameter adjustment capabilities of adaptive technology and the strong nonlinear dynamic approximation capabilities of neural network technology to design an observer based on an adaptive neural network. This achieves strong anti-interference capabilities and effectively estimates missing information. Specifically, combining adaptive and neural network control technologies, the design of an adaptive observer based on a neural network includes the following steps:

[0062] Step S201: Based on the constructed second-order dynamic model of the unmanned boat, the observation state of the unmanned boat position and speed is obtained. Combined with the obtained actual position and speed state of the unmanned boat, the observation error of the unmanned boat is constructed as:

[0063]

[0064] where x = [x1, x2] T is the actual state vector, x1 and x2 represent the actual position state and actual speed state respectively; is the observation state vector, is the position estimate, x s ,y s , the estimated value of ψ, is the velocity estimate, u s ,v s , the estimated value of r; e1 is the position observation error, and e2 is the velocity observation error.

[0065] Step S202: Using the radial basis function neural network in the neural network to approximate the online nonlinear dynamics g(x(t)) of the position and velocity states in the model can be expressed as:

[0066] g(x|W)=W T Ψ(x(t));

[0067] Where W represents the ideal weight of the neural network, Ψ(x(t)) is the Gaussian activation function, and the expression is where c l is the center of the activation function, b l is the width of the activation function, and exp represents the exponential function with the natural constant e as the base.

[0068] Further, using Represents the state vector x=[x1,x2] T The estimate of , can be obtained:

[0069]

[0070] in, represents an estimate of the ideal weights W of the neural network.

[0071] Step S203: Introduce the observer disturbance compensation term and design an adaptive observer based on a neural network, which can be expressed as:

[0072]

[0073] in, is the estimated output, Neural network approximation dynamics representing nonlinear dynamics, B=[0,I3] T , Υ=[0,I3] T , C=[I3,0] T , I3 is the 3D identity matrix, K is the compensation term for the observer disturbance, which is designed as:

[0074]

[0075] in, S(0,∞) represents the period of normal system operation, Ξ(0,∞) represents the period of system attack, η1 is a positive constant greater than 1, and η2 is a positive constant greater than 0; is an unknown positive constant, They are The estimated value of is adaptively updated as:

[0076]

[0077] Among them, λ1,λ2,λ3 are positive constants of adaptive weights, is a positive constant.

[0078] Step S3: According to the preset expected trajectory and the actual and estimated position states, the actual and estimated position tracking errors of the unmanned boat are determined, thereby constructing a virtual controller for the first-order position system of the unmanned boat.

[0079] Step S301: Establish the first-order position system error model of the unmanned boat. First, the differentiable expected trajectory is set as y r (t):=[y r1 ,y r2 ,y r3 ] T According to the expected trajectory and the constructed dynamic model, the actual position tracking error of the unmanned boat system is established: z1(t): = [z 1,1 ,z 1,2 ,z 1,3 ] T , defined as:

[0080] z1=yy r ;

[0081] Secondly, based on the observer and the expected trajectory in step S203, the position tracking error of the unmanned boat system with and without DoS attack is established as:

[0082]

[0083] Step S302: Design a virtual controller for the first-order system of the unmanned vehicle. Specifically, based on the estimated position tracking error of the unmanned vehicle obtained in the previous step, a virtual controller for the first-order position system of the unmanned vehicle is constructed. The virtual controller is used to output a virtual control signal β1 to ensure the stability of the position error system.

[0084] Among them, the output virtual control signal is expressed as:

[0085]

[0086] Among them, α>0.5, is the expected trajectory y r The derivative of .

[0087] Step S4: Design a nonlinear filter based on the virtual control signal output by the virtual controller to obtain a trajectory tracking signal of the second-order velocity system, and then construct an adaptive controller for the second-order velocity system in combination with the estimated velocity state.

[0088] Step S401: Based on the virtual control signal output by the virtual controller, a nonlinear filter is designed to filter the virtual control signal and compensate for the filtering error to provide a reference trajectory for the second-order velocity system of the unmanned boat. Let θ1 be the filtered virtual control vector, which can be expressed as:

[0089]

[0090] Among them, α 1,2 is a constant greater than 1, α 2,2 is a constant greater than 0, satisfying (α 1,2 -1)|q1| 2 ≥α 2,2 , q1=θ1-β1 is the filtering error, and the initial value θ1(0)=β1(0); is the dynamics of θ1, that is, θ1 is based on This dynamic equation changes.

[0091] Furthermore, the second-order speed system error model and safety control strategy of the unmanned boat are established.

[0092] Step S402: Based on the trajectory tracking signal of the second-order velocity system obtained in step S401 (i.e., the filtered virtual control vector θ1) and the estimated velocity state obtained in step S201, the estimated velocity tracking error of the unmanned vehicle under DoS attack is constructed as follows:

[0093]

[0094] Step S403: Design a speed control strategy. Based on the speed tracking error estimated in step S402, the adaptive observer (step S203) based on the neural network (step S202) and the nonlinear filter (step S401) are combined, and according to the Lyapunov stability principle, an adaptive controller for the second-order speed system is designed as follows:

[0095]

[0096] Among them, α2 is a positive constant, The adaptive law is:

[0097]

[0098] Where l = 1, 2, ..., L, κ l is a positive constant, r l is the adaptive weight.

[0099] Step S6: Based on the virtual controller and the adaptive controller, the desired trajectory of the unmanned boat is tracked under the DoS attack and disturbance.

[0100] As another implementation, step S7, theoretical verification of the above scheme is performed, that is, constructing a Lyapunov function, analyzing the error system of the unmanned vehicle according to the Lyapunov stability theorem, and performing stability verification on the observation error and tracking error of the unmanned vehicle system as well as the adaptive controller and the nonlinear filter, including the following steps:

[0101] Step S701: theoretical verification of the observer.

[0102] The above observation error model e(t) can be rewritten as:

[0103]

[0104] Construct the Lyapunov function as:

[0105]

[0106] in,

[0107] Taking the derivative of the above function we get:

[0108]

[0109] in, Satisfies ||ρ(t)||≤ρ 0 , ρ 0 >0 is a bounded constant.

[0110] exist In this case, the parameter K in step S203 is substituted, according to We can get:

[0111]

[0112] Where μ>0, By the following inequality:

[0113]

[0114] Finally, we get:

[0115]

[0116] Step S702: theoretical verification of the controller.

[0117] First, construct the Lyapunov function:

[0118]

[0119] in, z1=yy r .

[0120] Taking the derivative of the above function we get:

[0121]

[0122] The virtual control strategy in step S302 Substituting into the above formula, considering t∈S(0,∞) and t∈Ξ(0,∞), according to Young's inequality available:

[0123]

[0124] Secondly, construct the Lyapunov function as follows:

[0125]

[0126] in,

[0127] Taking the derivative of the above function we get:

[0128]

[0129] According to the definition of q1 and θ1 in step S302, we can obtain:

[0130]

[0131] And when (α 1,2 -1)||q1|| 2 ≥α2,2 When established, you can get:

[0132]

[0133] According to Young's inequality:

[0134]

[0135] Finally, we can get:

[0136]

[0137] in,

[0138] Select The final result of the above derivation can be rewritten as:

[0139]

[0140] when hour, V(t)≤p.

[0141] According to Lyapunov's stability theorem, the controller can ensure that the system output can track the reference signal and all error signals can converge to a small area.

[0142] Preferably, in order to further verify the superiority of the solution proposed in this embodiment, the effectiveness of the method and system of the present invention is verified by actual operation through computer simulation software MATLAB.

[0143] Specifically, this example uses the computer software MATLAB to verify the invented control method. The parameters related to each step in the simulation are selected as follows, among which the parameters of the unmanned boat are selected as follows:

[0144]

[0145] in,

[0146]

[0147] In the simulation, the expected trajectory is selected as y r =[2×sin(2t)m,2cos(0.5t)m,0.5rad] T , the parameters of the controller, observer, filter and adaptive law related to each step are selected as: μ = 0.4, α = 3, α2 = 1, α 1,2 =1.2,α 2,2 =0.01, eta1=1.2, eta2=0.01, λ k =0.2, κl =1, r l = 0.2, k = 1, 2, 3, l = 1, 2, 3, 4, 5. The external perturbation is set to d(t) = -0.1 × cos(0.2t) + 0.2. The DoS attack occurs within the interval Ξ(τ, t): = [7, 7.5] ∪ [13, 13.7] ∪ [24, 24.5] ∪ [27, 27.7] ∪ [35, 35.5].

[0148] like Figure 3 、 Figure 4 As shown in Figure 2, the proposed safety control method can track the desired trajectory and operate stably under DoS attacks and external disturbances. Figure 5 、 Figure 6 As shown in Figure 2, the designed safety controller and filter can make the speed state and filter signal of the unmanned boat run stably under DoS attacks and external disturbances; Figure 7 、 Figure 8 As shown in , the designed neural network-based adaptive observer can better estimate the position and speed information of the unmanned boat and has good robustness to external disturbances; Figure 9 、 Figure 10 As shown in , the self-adaptive parameter estimation of the unmanned boat makes the system more adaptable to disturbances, and the parameter estimation value can also change with the state change without divergence; Figure 11 、 Figure 12 As shown in the figure, the virtual control input and actual control input of the unmanned boat can adjust the control input compensation impact under DoS attacks and external disturbances.

[0149] This example addresses the safety control of unmanned watercraft systems under DoS attacks and external interference by proposing a neural network-based adaptive observation and control method. By constructing an adaptive neural network-based observer and nonlinear filter to approximate the state and design auxiliary reference signals, a safety control strategy based on neural networks and backstepping control is proposed based on the signals from the observer and filter. Lyapunov stability theory is used to obtain bounded safety results for the unmanned watercraft system. Furthermore, the effectiveness of the proposed adaptive neural network-based observation and safety control strategy is demonstrated using a class of unmanned watercraft systems as an example.

[0150] Example 2

[0151] This embodiment provides an unmanned boat safety control system based on an adaptive neural network observer, including:

[0152] The data acquisition and model building module is used to build a second-order dynamic model of the unmanned boat using the dynamic equations and obtain the actual position and speed state of the unmanned boat;

[0153] The state estimation module is used to use neural networks to approximate the online nonlinear dynamics of the position and velocity states in the second-order dynamic model, and to design a neural network-based adaptive observer to estimate the first-order system position state and the second-order system velocity state under DoS attacks and external disturbances;

[0154] The virtual controller construction module is used to determine the actual and estimated position tracking errors of the unmanned vehicle based on the preset desired trajectory and the actual and estimated position states, thereby constructing a virtual controller for the unmanned vehicle's first-order position system;

[0155] An adaptive controller building module is used to design a nonlinear filter based on the virtual control signal output by the virtual controller to obtain the trajectory tracking signal of the second-order velocity system. The module then combines the estimated velocity state to build an adaptive controller for the second-order velocity system.

[0156] The tracking control module is used to track the desired trajectory of the unmanned boat under DoS attacks and disturbances based on a virtual controller and an adaptive controller.

[0157] Example 3

[0158] This embodiment provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing the above method provided in this embodiment when executing the executable instructions stored in the memory.

[0159] Example 4

[0160] This embodiment further provides a computer-readable storage medium storing executable instructions. When the executable instructions are executed by a processor, the processor will be caused to execute the above method provided in this embodiment.

[0161] Example 5

[0162] This embodiment provides a computer program product including executable instructions, which are computer instructions stored in a computer-readable storage medium. When a processor of an electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the electronic device performs the method provided in this embodiment.

[0163] The steps involved in the above embodiments 2 to 5 correspond to those in embodiment 1. For detailed implementation, please refer to the relevant description of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media that includes one or more instruction sets; it should also be understood to include any medium that can store, encode, or carry an instruction set for execution by a processor and cause the processor to perform any method of the present invention.

[0164] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computer device. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0165] The above description is only a preferred embodiment of the present invention. Although the specific implementation of the present invention is described in conjunction with the accompanying drawings, it does not limit the scope of protection of the present invention. Those skilled in the art should understand that on the basis of the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present invention.

Claims

1. A safety control method for an unmanned boat based on an adaptive neural network observer, characterized in that: include: Using the dynamic equations, the second-order dynamic model of the unmanned boat is constructed, and the actual position and speed state of the unmanned boat is obtained; By using neural networks to approximate the online nonlinear dynamics of position and velocity states in a second-order dynamic model, a neural network-based adaptive observer is designed to estimate the first-order system position state and the second-order system velocity state under DoS attacks and external disturbances. According to the preset desired trajectory, combined with the actual and estimated position states, the actual and estimated position tracking errors of the unmanned vehicle are determined, thereby constructing a virtual controller for the first-order position system of the unmanned vehicle; According to the virtual control signal output by the virtual controller, a nonlinear filter is designed to obtain the trajectory tracking signal of the second-order velocity system. Then, combined with the estimated velocity state, an adaptive controller for the second-order velocity system is constructed. Based on the virtual controller and adaptive controller, the desired trajectory of the unmanned boat is tracked under DoS attack and disturbance.

2. The unmanned boat safety control method based on the adaptive neural network observer according to claim 1 is characterized in that: The construction process of the second-order dynamic model of the unmanned boat is as follows: The unmanned boat dynamics model is established through the Euler-Lagrange dynamics equation; The position and velocity state vectors of the unmanned boat are defined, and the unmanned boat dynamic model is converted into a second-order dynamic model; wherein, the model includes a first-order position system dynamic model and a second-order velocity system dynamic model.

3. The unmanned boat safety control method based on the adaptive neural network observer according to claim 1 is characterized in that: The radial basis function neural network in the neural network is used to approximate the online nonlinear dynamics of the position and velocity states in the model, and the observer disturbance compensation term is introduced to design an adaptive observer based on the neural network.

4. The unmanned boat safety control method based on the adaptive neural network observer according to claim 1 is characterized in that: Based on the position tracking error estimated by the unmanned vehicle, a virtual controller of the first-order position system of the unmanned vehicle is constructed. The virtual controller is used to output a virtual control signal to ensure the stability of the position error system. The output virtual control signal is expressed as: Among them, α>0.5, represents the expected trajectory y r The derivative of represents the estimated position tracking error of the unmanned boat with / without DoS attack; According to the virtual control signal output by the virtual controller, a nonlinear filter is designed to filter the virtual control signal and compensate for the filtering error to provide a reference trajectory for the second-order speed system of the unmanned boat. Expressed as: Among them, α 1,2 is a constant greater than 1, α 2,2 is a constant greater than 0, satisfying (α 1,2 -1)|q1| 2 ≥α 2,2 , q1=θ1-β1 is the filtering error, θ1 is the filtered virtual control vector, β1 is the virtual control signal, and the initial value θ1(0)=β1(0).

5. The unmanned boat safety control method based on adaptive neural network observer according to claim 1 is characterized in that: According to the trajectory tracking signal of the second-order velocity system and the estimated velocity state, the velocity tracking error estimated by the unmanned boat under DoS attack is constructed as follows: in, is the velocity estimate, θ1 is the filtered virtual control vector; According to the estimated speed tracking error, combined with the adaptive observer based on neural network and nonlinear filter, according to the Lyapunov stability principle, the adaptive controller of the second-order speed system is designed as follows: Among them, α2 is a positive constant, K is a constant, The adaptive law is: Where l = 1, 2, ..., L, κ l is a positive constant, r l is the adaptive weight, is the observation state vector.

6. The unmanned boat safety control method based on adaptive neural network observer according to claim 1, characterized in that: The Lyapunov function is constructed, and according to the Lyapunov stability theorem, the observation error and tracking error of the unmanned boat system as well as the stability of the adaptive controller and nonlinear filter are verified.

7. An unmanned boat safety control system based on an adaptive neural network observer, characterized in that: include: The data acquisition and model building module is used to build a second-order dynamic model of the unmanned boat using the dynamic equations and obtain the actual position and speed state of the unmanned boat; The state estimation module is used to use neural networks to approximate the online nonlinear dynamics of the position and velocity states in the second-order dynamic model, and to design a neural network-based adaptive observer to estimate the first-order system position state and the second-order system velocity state under DoS attacks and external disturbances; The virtual controller construction module is used to determine the actual and estimated position tracking errors of the unmanned vehicle based on the preset desired trajectory and the actual and estimated position states, thereby constructing a virtual controller for the unmanned vehicle's first-order position system; An adaptive controller building module is used to design a nonlinear filter based on the virtual control signal output by the virtual controller to obtain the trajectory tracking signal of the second-order velocity system. The module then combines the estimated velocity state to build an adaptive controller for the second-order velocity system. The tracking control module is used to track the desired trajectory of the unmanned boat under DoS attacks and disturbances based on a virtual controller and an adaptive controller.

8. An electronic device, characterized in that: include: a memory for storing executable instructions; The processor is configured to implement the unmanned boat safety control method based on the adaptive neural network observer according to any one of claims 1 to 6 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium, characterized in that Executable instructions are stored, which are used to cause the processor to execute the executable instructions to implement the unmanned boat safety control method based on the adaptive neural network observer according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes executable instructions stored in a computer-readable storage medium; When the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the unmanned boat safety control method based on the adaptive neural network observer according to any one of claims 1 to 6 is implemented.

Images