Data-driven safety control method and system for unmanned ship heading angle system

Abstract

The present invention discloses a data-driven safety control method and system for an unmanned ship heading angle system, which belongs to the field of unmanned ship intelligent control. A dynamic linearized data model of an unmanned ship heading angle system with interference terms is constructed; partial derivative estimates and controllers of the model are obtained based on the model-free adaptive control principle; unknown external interference and nonlinear uncertainty are estimated through a discrete extended state observer, and the output of the unmanned ship heading angle system is estimated; partial derivative estimates and controllers considering discrete extended state observers are obtained; the obtained controller is updated based on an anti-saturation compensation method; and finally, the safety control of the unmanned ship heading angle system is achieved. The unmanned ship heading controller developed by the present invention breaks through the limitations of traditional control methods, does not rely on complex system model information, and only uses the input and output data of the system to achieve a completely data-driven intelligent control strategy.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent control of unmanned ships, and in particular relates to a data-driven safety control method and system for an unmanned ship heading angle system. Background Art

[0002] An unmanned ship is an unmanned vessel that can perform predetermined tasks and plays an important role in enemy ship tracking, ocean monitoring, and maritime rescue. However, environmental factors such as wind, current, and waves pose challenges to the heading control of unmanned ships. At present, the heading control algorithms of unmanned ships are mainly divided into model-based and model-free. When the model information is accurate, the model-based control method is effective, but the complex nonlinear characteristics of unmanned ships make it very difficult to establish an accurate model, which affects the control effect.

[0003] Model-free control technologies mainly include PID control, iterative learning control, model-free adaptive control and reinforcement learning control. The controller of model-free control technology does not rely on the system model, but only needs system data information. When the system model is difficult to establish, model-free control technology can effectively control the system. Model-free adaptive control does not rely on the model parameters of the controlled system, but only uses the input / output data of the system. By estimating the system online in real time, model-free adaptive control can maintain good control even if the system parameters are inaccurate or change frequently.

[0004] Environmental disturbances such as wind, current, and waves can affect the motion of unmanned ships, as well as the nonlinear uncertainty of the model. In order to achieve high-performance motion control of unmanned ships in complex marine environments, disturbance and uncertainty estimation is a key issue. At the same time, actuator saturation is a serious problem in unmanned ship applications. Due to the physical limitations of actual actuators, the rotation amplitude and rate of the servo cannot exceed certain limits. Actuator saturation can affect system control accuracy and reduce system stability. These challenges need to be addressed through advanced control algorithms and technologies.

[0005] Currently, there is little research on data-driven heading control of unmanned ships, especially considering the nonlinear uncertainty, wave interference and actuator saturation of unmanned ships in actual situations, so it remains an important issue in this field. Summary of the invention

[0006] The purpose of the present invention is to provide a data-driven unmanned ship heading angle system safety control method and system. The proposed controller does not need to use the unmanned ship model information, but only uses the system input / output data to achieve the unmanned ship's heading angle to accurately track the reference heading angle. It takes nonlinear uncertainty, wave interference and actuator saturation into consideration and has wide applicability.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] In a first aspect, the present invention discloses a data-driven unmanned ship heading angle system safety control method, comprising:

[0009] 1) Based on unknown external disturbances and nonlinear uncertainties, a dynamic linearization data model of the unmanned ship heading angle system with disturbance terms is constructed;

[0010] 2) obtaining a partial derivative estimate and a controller of the model based on the model-free adaptive control principle;

[0011] 3) Estimating unknown external disturbances and nonlinear uncertainties through discrete extended state observers, as well as estimating the output of the unmanned ship heading angle system;

[0012] 4) Based on the result obtained in step 3), the partial derivative estimate and controller of step 2) are updated to obtain the partial derivative estimate and controller considering the discrete extended state observer;

[0013] 5) updating the controller obtained in step 4) based on the anti-saturation compensation method;

[0014] 6) Based on the result obtained in step 3), the partial derivative estimation obtained in step 4), and the controller obtained in step 5), the unmanned ship is subjected to heading angle tracking control to achieve safe control of the unmanned ship heading angle system.

[0015] In a second aspect, the present invention discloses a safety control system for an unmanned ship heading angle system for implementing the method, comprising:

[0016] A model acquisition module, which is used to construct a dynamic linearization data model of the unmanned ship heading angle system with interference terms based on unknown external interference and nonlinear uncertainty;

[0017] A partial derivative estimation and controller acquisition module, which is used to obtain the partial derivative estimation and controller of the model based on the model-free adaptive control principle;

[0018] An estimation module, which is used to estimate unknown external disturbances and nonlinear uncertainties through a discrete extended state observer, and to estimate the output of the unmanned ship heading angle system;

[0019] An initial update module, which updates the results obtained by the partial derivative estimation and controller acquisition module based on the results obtained by the estimation module, and obtains the partial derivative estimation and controller considering the discrete extended state observer;

[0020] An updating module, which is used to update the controller obtained by the initial updating module based on an anti-saturation compensation method;

[0021] The control module performs heading angle tracking control on the unmanned ship based on the results obtained by the estimation module, the partial derivative estimation obtained by the initial update module and the controller obtained by the update module, so as to realize the safe control of the heading angle system of the unmanned ship.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] 1) The present invention is based on model-free adaptive control, takes into account the equivalent dynamic linearization data modeling of the unmanned ship heading angle system with unknown external interference and nonlinear uncertainty, and designs a data-driven unmanned ship heading controller so that the heading angle of the unmanned ship can track the set reference heading angle. This controller has the characteristics of model-free, adaptive and fault-tolerant, and exhibits extremely high robustness and reliability. Model-free means that the controller does not require model information of the unmanned ship, and only uses system input / output data for control. Adaptability means that the controller can adjust controller parameters to maintain system stability according to changes in the external environment, and can adapt to changes and intensity of external interference. Fault tolerance means that the controller can still maintain system control capabilities when the actuator is saturated, ensuring system stability and safety, thereby improving the data-driven unmanned ship heading control capabilities in complex environments.

[0024] 2) The present invention takes into account the influence of nonlinear uncertainty, wave interference and actuator saturation. The discrete extended state observer is designed to estimate the unknown external interference and nonlinear uncertainty, and the corresponding compensation control is performed to reduce the influence of uncertainty and interference, thereby improving the stability of the system and having strong robustness; at the same time, the introduction of the anti-saturation compensator can effectively resist the adverse effects of actuator saturation, and achieve high performance under the condition of actuator saturation, providing key technical support for the safe control of the heading angle system of the unmanned ship based on data-driven. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a flow chart of a data-driven safety control method for an unmanned ship heading system according to an exemplary embodiment;

[0026] Figure 2 is a schematic diagram of the heading angle tracking of an unmanned ship according to an embodiment of the present invention;

[0027] Figure 3 is a schematic diagram of the heading angle tracking error of an unmanned ship according to an embodiment of the present invention;

[0028] Figure 4 is a schematic diagram of the change of the rudder angle of the unmanned ship according to an embodiment of the present invention;

[0029] Figure 5 is a schematic diagram of a saturation compensation signal of an actuator of an unmanned ship according to an embodiment of the present invention;

[0030] Figure 6 It is a schematic diagram of interference and uncertainty observation error of a discrete extended state observer of an unmanned ship according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The present invention is further described and illustrated below in conjunction with specific embodiments. The embodiments are merely exemplary of the present disclosure and do not define the scope of limitation. The technical features of each embodiment of the present invention may be combined accordingly without conflicting with each other.

[0032] Figure 1 is a flow chart of a data-driven unmanned ship heading angle system safety control method according to an exemplary embodiment. Figure 1 As shown, the method may include the following steps:

[0033] S1: Construct a dynamic linearized data model of the unmanned ship heading subsystem with interference terms;

[0034] S2: Obtaining a partial derivative estimate and a controller of the model based on a model-free adaptive control principle;

[0035] S3: Estimation of unknown external disturbances and nonlinear uncertainties, as well as the output of the unmanned ship heading angle system, through the discrete extended state observer;

[0036] S4: Based on the results obtained in S3, the partial derivative estimate and controller of S2 are updated to obtain the partial derivative estimate and controller considering the discrete extended state observer;

[0037] S5: Update the controller obtained in S4 based on the anti-saturation compensation method;

[0038] S6: Based on the result obtained in S3, the partial derivative estimation obtained in S4 and the controller obtained in S5, the unmanned ship is subjected to heading angle tracking control to achieve safe control of the unmanned ship heading angle system.

[0039] The discrete extended state observer, safe model-free adaptive control and anti-saturation compensation method are used to perform heading angle tracking control on the unmanned ship.

[0040] It can be seen from the above embodiments that the present invention aims at the problem of safe control of the unmanned ship heading system based on data-driven control, and considers the influence of nonlinear uncertainty, wave interference and actuator saturation at the same time, and constructs a discrete extended state observer, a safe model-free adaptive control and an actuator anti-saturation compensation method. The discrete extended state observer, the safe model-free adaptive control and the anti-saturation compensation method are used to perform heading angle tracking control on the unmanned ship. The controller does not need to rely on complex system model information, but only uses the input and output data of the system to realize a completely data-driven intelligent control strategy. It has significant advantages such as high computing efficiency, fast response speed, wide application range and good real-time performance, which significantly reduces the computing load, effectively saves energy consumption, and can effectively resist the adverse effects of actuator saturation, while reducing the adverse effects of wave interference on ship movement.

[0041] In the specific implementation of S1: construct a dynamic linearization data model of the unmanned ship heading angle system with interference terms;

[0042] Considering the ship fixed coordinate system and the earth coordinate system, the origin of the ship fixed coordinate system is set as the center of the unmanned ship. For an unmanned ship with uniform mass distribution and port-to-starboard symmetry, its kinematic model of horizontal motion can be described as:

[0043]

[0044] in, is the first derivative of the x-axis coordinate of the unmanned ship in the geodetic coordinate system; is the first derivative of the y-axis coordinate of the unmanned ship in the geodetic coordinate system; is the first-order derivative of the heading angle of the unmanned ship; U, V and r represent the surge speed, swing speed and yaw speed of the unmanned ship respectively.

[0045] In order to simplify the research on the horizontal motion control of the unmanned ship, the present invention adopts the Euler discretization method to express the kinematic model of its horizontal motion as follows:

[0046]

[0047] Wherein, T is the discrete sampling time, k is the moment; U(k) is the surge velocity of the unmanned ship at moment k; V(k) is the swing velocity of the unmanned ship at moment k; r(k) is the yaw velocity of the unmanned ship at moment k; x(k) is the x-axis coordinate of the unmanned ship in the geodetic coordinate system at moment k; y(k) is the y-axis coordinate of the unmanned ship in the geodetic coordinate system at moment k; ψ(k) is the heading angle of the unmanned ship at moment k.

[0048] In order to simplify the analysis without losing its generality, consider the following unmanned ship heading angle system with external disturbances:

[0049]

[0050] Among them, K is the ship maneuverability index of the unmanned ship, L is the ship maneuverability index of the unmanned ship, and they are both positive constants. u(k) is the control input of the unmanned ship heading angle system at time k, which represents the ship rudder angle here, and d(k) represents the current interference.

[0051] For a single-input single-output nonlinear system,

[0052]

[0053] Among them, Y(k)∈R, u(k)∈R and d(k)∈R represent the output, control input and disturbance of the unmanned ship heading angle system at time k, respectively. y 、n u and n d is an unknown integer and can be set by yourself; f(*) is a nonlinear function. The perturbation of the system is bounded, that is, |d(k)| d , b d is the limit value of the disturbance, b d >0 and is a constant. Obviously, the unmanned ship heading subsystem is the general form of formula (4). The present invention introduces a model-free adaptive control method, and formula (3) can be converted into the following compact dynamic linearization data model:

[0054] ΔY(k+1)=φ(k)Δu(k)+D(k),#(5)

[0055] Among them, ΔY(k+1)=Y(k+1)-Y(k), Δu(k)=u(k)-u(k-1), u(k) is the control input of the unmanned ship heading angle system at time k, φ(k) is the partial derivative of the dynamic linearization data model of the unmanned ship heading angle system with interference terms, |φ(k)|≤b φ , b φ is the limit value of the partial derivative, and b φ > 0 is a constant. D(k) is the sum of unknown external disturbances and nonlinear uncertainties at time k, and nonlinear uncertainties include model perturbation uncertainties (i.e., model parameter perturbation uncertainties).

[0056] The present invention uses a compact dynamic linearization-model-free adaptive control method to estimate the dynamic model of the unmanned ship heading system (3), and takes the linear sum of the heading angle and the heading angular velocity (yaw velocity) of the unmanned ship as the system output. The present invention proposes a compact dynamic linearization data model of the heading system considering external interference:

[0057]

[0058] ​Among them, Δψ(k+1)=ψ(k+1)-ψ(k), ψ(k) is the heading angle of the unmanned ship at time k; Δr(k+1)=r(k+1)-r(k), t(k) is the yaw speed of the unmanned ship at time k; K1>0 is the feedback gain of the heading and yaw speed of the unmanned ship, Δd(k)=d(k)-d(k-1),

[0059] Comparing formula (5) with formula (6), As D(k), the dynamic linearization data model of the unmanned ship heading system considering external interference (Equation (6)) can be transformed into (Equation (5), that is, the dynamic linearization data model of the unmanned ship heading subsystem with interference terms is Equation (5).

[0060] Since model-free adaptive control requires that the sign of φ(k) remains constant, the present invention can prove that when Δu(k)>0, there exists a minimum value K1, So that φ(k)>0. Similarly, when Δu(k)<0, there is a minimum value K1, Make φ(k)>0. This ensures the feasibility of the method proposed in the present invention.

[0061] In the specific implementation of S2: partial derivative estimation and controller for model-free adaptive control are constructed;

[0062] The design goal of the controller is to make the output Y(k) track the reference output signal Y expected by the unmanned ship as time increases. r (k). is a preset positive constant. The control performance is evaluated by minimizing the following function:

[0063] J(u(k))=|Y r (k+1)-Y(k+1)| 2 +λ|u(k)-u(k-1)| 2 ,#(7)

[0064] Among them, J(u(k)) is the performance index function of the controller; Y r (k+1) is the reference output signal expected by the unmanned ship at time k+1, and λ>0 is the weight coefficient. Substitute equation (5) into equation (7) and calculate the partial derivative of u(k) after substituting equation (5) into equation (7), and set the result after partial derivative to zero to obtain

[0065]

[0066] Where ρ∈(0,1] is the step size factor of u(k), which makes the control algorithm design more flexible.

[0067] In equation (8), φ(k) is unknown and cannot be used directly. Therefore, it is necessary to use an improved projection algorithm to estimate φ(k). The performance function of the unknown partial derivative is defined as:

[0068]

[0069] Among them, J(φ(k)) is the performance indicator function of the partial derivative; the weight factor μ>0. is the partial derivative estimate. is the partial derivative estimate at time k-1. Taking the partial derivative of equation (9) with respect to φ(k) and setting it to zero, we get

[0070] Among them, η∈(0,2] is The step size factor can provide greater flexibility in the control algorithm design.

[0071] In the specific implementation of S3: the unknown external disturbances and nonlinear uncertainties as well as the output of the unmanned ship heading angle system are estimated based on the discrete extended state observer;

[0072] Since D(k) in equations (8) and (10) is unknown and cannot be used directly, it is necessary to design a discrete extended state observer to estimate D(k):

[0073]

[0074] in, is the observed value of Y(k+1), i.e. the estimated output of the unmanned ship heading angle system; The observed value of D(k+1), that is, the estimated unknown external disturbance and nonlinear uncertainty M1 and M2 are appropriate parameters (that is, M1 and M2 are preset parameters).

[0075] set up is the observation error of Y(k); is the observation error of D(k), then we can get

[0076]

[0077] in, is the observer error, is the partial derivative estimation error, ΔD(k+1)=D(k+1)-D(k). When the matrix When the absolute values ​​of the eigenvalues ​​of are all less than 1, the discrete extended state observer can ensure that the estimation error is bounded.

[0078] In the specific implementation of S4: partial derivative estimation and controller for model-free adaptive control based on discrete extended state observer;

[0079] By discrete extended state observer, we can get Further partial derivative estimates are obtained as

[0080] Among them, ∈ is a small normal number (that is, ∈ is a preset normal number), It is initial sign(*) is the sign function. The algorithm reset mechanism (14) is introduced to make the partial derivative estimation algorithm more capable of tracking time-varying parameters.

[0081] Depend on Get the controller as

[0082]

[0083] Wherein, u0(k) is the controller of model-free adaptive control based on the construction of discrete extended state observer (i.e., u0(k) is the controller considering discrete extended state observer);

[0084] Adaptive error feedback control

[0085]

[0086] Among them, u0 ′ (k) is the updated controller obtained by updating the controller u0(k) based on adaptive error feedback control; β>0 is an adjustable controller parameter. The role of β is to weight the difference between the reference output and the estimated output at the current moment. By adjusting β, the controller's tracking performance of the reference output signal expected by the unmanned ship can be affected. Choosing a suitable β can achieve faster convergence speed, thereby reducing tracking error.

[0087] In the specific implementation of S5: an anti-saturation compensation method considering actuator saturation is constructed;

[0088] Actuator saturation is a serious problem in unmanned ship applications. Due to the physical limitations of actual actuators, the speed and torque of the motor in the drive system can only vary within a certain range, the rotation amplitude and rate of the servo cannot exceed a certain limit, and a certain control torque cannot be achieved. The existence of actuator saturation leads to oscillation, jitter and even instability when the command reaches near saturation, affecting the system control accuracy and reducing the system stability. In order to solve or alleviate this problem, by introducing auxiliary anti-saturation variables, the present invention designs a data-driven anti-saturation compensation control scheme, which achieves high performance when the actuator is saturated.

[0089] Aiming at the dynamic constraints in the heading angle control of unmanned ships, an anti-saturation compensation method is proposed to adjust the reference output signal Yr (k). The compensation signal θ(k) is designed as follows:

[0090]

[0091] Where γ∈(0,1], γ is the discount factor. u0 ′′ (k) is the value in u0 ′ The updated data-driven controller based on the anti-saturation compensation method is designed as follows:

[0092]

[0093] When considering actuator saturation, the actual actuator control is described as

[0094]

[0095] Among them, u max is the upper limit of the rudder angle. z ) is the final input signal of the system to the actuator, and the actuator control change amplitude satisfies

[0096]

[0097] Among them, Δu max is the upper limit of the rudder angle variation.

[0098] In the specific implementation of S6: based on the result obtained in S3 (i.e., Formula 11), the partial derivative estimation obtained in S4 (i.e., Formulas 13 and 14), and the controller obtained in S5 (i.e., Formula 18), the heading angle tracking control of the unmanned ship is performed to achieve safe control of the heading angle system of the unmanned ship.

[0099] In a specific embodiment of the present invention, S6 is: setting an initial value Will Substitute the value of into Equation 11 (that is, and get and Then set the preset And Y(1) and Y(2) obtained based on the actual situation are substituted into formula 13 to obtain Based on the preset θ(2), the obtained and And the known Y r (3), Y(2) obtains u0″(2), and substitutes the value of u0″(2) into equation 3 (i.e. let u(2)=u0″(2)), and obtains ψ(3) and r(3);

[0100] Based on the actual situation at the current moment and the partial values ​​obtained, the above steps are used to obtain the yaw speed and heading angle of the unmanned ship at a new moment, until the heading angle of the unmanned ship reaches the preset heading angle, completing the safety control of the unmanned ship heading angle system. If there is no subsequent task requirement, the unmanned ship will maintain the set heading angle for operation; if there is a new task requirement, the unmanned ship will perform heading angle safety tracking control according to the new reference angle.

[0101] The effectiveness of the proposed method of the present invention is verified through simulation;

[0102] The unmanned ship heading maneuverability parameters used in the simulation experiment are K=0.186 and T=1.068.

[0103] The initial state of the heading control subsystem is [ψ0r0] = [0°0° / s]. The controller parameters of this paper are λ = 0.1, μ = 1, η = 0.5, ρ = 0.5, β = 0.2, ε = 0.00001, γ = 0.2, K1 = 5, and the coefficients of the discrete extended state observer are m1 = 0.8 and M2 = 0.3. The reference heading angles are set to 90° and 180° respectively. The disturbance is set to d = 3*sin(0.2*k).

[0104] Under the complex conditions of reference heading angle change and current interference, the proposed data-driven unmanned ship heading angle system safety control method is applied to the simulation results of tracking the reference heading angle. Figure 2 shown. Figure 3 is the tracking error between the unmanned ship heading angle and the reference heading angle.

[0105] from Figure 2 and Figure 3 It can be seen that under the complex conditions of reference heading angle changes and current interference, the proposed data-driven unmanned ship heading angle system safety control method still has good control effect and small heading angle error. Figure 4 is the change of the rudder angle of the unmanned ship, Figure 5 is the compensation signal of the actuator saturation of the unmanned ship, from Figure 4 and Figure 5 It can be seen that the change of the rudder angle of the unmanned ship is always within a reasonable range. When the actuator is saturated, the anti-saturation compensator sends a compensation signal to improve the stability of the system. Figure 6 is the observation error of the discrete extended observer for the total disturbance, from Figure 6It can be seen that when the reference heading angle changes suddenly, the total disturbance estimation error curve fluctuates suddenly. This is because the design of the discrete extended state observer is related to the heading angle, so the fluctuation is reasonable; when the reference heading angle is constant, the total disturbance estimation responds quickly and the total disturbance estimation error converges to a boundary. This shows that the proposed data-driven safety control method for the unmanned ship heading angle system is feasible and effective.

[0106] The unmanned ship heading controller developed by the present invention breaks through the limitations of traditional control methods. It does not need to rely on complex system model information, but only uses the input and output data of the system to realize a completely data-driven intelligent control strategy. It has significant advantages such as high computing efficiency, fast response speed, wide application range and good real-time performance, which significantly reduces the computing load and effectively saves energy consumption. The controller can not only accurately track the preset reference heading angle to ensure that the unmanned ship successfully completes the established task, but also effectively resist the adverse effects of ocean current interference and nonlinear uncertainty of unmanned ships, while reducing the adverse effects of actuator saturation on ship movement, providing key technical support for the safe and stable operation of unmanned ships.

[0107] In this embodiment, a data-driven unmanned ship heading angle system safety control system is also provided, including:

[0108] A model acquisition module, which is used to construct a dynamic linearization data model of the unmanned ship heading angle system with interference terms based on unknown external interference and nonlinear uncertainty;

[0109] A partial derivative estimation and controller acquisition module, which is used to obtain the partial derivative estimation and controller of the model based on the model-free adaptive control principle;

[0110] An estimation module, which is used to estimate unknown external disturbances and nonlinear uncertainties through a discrete extended state observer, and to estimate the output of the unmanned ship heading angle system;

[0111] An initial update module, which updates the results obtained by the partial derivative estimation and controller acquisition module based on the results obtained by the estimation module, and obtains the partial derivative estimation and controller considering the discrete extended state observer;

[0112] An updating module, which is used to update the controller obtained by the initial updating module based on an anti-saturation compensation method;

[0113] The control module performs heading angle tracking control on the unmanned ship based on the results obtained by the estimation module, the partial derivative estimation obtained by the initial update module and the controller obtained by the update module, so as to realize the safe control of the heading angle system of the unmanned ship.

[0114] For the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment, and the implementation methods of the remaining modules will not be repeated here. The system embodiment described above is only schematic, 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 the present invention. Ordinary technicians in this field can understand and implement it without paying creative work.

[0115] The embodiments of the system of the present invention can be applied to any device with data processing capabilities, and the device with data processing capabilities can be a device or apparatus such as a computer. The system embodiments can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, the corresponding computer program instructions in the non-volatile memory are read into the memory by the processor of any device with data processing capabilities and run.

[0116] Those skilled in the art will readily appreciate other embodiments of the present application after considering the description and practicing the contents disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The description and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0117] Obviously, the above-described embodiments and drawings are only some examples of the present application. For those of ordinary skill in the art, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that, although the work done in this development process may be complicated and lengthy, for those of ordinary skill in the art, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application. Without departing from the concept of the present application, several variations and improvements can also be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A data-driven unmanned ship heading angle system safety control method, characterized in that: include: 1) Based on unknown external disturbances and nonlinear uncertainties, a dynamic linearization data model of the unmanned ship heading angle system with disturbance terms is constructed; 2) obtaining a partial derivative estimate and a controller of the model based on the model-free adaptive control principle; 3) Estimating unknown external disturbances and nonlinear uncertainties through discrete extended state observers, as well as estimating the output of the unmanned ship heading angle system; 4) Based on the result obtained in step 3), the partial derivative estimate and controller of step 2) are updated to obtain the partial derivative estimate and controller considering the discrete extended state observer; 5) updating the controller obtained in step 4) based on the anti-saturation compensation method; 6) Based on the result obtained in step 3), the partial derivative estimation obtained in step 4), and the controller obtained in step 5), the unmanned ship is subjected to heading angle tracking control to achieve safe control of the unmanned ship heading angle system; The step 2) is specifically: 2.1) Based on the model-free adaptive control principle, the partial derivative φ(k) of the model is obtained, and φ(k)= in, is the partial derivative estimate, the partial derivative estimate for: in, is the partial derivative estimate at time k-1; η is , η∈(0,2]; μ is the weight factor, and μ>0; φ(k) is the partial derivative of the dynamic linearization data model, L is the ship maneuverability index of the unmanned ship, K is the ship maneuverability index of the unmanned ship, Δψ(k)=ψ(k+1)-ψ(k), ψ(k) is the heading angle of the unmanned ship at time k, T is the discrete sampling time, K1 is the heading yaw speed feedback gain of the unmanned ship, Δr(k)=r(k+1)-r(k), r(k) is the yaw speed of the unmanned ship at time k, Δu(k)=u(k)-u(k-1), u(k) is the control input of the unmanned ship heading angle system at time k; D(k) is the sum of unknown external interference and nonlinear uncertainty at time k; ΔY(k)=Y(k)-Y(k-1), Y(k) is the output of the unmanned ship heading angle system at time k; 2.2) Based on the model-free adaptive control principle, the controller u(k) of the model is obtained, and the controller u(k) is: Where u(k-1) is the controller at time k-1; ρ is the step size factor of u(k), ρ∈(0,1]; Y r (k+1) is the reference output signal expected by the unmanned ship at time k+1, and the reference output signal is the linear sum of the heading angle and the yaw speed of the unmanned ship; λ is the weight coefficient, and λ>0; In the step 4), the partial derivative estimation of the discrete extended state observer is considered for: in, is the partial derivative estimate of the discrete extended state observer at time k; is the observed value of D(k-1), that is, the estimated unknown external disturbance and nonlinear uncertainty; The algorithm resets the partial derivative estimate The algorithm reset mechanism can track the parameters of real-time changes in real time: Among them, ∈ is a preset normal constant; It is initial And is a preset value; sign(*) is the sign function; The controller u0(k) considering the discrete extended state observer is: Among them, u0(k) is the controller considering the discrete extended state observer; Then, based on the adaptive error feedback control, the controller u0(k) is updated to obtain the updated controller u0 ′ (k) Where β is an adjustable controller parameter and β>0.

2. The method according to claim 1, characterized in that In step 1), the dynamic linearization data model of the unmanned ship heading angle system with interference terms is: ΔY(k+1)=φ(k)Δu(k)+D(k), Among them, ΔY(k+1)=Y(k+1)-Y(k), Y(k) is the output of the unmanned ship heading angle system at time k; φ(k) is the partial derivative of the dynamic linearization data model, L is the ship maneuverability index of the unmanned ship, K is the ship maneuverability index of the unmanned ship, Δψ(k)=ψ(k+1)-ψ(k), ψ(k) is the heading angle of the unmanned ship at time k, T is the discrete sampling time, K1 is the heading yaw speed feedback gain of the unmanned ship, Δr(k)=r(k+1)-r(k), r(k) is the yaw speed of the unmanned ship at time k, Δu(k)=u(k)-u(k-1), u(k) is the control input of the unmanned ship heading angle system at time k; D(k) is the sum of unknown external interference and nonlinear uncertainty at time k.

3. The method according to claim 1, characterized in that The step 3) is specifically: The output of the unknown external disturbance and nonlinear uncertainty and the heading angle system of the unmanned ship are estimated based on the discrete extended state observer: in, is the observed value of Y(k+1), i.e. the estimated output of the unmanned ship heading angle system; is the observed value of D(k+1), that is, the estimated unknown external disturbance and nonlinear uncertainty; M1 and M2 are preset parameters.

4. The method according to claim 1, characterized in that: In the step 5), specifically: First, based on the anti-saturation compensation method, the reference output signal Y is adjusted by the compensation signal θ(k) r (k); the compensation signal θ(k) is: Where γ is the discount factor, γ∈(0,1]; u0″(k) is the updated data-driven controller obtained based on u0′(k) based on the anti-saturation compensation method, which is:

5. A safety control system for an unmanned ship heading angle system for implementing the method described in claim 1, characterized in that: include: A model acquisition module, which is used to construct a dynamic linearization data model of the unmanned ship heading angle system with interference terms based on unknown external interference and nonlinear uncertainty; A partial derivative estimation and controller acquisition module, which is used to obtain the partial derivative estimation and controller of the model based on the model-free adaptive control principle; The partial derivative estimation and controller of the model are obtained based on the model-free adaptive control principle, specifically: 2.1) Based on the model-free adaptive control principle, the partial derivative φ(k) of the model is obtained, and in, is the partial derivative estimate, the partial derivative estimate for: in, is the partial derivative estimate at time k-1; η is , η∈(0,2]; μ is the weight factor, and μ>0; φ(k) is the partial derivative of the dynamic linearization data model, L is the ship maneuverability index of the unmanned ship, K is the ship maneuverability index of the unmanned ship, Δψ(k)=ψ(k+1)-ψ(k), ψ(k) is the heading angle of the unmanned ship at time k, T is the discrete sampling time, K1 is the heading yaw speed feedback gain of the unmanned ship, Δr(k)=r(k+1)-r(k), r(k) is the yaw speed of the unmanned ship at time k, Δu(k)=u(k)-u(k-1), u(k) is the control input of the unmanned ship heading angle system at time k; D(k) is the sum of unknown external interference and nonlinear uncertainty at time k; ΔY(k)=Y(k)-Y(k-1), Y(k) is the output of the unmanned ship heading angle system at time k; 2.2) Based on the model-free adaptive control principle, the controller u(k) of the model is obtained, and the controller u(k) is: Among them, u(k-1) is the controller at time k-1; ρ is the step size factor of u(k), ρ∈(0,1]; Y r (k+1) is the reference output signal expected by the unmanned ship at time k+1, and the reference output signal is the linear sum of the heading angle and the yaw speed of the unmanned ship; λ is the weight coefficient, and λ>0; An estimation module, which is used to estimate unknown external disturbances and nonlinear uncertainties through a discrete extended state observer, and to estimate the output of the unmanned ship heading angle system; An initial update module, which updates the results obtained by the partial derivative estimation and controller acquisition module based on the results obtained by the estimation module, and obtains the partial derivative estimation and controller considering the discrete extended state observer; Partial derivative estimation considering discrete extended state observer for: in, is the partial derivative estimate of the discrete extended state observer at time k; is the observed value of D(k-1), that is, the estimated unknown external disturbance and nonlinear uncertainty; The algorithm resets the partial derivative estimate The algorithm reset mechanism can track the parameters of real-time changes in real time: Among them, ∈ is a preset normal constant; It is initial And is a preset value; sign(*) is the sign function; The controller u0(k) considering the discrete extended state observer is: Among them, u0(k) is the controller considering the discrete extended state observer; Then, based on the adaptive error feedback control, the controller u0(k) is updated to obtain the updated controller u0 ′ (k) Where β is an adjustable controller parameter and β>0; An updating module, which is used to update the controller obtained by the initial updating module based on an anti-saturation compensation method; The control module performs heading angle tracking control on the unmanned ship based on the results obtained by the estimation module, the partial derivative estimation obtained by the initial update module and the controller obtained by the update module, so as to realize the safe control of the heading angle system of the unmanned ship.

Images