Agricultural machinery path tracking control method based on adaptive interval type-2 fuzzy second-order sliding mode

Abstract

The invention discloses an agricultural machinery path tracking control method based on a self-adaptive interval type-2 fuzzy second-order sliding mode, and belongs to the technical field of agricultural machinery navigation. The method mainly comprises the steps that 1, disturbance factors existing in the actual operation process of agricultural machinery are analyzed, and an agricultural machinery kinematic model and a path tracking model are constructed; 2, estimating a course-related unknown state and lumped disturbance by using an interval type-2 fuzzy logic system; 3, selecting a proper sliding variable, and establishing a second-order sliding mode kinetic equation; and 4, designing a self-adaptive interval type-2 fuzzy sliding mode controller to realize a path tracking target. The method has the advantages that firstly, the controller has higher robustness on parameter change and external interference; secondly, the controller can effectively reduce the chattering phenomenon in the control process, and the stability and reliability of the system are improved; and thirdly, the controller can improve the dynamic response speed and the control precision of the system while ensuring the stability of the system.

Description

Technical Field

[0001] The invention relates to an agricultural machinery path tracking control method based on interval type-2 fuzzy second-order sliding mode, belonging to the technical field of agricultural machinery navigation. Background Art

[0002] In the field of modern agricultural production, agricultural machinery is becoming more and more important. They play a key role in improving operating efficiency, reducing labor costs, and promoting the implementation of precision agriculture. The development of agricultural machinery navigation and path tracking technology is in line with the development trend of agricultural modernization and is conducive to improving the efficiency and accuracy of agricultural production. With the acceleration of urbanization, agricultural labor costs have risen, and rural areas are facing the problem of labor shortage, which has prompted agriculture to transform towards automation and intelligence. Agricultural machinery navigation and path tracking technology can help reduce dependence on manpower, improve crop yield and quality through precise farmland management and operations, and reduce resource waste. In addition, precision agriculture technology helps to achieve precise fertilization and pesticide application of crops, reduce the use of pesticides and fertilizers, improve the quality of agricultural products, and protect soil and water resources.

[0003] When designing a path tracking controller for the navigation system of an agricultural tractor, it is usually necessary to rely on the vehicle's position and heading data. However, the sensors used to determine the heading on agricultural machinery are often disturbed by measurement noise and vehicle vibration, which may cause large deviations in the heading data. This deviation will cause unnecessary fluctuations in the control signal, which in turn affects the accuracy and effectiveness of path tracking. Currently, second-order sliding modes have been widely studied in stability analysis, but their stability is usually assumed to be constant based on the uncertainty of the system. However, this assumption does not hold true in agricultural machinery path tracking where uncertainty changes with time and conditions. To this end, some scholars have introduced fuzzy logic systems, which have the ability to estimate uncertainty by integrating the empirical knowledge provided by human experts.

[0004] However, most existing studies rely on type-I fuzzy logic systems. Since the membership function is specified as a single value, it has limitations in dealing with the complex uncertainties in agricultural machinery path tracking, and it becomes challenging to obtain uncertainties with fuzzy boundaries or uneven distributions. In order to address these limitations, a type-II fuzzy logic system is introduced, which provides a more flexible way to deal with uncertainty by allowing fuzziness within the membership itself. Therefore, the present invention proposes a method that combines an adaptive type-II fuzzy logic system with a second-order sliding mode control, and uses the backstepping method to design a control strategy. By decomposing a high-order nonlinear system into multiple low-order subsystems, the control law design is simplified and the controllability of the system is improved. The control method has stronger robustness to parameter changes and external interference, effectively reduces the chattering phenomenon in the path tracking control process, improves the stability and reliability of the system, and improves the dynamic response speed and control accuracy of the system while ensuring the stability of the system. Summary of the invention

[0005] In order to solve the path tracking problem of existing wheeled agricultural machinery in complex realistic agricultural scenarios, the present invention studies the path tracking control of agricultural machinery from three aspects: vehicle and path tracking modeling, estimation of lumped disturbance using interval type-2 fuzzy logic system, and design of adaptive interval type-2 fuzzy sliding mode controller. A path tracking control method for agricultural machinery based on adaptive interval type-2 fuzzy second-order sliding mode is proposed.

[0006] A method for agricultural machinery path tracking control based on adaptive interval type-II fuzzy second-order sliding mode, comprising the following steps:

[0007] S1: Analyze the disturbance factors existing in the actual operation of agricultural machinery and build a path tracking model including disturbance;

[0008] S2: Based on the coordinate transformation method, the path tracking model is converted into a state equation in a strict feedback form that is convenient for controller design;

[0009] S3: Design fuzzy rules, fuzzy reasoning, type reduction methods and defuzzification methods in interval type-2 fuzzy logic systems;

[0010] S4: Using interval type-2 fuzzy logic system to estimate the unknown lumped disturbance of the system;

[0011] S5: Design of a second-order sliding mode controller based on adaptive interval type-2 fuzzy;

[0012] S6: Define and design the adaptive law parameters in the adaptive interval type-2 fuzzy sliding mode controller;

[0013] S7: Perform inverse transformation on the adaptive interval type-II fuzzy sliding mode controller to obtain the system control input, i.e., the steering angle of the front wheels of the agricultural machinery.

[0014] Considering that the actual operation of agricultural machinery will be affected by interference, a path tracking model including disturbance is established. The specific form is as follows:

[0015]

[0016] Where: L os Indicates the lateral deviation between the actual driving path of the agricultural machinery and the reference path. YesL os The first derivative of os Indicates the heading deviation between the actual driving path of the agricultural machinery and the reference path. is θ os The first-order derivative of , σ represents the direction coefficient, and is defined as negative in clockwise direction, v x represents the longitudinal speed of the agricultural machinery, L represents the wheelbase of the agricultural machinery, δ frepresents the steering angle of the front wheel of the agricultural machinery, R represents the radius of curvature of the reference path, and D(t) represents the aggregate disturbance of the external interference;

[0017] To facilitate reference path design, the curvature radius R of the reference path is converted into curvature c 0 , and assume that the agricultural machine moves forward along the reference path in a clockwise direction, that is, the direction coefficient σ=-1; in order to facilitate the processing of unknown system states x 2 , the system equation is further expressed using the coordinate transformation method, the specific form is as follows:

[0018]

[0019] Where: x 1 =L os , x 2 =v x sinθ os , x 1 and x 2 Indicates the system status. and Represents the system state x 1 and x 2 The first derivative of, u = tanδ f represents the input of the controller, p(t,x) and q(t,x) are auxiliary functions introduced to simplify complex problem solving processes, and are transformations of the original function form; represents the unknown lumped disturbance, D 1 (t) represents the disturbance acting on the controller u.

[0020] Select the single-point fuzzification method and define two fuzzy sets corresponding to the system state variables x 1 and x 2 , membership function μ 1 and μ 2 It is designed as a Gaussian function to quantify the membership of each state variable in its respective fuzzy set; the Gaussian membership function is designed, and the specific form is as follows:

[0021]

[0022] Where: μ 1 and μ 2 represents the Gaussian membership function, and is the standard form of the Gaussian function, corresponding to x 1 and x 2 The adjustment value of i is an index variable used to represent different fuzzy sets, with values ​​ranging from 1 to 5, which means that for the state variable x 1 and x2 There are five different Gaussian membership functions, each of which is By adjusting to change its position in the state space, each function corresponds to a different fuzzy set; 1 and x 2 Indicates the system status, x 1 =L os , x 2 =v x sinθ os , where L os Indicates the lateral deviation between the actual driving path of the agricultural machinery and the reference path, θ os Indicates the heading deviation between the actual driving path of the agricultural machinery and the reference path;

[0023] These membership functions will generate 5×1 vectors respectively, indicating the membership of each state variable on the five fuzzy sets;

[0024] The fuzzy basis function is obtained by using the product reasoning mechanism, the Karnik-Mendel (KM) algorithm, and the centroid defuzzification method. The specific form is as follows:

[0025] Ψ(x)=(ξ l (x)+ξ r (x)) / 2

[0026] Where: represents a vector consisting of normalized left interval membership values, represents a vector consisting of normalized right interval membership values, Represents the i-th element of the left interval vector, whose value is f l i With all f l i The ratio of the sum of (i from 1 to N), Represents the i-th element of the left interval vector, whose value is f l i With all f l i The ratio of the sum of (i from 1 to N), f l i and Determined by Karnik-Mendel reduction algorithm, where n represents the degree of membership of the input data point in the corresponding fuzzy set, N represents the dimension of the vector, and T represents the transposition operation;

[0027] The output of the interval type-2 fuzzy logic system is obtained in the following form:

[0028] y(x)=θT Ψ(x)

[0029] Where: θ T represents the adaptive parameter, and Ψ(x) represents the fuzzy basis function.

[0030] In the state equation of strict feedback form, p(t,x) and q(t,x) satisfy the following conditions, which are in the following form:

[0031]

[0032] Where: p(t,x) and q(t,x) are auxiliary functions introduced to simplify the complex problem solving process. They are transformations of the original function form. However, due to the influence of various uncertainties, these two functions have certain differences from the actual system. and q (t,x) are both greater than zero, represents the upper bound function of p(t,x), q (t,x) represents the lower bound function of q(t,x);

[0033] Using the output of interval type-2 fuzzy logic system, and q (t,x) is estimated, the specific form is:

[0034]

[0035] Where: and θ q represents a vector, and q (x) represents the fuzzy basis function, T represents the transposition operation, and Respectively and q A function of (t,x) that is dynamically approximated using a fuzzy logic system.

[0036] Design a second-order sliding mode controller u based on adaptive interval type-2 fuzzy, the specific form is:

[0037]

[0038] Where: β 1 , β 2 , ω is the system positive constant parameter, p and r 1 is a constant parameter and satisfies p ≥ r 1 =2r 2 >0,ω≥|ζ|, v represents the virtual control input used to compensate for uncertainty, and its specific form is:

[0039]

[0040] Where: and θ q represents the adaptive law parameters, and Respectively and q A function of (t,x) that is dynamically approximated using a fuzzy logic system.

[0041] The method according to claim 5 is characterized in that the second-order sliding mode controller defines and designs the adaptive law parameters, and the adaptive interval type-2 fuzzy sliding mode controller and Depends on and θ q , the specific form is:

[0042]

[0043] Where: and Respectively and θ q The first derivative of , γ 1 and γ 2 represents a normal number, and q (x) represents the fuzzy basis function.

[0044] By using the controller u = tanδ f Implement the inverse transformation to obtain the front wheel steering angle δ of the agricultural machinery f , the specific form is:

[0045]

[0046] Where: v represents the quantity composed of fuzzy logic system related functions, specific constants and sign functions in the adaptive second-order sliding mode controller, which is used to comprehensively adjust the controller behavior to adapt to system dynamic changes, handle uncertainties and achieve the desired control performance; It represents the dynamic approximation using interval type-2 fuzzy logic system q (t,x) function, β1, β 2 ,ω,p are the normal parameters of the system, r 1 、r 2 is the constant parameter of the system, s 1 、s 2 is the sliding variable; by adjusting the front wheel steering angle δ f Control, the final lateral deviation L os and heading deviation θ os will converge to zero.

[0047] Through the above technical scheme, compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The adaptive interval type-II fuzzy sliding mode controller described in the present invention has stronger robustness to parameter changes and external interference; the controller design only uses the agricultural machinery path tracking position deviation information, reducing the sensor cost.

[0049] 2. The adaptive interval type-2 fuzzy sliding mode controller described in the present invention can effectively reduce the chattering phenomenon in the control process, improve the stability and reliability of the system, and obtain higher path tracking accuracy.

[0050] 3. The adaptive interval type-II fuzzy sliding mode controller described in the present invention can improve the dynamic response speed and control accuracy of the system while ensuring the stability of the system, thereby achieving better control effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a control block diagram of the agricultural machinery path tracking control system of the present invention;

[0052] Figure 2 This is a schematic diagram of the path tracking of agricultural machinery;

[0053] Figure 3 It is the block diagram of interval type-2 fuzzy logic system;

[0054] Figure 4 It is a schematic diagram of interval type-2 fuzzy membership function; DETAILED DESCRIPTION

[0055] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0056] A path tracking control method for agricultural machinery based on interval type-2 fuzzy second-order sliding mode, the specific process of the implementation of the method is as follows:

[0057] S1: Analyze the disturbance factors existing in the actual operation of agricultural machinery and build a path tracking model including disturbance. The path tracking diagram of agricultural machinery is shown in Figure 2 As shown;

[0058] S1.1. Considering that the actual operation of agricultural machinery will be affected by disturbances, a path tracking model including disturbances is established. The specific form is as follows:

[0059]

[0060] Where: L os Indicates the lateral deviation between the actual driving path of the agricultural machinery and the reference path. YesL os The first derivative of osIndicates the heading deviation between the actual driving path of the agricultural machinery and the reference path. is θ os The first-order derivative of , σ represents the direction coefficient, and is defined as negative in clockwise direction, v x represents the longitudinal speed of the agricultural machinery, L represents the wheelbase of the agricultural machinery, δ f represents the steering angle of the front wheel of the agricultural machinery, R represents the radius of curvature of the reference path, and D(t) represents the aggregate disturbance of the external interference;

[0061] S1.2. To facilitate reference path design, convert the curvature radius R of the reference path into curvature c 0 , and assume that the agricultural machine moves forward along the reference path in a clockwise direction, that is, the direction coefficient σ=-1; in order to facilitate the processing of unknown system states x 2 , the system equation is further expressed using the coordinate transformation method, the specific form is as follows:

[0062]

[0063] Where: x 1 =L os , x 2 =v x sinθ os , x 1 and x 2 Indicates the system status. and Represents the system state x 1 and x 2 The first derivative of, u = tanδ f represents the input of the controller, p(t,x) and q(t,x) are auxiliary functions introduced to simplify complex problem solving processes, and are transformations of the original function form; represents the unknown lumped disturbance, D 1 (t) represents the disturbance acting on the controller u.

[0064] S2: Based on the coordinate transformation method, the path tracking model is converted into a state equation in a strict feedback form that is convenient for controller design.

[0065] S3: Interval type II fuzzy logic system block diagram Figure 3 As shown, the fuzzy rules, fuzzy reasoning, type reduction method and defuzzification method in interval type-2 fuzzy logic system are designed;

[0066] S3.1. Select the single-point fuzzification method and define two fuzzy sets corresponding to the system state variables x 1 and x 2 , membership function μ 1 and μ2 It is designed as a Gaussian function to quantify the membership of each state variable in its respective fuzzy set; the Gaussian membership function is designed, and the specific form is as follows:

[0067]

[0068] Where: μ 1 and μ 2 represents the Gaussian membership function, and is the standard form of the Gaussian function, corresponding to x 1 and x 2 The adjustment value of i is an index variable used to represent different fuzzy sets, with values ​​ranging from 1 to 5, which means that for the state variable x 1 and x 2 There are five different Gaussian membership functions, each of which is By adjusting to change its position in the state space, each function corresponds to a different fuzzy set; 1 and x 2 Indicates the system status, x 1 =L os , x 2 =v x sinθ os , where L os Indicates the lateral deviation between the actual driving path of the agricultural machinery and the reference path, θ os Indicates the heading deviation between the actual driving path of the agricultural machinery and the reference path;

[0069] These membership functions will generate 5×1 vectors respectively, indicating the membership of each state variable on the five fuzzy sets;

[0070] S3.2. Using the product reasoning mechanism, Karnik-Mendel (KM) algorithm, and the centroid defuzzification method, the fuzzy basis function is obtained, and the interval type II fuzzy membership function is as follows: Figure 4 As shown, the specific form of the fuzzy basis function is as follows:

[0071] Ψ(x)=(ξ l (x)+ξ r (x)) / 2

[0072] Where: represents a vector consisting of normalized left interval membership values, represents a vector consisting of normalized right interval membership values, Represents the i-th element of the left interval vector, whose value is f l i With all fl i The ratio of the sum of (i from 1 to N), Represents the i-th element of the left interval vector, whose value is f l i With all f l i The ratio of the sum of (i from 1 to N), f l i and It is determined by the Karnik-Mendel algorithm, i.e., the Karnik-Mendel reduction algorithm, where n represents the degree of membership of the input data point in the corresponding fuzzy set, N represents the dimension of the vector, and T represents the transposition operation;

[0073] The output of the interval type-2 fuzzy logic system is obtained in the following form:

[0074] y(x)=θ T Ψ(x)

[0075] Where: θ T represents the adaptive parameter, and Ψ(x) represents the fuzzy basis function.

[0076] S4: Using interval type-2 fuzzy logic system to estimate the unknown lumped disturbance of the system;

[0077] S4.1. In the state equation of strict feedback form, p(t,x) and q(t,x) satisfy the following conditions, which are in the form of:

[0078]

[0079] Where: p(t,x) and q(t,x) are auxiliary functions introduced to simplify the complex problem solving process. They are transformations of the original function form. However, due to the influence of various uncertainties, these two functions have certain differences from the actual system. and q (t,x) are both greater than zero, represents the upper bound function of p(t,x), q (t,x) represents the lower bound function of q(t,x);

[0080] S4.2. Using the output of the interval type-2 fuzzy logic system in S3.2, and q (t,x) is estimated, the specific form is:

[0081]

[0082] Where: and θ q represents a vector, and q (x) represents the fuzzy basis function, T represents the transposition operation, and Respectively and q A function of (t,x) that is dynamically approximated using a fuzzy logic system.

[0083] S5: Design a second-order sliding mode controller u based on adaptive interval type-2 fuzzy, the specific form is:

[0084]

[0085] Where: β 1 , β 2 , ω is the system positive constant parameter, p and r 1 is a constant parameter and satisfies p ≥ r 1 =2r 2 >0,ω≥|ζ|, v represents the virtual control input used to compensate for uncertainty, and its specific form is:

[0086]

[0087] Where: and θ q represents the adaptive law parameters, and Respectively and q A function of (t,x) that is dynamically approximated using a fuzzy logic system.

[0088] S6: The method according to claim 5 is characterized in that the second-order sliding mode controller defines and designs the adaptive law parameters in the adaptive interval type-2 fuzzy sliding mode controller, and the adaptive interval type-2 fuzzy sliding mode controller and Depends on and θ q , the specific form is:

[0089]

[0090] Where: and Respectively and θ q The first derivative of , γ 1 and γ 2 represents a normal number, and q (x) represents the fuzzy basis function.

[0091] S7: Perform inverse transformation on the adaptive interval type-II fuzzy sliding mode controller to obtain the system control input, i.e., the steering angle of the front wheels of the agricultural machinery; by changing the controller u = tanδ f Implement the inverse transformation to obtain the front wheel steering angle δ of the agricultural machinery f , the specific form is:

[0092]

[0093] Where: v represents the quantity composed of fuzzy logic system related functions, specific constants and sign functions in the adaptive second-order sliding mode controller, which is used to comprehensively adjust the controller behavior to adapt to system dynamic changes, handle uncertainties and achieve the desired control performance; It represents the dynamic approximation using interval type-2 fuzzy logic system q (t,x) function, β1, β 2 ,ω,p are the normal parameters of the system, r 1 、r 2 is the constant parameter of the system, s 1 、s 2 is the sliding variable; by adjusting the front wheel steering angle δ f Control, the final lateral deviation L os and heading deviation θ os will converge to zero.

[0094] In addition, the present invention also provides a reference method for research in the same field, and can be further extended to other related agricultural machinery path tracking control fields as a basis, and has high practicality and promotion value.

[0095] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention. They are not intended to limit the scope of protection of the present invention. All equivalent methods or changes that do not deviate from the technical creation of the present invention should be included in the scope of protection of the present invention.

Claims

1. A path tracking control method for agricultural machinery based on interval type-2 fuzzy second-order sliding mode, characterized in that: The following steps are involved: S1: Analyze the disturbance factors existing in the actual operation of agricultural machinery and build a path tracking model including disturbance; S2: Based on the coordinate transformation method, the path tracking model is converted into a state equation in a strict feedback form that is convenient for controller design; S3: Design fuzzy rules, fuzzy reasoning, type reduction methods and defuzzification methods in interval type-2 fuzzy logic systems; S4: Using interval type-2 fuzzy logic system to estimate the unknown lumped disturbance of the system; S5: Design of a second-order sliding mode controller based on adaptive interval type-2 fuzzy; S6: Define and design the adaptive law parameters in the adaptive interval type-2 fuzzy sliding mode controller; S7: Perform inverse transformation on the adaptive interval type-II fuzzy sliding mode controller to obtain the system control input, i.e., the steering angle of the front wheels of the agricultural machinery.

2. The method according to claim 1, characterized in that The S1 comprises the following steps: S1.

1. Considering that the actual operation of agricultural machinery will be affected by disturbances, a path tracking model including disturbances is established. The specific form is as follows: Where: L os Indicates the lateral deviation between the actual driving path of the agricultural machinery and the reference path. YesL os The first derivative of os Indicates the heading deviation between the actual driving path of the agricultural machinery and the reference path. is θ os The first-order derivative of , σ represents the direction coefficient, and is defined as negative in clockwise direction, v x represents the longitudinal speed of the agricultural machinery, L represents the wheelbase of the agricultural machinery, δ f represents the steering angle of the front wheel of the agricultural machinery, R represents the radius of curvature of the reference path, and D(t) represents the aggregate disturbance of the external interference; S1.

2. To facilitate the design of the reference path, the curvature radius R of the reference path is converted into the curvature c0, and it is assumed that the agricultural machine moves forward along the reference path in a clockwise direction, that is, the direction coefficient σ = -1; in order to facilitate the processing of the unknown system state x2, the system equation is further expressed using the coordinate transformation method, and the specific form is as follows: Where: x1 = L os , x2=v x sinθ os , x1 and x2 represent the system status, and Represent the first-order derivatives of the system states x1 and x2, respectively, u = tanδ f represents the input of the controller, p(t,x) and q(t,x) are auxiliary functions introduced to simplify complex problem solving processes, and are transformations of the original function form; represents the unknown lumped disturbance, and D1(t) represents the disturbance acting on the controller u.

3. The method according to claim 1, characterized in that The S3 comprises the following steps: S3.

1. Select the single-point fuzzification method and define two fuzzy sets, corresponding to the system state variables x1 and x2 respectively. The membership functions μ1 and μ2 are designed as Gaussian functions to quantify the membership of each state variable in its respective fuzzy set. The Gaussian membership function is designed in the following form: Where: μ1 and μ2 represent Gaussian membership functions, and is the standard form of the Gaussian function, corresponding to the adjusted values ​​of x1 and x2, respectively. i is an index variable used to represent different fuzzy sets, with values ​​ranging from 1 to 5, which means that there are five different Gaussian membership functions for the state variables x1 and x2, respectively. Each function is By adjusting to change its position in the state space, each function corresponds to a different fuzzy set; x1 and x2 represent the system state, x1 = L os , x2=v x sinθ os , where L os Indicates the lateral deviation between the actual driving path of the agricultural machinery and the reference path, θ os Indicates the heading deviation between the actual driving path of the agricultural machinery and the reference path; These membership functions will generate 5×1 vectors respectively, indicating the membership of each state variable on the five fuzzy sets; S3.

2. Using the product reasoning mechanism, the Karnik-Mendel (KM) algorithm, and the centroid defuzzification method, the fuzzy basis function is obtained. The specific form is as follows: Ψ(x)=(ξ l (x)+ξ r (x)) / 2 Where: represents the left interval vector, Right interval vector, Indicates that the i-th element of the left interval vector has a value of f l i With all f l i The ratio of the sum of (i from 1 to N), Indicates that the i-th element of the left interval vector has a value of f l i With all f l i The ratio of the sum of (i from 1 to N), f l i and Determined by Karnik-Mendel reduction algorithm, where n represents the degree of membership of the input data point in the corresponding fuzzy set, N represents the dimension of the vector, and T represents the transposition operation; The output of the interval type-2 fuzzy logic system is obtained in the following form: y(x)=θ T Ψ(x) Where: θ T represents the adaptive parameter, and Ψ(x) represents the fuzzy basis function.

4. The method according to claim 1, characterized in that The S4 comprises the following steps: S4.

1. In the state equation of strict feedback form, p(t,x) and q(t,x) satisfy the following conditions, which are in the form of: Where: p(t,x) and q(t,x) are auxiliary functions introduced to simplify the complex problem solving process. They are transformations of the original function form. However, due to the influence of various uncertainties, these two functions have certain differences from the actual system. and q (t,x) are both greater than zero, represents the upper bound function of p(t,x), q (t,x) represents the lower bound function of q(t,x); S4.

2. Using the output of the interval type-2 fuzzy logic system in S3.2, and q (t,x) is estimated, the specific form is: Where: and θ q represents a vector, and q (x) represents the fuzzy basis function, T represents the transposition operation, and Respectively and q A function of (t,x) that is dynamically approximated using a fuzzy logic system.

5. The method according to claim 1, characterized in that In S5, a second-order sliding mode controller u based on adaptive interval type-2 fuzzy is designed, and the specific form is: Where: β1, β2, ω are normal parameters of the system, p and r1 are constant parameters, and p≥r1=2r2>0, ω≥|ζ|, v represents the virtual control input used to compensate for uncertainty, and its specific form is: Where: and θ q represents the adaptive law parameters, and Respectively and q A function of (t,x) that is dynamically approximated using a fuzzy logic system.

6. The method according to claim 5, characterized in that The second-order sliding mode controller defines and designs the adaptive law parameters. and Depends on and θ q , the specific form is: Where: and Respectively and θ q The first-order derivative of , γ1 and γ2 represent positive constants, and q (x) represents the fuzzy basis function.

7. The method according to claim 1, characterized in that In S7, by controlling the controller u = tanδ f Implement the inverse transformation to obtain the front wheel steering angle δ of the agricultural machinery f , the specific form is: Where: v represents the quantity composed of fuzzy logic system related functions, specific constants and sign functions in the adaptive second-order sliding mode controller, which is used to comprehensively adjust the controller behavior to adapt to system dynamic changes, handle uncertainties and achieve the desired control performance; It represents the dynamic approximation using interval type-2 fuzzy logic system q (t, x), β1, β2, ω, p are normal parameters of the system, r1, r2 are constant parameters of the system, s1, s2 are sliding variables; by adjusting the front wheel steering angle δ f Control, the final lateral deviation L os and heading deviation θ os will converge to zero.

Images